CN114677144A - Vehicle insurance claim settlement fraud risk identification method and system based on geographic big data - Google Patents
Vehicle insurance claim settlement fraud risk identification method and system based on geographic big data Download PDFInfo
- Publication number
- CN114677144A CN114677144A CN202210194308.9A CN202210194308A CN114677144A CN 114677144 A CN114677144 A CN 114677144A CN 202210194308 A CN202210194308 A CN 202210194308A CN 114677144 A CN114677144 A CN 114677144A
- Authority
- CN
- China
- Prior art keywords
- vehicle insurance
- geographic
- fraud
- data
- address
- 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.)
- Pending
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
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- 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
- G06N20/00—Machine learning
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
Abstract
The invention discloses a vehicle insurance claim settlement fraud risk identification method and system based on geographical big data, which are used for mining areas with high fraud risk accidents and associated fraud groups based on the geographical positions of vehicle insurance accident sites and vehicle maintenance points, in combination with electronic maps, traffic monitoring camera data, mobile communication signaling data and other data and by using geographical big data and machine learning algorithm technology. The output result of the invention can be provided for insurance anti-fraud service discriminators to reference, and can also be output to an anti-fraud rule system or an anti-fraud model to be used as a factor characteristic, thereby improving the recall rate and the accuracy rate of the car insurance anti-fraud system.
Description
Technical Field
The invention relates to the field of big data, in particular to a vehicle insurance claim settlement fraud risk identification method and system based on geographical big data.
Background
With the development of social economy, the automobile holding capacity is rapidly increased, the fraud phenomenon in automobile insurance claims is greatly increased, the national financial tax order and social order are seriously damaged, and a great amount of loss is brought to insurance companies, other related financial institutions, related government departments and individual participants. The traditional anti-fraud method is difficult to deal with complex and variable vehicle insurance fraud methods, and how to utilize big data and artificial intelligence technology to improve the anti-fraud effect of vehicle insurance claims becomes an important research subject of government regulatory departments and insurance companies.
By utilizing various kinds of geographic big data information and combining a machine learning method, the accuracy of internet information service and financial insurance service can be effectively improved. The patent CN201910463148.1 and CN202011328132.9 propose to use the geographic big data technology, reduce the number of times of information query, and improve the query efficiency. The patent CN202010166566.7 utilizes the mobile operator data to predict the fraud of the customer online and determine the anti-fraud index, thus improving the hit rate and accuracy of the anti-fraud system. In the financial field, an anti-fraud detection method based on the density risk level is also proposed, and the application position density risk levels with different levels are established and applied to financial loan for anti-fraud risk identification. The method is applied to financial loan transaction. Currently, a method and a system for applying the geographic big data technology to vehicle insurance fraud prevention are lacked. However, in the field of car insurance claims, an anti-fraud identification method close to the actual situation is not available at present.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a vehicle insurance claim settlement fraud risk identification method and system based on geographic big data, wherein the result obtained by the method can be used as reference for an insurance anti-fraud service discriminator, and can also be output to an anti-fraud rule system or an anti-fraud model to be used as factor characteristics, so that the recall rate and the accuracy rate of the vehicle insurance anti-fraud system are improved.
The purpose of the invention is realized by the following technical scheme:
a vehicle insurance claim settlement fraud risk identification method based on geographic big data comprises the following steps:
the method comprises the following steps: obtaining the longitude and latitude of an address where a single car insurance case occurs through a geocoding technology; calculating a geographical hash block corresponding to the vehicle insurance case occurrence place according to the longitude and latitude of the address by utilizing an address space index technology;
step two: collecting vehicle insurance case data and geographical big data information in a period of time, calculating the average vehicle insurance case quantity and average traffic flow in each geographical Hash block, then calculating the vehicle insurance accident occurrence rate according to the vehicle insurance case quantity/average traffic flow, screening the areas with the vehicle insurance accident occurrence rate higher than a set threshold value, eliminating the abnormality caused by road conditions or traffic objective state and other factors, and defining other areas higher than the set threshold value as vehicle insurance fraud high-risk areas;
step three: calculating the association aggregation effect between the geographic hash block corresponding to the vehicle insurance case occurrence place and the automobile maintenance point address hash block by utilizing a clustering algorithm, and positioning an automobile insurance fraud high risk area-automobile maintenance point association pair;
Step four: and summarizing and outputting the vehicle insurance fraud high-risk area, the vehicle insurance fraud high-risk area-automobile maintenance point association pairs and the vehicle insurance claim cases according to a certain standardized format, and giving a prompt reason to obtain a vehicle insurance claim fraud risk identification result.
Further, in the first step, the address longitude and latitude are converted into the address hash block through a longitude and latitude hash algorithm.
Further, in the first step, a geocoding service is acquired through an online API provided by a map information service provider, and the longitude and latitude acquired according to the geocoding is matched and checked with the map positioning longitude and latitude.
Further, the step two of summarizing the vehicle insurance case data and the geographic big data information within a period of time and calculating the average vehicle insurance case quantity and the average traffic flow in each geographic hash block are specifically realized through the following substeps:
(1) collecting the data of the vehicle insurance cases in a period of time, and counting the number, the category and the amount of the vehicle insurance cases in each geographic zone;
(2) and obtaining passenger flow data, traffic statistical data and mobile communication instruction data in each geographic zone in a period of time, and calculating traffic flow, average speed and road condition complexity in each geographic zone in a period of time.
Further, in the second step, a geographical hash fast search algorithm is used, the address hash block where the accident occurrence location is located is taken as the center, the surrounding eight hash blocks are brought into and integrated into one large block, and the average number of the car insurance cases in the large block within a period of time is counted.
Further, the clustering algorithm in step three is a bipartite graph clustering algorithm.
A vehicle insurance claim settlement fraud risk identification system based on geographic big data comprises the following modules:
the geographic coding and address space indexing module converts the longitude and latitude of an address into an address hash block through a longitude and latitude hash algorithm, takes the address hash block where an accident occurs as a center by utilizing a geographic hash quick searching algorithm, brings the eight hash blocks around into the address hash block, integrates the eight hash blocks into a large block, and counts the number of automobile accidents in the large block within a period of time;
the traffic flow information acquisition and calculation module acquires electronic map software, traffic camera video monitoring and mobile communication signaling data and counts average traffic flow in each large geographic area;
the vehicle insurance claim settlement fraud risk calculation module of the geographic area is used for calculating the accident occurrence rate of each geographic area, namely the number of automobile accidents/average traffic flow, if the accident traffic flow ratio of a specific area is found to be significantly higher than that of other areas, the area is defined as a high vehicle insurance fraud risk area except for the factors of road conditions, objective traffic conditions and the like;
The vehicle insurance accident occurrence place-automobile maintenance point correlation module is used for calculating and calculating a correlation bipartite graph between an accident occurrence place address hash block and an automobile maintenance point address hash block, and if a significant aggregation effect exists between the two blocks and the distance between the two blocks is long, a higher fraud risk is considered to exist;
and the result output and application module comprises a case unique identification code and graph node conversion unit, maps the searched associated graph nodes into specific case unique identification codes in the structured database, and calls data to return to the user.
The invention has the following beneficial effects:
the invention discloses a vehicle insurance claim settlement fraud risk identification method based on geographical big data, which utilizes geographical big data and machine learning algorithm technology to mine high fraud risk accident areas and associate fraud groups. The output result of the invention can be provided for insurance anti-fraud service discriminators to reference, and can also be output to an anti-fraud rule system or an anti-fraud model to be used as a factor characteristic, thereby improving the recall rate and the accuracy rate of the car insurance anti-fraud system.
Drawings
Fig. 1 is a schematic flow chart of the method for identifying fraud risk in car insurance claim settlement based on geographic big data according to the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments, and the objects and effects of the present invention will be more apparent, it being understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.
As shown in fig. 1, the method for identifying claims and fraud risk in car insurance settlement based on geographic big data of the present invention is based on the geographic location of the accident location and the car repair location of the car insurance, and utilizes the geographic big data and the machine learning algorithm technology to mine the high fraud risk accident area and the associated fraud group by combining the data such as the electronic map, the traffic monitoring camera data, the mobile communication signaling data, etc. The output result of the invention can be provided for insurance anti-fraud service discriminators to be referred, and can also be output to an anti-fraud rule system or an anti-fraud model to be used as factor characteristics, thereby improving the recall rate and the accuracy rate of the car insurance anti-fraud system.
The method specifically comprises the following steps:
the method comprises the following steps: obtaining the longitude and latitude of an address where a single car insurance case occurs through a geocoding technology; and calculating a geographical hash block corresponding to the vehicle insurance case occurrence place according to the longitude and latitude of the address by utilizing an address space index technology.
Geocoding services provide functionality to convert structured address strings (e.g., eight tenths of ten street in the hai lake area, beijing) into coordinate latitudes and longitudes. The address longitude and latitude can obtain the geocoding service through an online API (application program interface) provided by map information service providers such as a Goodpasture map, a Baidu map and the like, and the longitude and latitude obtained by the geocaching code can be matched and verified with the map positioning longitude and latitude if the data allows the result authenticity to be ensured and the accuracy to be improved. In addition, the address longitude and latitude are converted into an address hash block through a longitude and latitude hash algorithm.
The geospatial index may convert address latitude and longitude into address hash strings, each string representing a rectangular geographic region. The length of the address hash character string can be set according to requirements, and the longer the length, the more accurate the range of representation. For example, a five-bit address hash code string can represent a rectangular area of 10 square kilometers, while a six-bit code may represent an area of about 0.34 square kilometers. The similar character strings are very close in distance, and the adjacent area of a specific position can be quickly searched and positioned by using the prefix matching degree of the character strings. Hash mapping of different lengths can be tried to obtain the most suitable code length.
Step two: the method comprises the steps of summarizing vehicle insurance case data and geographical big data information in a period of time, calculating the average number of vehicle insurance cases and the average traffic flow in each geographical Hash block, then calculating the vehicle insurance accident occurrence rate according to the number of vehicle insurance cases/the average traffic flow, screening areas with the vehicle insurance accident occurrence rate higher than a set threshold value, eliminating abnormalities caused by road conditions or traffic objective states and other factors, and defining other areas higher than the set threshold value as vehicle insurance fraud high-risk areas.
(1) And (4) collecting the data of the vehicle insurance cases in a period of time, and calculating the number, the category, the amount and the like of the vehicle insurance cases in each geographic zone. Optionally, on the premise that the data conditions are allowable and compliant, data intercommunication statistics with government traffic authorities and other insurance companies can be realized by using a data privacy protection technology.
(2) Passenger flow data in each geographic block is obtained through an electronic map service provider (such as a high-grade map and a Baidu map), traffic camera video monitoring is obtained through relevant government departments to obtain traffic statistical data, and mobile communication signaling data are obtained through mobile communication service providers such as mobile communication, Unicom communication and telecommunication. And comprehensively utilizing the data of all the parts to calculate the information such as traffic flow, average speed, road condition complexity and the like in each geographic area within a period of time.
(3) The accident occurrence rate (the number of vehicle insurance accidents/the average traffic flow) of each block is calculated, and the number of the vehicle insurance accidents and the information of the average traffic flow, the average speed, the density of traffic lights, the traffic road conditions and the like can be considered to have a certain model relation in a statistical sense. And the average traffic flow in each large geographic area is counted by using electronic map software (such as a high-grade map and a Baidu map), traffic camera video monitoring, mobile communication signaling data and the like. If the accident traffic flow ratio of a specific area is found to be significantly higher than that of other areas, or a significant increase occurs in the recent period, the area is reasonably suspected to be an area with high risk of vehicle risk fraud, and the area can be checked in a targeted manner.
Step three: and calculating the association aggregation effect between the geographic hash blocks corresponding to the vehicle insurance case occurrence places and the automobile maintenance point address hash blocks by using a clustering algorithm (preferably a bipartite graph clustering algorithm), and positioning the association pair of the automobile maintenance point and the high risk area of vehicle insurance fraud.
If a significant association aggregation effect appears between the accident site address hash block and the vehicle repair site address hash block, and the geographic location between the accident site address hash block and the vehicle repair site address hash block is relatively far away, the situation of high fraud risk can be suspected.
Step four: and summarizing and outputting the vehicle insurance fraud high-risk area, the vehicle insurance fraud high-risk area-automobile maintenance point association pairs and the vehicle insurance claim cases according to a certain standardized format, and giving a prompt reason to obtain a vehicle insurance claim fraud risk identification result.
Summarizing and outputting according to certain standardized formats of high-risk geographic areas, high-suspicious vehicle insurance accident areas-automobile maintenance point association pairs, vehicle insurance claim cases and the like, for example, mapping the retrieved association graph nodes into specific case unique identification codes in a structured database, calling the data back to the user, giving out prompting reasons, and providing the prompting reasons for insurance anti-fraud service discriminators to make main viewing reference. Outputting the structured data factor or the vector characteristic, and outputting a file system or a database in a normalized format for the vehicle insurance anti-fraud rule system to call or using as the characteristic of a machine learning anti-fraud model.
The invention discloses a vehicle insurance claim settlement fraud risk identification system based on geographic big data, which comprises the following modules:
the geographic coding and address space indexing module converts the longitude and latitude of an address into an address hash block through a longitude and latitude hash algorithm, takes the address hash block where an accident occurs as a center by utilizing a geographic hash quick searching algorithm, brings the eight hash blocks around into the address hash block, integrates the eight hash blocks into a large block, and counts the number of automobile accidents in the large block within a period of time;
The traffic flow information acquisition and calculation module acquires electronic map software, traffic camera video monitoring and mobile communication signaling data and counts average traffic flow in each large geographic area;
the vehicle insurance claim settlement fraud risk calculation module of the geographic area, the module is used for calculating the accident incidence of each geographic area, namely car accident quantity/average traffic flow, if find the accident traffic flow ratio of the particular area is obviously higher than other areas, in excluding factors such as road condition, objective condition of traffic, etc., define the area as the high vehicle insurance fraud risk area;
the automobile insurance accident occurrence place-automobile maintenance point association module is used for calculating and calculating an association bipartite graph between an accident occurrence place address Hash block and an automobile maintenance point address Hash block, and if a significant aggregation effect exists between the two blocks and the distance is long, a higher fraud risk is considered to exist;
and the result output and application module comprises a case unique identification code and graph node conversion unit, maps the retrieved associated graph nodes into specific case unique identification codes in the structured database, and calls data to return to the user.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the invention and is not intended to limit the invention to the particular forms disclosed, and that modifications may be made, or equivalents may be substituted for elements thereof, while remaining within the scope of the claims that follow. All modifications, equivalents and the like which come within the spirit and principle of the invention are intended to be included within the scope of the invention.
Claims (7)
1. A vehicle insurance claim settlement fraud risk identification method based on geographic big data is characterized by comprising the following steps:
the method comprises the following steps: obtaining the longitude and latitude of an address where a single car insurance case occurs through a geocoding technology; calculating a geographical hash block corresponding to the vehicle insurance case occurrence place according to the longitude and latitude of the address by utilizing an address space index technology;
step two: collecting vehicle insurance case data and geographical big data information in a period of time, calculating the average vehicle insurance case quantity and average traffic flow in each geographical Hash block, then calculating the vehicle insurance accident occurrence rate according to the vehicle insurance case quantity/average traffic flow, screening the areas with the vehicle insurance accident occurrence rate higher than a set threshold value, eliminating the abnormality caused by road conditions or traffic objective state and other factors, and defining other areas higher than the set threshold value as vehicle insurance fraud high-risk areas;
Step three: calculating the association aggregation effect between the geographic hash block corresponding to the vehicle insurance case occurrence place and the automobile maintenance point address hash block by utilizing a clustering algorithm, and positioning an automobile insurance fraud high risk area-automobile maintenance point association pair;
step four: and summarizing and outputting the vehicle insurance fraud high-risk area, the vehicle insurance fraud high-risk area-automobile maintenance point association pair and the vehicle insurance claim case according to a certain standardized format, and giving a prompt reason to obtain a vehicle insurance claim fraud risk identification result.
2. The geographic big data-based vehicle insurance claim settlement fraud risk identification method of claim 1, wherein in the first step, the address longitude and latitude are converted into an address hash block through a longitude and latitude hash algorithm.
3. The method for recognizing the vehicle insurance claim settlement fraud risk based on the geographic big data as claimed in claim 1, wherein in the first step, a geocoding service is obtained through an online API provided by a map information service provider, and the longitude and latitude obtained according to the geocoding is matched and verified with the map positioning longitude and latitude.
4. The geographic big data-based vehicle insurance claim settlement fraud risk identification method according to claim 1, wherein the step two of summarizing vehicle insurance case data and geographic big data information within a period of time and calculating average number of vehicle insurance cases and average traffic flow in each geographic hash block are specifically realized by the following sub-steps:
(1) Collecting the data of the vehicle insurance cases in a period of time, and counting the number, the category and the amount of the vehicle insurance cases in each geographic zone;
(2) and obtaining passenger flow data, traffic statistical data and mobile communication instruction data in each geographic zone in a period of time, and calculating traffic flow, average speed and road condition complexity in each geographic zone in a period of time.
5. The method for recognizing the vehicle insurance claim settlement fraud risk based on the geographic big data as claimed in claim 1, wherein in the second step, a geographic hash fast search algorithm is used, an address hash block where an accident occurrence location is located is used as a center, the surrounding eight hash blocks are included and integrated into one big block, and the average number of vehicle insurance cases in the big block in a period of time is counted.
6. The geographic big data-based vehicle insurance claim fraud risk identification method according to claim 1, wherein the clustering algorithm in step three is a bipartite graph clustering algorithm.
7. A vehicle insurance claim settlement fraud risk identification system based on geographic big data is characterized by comprising the following modules:
the geographic coding and address space indexing module converts the longitude and latitude of an address into an address hash block through a longitude and latitude hash algorithm, takes the address hash block where an accident occurs as a center by utilizing a geographic hash quick searching algorithm, brings the eight hash blocks around into the address hash block, integrates the eight hash blocks into a large block, and counts the number of automobile accidents in the large block within a period of time;
The traffic flow information acquisition and calculation module acquires electronic map software, traffic camera video monitoring and mobile communication signaling data and counts average traffic flow in each large geographic area;
the vehicle insurance claim settlement fraud risk calculation module of the geographic area, the module is used for calculating the accident incidence of each geographic area, namely car accident quantity/average traffic flow, if find the accident traffic flow ratio of the particular area is obviously higher than other areas, in excluding factors such as road condition, objective condition of traffic, etc., define the area as the high vehicle insurance fraud risk area;
the vehicle insurance accident occurrence place-automobile maintenance point correlation module is used for calculating and calculating a correlation bipartite graph between an accident occurrence place address hash block and an automobile maintenance point address hash block, and if a significant aggregation effect exists between the two blocks and the distance between the two blocks is long, a higher fraud risk is considered to exist;
and the result output and application module comprises a case unique identification code and graph node conversion unit, maps the retrieved associated graph nodes into specific case unique identification codes in the structured database, and calls data to return to the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210194308.9A CN114677144A (en) | 2022-03-01 | 2022-03-01 | Vehicle insurance claim settlement fraud risk identification method and system based on geographic big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210194308.9A CN114677144A (en) | 2022-03-01 | 2022-03-01 | Vehicle insurance claim settlement fraud risk identification method and system based on geographic big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114677144A true CN114677144A (en) | 2022-06-28 |
Family
ID=82073108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210194308.9A Pending CN114677144A (en) | 2022-03-01 | 2022-03-01 | Vehicle insurance claim settlement fraud risk identification method and system based on geographic big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114677144A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116012169A (en) * | 2022-12-21 | 2023-04-25 | 南京睿聚科技发展有限公司 | Method and system for screening risk of insurance claim settlement based on position data |
-
2022
- 2022-03-01 CN CN202210194308.9A patent/CN114677144A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116012169A (en) * | 2022-12-21 | 2023-04-25 | 南京睿聚科技发展有限公司 | Method and system for screening risk of insurance claim settlement based on position data |
| CN116012169B (en) * | 2022-12-21 | 2024-03-22 | 南京睿聚科技发展有限公司 | Method and system for screening risk of insurance claim settlement based on position data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103278833B (en) | A kind of circuit recommendation system and method based on the Big Dipper/gps data | |
| US8515673B2 (en) | Crime risk assessment system | |
| CN108280550B (en) | Visual analysis method for comparing community division of public bicycle stations | |
| CN110111539B (en) | Internet of things cloud early warning method, device and system integrating multivariate information | |
| CN107872767A (en) | A kind of net about car brush single act recognition methods and identifying system | |
| CN106323301A (en) | Road information obtaining method and device | |
| CN103116696A (en) | Personnel resident site recognizing method based on sparsely sampled mobile phone locating data | |
| CN109741482A (en) | A kind of information sharing method and device | |
| CN104778231A (en) | Feature identification method and device for geographic areas | |
| CN105160173A (en) | Security assessment method and device | |
| CN115083161B (en) | Vehicle stay point evaluation method and device, electronic equipment and readable storage medium | |
| CN114677144A (en) | Vehicle insurance claim settlement fraud risk identification method and system based on geographic big data | |
| CN106504524A (en) | A kind of method that express highway section is divided based on mobile signaling protocol dynamic | |
| WO2020192123A1 (en) | Method for improving accuracy of positioning traffic accident site | |
| CN108447257B (en) | Web-based traffic data analysis method and system | |
| CN113256978A (en) | Method and system for diagnosing urban congestion area and storage medium | |
| CN116384844B (en) | Decision method and device based on geographic information cloud platform | |
| CN108563706A (en) | A kind of collection big data intelligent service system and its operation method | |
| WO2021114615A1 (en) | Method, apparatus, and device for visualization of behavior risk identification, and storage medium | |
| CN109166336B (en) | Real-time road condition information acquisition and pushing method based on block chain technology | |
| CN110851547A (en) | Multi-data-source map data fusion method | |
| Dash et al. | From Mobile Phone Data to Transport Network--Gaining Insight about Human Mobility | |
| CN115203354A (en) | Vehicle code track pre-association method and device, computer equipment and storage medium | |
| CN111339233B (en) | Address security identification control method | |
| CN109990791A (en) | Method, apparatus, equipment and the medium that road data extracts |
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 |