KR101660160B1 - A Method for Estimating a Crime Risk Using Big Data and A System for Reporting the Crime Risk Using thereof - Google Patents
A Method for Estimating a Crime Risk Using Big Data and A System for Reporting the Crime Risk Using thereof Download PDFInfo
- Publication number
- KR101660160B1 KR101660160B1 KR1020150026941A KR20150026941A KR101660160B1 KR 101660160 B1 KR101660160 B1 KR 101660160B1 KR 1020150026941 A KR1020150026941 A KR 1020150026941A KR 20150026941 A KR20150026941 A KR 20150026941A KR 101660160 B1 KR101660160 B1 KR 101660160B1
- Authority
- KR
- South Korea
- Prior art keywords
- crime
- risk
- user
- data
- relative
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G06F17/30—
-
- G06F19/00—
Abstract
The present invention relates to a method for estimating the risk of crime using Big Data and a system for notifying a risk of crime using the method.
To this end, the present invention comprises: collecting crime data counted according to a predetermined classification criterion; Calculating an absolute crime risk level for a combination of items selected for each of the classification criteria based on the crime data; Obtaining priority item information of a user for each classification criterion; Calculating a relative risk of crime based on the obtained priority item information of the user; Generating a user crime risk by combining the absolute crime risk and the relative crime risk; And providing the generated user crime risk information to the user; A method for estimating a crime risk using Big Data, and a system for reporting a crime risk using the method.
Description
The present invention relates to a method for estimating a crime risk using Big Data and a system for reporting a crime risk using the same, and more particularly, to provide a user-customized value of a crime risk and provide the same.
Big data refers to large-scale data that is generated in a digital environment, has a large size, has a short generation cycle, and includes not only numerical data but also various forms such as text and image data. Big Data has emerged with increasing data due to the development of various sensors and the Internet. As computers and processing technologies develop, analysis based on big data generated in the digital environment has increased the possibility of discovering new perspectives and laws about changes in diseases and social phenomena. Therefore, Big Data can be used to solve social problems, especially in crime prevention and investigation.
For example, using Big Data technology can analyze historical crime data and identify patterns that can predict places and times of high crime risk. In addition, crime location and type can be provided in detail around the address, to identify and prevent specific crimes, and to prevent crime by prioritizing police personnel in areas of high crime incidence.
However, the individual and societal values of each crime can be different. For example, in the case of a gun crime, the severity or risk of the crime may differ between countries where individual gun possession is allowed and unacceptable. In addition, since the degree of interest in each type of crime differs from person to person, the same value can not be given collectively for the same kind of crime. Therefore, it is necessary to provide differentiated crime risk information from such personal, social and political perspectives to users who are provided with the possibility of crime in each region.
The present invention has a purpose to consider the value possessed by each crime information in terms of individual, socio-political, and statistical perspectives, to quantify the crime information, and to provide such data to the user.
According to another aspect of the present invention, there is provided a method for estimating a crime risk using Big Data, the method comprising: collecting crime data counted according to a predetermined classification criterion; And at least one of a crime occurrence time, the crime data indicating the number of crime incidents according to each item in the classification standard; Calculating an absolute crime risk score for a combination of items selected for each classification criterion based on the crime data, the absolute crime risk level being determined by a combination of the number of crime occurrences in each item selected for each classification criterion; Obtaining priority item information of a user for each classification criterion; Calculating a relative risk of crime based on the obtained priority item information of the user; Generating a user crime risk by combining the absolute crime risk and the relative crime risk; And providing the generated user crime risk information to the user; And a control unit.
In this case, when the crime data is counted as n classification criteria, the absolute crime risk is calculated as an n-dimensional vector.
In addition, the absolute crime risk is an n-dimensional vector having the number of crimes occurring in each item selected for each classifier as coordinates of each axis.
According to an embodiment of the present invention, the relative crime risk is calculated as an n-dimensional vector of a combination of items selected for each of the classification criteria, and the user crime risk is calculated using the absolute crime risk vector and the relative crime risk vector Is summed and summed.
According to another embodiment of the present invention, the relative crime risk is calculated as a weight for the priority item of the user, and the user crime risk is calculated by using the coordinates corresponding to the priority item in the absolute crime risk vector as the weight And is generated based on the multiplied value.
According to an embodiment of the present invention, the method further includes acquiring the personal information of the user, and the priority item information of the user is generated based on the personal information of the user.
The method may further include collecting real-time social crime risk information using at least one of news data, social network service (SNS) data, and web data, and the relative crime risk is calculated using the collected social crime risk information .
Meanwhile, a crime risk alert system using Big Data according to an embodiment of the present invention includes a communication unit for transmitting / receiving data to / from an external terminal or a network; Wherein the classification data includes at least one of a crime type, a place of crime occurrence and a crime occurrence time, and the crime data includes at least one of the number of crime incidents A data collection unit for acquiring priority item information of a user for each of the classification criteria; And an absolute crime risk level for a combination of items selected for each of the classification criteria based on the crime data, wherein the absolute crime risk level is determined by a combination of the number of crime occurrence times in each of the items selected for each of the classification criteria A risk calculating unit for calculating a relative crime risk based on the obtained priority item information of the user and generating a user crime risk by combining the absolute crime risk and the relative crime risk; And the system provides the generated user crime risk information to the user terminal.
According to the present invention, it is possible to calculate an absolute crime risk value according to the incidence of crime using big data, and at the same time, a weight is added to a crime type of which the user is highly interested, thereby providing user crime risk information suitable for the user .
1 is a block diagram illustrating a crime risk alert system using Big Data according to an embodiment of the present invention.
FIG. 2 is a table showing an example of crime data counted according to predetermined classification criteria according to the present invention. FIG.
FIG. 3 is a table showing one embodiment of a method in which the relative risk of crime is calculated; FIG.
FIG. 4 is a table showing another embodiment of a method in which the relative risk of crime is calculated; FIG.
5 illustrates a method for generating a user crime risk using absolute crime risk and relative crime risk according to an embodiment of the present invention.
Figure 6 illustrates a method for generating a user crime risk using absolute crime risk and relative crime risk according to another embodiment of the present invention.
7 is a flowchart illustrating a method for estimating a crime risk using Big Data according to an embodiment of the present invention.
As used herein, terms used in the present invention are selected from general terms that are widely used in the present invention while taking into account the functions of the present invention. However, these terms may vary depending on the intention of a person skilled in the art, custom or the emergence of new technology. Also, in certain cases, there may be a term arbitrarily selected by the applicant, and in this case, the meaning thereof will be described in the description of the corresponding invention. Therefore, it is intended that the terminology used herein should be interpreted relative to the actual meaning of the term, rather than the nomenclature, and its content throughout the specification.
FIG. 1 is a block diagram illustrating a crime risk alert system using Big Data according to an embodiment of the present invention. Referring to FIG. As shown in the figure, the crime risk notification system according to the embodiment of the present invention includes a
The
First, the
Next, the
Also, the
Next, the
The Big Data DB 140 stores various digital data and may store information such as crime data and crime risk according to an embodiment of the present invention. The big data DB 140 can be implemented through various digital data storage media such as a hard disk drive, a flash memory, a random access memory (RAM), and a solid state drive (SSD).
Meanwhile, the
The
The
The
FIG. 2 is a table showing an example of crime data counted according to predetermined classification criteria according to the present invention. According to the embodiment of the present invention, the number of crime occurrence times can be classified according to various classification criteria and can be classified according to, for example, a crime type?, A crime occurrence place?, A crime occurrence time? .
Each classification criterion can be composed of at least one item. The crime category (α) can be composed of different kinds of crime items (α1, α2, α3, ...). Such crime items can be organized according to the crime classification criteria of the Supreme Prosecutors' May be set. The crime data shows information on the number of crime incidents according to each crime type item (α1, α2, α3, ...).
In addition, each item (β1, β2, β3, ...) of crime occurrence place (β) can be set according to the type of crime occurrence place such as apartment, single house, highway, shop, , Schools, warehouses, subways, public transportation, and the like. According to another embodiment of the present invention, each item (? 1,? 2,? 3, ...) of the crime occurrence place (?) May be set according to the area of the place where the crime occurs, such as Seoul, Gyeonggi, Incheon, Busan, etc., or may be set according to a more detailed geographical classification.
The items of the crime occurrence time γ may be configured in units of a predetermined time as illustrated in FIG. 2, or may be configured in a time zone such as dawn, morning, day, morning, afternoon, Night, and the like.
According to the embodiment of the present invention, each item in a specific classification criterion may be set to an exclusive range mutually, and some range may be set to overlap. For example, each item? 1,? 2,? 3, ... of the crime occurrence time? May be set for mutually exclusive time zones as in the example of FIG. 2, 2 o'clock to 5 o'clock, and
On the other hand, the crime data may show the absolute value of the number of crimes according to each item in the classification standard, or may show the relative value with respect to the total number of crimes. If the crime data is represented by a relative value, the crime data for each item can be determined by the ratio of the number of crimes in the item to the total number of crimes according to each item in the same classification standard.
In this manner, the
According to one embodiment, the crime risk V (? 3,? 2,? 1) can be expressed as a three-dimensional vector having an x value of 52, a y value of 34, That is, the absolute crime risk level can be expressed by an n-dimensional vector having the number of crimes occurring in the items selected for each classification standard as the coordinates of each axis. Thus, when crime data is counted as n classification criteria, the absolute crime risk can be calculated as an n-dimensional vector.
FIG. 3 is a table showing an embodiment of a method in which the relative risk of crime is calculated. The
In order to calculate the relative risk of crime, the
According to the embodiment of FIG. 3, the
Next, the
According to an embodiment of the present invention, the
Meanwhile, according to a further embodiment of the present invention, the
The
The
4 is a table showing another embodiment of a method in which the relative risk of crime is calculated. In the embodiment of FIG. 4, a detailed description of the parts overlapping with the embodiment of FIG. 3 will be omitted.
According to the embodiment of FIG. 4, the relative risk of crime can be calculated as a weight for each item. The
Next, the
According to a further embodiment, the
Meanwhile, in the embodiment of FIGS. 3 and 4, the addition risk value or the weight value for an item not included in the user's priority item may be determined as a predetermined basic value. For example, in the example of FIG. 3 and FIG. 4, the added risk value or the weight value of? 2,? 4,? 2,? 4, etc., which are not included in the priority item of the user, However, the default value of these items is not limited to 0, and may be set to a different value.
5 is a diagram illustrating a method for generating a user crime risk using absolute crime risk and relative crime risk according to an embodiment of the present invention. According to an embodiment of the present invention, the relative risk of crime can be calculated in the form of a vector as described above in Fig. 3, and the risk of user crime can be generated by a vector sum of absolute crime risk and relative crime risk.
For example, the user crime risk V * (α3, β2, γ1) for crime C (α3) at 0 to 3 o'clock (γ1) in place S2 (β2) is calculated as the absolute crime risk vector Can be generated by the vector sum of V (α3, β2, γ1) and the relative crime risk vector V '(α3, β2, γ1). That is, the coordinate value of the absolute crime risk vector (x α3, y β2, z γ1), and the relative crime risk vector V '(α3, β2, γ1) coordinate values (x a' α3, y 'β2, z' γ1) one time, the coordinate values of the user crime risk vector V * (α3, β2, γ1 ) (x * α3, y * β2, z * γ1) is (x α3 + x 'α3, y β2 + y' β2, z? 1 + z '? 1 ).
6 is a diagram illustrating a method for generating a user crime risk using absolute crime risk and relative crime risk according to another embodiment of the present invention. According to another embodiment of the present invention, the relative crime risk may be calculated as a weight value for the user priority item as described above in Fig. 4, and the user crime risk may be calculated from the absolute crime risk vector And may be generated based on a value obtained by multiplying the coordinate by the weight.
More specifically, the user crime risk V * (α5, β4, γ2) for the crime E (α5) at 4 o'clock to 6 o'clock (γ2) at the place S4 (β4) is calculated as the absolute crime risk vector V may be generated by the coordinate values obtained by multiplying each coordinate value (x α5, β4 y, z γ2) a weight value of the item (k α5, β4 k, γ2 k) of (α5, β4, γ2). That is, when the absolute coordinates of the crime risk vector (x α5, y β4, z γ2), and the relative crime risk corresponding (k α5 = 1, k β4 = 1, k γ2 = 2), the user crime risk vector V * coordinate value (x * α5, y * β4 , z * γ2) of (α5, β4, γ2) can be determined as (x α5, y β4, 2z γ2).
The
7 is a flowchart illustrating a method for estimating the risk of crime using Big Data according to an embodiment of the present invention. Each step of FIG. 7 can be performed by the
First, the server collects crime data counted according to predetermined classification criteria (S110). The classification standard includes at least one of the type of the crime, the location of the crime and the time of occurrence of the crime, and the crime data represents the number of crimes according to each item in the classification standard.
Next, the server calculates an absolute crime risk level for a combination of items selected for each classification criterion based on the crime data (S120). The absolute crime risk is determined by a combination of the number of crimes in each item selected for each classification criterion. The absolute crime risk is determined as the higher the frequency of crime occurrence in each item is, the higher the frequency of occurrence of crime in each item, the n times the number of crimes in the selected item can be expressed as an n-dimensional vector with the coordinates of each axis.
On the other hand, the server obtains priority item information of the user for each classification criterion (S130). According to an embodiment of the present invention, the priority item information may be directly selected by each user and delivered to the server. According to another embodiment, the server may include priority item information of the user based on the personal information of each user Can be generated.
Next, the server calculates the relative risk of crime based on the obtained priority item information of the user (S140). According to one embodiment of the present invention, the relative risk of crime can be calculated in the form of a vector, such as absolute crime risk. That is, the server can calculate the risk risk value for each item based on the obtained priority item information of the obtained user, and calculate the relative risk type of the crime vector using the risk risk value. At this time, the coordinates of each axis of the relative crime risk vector are determined by the addition risk value of the selected item for each classification criterion. According to another embodiment of the present invention, the relative risk of crime can be calculated as a weight for each item.
According to a further embodiment of the present invention, the server can further collect social crime risk information in real time, and use the collected social crime risk information together with user priority item information to calculate the relative crime risk.
Thus, when the absolute crime risk and the relative crime risk are calculated, the server generates a user crime risk by combining the absolute crime risk and the relative crime risk (S150). If the relative risk of crime is calculated as a vector, the risk of user crime can be generated by a vector sum between the absolute and relative crime risk vectors. If the relative crime risk is calculated as a weight for each item, the user crime risk can be generated based on the absolute crime risk vector, the coordinates of each item multiplied by the corresponding weight.
Next, the server provides the generated user crime risk information to the user (S160). The server may transmit user crime risk information to the user terminal through the communication unit, and the user terminal receiving the information may output the user crime risk information as video and / or audio.
While the present invention has been described with reference to the particular embodiments, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the spirit and scope of the invention. Therefore, it is to be understood that those skilled in the art can easily deduce from the detailed description and the embodiments of the present invention that they fall within the scope of the present invention.
100: server 110:
120: Data collecting unit 130: Risk calculating unit
140: Big data DB 200: User terminal
210: communication unit 220: output unit
230:
Claims (8)
The method comprising the steps of: collecting crime data counted according to a predetermined classification criterion, the classification criterion including at least one of a crime type, a place of crime occurrence and a crime occurrence time, Indicates the number of times;
Calculating an absolute crime risk level for a combination of items selected for each classification criterion based on the crime data, wherein the absolute crime risk level is an n-dimensional level of the number of crimes occurring in each item selected for each classification criterion, Calculated as a vector;
Obtaining priority item information of a user for each classification criterion;
Calculating a relative crime risk based on the obtained priority item information of the user, calculating the relative crime risk as an n-dimensional vector having each axis selected for each classification criterion, The higher the priority of the user, the higher the risk of relative crime is determined;
Generating a user crime risk by combining the absolute crime risk vector and the relative crime risk vector for each item; And
Providing the generated user crime risk information to the user;
And calculating the risk of crime using the Big Data.
Wherein the user crime risk level is generated by a sum of the absolute crime risk vector and the relative crime risk vector.
The relative risk of crime is calculated as a weight for the priority item of the user,
Wherein the user crime risk level is generated based on a value obtained by multiplying a coordinate corresponding to the priority item in the absolute crime risk vector by the weight value.
Further comprising the step of acquiring the personal information of the user,
Wherein the priority item information of the user is generated based on the personal information of the user.
Collecting real-time social crime risk information using at least one of news data, social network service (SNS) data, and web data,
Wherein the relative risk of crime is calculated using the collected social crime risk information.
A communication unit for transmitting / receiving data to / from an external terminal or a network;
Wherein the classification data includes at least one of a crime type, a place of crime occurrence and a crime occurrence time, and the crime data includes at least one of the number of crime incidents A data collection unit for acquiring priority item information of a user for each classification criterion; And
And calculating an absolute crime risk level for a combination of the items selected for each classification criterion based on the crime data, wherein the absolute crime risk level is an n-dimensional vector having the number of crimes occurrence in each item selected for each classification criterion as coordinates of each axis And calculating the relative risk of crime based on the obtained priority item information of the user, wherein the relative risk of crime is calculated as an n-dimensional vector having each axis selected for each classification criterion, Wherein the relative risk of crime is determined to be higher as the user's priority for the item is higher, and a risk calculating unit for generating a user crime risk by combining the absolute crime risk vector and the relative crime risk vector for each item; / RTI >
Wherein the system provides the generated user crime risk information to the user terminal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150026941A KR101660160B1 (en) | 2015-02-26 | 2015-02-26 | A Method for Estimating a Crime Risk Using Big Data and A System for Reporting the Crime Risk Using thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150026941A KR101660160B1 (en) | 2015-02-26 | 2015-02-26 | A Method for Estimating a Crime Risk Using Big Data and A System for Reporting the Crime Risk Using thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20160104221A KR20160104221A (en) | 2016-09-05 |
KR101660160B1 true KR101660160B1 (en) | 2016-09-30 |
Family
ID=56938680
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020150026941A KR101660160B1 (en) | 2015-02-26 | 2015-02-26 | A Method for Estimating a Crime Risk Using Big Data and A System for Reporting the Crime Risk Using thereof |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101660160B1 (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101853386B1 (en) * | 2017-01-11 | 2018-06-15 | 동국대학교 산학협력단 | Apparatus and method for predicting crime |
WO2019103205A1 (en) * | 2017-11-24 | 2019-05-31 | 주식회사 웬즈데이에잇피엠 | System for predicting location-specific crime occurrence probability on basis of machine learning algorithm by using crime-related big data |
KR101975969B1 (en) * | 2017-12-05 | 2019-05-07 | 주식회사 이엠따블유 | System and method for assessing crime risk |
KR20190077682A (en) | 2017-12-26 | 2019-07-04 | 부경대학교 산학협력단 | System and Method for Analysing Urban Safety Index using Public Big Data and SNS Data |
KR20190080414A (en) | 2017-12-28 | 2019-07-08 | 부경대학교 산학협력단 | Preprocessing System and Method for Analyzing the Number of Disaster Safety Data Incidents and Related Information |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002156236A (en) | 2000-11-20 | 2002-05-31 | Denso Corp | Information display, route-setting apparatus and navigation apparatus |
KR101071194B1 (en) * | 2009-06-10 | 2011-10-10 | (주)시터스 | Method for selectively providing text message based on user location information in mobile phone |
KR101441664B1 (en) * | 2012-11-16 | 2014-09-29 | 목원대학교 산학협력단 | Crime map server using active data collection and crime risk area notification service methodes |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120051246A (en) * | 2010-11-12 | 2012-05-22 | (주)에스웨어 | Crime index interlocking type system for controlling emergency situation using cellular phone |
-
2015
- 2015-02-26 KR KR1020150026941A patent/KR101660160B1/en active IP Right Grant
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002156236A (en) | 2000-11-20 | 2002-05-31 | Denso Corp | Information display, route-setting apparatus and navigation apparatus |
KR101071194B1 (en) * | 2009-06-10 | 2011-10-10 | (주)시터스 | Method for selectively providing text message based on user location information in mobile phone |
KR101441664B1 (en) * | 2012-11-16 | 2014-09-29 | 목원대학교 산학협력단 | Crime map server using active data collection and crime risk area notification service methodes |
Also Published As
Publication number | Publication date |
---|---|
KR20160104221A (en) | 2016-09-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101660160B1 (en) | A Method for Estimating a Crime Risk Using Big Data and A System for Reporting the Crime Risk Using thereof | |
US20210216928A1 (en) | Systems and methods for dynamic risk analysis | |
US10673966B2 (en) | System and method for continuously monitoring and searching social networking media | |
US20210104001A1 (en) | Methods and Systems for Security Tracking and Generating Alerts | |
US8874071B2 (en) | Method and apparatus for prioritizing and routing emergent activity reporting | |
CA2773749C (en) | Public safety analysis system | |
US9792434B1 (en) | Systems and methods for security data analysis and display | |
CN110268409B (en) | Novel nonparametric statistical behavior recognition ecosystem for power fraud detection | |
US9213996B2 (en) | System and method for analyzing social media trends | |
CN104750768B (en) | Method and system for identification, monitoring and ranking event from social media | |
US20150145991A1 (en) | System and method for shared surveillance | |
CN108027888A (en) | Detected using the local anomaly of context signal | |
US9043317B2 (en) | System and method for event-driven prioritization | |
US20180150683A1 (en) | Systems, methods, and devices for information sharing and matching | |
US20140143013A1 (en) | System and method for analyzing social media trends | |
KR20160104223A (en) | A Method for a Crime Prediction Using a Crime Pattern Analysis based on Big Data and A System for the Same | |
US11934937B2 (en) | System and method for detecting the occurrence of an event and determining a response to the event | |
JP2018077821A (en) | Method, program, server device, and processor for generating predictive model of category of venue visited by user | |
KR20160104940A (en) | A Method for Providing Event Occurrence Information Using Big Data and A System for the Same | |
US20150348059A1 (en) | System and method for determining the shopping phase of a shopper | |
Drosio et al. | The Big Data concept as a contributor of added value to crisis decision support systems | |
KR101738745B1 (en) | A Method for a Crime Prediction by Estimating a Cell Value and A System for the Same | |
Singleton et al. | Twitter Analytics-Based Assessment: Are the United States Coastal Regions Prepared for Climate Changeƒ | |
US20160342846A1 (en) | Systems, Methods, and Devices for Information Sharing and Matching | |
CN116797180A (en) | Complaint early warning method, complaint early warning device, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
E701 | Decision to grant or registration of patent right | ||
GRNT | Written decision to grant | ||
FPAY | Annual fee payment |
Payment date: 20190603 Year of fee payment: 4 |