KR101785823B1 - Apparatus and method for risk prediction using big-data - Google Patents
Apparatus and method for risk prediction using big-data Download PDFInfo
- Publication number
- KR101785823B1 KR101785823B1 KR1020160012062A KR20160012062A KR101785823B1 KR 101785823 B1 KR101785823 B1 KR 101785823B1 KR 1020160012062 A KR1020160012062 A KR 1020160012062A KR 20160012062 A KR20160012062 A KR 20160012062A KR 101785823 B1 KR101785823 B1 KR 101785823B1
- Authority
- KR
- South Korea
- Prior art keywords
- user
- information
- risk
- walking
- walking information
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004891 communication Methods 0.000 claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 11
- 230000005021 gait Effects 0.000 description 7
- 230000009194 climbing Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- 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
- G06Q90/00—Systems or methods specially adapted for administrative, commercial, financial, managerial or supervisory purposes, not involving significant data processing
-
- H04W4/028—
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Computer Security & Cryptography (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a method and an apparatus for evaluating a user's risk index based on information related to a user's walking, information on risk prediction parameters received from the outside, and information on walking of an accidenter.
According to an embodiment of the present invention, there is provided a communication system including a communication unit for transmitting / receiving information to / from an external communication device, receiving accidenter walking information and risk prediction parameter information from an external server, detecting a movement pattern according to the user's biological signal, Wherein the control unit controls each unit of the detection unit and the risk prediction apparatus to calculate a risk index indicating a danger level of the user based on the risk prediction parameter information, Calculating the degree of similarity between the occupant walking information and the user walking information, correcting the risk index based on the result of the similarity calculation, and if the corrected risk index is equal to or greater than a predetermined threshold value, And a control unit for informing the user of the corrected risk index There is a risk that the device could be provided by Jing.
Description
The present invention relates to a large data-based risk prediction apparatus and method, and more particularly to a large data-based risk prediction apparatus and method for estimating a risk index of a user based on information related to a user's walking, information on risk prediction parameters received from the outside, And more particularly,
With the development of information and communication technology, various portable electronic products for users' convenience such as smart phones and smart tablets appeared on the market. Most of handsets include a wireless communication module, so users can connect to the network at any time to exchange various types of data such as multimedia. Accordingly, the terminals can share various types of data generated by the user and sensing data generated by sensing the terminal itself. As the number of users of such terminals has increased explosively, the data shared and collected among the users have also increased exponentially. Although the amount of the data is too large and its form is variable, it is not easy to handle, but very meaningful information can be extracted depending on the method of analyzing and processing the data. A related technology is Big Data Analysis. Big data analysis techniques represent a large set of formal or unstructured data beyond existing data collection, storage, management, and analysis capabilities, and techniques for extracting value from these data and analyzing the results.
The development of Big Data Technology, which is characterized by the generation, collection, analysis and expression of various kinds of large data, predicts the more diverse modern society more accurately, works efficiently, provides customized information for individualized modern society members, Management, and analysis, and realizes technologies that were not possible in the past. Thus, Big Data presents the possibility of providing valuable information to society and mankind in all fields such as politics, society, economy, culture, science and technology, and the importance of it is highlighted.
On the other hand, in relation to public safety, various studies are being conducted on various services that prevent accidents and share countermeasures against risk factors with the general public. However, most of them are limited to performing superficial information analysis or simple notification service of information, and can not provide personalized information to each individual. In this regard, the big data analysis technique can be suggested as a tool for public safety. However, there is still a lack of research in related fields.
SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and it is an object of the present invention to provide a risk prediction apparatus and method capable of predicting a risk index based on a current time and a current position of a user, And the like.
The present invention also aims to provide an optimal risk index for each individual situation.
According to an aspect of the present invention, there is provided a risk prediction apparatus for predicting a risk of a user, the apparatus comprising: an information transmitting / receiving unit for communicating information with an external communication apparatus; And the risk prediction parameter information is information indicating a current time and a position of the user, and the risk prediction parameter information is information indicating a characteristic of a person who has experienced an accident while walking on the gait path related to the current time and the position of the user, Information indicating the risk involved; A sensing unit for sensing a biometric signal of the user and a movement pattern corresponding to the movement of the user; And a controller for controlling each unit of the risk prediction apparatus, calculating a risk index indicating a degree of danger of the user based on the risk prediction parameter information, and calculating a risk index based on the user's walking information Calculates the degree of similarity between the occupant walking information and the user walking information, corrects the risk index based on the result of the similarity calculation, and if the corrected risk index is equal to or greater than a predetermined threshold value, A control unit for informing the user of the index; The risk prediction apparatus according to the present invention can be provided.
Here, the controller may select the past user walking information related to the current time and the user location, which has not occurred in the past user walking information, as the safe walking information, and the user walking information and the safe walking information Calculates the similarity, and corrects the risk index based on the calculated similarity.
According to another embodiment of the present invention, there is provided a method for controlling an accident, comprising the steps of: receiving an accidenter's walking information and risk prediction parameter information from an external server; Wherein the risk prediction parameter information is information indicating a risk according to a current time and a location of the user; Sensing a biological signal of the user and a movement pattern according to the movement of the user; Calculating a risk index indicating a risk level of the user based on the risk prediction parameter information; Generating user walking information based on the bio-signal and the movement pattern according to the movement of the user; Calculating a degree of similarity between the occupant walking information and the user walking information; And correcting the risk index based on the result of the similarity calculation. The risk prediction method of the present invention can be provided.
According to the present invention, the user's risk index can be calculated based on the current time and position, and the calculated risk index can be corrected based on the user's walking information, thereby accurately and easily calculating the risk according to the user's situation have.
In particular, according to the present invention, it is possible to calculate the degree of similarity between the user walking information and the occupant walking information, and to correct the degree of risk according to the degree of similarity of the walking information of the user with the walking information of the occupant.
1 is a diagram illustrating a risk prediction apparatus according to an embodiment of the present invention.
2 is a view showing a state in which a risk prediction apparatus according to an embodiment of the present invention is actually used.
3 is a diagram illustrating a method for estimating risk prediction parameter information according to an embodiment of the present invention.
4 is a diagram illustrating weights of risk prediction parameter information according to an embodiment of the present invention.
5 is a diagram illustrating a similarity measurement method according to an embodiment of the present invention.
6 is a diagram illustrating a risk prediction method according to an embodiment of the present invention.
The present invention relates to a device and method for predicting a big data-based risk, and more particularly, to a device and method for predicting a big data based risk based on information related to a walking of a user acquired by a terminal, information on risk prediction parameters received from the outside, And a method and an apparatus for evaluating a risk index. Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings.
1 is a diagram illustrating a
The
The
The
The
The calculation of the degree of similarity, the calculation of the risk index, and the correction of the risk index will be described in more detail with reference to FIGS. 3 to 5.
Meanwhile, the
2 is a diagram showing a state in which a risk prediction apparatus (not shown) according to an embodiment of the present invention is actually used. In FIG. 2, it is assumed that each of the users user_a, user_b, and user_c is carried by the risk prediction apparatus. According to FIG. 2, each user is located in the Hallasan Spirit room, and the time is January 1, 2016 at 14:30.
2, the
According to the above description, the risk prediction apparatus according to the embodiment of the present invention can receive the accidenter walking information and the risk prediction variable information from the
In addition, the risk prediction apparatus according to the present invention can correct the calculated risk index based on the similarity. These risk indices can be used to calculate a more personalized risk index.
For example, the user user_b may receive a risk value of 70 according to each combination of weights. In this case, if the similarity degree between the user walking information of the user user_b generated by the risk prediction apparatus and the accidental walking information received from the
3 is a diagram illustrating a method for estimating risk prediction parameter information according to an embodiment of the present invention. Figures 3 (a), 3 (b), and 3 (c) show various information referenced to determine the weights included in the risk prediction variable information. In the graph of FIG. 3 (a), the horizontal axis represents information indicating a specific location or a specific area, and the vertical axis indicates an accident-related value in each location or area. In this case, the accident-related numerical value may be the number of the accidents or the ratio of the accidents relative to the total number of persons using the specific location or the specific area, but the present invention is not limited thereto. In the graph of FIG. 3 (b), the horizontal axis may be a specific time or a specific time zone or a specific time range or a specific time range or a specific day of the week, month, year, season, and the like. In the graph of Fig. 3 (b), the vertical axis indicates accident-related numerical values. Fig. 3 (c) is a plane map showing the accident related numerical values of the specific area according to the positional coordinates, and the contour line and the shading brightness are expressed based on the value of the accident related numerical value. The vertical axis in FIG. 3 (c) may be the x coordinate of the GPS and the horizontal axis may be the y coordinate of the GPS. The shade is closer to black as the incident-related numerical value is larger, and the shade is closer to black as the incident- related numerical value is smaller.
3 (a) is a graph showing the accident-related numerical values according to the position or the area. The graph can be calculated from accident-related statistics by location or area. At this time, the weight for the risk prediction parameter information may be determined in proportion to the value of the accident related value. Alternatively, the weight for the risk prediction parameter information may be determined according to whether the value of the accident-related value is larger or smaller than a predetermined threshold value (thr_a, thr_b). For example, if the incident-related number exceeds the threshold value thr_a, the location or area associated with the incident-related value can be assigned the largest weight. If the incident-related value is greater than the threshold value thr_b but less than the threshold value thr_b, the location or region associated with the incident-related value may be assigned a moderate weight. If the incident-related value is less than the threshold value thr_b, the location or area associated with the incident-related value can be assigned the smallest weight. Accordingly, the largest weight can be assigned to the L3 region and the L7 region. If the user is located at L3 and L7, the risk prediction parameter information for the user may include a large weight, and thus the risk index of the user may be increased to be in a dangerous state.
3 (a) can also be a graph showing accident-related numerical values with respect to time. That is, when the legend indicating the time in the accident-related statistical data is expressed in discrete time units such as year, month, week, day, hour, minute, day of the week, seasons, Can be expressed by the graph of Fig. 3 (a), which is a legend of the horizontal axis. Hereinafter, weighting based on the respective threshold values is the same as described above, so that a description thereof will be omitted.
3 (b) is a graph showing the accident-related numerical values with respect to time. The graph can be computed from accident-related statistics over time. As in the case of FIG. 3 (a), the weight for the risk prediction parameter information may be determined in proportion to the value of the accident related value. Or the weight for the risk prediction parameter information may be determined according to whether the value of the accident related value is greater than or less than a predetermined threshold value (thr_a, thr_b). Referring to FIG. 3 (b), since the time intervals T1 to T2 and the time intervals T3 to T4 have accident-related values between the threshold values thr_a and thr_b, a middle weight can be allocated in the time interval. Since the time intervals T2 to T3 have accident-related values equal to or greater than the threshold value thr_a, the largest weight values can be allocated. Since the time interval T1 or after the time interval T4 has an accident related value less than the threshold value thr_b, the smallest weight can be allocated in the time interval. That is, when a specific user performs an activity such as climbing at a time corresponding to the time before the time interval T1, the weight of the risk prediction parameter information for the user's climbing time has the lowest value, Risk index can be calculated lower.
Fig. 3 (c) is a graph showing accident-related numerical values according to positional coordinates. As described above, in FIG. 3 (c), it is possible to have a higher accident-related numerical value nearer to white and a lower accident-related numerical value nearer to black. As in the case of FIG. 3 (a), the weight for the risk prediction parameter information may be determined in proportion to the value of the accident related value. Accordingly, the accident-related value of the point P1 is larger than the accident-related value of the point P2, and in particular, the largest weight can be applied to the point P1. Therefore, a user's risk prediction device located near the point P1 can be evaluated as having a high risk index of the user.
As described above, the risk prediction parameter information can be selected based on various accident-related statistics. However, references for weighting risk prediction parameter information are not limited to this. According to a preferred embodiment of the present invention, the risk prediction parameter information may be determined based on time-based accident statistics, location-based accident statistics, and weather-related accident statistics. At this time, the accident statistics over time may include monthly accident statistics, accident statistics by day of the week, and accident statistics by time of day. The risk prediction parameter information may be determined based on information on the communication environment of the risk prediction apparatus. Here, the information on the communication environment may include the number of base stations capable of performing wireless communication by the risk prediction device, the strength of a radio signal sensed by the risk prediction device, and the number of available GPS satellites. In addition, the risk prediction parameter information may be determined based on rescue accessibility according to location. In addition, the risk prediction parameter information may be determined based on the age of the user.
4 is a diagram illustrating weights of risk prediction parameter information according to an embodiment of the present invention. FIG. 4 is a table of weights according to respective weight variables. The right side of the table shows weight values determined by various statistical data. According to FIG. 4, A, the weight variable according to the monthly accident statistics is B, the weight variable according to the accident statistics according to the day of the week is C, the weight variable according to the time-based accident statistics is T, D, the weight parameter according to the number of base stations detected in the area where the risk prediction device is located is R, the number of effective GPS satellites in the area where the risk prediction device is located is Y, and the weight variable according to the accident statistics by the national park is F , G is the weight variable according to the weather accidents statistics, G is the weight variable according to the 119 response time of the region where the risk prediction device is located, and P is the weight variable according to the fire helicopter dispatch time in the region where the risk prediction device is located. The weight value of each weight variable may be a predetermined fixed weight value not depending on each accident statistic. When the weighting variable is determined as described above, the median value Ens for calculating the risk index can be calculated by the following equation.
(1)
The median value is a value calculated from a weight variable according to time and area, and the risk index can be calculated by applying the remaining weight variable to the median value. At this time, the median value may be converted to a risk index by the following equation such that the maximum risk index is a specific value.
(2)
That is, referring to FIG. 4, it is possible to easily calculate the risk index by selecting a weight value according to the position and time of the user or the risk prediction apparatus for each weight parameter, and assigning the weight value to the two equations. However, FIG. 4 and the two equations are only examples of obtaining the risk index from the risk prediction parameter information, and the present invention is not limited thereto.
5 is a diagram illustrating a similarity measurement method according to an embodiment of the present invention. In particular, FIG. 5 shows the similarity between the user walking information and the accidental walking information, and the comparison between the user walking information and the safe walking information. In FIG. 5, the abscissa of each graph represents time, and the ordinate represents values of signals or information.
The risk prediction apparatus according to the present invention generates user walking information based on a biological signal and a movement pattern corresponding to a movement of a user, calculates the similarity between the occupant walking information and the user walking information, The risk index can be corrected. The accidenter walking information is information indicating a characteristic of a person who has experienced an accident while walking on a walking path related to the current time and the position of the user. The accidenter walking information includes a time related to the current time, And movement pattern information according to the bio-signal and motion information of a person who has experienced an accident at a position related to the motion. The time associated with the current time may be a year, month, day, hour, minute, time zone, time range, seasonal time that is the same as at least one of the year, month, day, hour, minute, . The location associated with the user's location may be within the predetermined distance range from the GPS coordinates of the user, the same administrative area or the same terrain.
Meanwhile, the risk prediction apparatus according to the present invention selects safety gait information as the past user gait information related to the current time and the user position, which has not occurred in the past user gait information, The similarity of the safe walking information can be calculated and the risk index can be corrected based on the calculated similarity. At this time, the safe walking information may be selected in a different manner. That is, the risk prediction apparatus can sort the past user walking information, which is included in the past user walking information, together with the safety index that is less than the preset safety index as the safe walking information.
In summary, when the user walking information and the occupant walking information are similar to the current time and the user's position, the user can be determined to be in a dangerous situation. That is, the increase width of the crisis index calculated according to the degree of similarity between the user walking information and the accidenter walking information can be determined. According to a preferred embodiment of the present invention, the degree of similarity can be calculated by a correlation between user walking information and accidenter walking information. For any two pieces of information, correlation 1 indicates that the two pieces of information are completely identical, and correlation 0 indicates that the two pieces of information are not related to each other or linearly. For example, if the correlation between the user walking information and the occupant walking information is 0.5 to 0.7, the calculated risk index can be added to 40. [ Alternatively, if the correlation between the user walking information and the occupant walking information is 0.4 to 0.5, the calculated risk index may be increased by 30. If the correlation between the user walking information and the occupant walking information is 0.4 to 0.3, the calculated risk index can be added to 20.
If the user walking information and the safe walking information are similar to the current time and the user's position, the user can be determined to be safe. That is, the decrease width of the crisis index calculated according to the similarity between the user walking information and the safe walking information can be determined. For example, if the correlation between the user walking information and the accidenter walking information is 0.5 to 0.6, the calculated risk index may be subtracted from 40. Alternatively, when the correlation between the user walking information and the occupant walking information is 0.4 to 0.5, the calculated risk index may be subtracted from 30. Alternatively, when the correlation between the user walking information and the occupant walking information is 0.3 to 0.4, the calculated risk index may be subtracted from 20.
According to an embodiment of the present invention, the user walking information, the accidental walking information, and the safe walking information may include a biological signal and movement pattern information. In FIG. 5, sig_a and pt_a represent biometric signals and movement pattern information of the user walking information, sig_b and pt_b refer to biometric signals and movement pattern information of the accidental walking information, and sig_c and pt_c represent biometric signals of safety walking information And movement pattern information. The risk prediction apparatus according to the embodiment of the present invention can calculate the degree of similarity between the similarity between the biological signals and the movement pattern information individually. In this case, the similarity between the user walking information and the accidenter walking information may be a linear sum of the similarity between the biometric signals of the two walking information and the movement pattern information of the two walking information. Or the similarity between the user walking information and the accidenter walking information may be an average value of the similarities between the similarity between the biometric signals of the two walking information and the movement pattern information of the two walking information. However, the method of calculating the similarity between the two walking information is not limited to this.
Meanwhile, according to another embodiment of the present invention, the risk prediction apparatus can transmit the location of the user and the user's walking information to the external server. Accordingly, the external server calculates the risk index according to the current time and the location of the user, and corrects the risk index based on the similarity between the user walking information and the user walking information or the user walking information and the safe walking information . The external server can transmit the calibrated risk index to the risk prediction device. If the risk index is greater than or equal to the predetermined threshold value, the external server can transmit a warning signal to the risk prediction device.
According to an embodiment of the present invention, a risk prediction apparatus that utilizes user walking information, occupant walking information, safe walking information, risk prediction parameter information, and various statistical information related thereto can be provided. The information is information that is routinely collected and analyzed by the risk prediction devices. Thus, the risk index is one of the results analyzed by the big data technique.
6 is a diagram illustrating a risk prediction method according to an embodiment of the present invention. Referring to FIG. 6, a method for predicting a risk according to an embodiment of the present invention includes: receiving information on an accidenter's walking information and predicted risk variable from an external server (S110); detecting a movement based on the user's bio- (S130) of calculating a risk index indicative of a degree of danger of the user based on the risk prediction parameter information (S130); detecting a pattern based on the biological signal and a movement pattern according to the movement of the user (S140) of calculating gait information, step (S150) of calculating a similarity degree between the accidental gait information and the user walking information, and correcting the risk index based on the similarity calculation result (S160) . The user walking information generating step S140 and the similarity calculating step S150 may be performed after the user's biological signal and movement pattern sensing step S120 and the risk index calculating step S130, S160) may be performed. According to an embodiment of the present invention, the risk prediction method may further include calculating a similarity between the user walking information and the safe walking information, and correcting the risk index based on the similarity between the user walking information and the safe walking information have.
In the step of calculating the risk index (S130), the risk prediction parameter information may be determined based on time-based accident statistics, location-based accident statistics, and weather-related accident statistics. Alternatively, the risk prediction parameter information may be determined based on information on the communication environment of the risk prediction device. Alternatively, the risk predictor information can be determined based on location rescue accessibility. Alternatively, the risk prediction parameter information may be determined based on the age of the user.
The detailed description of each step is omitted since it has been discussed with reference to FIGS. 1 to 5. FIG.
According to the present invention, the user's risk index can be calculated based on the current time and position, and the calculated risk index can be corrected based on the user's walking information, thereby accurately and easily calculating the risk according to the user's situation have.
In particular, according to the present invention, it is possible to calculate the degree of similarity between the user walking information and the occupant walking information, and to correct the degree of risk according to the degree of similarity of the walking information of the user with the walking information of the occupant.
While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention. Accordingly, it is to be understood that within the scope of the appended claims, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
100: Risk prediction device
200: external server
Claims (10)
A communication unit for transmitting and receiving information to and from the external communication device, receiving information of the accidenter's walking information and the predicted risk variable from an external server, the accidenter's walking information includes a current time and a walking path associated with the user's location Wherein the risk prediction parameter information is information indicating a risk according to the number of base stations capable of performing wireless communication with the communication unit;
A sensing unit for sensing a biometric signal of the user and a movement pattern corresponding to the movement of the user; And
Wherein the control unit controls each unit of the risk prediction apparatus, calculates a risk index indicating a risk level of the user based on the risk prediction parameter information, and calculates user risk information based on the bio- Calculating the degree of similarity between the occupant walking information and the user walking information, correcting the calculated risk index based on the similarity calculation result, and if the corrected risk index is equal to or greater than a predetermined threshold value, And a control unit for informing the user of the risk index.
Wherein,
Selecting the past user walking information related to the current time and the user's position among the user walking information of the past that did not cause an accident as safety walking information,
Calculates the similarity between the user walking information and the safe walking information,
Correcting the risk index based on the calculated similarity,
The degree of increase of the risk index increases as the degree of similarity between the user walking information and the accidenter walking information increases,
Wherein the degree of decrease of the risk index increases as the degree of similarity between the user walking information and the safe walking information increases.
Wherein the control unit selects the past user walking information having the risk index calculated together with the past user walking information less than a predetermined safety index as the safe walking information.
Wherein the risk prediction parameter information is determined based on time-based accident statistics, location-based accident statistics, and weather-related accident statistics.
Wherein the accident statistics according to the time include monthly accident statistics, accident statistics by day of the week, and accident statistics by time of day.
Wherein the risk prediction parameter information is determined based on information on a communication environment of the risk prediction apparatus.
Wherein the information on the communication environment includes the number of base stations capable of performing wireless communication with the communication unit, the strength of a radio signal sensed by the communication unit, and the number of valid GPS satellites.
Wherein the risk prediction parameter information is determined on the basis of the positional rescue approach.
Wherein the risk prediction parameter information is determined based on the age of the user.
Receiving from the external server the information of the occupant walking information and the predicted risk variable, the occupant walking information includes a current time and a movement pattern according to the movement of the user who experienced the accident in the walking path related to the user's position Information indicating a risk according to the number of base stations capable of performing wireless communication with the risk prediction device;
Sensing a biological signal of the user and a movement pattern according to the movement of the user;
Calculating a risk index indicating a risk level of the user based on the risk prediction parameter information;
Generating user walking information based on the bio-signal and the movement pattern according to the movement of the user;
Calculating a degree of similarity between the occupant walking information and the user walking information;
Correcting the calculated risk index based on the result of the similarity calculation; And
And notifying the user of the corrected risk index if the corrected risk index is greater than or equal to a predetermined threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020160012062A KR101785823B1 (en) | 2016-01-31 | 2016-01-31 | Apparatus and method for risk prediction using big-data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020160012062A KR101785823B1 (en) | 2016-01-31 | 2016-01-31 | Apparatus and method for risk prediction using big-data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| KR20170091272A KR20170091272A (en) | 2017-08-09 |
| KR101785823B1 true KR101785823B1 (en) | 2017-10-16 |
Family
ID=59652493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020160012062A KR101785823B1 (en) | 2016-01-31 | 2016-01-31 | Apparatus and method for risk prediction using big-data |
Country Status (1)
| Country | Link |
|---|---|
| KR (1) | KR101785823B1 (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4064521B2 (en) * | 1998-04-07 | 2008-03-19 | 東芝ソリューション株式会社 | Iriyama management system |
| JP2012118915A (en) * | 2010-12-03 | 2012-06-21 | Fujitsu Ten Ltd | Information notification system, server device, on-vehicle device, and information notification method |
| KR101513370B1 (en) * | 2013-12-23 | 2015-04-17 | 대한지적공사 | Method and system for providing safety information using location information |
| JP5838879B2 (en) * | 2012-03-22 | 2016-01-06 | 株式会社デンソー | Prediction system |
-
2016
- 2016-01-31 KR KR1020160012062A patent/KR101785823B1/en active IP Right Grant
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4064521B2 (en) * | 1998-04-07 | 2008-03-19 | 東芝ソリューション株式会社 | Iriyama management system |
| JP2012118915A (en) * | 2010-12-03 | 2012-06-21 | Fujitsu Ten Ltd | Information notification system, server device, on-vehicle device, and information notification method |
| JP5838879B2 (en) * | 2012-03-22 | 2016-01-06 | 株式会社デンソー | Prediction system |
| KR101513370B1 (en) * | 2013-12-23 | 2015-04-17 | 대한지적공사 | Method and system for providing safety information using location information |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20170091272A (en) | 2017-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6295250B2 (en) | Method and apparatus for positioning | |
| US20150213555A1 (en) | Predicting driver behavior based on user data and vehicle data | |
| CN106901444B (en) | A kind of physiology monitor Intelligent insole | |
| US10430528B2 (en) | Method and system for managing space configurations | |
| JP6351860B2 (en) | Action identification device, air conditioner and robot control device | |
| EP2880401A1 (en) | Positioning apparatus, computer program, and appliance control system | |
| KR102167296B1 (en) | Life-based care system for the elderly | |
| US20160242680A1 (en) | Intelligent comfort level monitoring system | |
| EP3525673B1 (en) | Method and apparatus for determining a fall risk | |
| EP2541474A1 (en) | Monitoring a user activity using a mobile device | |
| CN104269025A (en) | Wearable type single-node feature and position selecting method for monitoring outdoor tumble | |
| CN109343051A (en) | A kind of multi-Sensor Information Fusion Approach driven for advanced auxiliary | |
| JP2008086479A (en) | Physical activity measuring system | |
| Choo et al. | Automated detection of construction work at heights and deployment of safety hooks using IMU with a barometer | |
| KR101785823B1 (en) | Apparatus and method for risk prediction using big-data | |
| KR102173918B1 (en) | Multi-sensor based walking status analysis system and method thereof | |
| KR102481794B1 (en) | Method and Apparatus of danger detection based on time series analysis of human activities | |
| US20230389880A1 (en) | Non-obtrusive gait monitoring methods and systems for reducing risk of falling | |
| CN106920366B (en) | Human body falling detection method, device and system | |
| CN115024690A (en) | Alcohol metabolism detection method, computer device and storage medium | |
| CN114098719A (en) | Action detection method and device and wearable device | |
| CN113415292A (en) | Driving takeover capability evaluation method and electronic device | |
| US11564439B2 (en) | System and method for determining foot strike pattern | |
| CN106092133A (en) | Start the decision method of guest mode, device | |
| Ahmed et al. | Recognition of professional activities with displaceable sensors |
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 |