KR20160001994A - Server and method for managing crime using big data - Google Patents

Abstract

The present invention relates to a method and a server for managing the occurrence of crime by analyzing data collected in the online. According to a first aspect of the present invention, a server for managing the crime to manage the occurrence of the crime by analyzing data collected online comprises: a data collection extracting unit for collecting data online and for extracting a notice notified in an online notification service in the collected data; a crime analysis unit for determining a crime index which indicates a dangerous degree of the crime having occurred by analyzing the extracted notice; and a notification unit for notifying an analysis result of the notice to at least one among the server of an associated institute and a user terminal based on the crime index.

Description

TECHNICAL FIELD [0001] The present invention relates to a method and a server for managing crime using big data,

The present invention relates to a method and system for managing crime using big data. More particularly, the present invention relates to a method and system for managing crime by collecting data existing on the Internet, analyzing collected big data, To a method and system for minimizing the damage caused by crime by preventing a crime by arranging a police or a soldier at a tracked position or by promptly dispatching a crime when the crime occurs.

In recent years, various data that have not been recorded or stored in the past due to the development and spread of digital technology are stored. The stored data is referred to as big data and big data is used in various fields.

These big data include personal or social safety related data, such as articles that describe consumer preferences or preferred services, as well as articles that simulate crimes or ask for urgent help.

However, in the field where the big data is currently used, it is mainly used by companies that intend to increase sales by analyzing the tendency of consumers or preferred services. In the case of data related to personal or social safety included in big data, , Are not used to predict crime, establish policies for reducing crime rates, and track offenders.

In this regard, Korean Patent Laid-Open Publication No. 10-2014-0058753 relates to a system and method for providing a Big Data-based interested product through recognition of a receipt, and a commerce platform for collecting and analyzing receipt information and providing product mapping of an affiliated company And provides raw data of the receipt as big data, thereby providing the user with information of the interested goods differentiated from the product page of the general open market and the event information, and increasing the probability of purchase of the goods by the user. However, the techniques disclosed in the above patent documents do not solve the above-described problems.

Therefore, a technique for solving the above-described problems is required.

On the other hand, the background art described above is technical information acquired by the inventor for the derivation of the present invention or obtained in the derivation process of the present invention, and can not necessarily be a known technology disclosed to the general public before the application of the present invention .

One embodiment of the present invention aims at preventing crime reduction and crime by collecting posts posted on SNS (Social Network Service) among various data collected online and analyzing the collected posts to predict the occurrence of crime have.

An embodiment of the present invention also aims at analyzing the collected posts, reporting to relevant organizations for crime victim structure, collecting criminal tracking and crime evidence.

According to a first aspect of the present invention, there is provided a crime managing server for analyzing data collected on-line and managing crime occurrence, the crime managing server comprising: A data collecting and extracting unit for extracting a post posted on an online bulletin board service, a crime analyzing unit for analyzing the extracted post to determine a crime index indicating a risk of crime occurrence, and an analysis result of the post based on the crime index And a notification unit for notifying at least one of a server and a user terminal of an associated organization.

According to a second aspect of the present invention, there is provided a crime managing method for managing crime occurrence by analyzing data collected online on a crime management server, the crime managing method comprising the steps of: collecting data on- Analyzing the extracted postings to determine a crime index indicating a risk of occurrence of a crime, and analyzing a result of analysis of the post based on the crime index to at least one of a server and a user terminal of a related institution .

According to one embodiment of the present invention, an embodiment of the present invention collects posts posted on a social network service (SNS) among various data collected online and analyzes the collected posts, , It is possible to reduce the crime rate and prevent crime by pre-arranging police or military forces at predicted locations and times.

In addition, according to any one of the tasks of the present invention, by analyzing the collected posts, the rescue request for the victim of the present crime is prompted to prevent the rapid structure and damage, and the criminal tracking and crime proof Can be collected.

The effects obtained by the present invention are not limited to the above-mentioned effects, and other effects not mentioned can be clearly understood by those skilled in the art from the following description will be.

1 is a block diagram showing a configuration of a crime management system according to an embodiment of the present invention.
2 is a block diagram illustrating each component of the crime management server according to an embodiment of the present invention.
3 is a flowchart illustrating a method for managing a crime according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Throughout the specification, when a part is referred to as being "connected" to another part, it includes not only "directly connected" but also "electrically connected" with another part in between . Also, when an element is referred to as "comprising ", it means that it can include other elements as well, without departing from the other elements unless specifically stated otherwise.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

Before describing this, we first define the meaning of the terms used below.

In the present invention, 'big data' refers to a large amount of data that is difficult to collect, store, search, and analyze in the conventional method because the generation amount, the period, and the format of the data are too large as compared with the existing data.

A "post", a kind of data belonging to such big data, can include at least a part of text, image, and video in a unit content that can be viewed online for others to view, and can be created, posted, shared, Distributed or evaluated.

The post may be posted on an 'online bulletin board service' which is a service for displaying a plurality of posts on the online in the order of time or in registration order, and the online bulletin board service may be, for example, an SNS.

The big data may include a keyword, which is an important word for analyzing a post, and these keywords may include a crime keyword and a structural keyword.

First, 'crime keyword' is a keyword related to crime, for example, a crime name, a word that meets the requirement for the crime to be established, a language that reminds of intimidation or stalking and disappearance, Or a hermit crab.

The 'rescue keyword' is a keyword related to the rescue request. For example, it may include a term indicating a rescue request such as SOS, Help, Help, Rescue, etc., for a victim at a crime scene or a disaster site to request a rescue have.

A word expressing the emotion of a publisher about these keywords is called an emotional word. For example, bad, bad, bad, good, charming, and so on. Emotional words include not only Hangul but also foreign languages.

When the emotional word has a negative meaning, the index expressing the negative strength of the emotional word is called the emotional index. For example, the emotional index of emotional words such as 'hate', 'bad', 'hate' and 'curse' is 3 if the emotional index of the bad is 3.

The crime index refers to a crime related term, a structural keyword, which is related to the structure, or a structural keyword, which is related to the structure. It can be determined based on the number of inclusion clauses used by a particular group or the history record of an individual's past crime record.

If the crime index of the post is higher than a certain value, the organization reporting the crime prevention and victim structure is referred to as 'related organization', for example, a police station or a fire department.

1 is a block diagram illustrating a network configuration including a crime management server 20 according to an embodiment of the present invention.

The network N that enables communication between the configuration of the crime management server 20 and the rest of the components includes a local area network (LAN), a wide area network (WAN), a value added network All kinds of wireless communication devices such as cellular phones, VANs, personal area networks (PANs), mobile radio communication networks, Wibro (Wireless Broadband Internet), Mobile WiMAX, HSDPA (High Speed Downlink Packet Access) Wired / wireless network.

The user terminal 10 can be implemented as a computer, a portable terminal, a television, a wearable device, or the like, which can be connected to a remote server through a network N or connected to other terminals and servers. Here, the computer includes, for example, a notebook computer, a desktop computer, a laptop computer, and the like, each of which is equipped with a web browser (WEB Browser), and the portable terminal may be a wireless communication device , Personal Communication System (PCS), Personal Digital Cellular (PDC), Personal Handyphone System (PHS), Personal Digital Assistant (PDA), Global System for Mobile communications (GSM), International Mobile Telecommunication (IMT) (W-CDMA), Wibro (Wireless Broadband Internet), Smart Phone, Mobile WiMAX (Mobile Worldwide Interoperability for Microwave Access) (Handheld) based wireless communication device. In addition, the television may include an Internet Protocol Television (IPTV), an Internet television (TV), a terrestrial TV, a cable TV, and the like. Further, the wearable device is an information processing device of a type that can be directly worn on a human body, for example, a watch, a glasses, an accessory, a garment, shoes, and the like. The wearable device can be connected to a remote server via a network, Lt; / RTI >

At this time, the user terminal 10 may be a terminal of an employee of an associated institution that communicates with an associated institution server or a terminal of a general user.

The SNS server 11 can communicate with the user terminal 10 or the other server via the network N and can post the post received from any user terminal on the online bulletin board.

Next, the crime management server 20 is a server capable of communicating with the components of the crime management system 100 via the network N, and receives a post from at least one of the user terminal 10 or the SNS server 11 You can also collect posts posted on the web as big data, and analyze the collected posts to determine the crime index.

At this time, in order to determine the crime index, the crime management server 20 may further collect keywords such as a term related to a crime related term, a structure keyword as a term related to the structure, or a hare used by a specific group, And the like can be collected.

Based on the information thus collected, the crime management server 20 can determine the emotion index of the emotional language included in the post including the keywords collected from the posts in order to analyze the post, The crime index of the post can be determined based on the transcript of the post and the analysis result of the post is transmitted to the general user terminal 10 or the related institution server 40, Can be notified.

The criminal record server 30 is a server capable of communicating with the crime management server 20 via the network N. The criminal record server 30 can store a criminal record of an individual, A transcript can be provided.

Finally, the related institution server 40 can communicate with the crime management server 20 by connecting a plurality of related institution servers 40 on the network N according to the number of related organizations, To dispatch related personnel according to the analysis result of the post.

For example, the related institution server 40 may arrange a police officer, an ambulance, a soldier, and the like in an area where the publisher who posted the post is located according to the analysis result of the post.

Hereinafter, the configuration of the crime management server 20 will be described in detail with reference to FIG.

First, the data collection and extraction unit 210 of the crime management server 20 collects online data and extracts an analysis object based on the posted articles on the online bulletin board service among the collected big data.

That is, the data collection and extraction unit 210 may collect all the data that the user of the user terminal 10 uploaded on-line through a crawling method. The crawling method refers to a method of collecting distributed documents and information and incorporating them into the index of the search target.

The target of the big data collected by the data collection and extraction unit 210 is not limited to the type of the data. For example, all types of data such as a text, a moving image, and an image written in a document can be collected.

An object to which the data collecting and extracting unit 210 collects data is an accessible site for anyone. Preferably, the site is an online site in which people's thoughts, conversations, opinions, and the like are intervened, such as Twitter, Facebook and LinkedIn A social network service (SNS) site, a blog operated by an arbitrary entity (an individual or a corporation), a video site such as YouTube, a search engine site such as Google, and other online sites disclosed to any user.

As described above, the data collection and extraction unit 210 collects data from sites accessible to all, and as the time passes, the number of data to be collected increases, and accurate analysis results can be obtained.

The data collecting and extracting unit 210 can extract information on the emotions or intentions of the individual among the various data of the collected big data, in particular, information about the post posted on the post online bulletin board service.

The data collection and extraction unit 210 may collect crime keywords or structural keywords to analyze the collected data, and may connect to the history and record server 30 where the criminal record, Can be collected.

For example, the data collection and extraction unit 210 can access a web page of a broadcast medium to collect crime keywords contained in an article dealing with crimes posted online, or record criminal records, It is possible to connect to the police recording server 30, that is, the police station server, and collect personal records.

On the other hand, the data collection and extraction unit 210 can collect not only the criminal keywords but also the structural keywords.

For example, the data collection and extraction unit 210 may access the server of the fire department to collect the damage report record, and may request the help from the report of the report of the damage report collected, And so on.

The database unit 220 may classify and store keywords or posts included in the big data collected by the data collection and extraction unit 210 as described above.

In particular, the database unit 220 can sort the posts extracted from the collected big data by the data collection and extraction unit 210 according to the publishers that generate the respective posts. For example, the database unit 220 may classify and store a plurality of posts extracted by the data collection and extraction unit 210 according to IDs of publishers that have created the respective posts.

The database unit 220 may classify and store the crime keywords collected by the data collection and extraction unit 210 according to a crime name, a specific group using a specific crime keyword, or a situation in which a crime keyword is used.

For example, the database unit 220 may classify and store the keywords related to the theft of the criminal keywords into the category of theft, and the criminal keywords mainly used by the organizations related to the anti-state system among the criminal keywords are stored .

Next, the personal information managing unit 230 receives the data collected by the data collecting and extracting unit 210 from the transcription history server 30, and determines the number of times the publisher has recorded the transcript and the number of times the publisher has created a post having a crime index equal to or greater than a predetermined value The publisher can be classified based on at least one of them, and the personal information of the publisher can be managed.

For example, the personal information management unit 230 may classify publishers as ex-confessions and non-confectioners according to whether or not the publisher who created the post based on the transcripts received from the data collection / It is possible to manage the personal information of the publisher by classifying the publication as a publisher rather than a publisher.

Also, for example, the personal information manager 230 may classify a plurality of publishers who sympathize or comment on a post having a certain crime index value or more as a dangerous person, classify the same as a group, You can manage the personal information of one or more publishers belonging to the same group by creating a connection relationship.

In this way, by classifying and managing a large number of publishers simulating one crime as a group, it is possible to enhance the accuracy of crime prediction by analyzing the posts of a plurality of publishers.

Thereafter, the crime analysis unit 240 can analyze the data collected by the data collection and extraction unit 210, in particular, the posts posted on the online bulletin board service, and determine the crime index indicating the risk of crime occurrence.

First, the crime analysis unit 240 extracts one or more emotional words representing the emotional state of the publisher from a post including the keywords among the collected posts stored in the database unit 220, calculates a negative degree indicated by the extracted one or more emotional words Can be determined.

For example, the crime analyzing unit 240 extracts emotional words such as 'killing' and 'real', which express the emotions of a publisher of a post, with respect to a post including a keyword 'assault' The sensitivity index for each emotional word can be determined by weighting according to the negative degree of each emotional word.

The crime analysis unit 240 can determine the crime index based on at least one of the sensitivity index of the emotional word included in the post, the number of times the keyword is included, and the past record of the publisher of the post.

For example, the crime analysis unit 240 determines the crime index by adding the crime index according to the number of times the crime-related term appears in the post and whether the crime-related term having a high weight is included in the crime- (Eg, a person's name, address, etc.) are listed together with a higher crime index (eg, a person's name, address, etc.) Can be determined.

Also, for example, if a post including the keyword 'police' is repeatedly included in a sentence having a high emotion index, the crime analysis unit 240 may determine the crime index to be higher than that of a post including the same keyword .

For example, the crime analysis unit 240 can determine a crime index in accordance with whether a publisher has a criminal record, even if the crime keyword is a post with the same crime keyword. In addition, The crime index can be determined to be very high if the crime is in agreement.

According to another embodiment, if there is a transcript of a crime index of a predetermined value or less, and a publisher of a post has a transgression and there is another post posted by the publisher, the crime analysis unit 240 synthesizes the crime indexes of all the posts, You can decide.

For example, if the crime index of a single post is not equal to or greater than a predetermined value, and if the publisher of the post has a criminal record, the crime analysis unit 240 can simultaneously analyze the posters created by the relevant publisher for a certain period of time , Increasing the crime index of each post, or combining criminal terms included in each post to determine the crime index.

And according to another embodiment, the crime analysis unit 240 may determine the crime index of a particular post based on the emotion index of one or more other posts for that particular post.

For example, when the first user continuously and repeatedly sends the post to the second user or writes the post to the SNS of the second user, the crime analyzing unit 240 judges whether or not the second user The sentence word included in the posting can be analyzed. If the emotion index is high as a result of the analysis, the crime analysis unit 240 can determine the crime index of the posting of the first user to be high.

On the other hand, the crime analysis unit 240 can determine the type of the crime based on the criminal keyword included in the post having a certain crime index or more and the past record of the publisher of the post.

For example, if the post contains keywords such as 'apartment', 'empty house', 'extension', 'mask', and the like, and if the publisher has a criminal record for theft, the crime analysis unit 240 may determine that the post- It can be judged that it is preparing.

If the posting includes a structural keyword for requesting help, the crime analysis unit 240 may determine the current status of the publisher based on the contents of the post and the time at which the post was registered.

For example, if the posting includes keywords such as 'intrusion', 'masking', and 'knife', and if the time the publisher registered the posting is within 10 minutes from the current time, the crime analysis unit 240 It can be judged that a robber has entered the house, and the publisher can be determined to be held hostage.

For example, if the posting includes keywords such as 'urgent', 'bleeding', 'falling', 'climbing', etc., the crime analysis unit 240 may detect that the current publisher has fallen during mountain climbing, You can decide it is a situation.

In this way, the crime analysis unit 240 analyzes the big data collected by the data collection and extraction unit 210 to determine whether the publisher simulates or prepares crime, or can determine that the publisher is in an emergency, And can transmit the analysis result of the post to the notifying unit 250 to be described later to the relevant institution server 40 or the general user terminal 10 according to each determined matter.

Then, based on the crime index, the notifying unit 250 can notify the relevant institution server 40 of the analysis result of the post.

For example, when the crime analysis unit 240 analyzes a post to determine that it is a crime simulation stage or a crime occurrence stage, the notification unit 250 may include a police server The analysis result of the post such as the content of the post or the type of the crime can be transmitted to the report server and the analysis result of the post can be transmitted to the user terminal 10 in the area where the publisher of the post is located.

For example, when the crime analysis unit 240 analyzes the post and determines that the post is an emergency situation, the notifying unit 250 notifies the contents of the corresponding post or the current state of the post to the fire department notification server, Patient status, and the like.

A method of managing crimes by analyzing the posts included in the data collected by the crime management server 20 will be described below with reference to FIG.

The crime management method according to the embodiment shown in FIG. 3 includes steps that are processed in a time-series manner in the crime management server 20 shown in FIG. Therefore, even though omitted from the following description, the above description of the crime management server 20 shown in FIG. 2 can be applied to the crime management method according to the embodiment shown in FIG.

First, the crime management server 20 can collect data on-line, and can extract a post posted on the online bulletin board service from the collected data (S3000).

For this, the crime management server 20 can collect data on-line through a crawling method, and preferably, the SNS server 11 can collect data on a daily basis.

In this way, the crime management server 20 can be provided with an SNS site such as Twitter, Facebook and LinkedIn, blogs operated by arbitrary objects (individuals or companies), YouTube, By collecting data from the same video site, you can collect data that accurately predicts the intentions and thoughts of the publisher.

Then, the crime management server 20 can extract the postings reflected in the online bulletin board service, that is, the postings reflecting the thoughts and tendencies of the individual.

Also, the crime management server 20 can collect at least one of criminal keywords, structural keywords, and criminal records, which are personal past crime records, as big data.

That is, the crime management server 20 can collect the crime keywords by accessing a server of a company providing news on-line or a police office server to analyze a post included in the collected big data.

For example, the crime management server 20 may collect the requirements for establishing the crime included in the laws posted on-line or the crime related data stored in the database of the police server.

In addition, the crime management server 20 may access the transcription server 30 to collect or retrieve personal transcripts.

For example, the crime management server 20 may collect or search the past record of the publisher who has created the collected post by accessing the police server of the police record server 30, and if the crime index is a certain value You can only collect transcripts for publishers of posts longer than.

By collecting individual criminal records in this way, criminals can be predicted and prevented by locating people in excess of the risk level of criminal tendency, and managing bulletins written by people who exceed the risk level.

Then, the crime management server 20 can classify the publishers according to the presence or absence of the transcript of the publisher.

That is, the crime management server 20 compares the personal information of the publisher of the bulletin included in the collected data with the criminal record of the individual collected in the criminal record server 30, Can be classified and managed.

Also, the crime management server 20 can analyze the postings by a method to be described later, and re-classify the publishers according to the number of times the postings having the crime indexes of a certain value or more are created, and manage the publishers according to the degree of risk.

Thereafter, the crime management server 20 may classify and store the postings according to the classification of the publisher that created the collected posts.

In particular, the crime management server 20 can centrally manage the postings created by the publishers having the classified transcripts, by storing them separately from other publishers.

By doing this, the crime management server 20 can efficiently utilize the limited resources by analyzing the posts of the publishers having a high probability of causing crime among the many articles included in the data, and can continuously transmit the posts of the publishers having the criminal record More accurate crime forecasting is possible by tracking the analysis.

Then, the crime management server 20 may analyze the bulletin extracted from S3000 to determine the crime index indicating the risk of crime occurrence (S3001).

First, the crime management server 20 can extract the emotional word indicating the emotion of the publisher in the post including the keyword among the posts collected in S3000, and determine the emotional index of the post based on the emotional word.

For example, the crime management server 20 can extract 'killing' or 'spoof' emotional words representing emotions of a publisher included in a post including the keyword 'gross' It is possible to determine the sensitivity index with different weights according to the intensity.

Thereafter, the crime management server 20 may determine the crime index based on at least one of emotion index of the post, number of times the keyword is included in the post, and past record of the publisher of the post.

For example, the crime management server 20 may determine the crime index as the number of inclusion of the crime keyword in the extracted post, or may assign a score to each crime keyword with different weights. In addition, the crime management server 20 may sum up the scores of the respective criminal keywords included in the post, and may additionally determine the crime index by reflecting the emotion index of the post including the keyword.

For example, the crime management server 20 can determine the crime index to be very high if the posting includes the crime keyword used in the crime recorded in the past record of the publisher who wrote the post.

Alternatively, the crime management server 20 may determine the crime index of a particular post based on the emotion index of the emotional word for the keywords contained in one or more other posts for that particular post.

For example, if a first publisher repeatedly posts a post with a low crime index repeatedly to a second publisher, and the second publisher posts a post with a high emotion index as a response to the first publisher's post, The server 20 can highly determine the crime index of the first publisher's post.

If the crime index of the post is equal to or greater than a certain value, the crime management server 20 can determine the type of the crime of the post or the current situation of the victim (S3002).

In one embodiment, if the publisher of the post has a transcript, the crime management server 20 may determine the type of the crime based on at least one of the criminal keywords included in the post and the transcript of the publisher.

For example, if the publisher of a post has a criminal record of an assault, and the post written by the publisher includes a crime keyword such as "slap" or "kill", the crime management server 20 Can be predicted.

In another embodiment, if the post has a structure keyword, the crime management server 20 may determine the current status of the publisher based on at least one of the crime keyword, the structure keyword, and the time the post is registered in the post.

For example, a post may contain crime keywords such as "kidnapping", "place", "ransom", as well as additional structural keywords such as "help me" or "help me" If the uplink time is less than 10 minutes, the crime management server 20 can predict that the current publisher has been kidnapped, requested the structure, and the victim is alive. Based on the access address of the publisher who has accessed the online bulletin board service So that the position of the missing person can be predicted.

When the analysis of the post is completed, the crime management server 20 can notify the analysis result of the post to at least one of the related institution server 40 or the user terminal 10 (S3003).

That is, when the occurrence of crime is predicted as a result of analysis of the post, the crime management server 20 can transmit the analysis result to the police server or the like, which is the server 30 of the related institution. Alternatively, The analysis result of the post can be transmitted to the fire department or the server of the hospital, which is the related institution server 40.

For example, the crime management server 20 may transmit the location of the current publisher to the police server based on personal information of the publisher who created the post having a crime index of a certain value or more or the access address of the publisher.

In this way, the police can prevent the occurrence of crime by arranging additional manpower in addition to the existing manpower, or can solve the crime that occurred earlier, thereby reducing the crime rate of the publisher by reducing the crime intention of the publisher.

For example, if it is determined that the crime has been committed in the past as a result of the determination of the content of the crime, the crime management server 20 can analyze the location pattern of the publisher who escapes after the crime by transmitting the analyzed result to the police server, It is possible to facilitate the arrest, and the post can be used as evidence.

For example, the crime management server 20 can improve the environment and reduce the crime rate by notifying the administration server of the address of the publisher who has created a post having a certain crime index value or more.

In addition, when the crime occurrence is predicted as a result of the analysis of the post, the crime management server 20 transmits the analyzed post to the user terminal 10 around the publisher of the post, have.

Alternatively, if analysis of the post is analyzed as a structure request, the crime management server 20 may transmit the current location of the publisher to the fire station server based on the personal information of the publisher or the access address of the publisher.

By doing this, you can quickly rescue a publisher, not a situation where you can call a police station or a government office.

The crime management method according to the embodiment described with reference to FIG. 3 may also be implemented in the form of a recording medium including instructions executable by a computer such as a program module executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer-readable medium may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically includes any information delivery media, including computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transport mechanism.

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

100: Crime management server
10: user terminal 11: SNS server
20: crime management server 30: criminal record server
40: Related institution server
210: data collection and extraction unit 220:
230: personal information management unit 240: crime analysis unit
250: Notification Department?

Claims (16)

A crime management server for managing crime occurrence by analyzing data collected online,
A data collection and extraction unit for collecting data on-line and extracting a post posted on the online bulletin board service from the collected data;
A crime analysis unit for analyzing the extracted posts to determine the crime index indicating the risk of crime occurrence; And
And a notification unit for notifying, based on the crime index, at least one of a server and a user terminal of an analysis result of the posting. The method according to claim 1,
The crime management server comprises:
Further comprising a database unit for classifying and storing the collected posts by the publishers based on the personal information of the publishers of the extracted posts. The method according to claim 1,
Wherein the data collection /
Extracts a criminal record, which is an individual's past criminal record, from the data,
The crime management server comprises:
A publisher who manages the past record of the publisher of the post based on the extracted transcript of the individual, a publisher who created a post having a crime index of a certain value or more, and a personal information manager associating personal information of each individual related to the post Crime management server. The method according to claim 1,
Wherein the data collection /
Extracting at least any one of a keyword related to the crime and a keyword requesting help from the data,
The crime analysis unit,
Extracting one or more emotional words representing emotions of the publisher from the posts in the posts including the keywords, and determining emotional indices indicating the degree of negativeness of the extracted one or more emotional words. The method according to claim 1,
The crime analysis unit,
And determining the crime index based on at least one of an emotion index of emotional words included in the post, a number of inclusion times of the keyword, and existence of the past record of the publisher. The method according to claim 1,
The crime analysis unit,
Determining a crime index of the particular post based on an emotion index of emotional words contained in one or more other posts for a particular post. The method according to claim 1,
The crime analysis unit,
And when the publisher of the post has a transcript, determines a crime type based on at least one of a keyword included in the post and a transcript of the publisher. The method according to claim 1,
The crime analysis unit,
Wherein the current status of the publisher is determined based on at least one of a keyword included in the post and a time at which the post is registered when there is a keyword requesting help in the post. A method for managing a crime by analyzing data collected online by a crime management server,
Collecting the data on-line and extracting a post posted on the online bulletin board service from the collected data;
Analyzing the extracted posts to determine the crime index indicating the risk of crime occurrence; And
And notifying at least one of a server and a user terminal of the relevant institution of the analysis result of the post based on the crime index. 10. The method of claim 9,
Wherein the step of extracting the posting comprises:
And categorizing and storing the collected posts by the publishers based on the personal information of the publishers of the extracted posts. 10. The method of claim 9,
Wherein the step of extracting the posting comprises:
Extracting a criminal record, which is an individual's past criminal record, from the data,
The crime management method includes:
Managing the past record of the publisher of the post based on the extracted past record of the individual; And
Further comprising associating personal information of a publisher who created a post having a crime index greater than or equal to a predetermined value and an individual of the individual associated with the post. 10. The method of claim 9,
Wherein the step of extracting the posting comprises:
Extracting at least any one of a keyword related to the crime and a keyword requesting help from the data,
The step of determining the crime index comprises:
Extracting at least one emotional word representing emotion of the publisher from the post in the post including the keyword among the posts; And
Determining an emotion index indicating a degree of a negative of at least one of the extracted emotional words. 10. The method of claim 9,
The step of determining the crime index comprises:
Determining the crime index based on at least one of an emotional index of the emotional word included in the post, a number of inclusion times of the keyword, and existence of the past record of the publisher. 10. The method of claim 9,
The step of determining the crime index comprises:
Determining a crime index of the particular post based on an emotional index of emotional words contained in one or more other posts for a particular post. 10. The method of claim 9,
The step of determining the crime index comprises:
Determining a type of a crime based on at least one of a keyword included in the post and a past record of the publisher when the publisher of the post has a criminal record. 10. The method of claim 9,
The step of determining the crime index comprises:
Determining a current status of the publisher based on at least one of a keyword included in the post and a time when the post is registered when the post has a keyword requesting help.

Images