CN111031487B - Method for real-time detection of tourist trip risk by using artificial intelligence - Google Patents
Method for real-time detection of tourist trip risk by using artificial intelligence Download PDFInfo
- Publication number
- CN111031487B CN111031487B CN201911299564.9A CN201911299564A CN111031487B CN 111031487 B CN111031487 B CN 111031487B CN 201911299564 A CN201911299564 A CN 201911299564A CN 111031487 B CN111031487 B CN 111031487B
- Authority
- CN
- China
- Prior art keywords
- risk
- tourists
- coordinate
- equal
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q50/14—Travel agencies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/35—Services specially adapted for particular environments, situations or purposes for the management of goods or merchandise
Abstract
The method for detecting the trip risk of the tourists in real time by using the artificial intelligence can quickly and effectively extract the behavior characteristics of a plurality of tourists by analyzing the behavior track of the tourists in the trip process, and predict the risk probability of the tourists in the trip process according to the behavior characteristics. The channel neural network calculates periodic behavior characteristics on a plurality of time dimensions, and combines positioning information to convert the information into risk probability. The high-precision real-time prediction model can be constructed for the data sequences of multiple tourists and different behavior tracks in a low training cost mode. Because the time dimension and the geographical positioning option are introduced into the risk assessment model as additional input, the time step length for training the neural network risk assessment model can be greatly shortened, the training cost can be effectively reduced, and the prediction precision is improved.
Description
Technical Field
The invention relates to the technical field of data security and protection of information technology, in particular to a method for detecting trip risks of tourists in real time by using artificial intelligence.
Background
At present, the turnover of the tourism industry is rapidly increased by 10% every year, and effective means for evaluating the trip risk of tourists is lacked while the tourism industry is greatly developed. The problems of unauthorized group separation, illegal tourism and the like are frequently prohibited during traveling. For tourists with potential high-risk behaviors, the method can discover and take preventive measures in time, and is the most effective means for reducing risks.
Generally, tourists, who are prone to high-risk activities, have the following activities:
1, higher voluntary action
2, often act separately from the bolus.
In the traditional mode, distinguishing, early warning prompting and the like are carried out by depending on the personal work experience of the tour guide, so as to control the generation of risks. The invention hopes to automatically give early warning and prompt to the guide and the tourist through the artificial intelligence technology and the analysis of the behavior track, thereby strengthening the safety consciousness and preventing the generation of risks.
Disclosure of Invention
In order to overcome the defects of the technology, the invention provides a method for detecting the trip risk of the tourist in real time by using artificial intelligence, which utilizes the artificial intelligence neural network to combine geographical positioning and network communication to send early warning information to the possible risk behavior of the tourist.
The technical scheme adopted by the invention for overcoming the technical problems is as follows:
a method for real-time detection of tourist travel risks by using artificial intelligence comprises the following steps:
a) collecting coordinate positions of N tourists in a tourist group at fixed time intervals, uploading the obtained coordinate positions to a server, and obtaining a circular range capable of containing all the tourists according to the coordinate positions of all the tourists, wherein the center coordinate of the circular range is OiThe center of a circle coordinate OiAn uploading server, t is a timestamp when the circle center coordinates are reported to the server, i is more than or equal to 1 and less than or equal to t, wherein the circle center OiIs expressed as (x)middle,i=t,ymiddle,i=t) X is a longitude value and y is a latitude value, wherein:
xmax,i=tmaximum in longitude, x, of the set of coordinates of all guests at time tmin,i=tThe minimum value in longitude in the coordinate set of all the tourists;
ymax,i=tis the maximum value in latitude, y, in the coordinate set of all the tourists at the moment tmin,i=tThe minimum value in latitude in the coordinate set of all the tourists;
b) the coordinate series from the departure to the time t of the N tourists is
[(xm,j=1ym,j=1),(xm,j=2ym,j=2),...(xm,j=tym,j=t)]J is a timestamp serial number, j is more than or equal to 1 and less than or equal to t, m is any visitor, m is more than or equal to 1 and less than or equal to N, and the coordinate sequence of each visitor is uploaded to the server;
c) through a formula of & 'O'i,m=[O′1,m,O′2,m,...,O′,tm]Calculating the center coordinates o 'of a circular range which can contain the remaining visitors after the visitor m is removed'i,mCollecting m is more than or equal to 1 and less than or equal to N, and uploading the collection to a server;
d) the server follows the formula | Oi-O′i,mI calculating the coordinate of the center of a circle as OiAnd a circle center coordinate o 'of a circular range in which the guest m is removed and the remaining guests can be contained'i,mAbsolute value of difference, | Oi-O′i,mThe larger the value of | indicates the larger the probability that the tourist m leaves the group, when | Oi-O′i,mAnd after the value of | exceeds a set threshold value, the server sends the alarm information to the mobile phone for guiding.
Further, step d) is performed by the formulaCalculating Oi,mWherein alpha is the group bulk, alpha is more than or equal to 1 and less than or equal to 99, Oi,mA larger value of (a) indicates a higher possibility that the guest m alone gets out of the group,the risk weight is taken according to the risk prompt of chapter three of the national travel administration No. 41 'travel safety management method', when the risk prompt is no risk,when the risk cue is a four-level risk,when the risk cue is a tertiary risk,when the risk cue is a secondary risk,when the risk cue is a first-degree risk,
the invention has the beneficial effects that: by analyzing the behavior track of the tourists in the trip process, the behavior characteristics of a plurality of tourists can be extracted quickly and effectively, and the risk probability of the tourists in the trip process is predicted according to the behavior characteristics. The channel neural network calculates periodic behavior characteristics in multiple time dimensions (such as year, month, week and day) and combines positioning information to convert the information into risk probability. The high-precision real-time prediction model can be constructed for the data sequences of multiple tourists and different behavior tracks in a low training cost mode. Because the method introduces the options of time dimension and geographical positioning into the risk assessment model as additional input, the time step length for training the neural network risk assessment model can be greatly shortened, the training cost can be effectively reduced, and the prediction precision is improved.
Detailed Description
The present invention is further explained below.
A method for real-time detection of tourist travel risks by using artificial intelligence comprises the following steps:
a) collecting coordinate positions of N tourists in a tourist group at fixed time intervals, uploading the obtained coordinate positions to a server, and obtaining a circular range capable of containing all the tourists according to the coordinate positions of all the tourists, wherein the center coordinate of the circular range is OiThe center of a circle coordinate OiAn uploading server, t is a timestamp when the circle center coordinates are reported to the server, i is more than or equal to 1 and less than or equal to t, wherein the circle center OiIs expressed as (x)middle,i=t,ymiddle,i=t) X is a longitude value, y is a latitude value, the latitude takes the equator as a boundary line, and north is a positive direction; the longitude is defined by the meridian of this initial meridian and the eastern direction is defined as the positive direction. The steps of installing the server environment are: installing a server ServerA having an International IPThe address can be accessed by other internet devices according to the IP address or the domain name. And opening a specific service port to respond to a message request sent by the client or the mobile terminal. And then, service software is built on a server, identity authentication, line registration and geographic position verification can be provided, and a platform environment required by the operation of the artificial intelligent neural network system is built, wherein the platform environment comprises Ubuntu 18.0.464 bit operating system, Python3 and other software. Wherein:
xmax,i=tmaximum in longitude, x, of the set of coordinates of all guests at time tmin,i=tThe minimum value in longitude in the coordinate set of all the tourists;
ymax,i=tis the maximum value in latitude, y, in the coordinate set of all the tourists at the moment tmin,i=tThe minimum value in latitude in the coordinate set of all the tourists;
b) the coordinate series from the departure to the time t of the N tourists is
[(xm,j=1ym,j=1),(xm,j=2ym,j=2),...(xm,j=tym,j=t)]J is a timestamp serial number, j is more than or equal to 1 and less than or equal to t, m is any visitor, m is more than or equal to 1 and less than or equal to N, and the coordinate sequence of each visitor is uploaded to the server;
c) through a formula of & 'O'i,m=[O′1,m,O′2,m,...,O′,tm]Calculating the center coordinates o 'of a circular range which can contain the remaining visitors after the visitor m is removed'i,mCollecting m is more than or equal to 1 and less than or equal to N, and uploading the collection to a server;
d) the server follows the formula | Oi-O′i,mI calculating the coordinate of the center of a circle as OiAnd a circle center coordinate o 'of a circular range in which the guest m is removed and the remaining guests can be contained'i,mAbsolute value of difference, | Oi-O′i,mThe larger the value of | indicates that the more distant the tourist m is from other people in the tourist party, the greater the probability that the tourist is in danger of leaving the party alone, when | Oi-O′i,mAnd after the value of | exceeds a set threshold value, the server sends the alarm information to the mobile phone for guiding.
By analyzing the behavior track of the tourists in the trip process, the behavior characteristics of a plurality of tourists can be extracted quickly and effectively, and the risk probability of the tourists in the trip process is predicted according to the behavior characteristics. The channel neural network calculates periodic behavior characteristics in multiple time dimensions (such as year, month, week and day) and combines positioning information to convert the information into risk probability. The high-precision real-time prediction model can be constructed for the data sequences of multiple tourists and different behavior tracks in a low training cost mode. Because the method introduces the options of time dimension and geographical positioning into the risk assessment model as additional input, the time step length for training the neural network risk assessment model can be greatly shortened, the training cost can be effectively reduced, and the prediction precision is improved.
Further, step d) is performed by the formulaCalculating Oi,mIn the formula, alpha is the looseness of the team, alpha is more than or equal to 1 and less than or equal to 99, and the larger the parameter alpha is set, the larger the radius of the activity of the tourist group is allowed to be, and the less early warning is generated. Smaller settings mean more compact tourist groups are required, Oi,mA larger value of (a) indicates a higher possibility that the guest m alone gets out of the group,the risk weight is taken according to the risk prompt of chapter three of the national travel administration No. 41 'travel safety management method', when the risk prompt is no risk,when the risk cue is a four-level risk,when the risk cue is a tertiary risk,when the risk cue is a secondary risk,when the risk cue is a first-degree risk,setting a risk weight according to risk prompts in a grading manner, referring to the position information of the visitor and obtaining an accurate output result value Oi,m,Oi,mA larger value indicates a higher probability of risk for the guest m to leave the group alone.
Claims (1)
1. A method for real-time detection of tourist travel risks by using artificial intelligence is characterized by comprising the following steps:
a) collecting coordinate positions of N tourists in a tourist group at fixed time intervals, uploading the obtained coordinate positions to a server, and obtaining a circular range capable of containing all the tourists according to the coordinate positions of all the tourists, wherein the center coordinate of the circular range is OiThe center of a circle coordinate OiAn uploading server, t is a timestamp when the circle center coordinates are reported to the server, i is more than or equal to 1 and less than or equal to t, wherein the circle center OiIs expressed as (x)middle,i=t,ymiddle,i=t) X is a longitude value and y is a latitude value, wherein:
xmax,i=tmaximum in longitude, x, of the set of coordinates of all guests at time tmin,i=tThe minimum value in longitude in the coordinate set of all the tourists;
ymax,i=tis the maximum value in latitude, y, in the coordinate set of all the tourists at the moment tmin,i=tThe minimum value in latitude in the coordinate set of all the tourists;
b) the coordinate series from the departure to the time t of the N tourists is
[(xm,j=1ym,j=1),(xm,j=2ym,j=2),...(xm,j=tym,j=t)]J is a timestamp serial number, j is more than or equal to 1 and less than or equal to t, m is any visitor, m is more than or equal to 1 and less than or equal to N, and the coordinate sequence of each visitor is uploaded to the server;
c) through a formula of & 'O'i,m=[O’1,m,O’2,m,...,O’,tm]Calculating the center coordinates o 'of a circular range which can contain the remaining visitors after the visitor m is removed'i,mCollecting m is more than or equal to 1 and less than or equal to N, and uploading the collection to a server;
d) the server follows the formula | Oi-O’i,mI calculating the coordinate of the center of a circle as OiAnd a circle center coordinate o 'of a circular range in which the guest m is removed and the remaining guests can be contained'i,mAbsolute value of difference, | Oi-O’i,mThe larger the value of | indicates the larger the probability that the tourist m leaves the group, when | Oi-O’i,mAfter the value of | exceeds a set threshold value, the server sends alarm information to a mobile phone for guiding;
in step d) by the formulaCalculating Oi,mWherein alpha is the group bulk, alpha is more than or equal to 1 and less than or equal to 99, Oi,mA larger value of (a) indicates a higher possibility that the guest m alone gets out of the group,is a risk weight, when the risk hint is no risk,when the risk is prompted to be fourAt the time of the stage of the risk,when the risk cue is a tertiary risk,when the risk cue is a secondary risk,when the risk cue is a first-degree risk,
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911299564.9A CN111031487B (en) | 2019-12-16 | 2019-12-16 | Method for real-time detection of tourist trip risk by using artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911299564.9A CN111031487B (en) | 2019-12-16 | 2019-12-16 | Method for real-time detection of tourist trip risk by using artificial intelligence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111031487A CN111031487A (en) | 2020-04-17 |
CN111031487B true CN111031487B (en) | 2021-03-30 |
Family
ID=70209916
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911299564.9A Active CN111031487B (en) | 2019-12-16 | 2019-12-16 | Method for real-time detection of tourist trip risk by using artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111031487B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102521486A (en) * | 2011-11-28 | 2012-06-27 | 苏州迈普信息技术有限公司 | Method for automatically judging whether tourists fall behind |
CN103813450A (en) * | 2014-03-07 | 2014-05-21 | 山东大学 | Optimized mobile wireless sensor network node positioning method |
CN108966115A (en) * | 2017-05-23 | 2018-12-07 | 陕西胜慧源信息科技有限公司 | Using the travelling group team management system of GPS and GIS |
KR20190074532A (en) * | 2017-12-20 | 2019-06-28 | 경희대학교 산학협력단 | Method and system for user's location context inference |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102421060B (en) * | 2011-11-28 | 2013-01-23 | 苏州迈普信息技术有限公司 | GIS (Geographic Information System)-based emergency condition management system for tour group |
CN102522044B (en) * | 2011-11-28 | 2013-12-04 | 常熟南师大发展研究院有限公司 | Method for judging dispersion degree of team and application thereof in tour guide field |
-
2019
- 2019-12-16 CN CN201911299564.9A patent/CN111031487B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102521486A (en) * | 2011-11-28 | 2012-06-27 | 苏州迈普信息技术有限公司 | Method for automatically judging whether tourists fall behind |
CN103813450A (en) * | 2014-03-07 | 2014-05-21 | 山东大学 | Optimized mobile wireless sensor network node positioning method |
CN108966115A (en) * | 2017-05-23 | 2018-12-07 | 陕西胜慧源信息科技有限公司 | Using the travelling group team management system of GPS and GIS |
KR20190074532A (en) * | 2017-12-20 | 2019-06-28 | 경희대학교 산학협력단 | Method and system for user's location context inference |
Also Published As
Publication number | Publication date |
---|---|
CN111031487A (en) | 2020-04-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20190087464A1 (en) | Regional population management system and method | |
CN105741486B (en) | Urban Public Space based on mobile phone location data tramples accident real time early warning method | |
CN104023064B (en) | Statistical method of working hours of field personnel based on intelligent mobile terminal and activity characteristic analysis | |
CN114022988B (en) | Visitor information management verification system and method based on artificial intelligence | |
CN108595606A (en) | Public security case space-time analysis method and device based on carrier data | |
CN111028471B (en) | Method for preventing tourists from approaching high-risk area by using neural network technology | |
CN111182463B (en) | Regional real-time passenger flow source analysis method and device | |
CN111031487B (en) | Method for real-time detection of tourist trip risk by using artificial intelligence | |
US20230170096A1 (en) | Systems, devices, and methods for managing contact instances of persons of interest | |
CN113096785B (en) | Epidemic situation period medical resource allocation method | |
CN113420054B (en) | Information statistics method, server, client and storage medium | |
CN111182445B (en) | Method and system for analyzing aggregated groups based on mobile phone signaling data | |
CN110555923A (en) | Personnel registration method and system | |
CN112002052A (en) | Data sharing method for smart community | |
CN110727688A (en) | Key personnel gridding service management system | |
CN109379716A (en) | A kind of indoor orientation method and system for safety monitoring project | |
CN111372197B (en) | Early warning method and related device | |
CN108491902B (en) | Two-dimensional code anti-lost method and system based on public platform | |
CN113011746A (en) | Early warning system for airborne disease high-risk place based on digital portrait | |
Liou et al. | Deriving the vehicle speeds from a mobile telecommunications network | |
Zhou et al. | Design of the intelligent internship management platform for vocational colleges | |
CN115641105B (en) | Data processing method for monitoring leave-out of community correction object | |
Shahin et al. | Disaster Resilient Rescue of Coastal Community on Cyclone Warning | |
Hiroi et al. | Study about the effect of the signposting for evacuation in the underground space | |
CN116744237B (en) | Data determination method, device, equipment and medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |