CN107958364A - A kind of logistics user behavior pattern analysis and processing method and system - Google Patents
A kind of logistics user behavior pattern analysis and processing method and system Download PDFInfo
- Publication number
- CN107958364A CN107958364A CN201711396626.9A CN201711396626A CN107958364A CN 107958364 A CN107958364 A CN 107958364A CN 201711396626 A CN201711396626 A CN 201711396626A CN 107958364 A CN107958364 A CN 107958364A
- Authority
- CN
- China
- Prior art keywords
- data
- logistics
- information
- infrastructure
- different
- 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
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
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0835—Relationships between shipper or supplier and carriers
- G06Q10/08355—Routing methods
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of logistics user behavior pattern analysis and processing method and system, the described method includes：S1：The logistics data collected is pre-processed, excludes exceptional data point；S2：Pretreated data are divided into different classes of data；S3：The data of different spaces are transformed into the same space；S4：Analysis is compared the data for transforming to the same space and is collected as different subsets；S5：Result based on purpose data classifying in step S4 optimizes logistics route.
Description
Technical field
The present invention relates to big data analysis and technical field of traffic transportation, and in particular to a kind of logistics user behavior pattern point
Analyse processing system and method.
Background technology
Logistics is the most basic form of expression of configuration of social resources, is an importance of supply chain management, and logistics is imitated
Efficiency, direct relation people production, the height of living cost of the height direct relation social economy operation of rate.
Information technology is applied in modern logistics so that Modern Logistics Technology shows alarming development speed and huge
Big development potentiality.Firstly the need of acquisition promptly and accurately and using logistics information in logistics activity, on this basis to sea
The logistics data information of amount carries out analysis recycling, and for improving logistic efficiency, reduction logistics cost, meeting customer need has
And its important effect.
The content of the invention
It is an object of the invention to propose a kind of logistics user behavior pattern side analysis process system and method, to logistics
On the basis of data message is effectively collected, big data analysis and processing are carried out to the logistics data information of magnanimity, so as to reach
To the purpose for improving logistic efficiency, reducing logistics cost.
For this purpose, the present invention uses following technical scheme：
A kind of logistics user behavior pattern analysis and processing method, including：S1：The logistics data collected is located in advance
Reason, excludes exceptional data point；S2：Pretreated data are divided into different classes of data；S3：The data of different spaces are become
Change to the same space；S4：Analysis is compared the data for transforming to the same space and is collected as different subsets；S5：Based on step
The result of purpose data classifying optimizes logistics route in S4.
A kind of logistics user behavior pattern analysis process system, including：Infrastructure layer, data Layer, supporting layer, podium level
And application layer；
The infrastructure layer includes network infrastructure, the communications infrastructure, information infrastructure, information technology hardware
Facility, logistics warehouse, berthing facilities, goods station, logistics node, logistics transportation instrument, the information hardware of the infrastructure layer
Facility includes a variety of positioners；
The data Layer includes：Basic data acquisition system, for gathering logistics data, the bar shaped yardage of infrastructure layer
According to storehouse, two-dimensional code data storehouse, RF tag database, positioning database of record, geographic information database, Data Analysis Services system
System, Telecommunication operation Network information system；
The Data Analysis Services system includes：For discharging the data preprocessing module of exceptional data point, for by advance
Data after processing are divided into the data segmentation module, same for the data of different spaces to be transformed to of different classes of data
The sameization processing module in space, for analyzing to compare transform to the data of the same space and collected the number for different subsets
According to the path optimization's module for collecting processing module, optimizing for logistics route.
As the presently preferred embodiments, the detection of exceptional data point is detected using mesh generation detection method.
As the presently preferred embodiments, the data segmentation includes the identification of vehicle parking point and company during logistics vehicles travel
The identification of continuous driving trace.
As the presently preferred embodiments, different spaces are rotated, translated so as to fulfill to the processing of sameization of different spaces.
As the presently preferred embodiments, by the purpose data classifying of the same space for different subsets by compare by sameization processing after
The distance between different driving paths positioned at the same space are realized.
As the presently preferred embodiments, the path optimization refers to optimize specific logistics vehicles traffic route, logistics user city
Field information push.
As the presently preferred embodiments, exceptional data point detection is realized by normal distribution data method of identification.
The beneficial effects of the present invention are：A kind of logistics user behavior pattern side analysis process system and method are provided,
On the basis of being effectively collected to logistics data information, big data analysis and processing are carried out to the logistics data information of magnanimity,
So as to achieve the purpose that to improve logistic efficiency, reduce logistics cost.Its specific detailed beneficial effect will be embodied below
Further embodied in the description of example.
Brief description of the drawings
Fig. 1 is the configuration diagram of logistics user behavior pattern analysis process system of the present invention；
Fig. 2 is that the vehicle carried data collecting system structure of logistics user behavior pattern analysis process system of the present invention is shown
It is intended to；
Fig. 3 is the structure diagram of data handling system of the present invention；
Fig. 4 is data analysis processing method flow diagram of the present invention.
Embodiment
Further illustrate technical scheme below with reference to the accompanying drawings and specific embodiments.Need exist for spy
It is attached drawing listed by description of the invention merely to describing the problem example arrangement schematic diagram that is convenient and providing not mentionlet alone bright
Or method flow diagram, it is not unique achievable mode of the invention, it must not be explained as being limitation of the present invention
Explanation.
Fig. 1 is the configuration diagram of logistics user behavior pattern analysis process system of the present invention, and the logistics is used
Family Behavior Pattern Analysis processing system includes infrastructure layer 101, data Layer 102, supporting layer 103, podium level 104 and application
Layer 105.
Infrastructure layer 101 includes network infrastructure, the communications infrastructure, information infrastructure, information technology hardware
Facility, logistics warehouse, berthing facilities, goods station, logistics node, logistics transportation instrument；The data Layer 102 includes：Basic number
According to acquisition system, for gathering logistics data, bar code data storehouse, two-dimensional code data storehouse, the RF tag number of infrastructure layer
According to storehouse, positioning database of record, geographic information database, Data Analysis Services system, Telecommunication operation Network information system；It is described
Supporting layer 103 includes：Authentication center, security management mechanism, telecom operators' ability open interface, each public database of data Layer
Data-interface；Podium level 104 includes：Server resource distribution system, system load monitoring system, disaster-tolerant backup recovery system,
Data transfer encryption system；Application layer 105 includes：Logistics order status tracking system, logistics information real time inquiry system, logistics
Information transmission system, logistics information delivery system, vehicle operation management system.
Wherein described infrastructure layer 101 provides data and service support for data Layer 102, and infrastructure flat bed is to establish
On the basis of more mature hardware facility, and its infrastructure layer occupy in whole logistics service information system it is important
Status.Specifically, logistics infrastructure layer is combined with otherwise infrastructure construction, it is contemplated that existing basis is set
The characteristics of applying, such as the features such as in view of storage repository, berthing facilities, logistics node and corresponding transport network, will be existing
Hardware facility is integrated and optimized with newly-built hardware facility, thus build suitable Developing Logistics, it is rational, expansible
Logistics infrastructure layer, certainly constructed logistics infrastructure layer should have certain foresight and advanced, will also be
Meet the timeliness of logistics behavior.The key of structure logistics infrastructure layer seeks to fully plan that logistics infrastructure is built
If, analyze and assess the transport capacity of various types of transportation, the practicality of stream line, the node location sum number of stream line
Amount, logistics capacity and logistics demand, the external degree of contact of logistics, the radius at logistics network center and the timeliness of logistics behavior
Etc. key element, these key elements are all the bases for building logistics infrastructure layer, and compatible various during whole structure
Means of transportation, ensures that the stream line based on means of transportation can be seamlessly connected, and keeps the connective and reasonable of logistics network
Ground distributes logistic resources, and the programme of strict implement logistics infrastructure layer is to ensure the using effect of infrastructure layer.
The network infrastructure, the communications infrastructure, information infrastructure in the infrastructure layer 101 preferably make
With commercial public infrastructure.Information hardware infrastructure for information gathering and transmission should be configured accordingly,
Such as：
Physical distribution localization, physical distribution localization technology are related to the content of three aspects:Utilize the positioning of mobile equipment user such as mobile phone；Profit
With RFID technique locating goods；Utilize global position system positioning vehicle.Physical distribution localization technology carries out the technology of this three aspect
Organically combine, so as to form suitable logistic industry feature location technology, it can have both been realized to user, commodity and vehicle
Positioning, can also easily dispatch buses and commodity, so as to improve the utilization rate of resource.In order to ensure locating effect, it will usually
Using satellite positioning and big-dipper satellite technological orientation vehicle and mobile phone location, vehicle and the real-time positioning of personnel are realized.In order to protect
Links are held in the uniformity in terms of location technology, it is necessary to solve the time reference used, the coordinate in each logistics platform
The uniformity of the problems such as system, addressing algorithm scheme and access mode.
To solve the technical problem, the present invention using Big Dipper positioning, mobile telecommunications network base station location, wireless city hot spot,
Wireless near field communication is combined locating source, and intercrossed calibration, cross validation, unified in the alignment system of logistics platform with this
The parameter such as mark, addressing algorithm scheme, coordinate and time reference, and the heterogeneous element of logistics integration system, but also can unite
The interface of one system application layer, further improves the scalability of research and development.
Fig. 2 is that the vehicle carried data collecting system structure of logistics user behavior pattern analysis process system of the present invention is shown
It is intended to；
The vehicle carried data collecting system includes：Micro-chip processor 200, the micro-chip processor 200 preferably use
STM32F-103ZET6 chips, and cortex-M3 is selected as master chip, so that the microprocessor chip has high property
Can, the advantages that arithmetic speed is fast, rich interface, advanced interrupt processing function, low-power consumption, low cost and debugging are supported；Serially
Data transmit-receive module 201-204, it is preferred to use USART modules, the data transmit-receive module 201-204 and other function module phases
Connection, for the micro-chip processor 200 and extraneous data exchange；Wherein serial data transceiver module 201 and information transmit-receive
Module 211 connects, and described information transceiver module is GSM/GPRS modules, or the signal transmitting and receiving mould such as WIFI, bluetooth, infrared
Block, it is preferred to use ATK-SIM900 modules, described information transceiver module 211 are put down by common information transmission network with remote monitoring
Platform 212 connects, and is transmitted into row information, and information transmission uses TCP/IP transport protocols.
The data transmit-receive module 202 is transported by CAN bus and entire car controller 208, engine controller 209, vehicle
Row state sensor 210 be connected, wherein travel condition of vehicle sensor 210 be used for detect engine temperature, vehicle is continuously run
The parameters such as time, vehicle load situation, running velocity；Engine controller 209 can control the operation of vehicle motor
State, in some cases it may remote control is carried out to engine control 209 by remote control platform, so that just
In management and control of the manager to the measurement in transport；The entire car controller 208 can control vehicle in addition to the engine
Other controllable devices, such as：Light, sound equipment, instrument instruction, Vehicular display device, steering wheel, brake apparatus etc., such as when remote
Process control platform judges that the vehicle situation of facing a danger is by the entire car controller 208 vehicle sound can be controlled to remind in time
Driver note that paid attention to by light prompting surrounding vehicles, can also start in the case of some particularly urgents to steering wheel and
The control of brake apparatus；Control platform can by Vehicular display device Push Service information, such as：Periphery logistics transportation supply and demand letter
Breath, Service Order etc..
The data transmit-receive module 203 is connected with vehicle-mounted cargo condition monitoring sensors 206, the vehicle-mounted cargo state
Sensor 206 can be temperature sensor in conveying carriage, humidity sensor etc., implement collection article temperature, wet
The data such as degree.When data are unsatisfactory for storage condition, control device automatic adjustment epidemic disaster, to reach requirement of guaranteeing the quality, meanwhile,
Dynamic data is sent to network node using vehicle mobile equipment, recycles internet to transmit data to control centre, with
After database article essential information is associated, you can the multidate information of the article of inquiry transport in time.These information can also pass through shifting
Moved end software is sent to the client of driver and related personnel, to inquire about in time.
The vehicle-mounted cargo state sensor 206 can also be radio frequency identification reading device, bar code recognition reading
Device, magnetic stripe magnetic card reading devices, monitoring camera, image automatic identification device etc..
The data transmit-receive module 204 is connected with satellite positioning module 205, and the satellite positioning module 205 can be
Big-dipper satellite locating module, satellite positioning module, such as：ATK-NEO-6M satellite positioning modules.
Essential structure and the hardware configuration of infrastructure layer 101 are described above is, base is collected by infrastructure layer 101
The data are sent to the data Layer 102 after plinth logistics data, and the critical function of the data Layer 102 is to above-mentioned number
According to classification storage is carried out, analyze and process.The data Layer 102 includes：Basic data acquisition system, bar code data storehouse, two dimension
Code database, RF tag database, positioning database of record, geographic information database, Data Analysis Services system, telecommunications fortune
Seek network information system.Wherein Data Analysis Services system is the core system of data Layer high-efficiency operation, below to the data
The structure and working method of analysis process system are described in detail：
Data Analysis Services system structure diagram of the present invention as described in Figure 3, including：Data preprocessing module
2001st, data segmentation module 2002, sameization processing module 2003, purpose data classifying processing module 2004, path optimization's module
2005；Flow chart of data processing is accordingly：S2001：Data prediction；S2002：Data are split；S2003：Data sameization place
Reason；S2004：Purpose data classifying processing；S2005：Logistics route optimizes.
Wherein：Data preprocessing module 2001 and the concrete mode of data prediction step S2001 are as follows：
The running course data of logistics data, especially logistics vehicles has following features：
(1) data volume is big.The data recording number averagely produced weekly by the logistics vehicles of load running is about 4,000 ten thousand
Bar；(2) Data duplication.The reason for causing Data duplication is diversified, such as when vehicle is in the region of signal difference, mountain
Area, tunnel etc., either exception or failure cause to repeat to send identical satellite positioning location data, vehicle parking equipment in itself
When be able to may also cause satellite location data send repeat, to these data be necessary carry out duplicate removal processing；(3) shortage of data.
Logistics goods stock during its operation satellite positioning receiver set receiving time interval be generally 30 seconds to 1 minute it
Between, but due to geographic factor (such as vehicle traveling is in mountain area, sleety weather), equipment fault reason, do not ensure that each
There is complete satellite positioning information in a section, or even has the satellite location data that some are mistakes.The data of these missings
The serious influence for caused by obtaining and analyze run routing information；(4) satellite positioning drifts about.Positioned in mobile satellite location equipment
During, the position and user's actual bit that are identified are equipped with certain discrepancy, and common phenomenon is actual path and the rail that first drifts about
Mark is mixed in together.Even if the latitude and longitude information that the actual original place position of vehicle produces when motionless is also constantly to convert.Have
Many odjective causes can cause this phenomenon, such as mobile satellite location equipment not to initialize or adjust in the long-term use
School, causes have certain error between physical location and the position of display, and number of satellite that equipment searches out in real time, satellite are in itself
Position distribution etc., since CPU processing speeds or algorithm are not good enough so that vehicle is in the satellite positioning with fast speed when driving
For signal compared with when stationary vehicle, longitude and latitude offset, these offset foots can influence the data analysis of vehicle running path
As a result.
Above-mentioned characteristic based on logistics data is accurately to analyze and process the logistics data, it is necessary first to the logistics number
According to being pre-processed, specifically include：Exceptional data point detects, such as normal distribution outlier detection, if some data object
Bias data collection average is then classified as abnormal point to threshold value；Can also be that cluster analysis detects, it is by by all data clusters
Into different clusters, the data point for not then being referred to any cluster is then abnormal point；Density Detection, by vehicle running path data
Each track of concentration is projected on different dimensions, then the density and neighborhood size in more each piece of region,
The big local track data of density more tends to normal, and the smaller region track of density is larger for abnormal data possibility；It is also favourable
The outlier detection of the thought progress of path adaptation is carried out with the GIS such as road network information.
Net region division detection is another important abnormal point detecting method proposed by the present invention, its algorithmic procedure
It is as follows：
(1) map area is pressed into mesh generation.Such as：One satellite location data is defined as in a two dimensional surface
Point pi{loni,lati, loniRepresent longitude, latiIt is expressed as latitude.It will include ground as reference axis using terrestrial latitude and longitude
Graph region can be mapped as a two dimensional surface R2{(lon,lat)|lon∈R+,lat∈R+}.Then use parallel to reference axis
The equal-sized grid R of bundle of lines map partitioningi{lonmax,lonmin,latmax,latmin, wherein lonmax,lonmin,
latmax,latminThe respectively coboundary of grid, lower boundary, right margin, left margin, divide to obtain the set S=of grid
{R1,R2,R3,…,Ri-1,Ri}.Define a mapping relations F:R2 →S, R is obtained by rounding about pair warp and weft degree respectivelyi={ ceil
(loni),floor(loni),ceil(lati),floor(lati), wherein loni,latiThe difference of precision will influence lattice
The size of son.
(2) calculate and be mapped to grid track data point quantity Pcnt.Judge PcntWhether abnormal point threshold value C is less thanthreIf
Set up, then all data points in the grid are judged to abnormal point, otherwise non-abnormal point.
(3) for the grid R of non-abnormal pointi, the grid of quantity maximum in grid is found as first class G1, calculate net
Central point R inside latticec=(R1+R2+R3+…+Ri-1+Ri)/i, then finds Euclidean distance distance G1Farthest mesh point conduct
Second class G2。
(4) the Euclidean distance d of grid of other grids to initial two classes is calculatedij.If grid distance is less than Dthre, then
The grid is grouped into such, otherwise, is defined as new class Gi。
(5) obtain and be not classified into grid in any class, the point in the grid both may be considered that abnormal point.
This algorithm has the following advantages:(1) classification number K need not be specified in advance, and classification number is obtained in constantly classification iteration.
(2) preliminary classification center is not randomly generated, and effectively prevent the situation that can only converge to local optimum.(3) can have
Imitate and easily detect abnormal point, since road is generally more dispersed, the circuit that especially goods stock is travelled, not in net
Data point in lattice can both be judged to abnormal point.(4) time complexity is low.Due to being calculated according to mesh generation whole region,
All its time complexities are close to linear complexity, and when number of classifying is smaller, time complexity is lower when data are more concentrated.
After completing data prediction, data segmentation S2002 is carried out, it is completed by the data segmentation module 2002, tool
Body is as follows：
Satellite site is discrete data point, distinguish the discrete point be vehicle parking point or vehicle traveling point for
The behavior pattern of research logistics user has vital meaning.Calculating for vehicle parking point as follows into
OK：
(1) calculate the speed of anchor point, the speed of the anchor point by the distance between adjacent front and rear satellite site with
The ratio of the time difference of the adjacent front and rear anchor point determines；
(2) vehicle parking point judges, a specific threshold speed is set, for example, the threshold speed is set as 1m/
S, when the speed of a certain specified point is less than above-mentioned threshold value, judges that it, for doubtful stop, passes through the system being the previously calculated
Doubtful stop is arranged, while the threshold range of stopping distance can be combined, selects down time longest doubtful stop conduct
Final parking spot.
Identified by stop, the simple traveling rule of logistics freight, such as parking site, Sojourn times can be found
Between, this Behavior Pattern Analysis to logistics user is particularly important.
(3) on the basis of the identification of step (2) vehicle parking point, the satellite positioning point data collection is divided into vehicle and is stopped
By point data collection and vehicle traveling satellite positioning point data collection.
After data dividing processing is completed, for generally requiring to analyze between different types of magnanimity satellite location data
Compare, so as to carry out depth data excavation, such as driving path traveling or identical data are divided into one kind, are then based on the number
According to progress user behavior pattern prediction, logistics information specific aim push etc..But the base that all kinds of satellite location data analyses are compared
This premise is that different satellite location datas will be comparable, i.e. different vehicle driving traces is projected to the more of unification
Dimensional space, that is, need to data carry out sameization processing, specifically, the data sameization processing step S2003, its by
Sameization processing module 2003 is completed, it can be transformed to the data in the same space by projection algorithm, the projection
The advantages of algorithm includes rotating different spaces, translates and is handled so as to fulfill to sameization of different spaces, above-mentioned processing
While being to realize sameization processing, it can ensure the phase in the vehicle running path data entirety in the same space originally
To position relationship, path integrally moves towards constant.
After the processing of data sameization, can by purpose data classifying processing module 2004 to the logistics data into line number
S2004 is handled according to collecting；It by the purpose data classifying with similar or identical feature is same category that the processing of so-called purpose data classifying, which is exactly,
The data of specific similar or identical feature refer to the same or like satellite location data of logistics vehicles driving path, citing and
Speech, same logistics vehicles repeatedly pass through same or like section within the different periods, then satellite location data is shown as,
Location data in the different periods is exactly the data of foregoing different spaces, different after being handled by sameization
Period in satellite location data, i.e. vehicle running path data become to be compared to each other, by calculating different travelings
Space length between path, then can determine whether the different path is the same or similar road by above-mentioned distance
Footpath, i.e., less than the purpose data classifying of a certain threshold value be same data set by above-mentioned distance.
On the basis of data analysis above, the specific of effluent stream user can accurately be analyzed according to above-mentioned purpose data classifying
Behavior pattern, that is, the place that the section for getting used to travelling, time, vehicle are often stopped etc., is then based on above-mentioned data and utilizes road
Footpath optimization module 2005 carries out path optimization step S2005, and the path optimization refers to optimize specific logistics vehicles roadway
Line, the push of logistics user market information etc..
Although exemplary embodiment describing the present invention with reference to several, it is to be understood that, term used is explanation and shows
Example property and nonrestrictive term.Since the present invention can be embodied without departing from the spiritual or real of invention in a variety of forms
Matter, it should therefore be appreciated that above-described embodiment is not limited to any foregoing details, and should be in the spirit that appended claims are limited
With widely explained in scope, therefore the whole changes fallen into claim or its equivalent scope and remodeling all should be the power of enclosing
Profit requires to be covered.
Claims (8)
1. a kind of logistics user behavior pattern analysis and processing method, including：S1：The logistics data collected is pre-processed,
Exclude exceptional data point；S2：Pretreated data are divided into different classes of data；S3：The data of different spaces are converted
To the same space；S4：Analysis is compared the data for transforming to the same space and is collected as different subsets；S5：Based on step S4
The result of middle purpose data classifying optimizes logistics route.
2. a kind of logistics user behavior pattern analysis process system, including：Infrastructure layer, data Layer, supporting layer, podium level with
And application layer；
The infrastructure layer includes network infrastructure, the communications infrastructure, information infrastructure, information technology hardware and sets
Apply, logistics warehouse, berthing facilities, goods station, logistics node, logistics transportation instrument, the information hardware of the infrastructure layer sets
Apply including a variety of positioners；
The data Layer includes：Basic data acquisition system, it is used to gather the logistics data of infrastructure layer, bar code data
Storehouse, two-dimensional code data storehouse, RF tag database, positioning database of record, geographic information database, Data Analysis Services system
System, Telecommunication operation Network information system；
The Data Analysis Services system includes：For discharging the data preprocessing module of exceptional data point, for that will pre-process
Data afterwards are divided into the data segmentation module of different classes of data, for the data of different spaces to be transformed to the same space
Sameization processing module, for analyzing compare to transform to the data of the same space and collected and return for the data of different subsets
Collect processing module, path optimization's module for logistics route optimization.
3. the system described in the method as described in claim 1 or claim 2, the detection of exceptional data point uses mesh generation
Detection method is detected.
4. the system described in the method as described in claim 1 or claim 2, the data segmentation includes logistics vehicles traveling
During vehicle parking point identification and continuously drive the identification of track.
5. the system described in the method as described in claim 1 or claim 2, rotates different spaces, translation so as to
Realize and sameization of different spaces is handled.
6. the system described in the method as described in claim 1 or claim 2, is different by the purpose data classifying of the same space
Subset will be realized by comparing after sameization processing positioned at the distance between different driving paths of the same space.
7. the system described in the method as described in claim 1 or claim 2, the path optimization refers to optimize specific thing
Flow vehicle driving route, the push of logistics user market information.
8. the system described in the method as described in claim 1 or claim 2, exceptional data point detection passes through normal distribution number
Realized according to method of identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711396626.9A CN107958364A (en) | 2017-12-21 | 2017-12-21 | A kind of logistics user behavior pattern analysis and processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711396626.9A CN107958364A (en) | 2017-12-21 | 2017-12-21 | A kind of logistics user behavior pattern analysis and processing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107958364A true CN107958364A (en) | 2018-04-24 |
Family
ID=61956837
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711396626.9A Pending CN107958364A (en) | 2017-12-21 | 2017-12-21 | A kind of logistics user behavior pattern analysis and processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107958364A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110782088A (en) * | 2019-10-25 | 2020-02-11 | 嘉应学院 | UWB-based vehicle scheduling optimization system and method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103051707A (en) * | 2012-12-20 | 2013-04-17 | 浪潮集团有限公司 | Dynamic user behavior-based cloud forensics method and dynamic user behavior-based cloud forensics system |
| CN103278833A (en) * | 2013-05-13 | 2013-09-04 | 深圳先进技术研究院 | Line recommendation system and method based on Beidou satellite/GPS (global positioning system) data |
| CN104077308A (en) * | 2013-03-28 | 2014-10-01 | 阿里巴巴集团控股有限公司 | Logistics service range determination method and device |
| CN107256631A (en) * | 2017-08-08 | 2017-10-17 | 南京英斯特网络科技有限公司 | A kind of track of vehicle data aggregate operation method |
| CN107528735A (en) * | 2017-09-01 | 2017-12-29 | 苏州云联智慧信息技术应用有限公司 | big data analysis platform based on spatial analysis |
-
2017
- 2017-12-21 CN CN201711396626.9A patent/CN107958364A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103051707A (en) * | 2012-12-20 | 2013-04-17 | 浪潮集团有限公司 | Dynamic user behavior-based cloud forensics method and dynamic user behavior-based cloud forensics system |
| CN104077308A (en) * | 2013-03-28 | 2014-10-01 | 阿里巴巴集团控股有限公司 | Logistics service range determination method and device |
| CN103278833A (en) * | 2013-05-13 | 2013-09-04 | 深圳先进技术研究院 | Line recommendation system and method based on Beidou satellite/GPS (global positioning system) data |
| CN107256631A (en) * | 2017-08-08 | 2017-10-17 | 南京英斯特网络科技有限公司 | A kind of track of vehicle data aggregate operation method |
| CN107528735A (en) * | 2017-09-01 | 2017-12-29 | 苏州云联智慧信息技术应用有限公司 | big data analysis platform based on spatial analysis |
Non-Patent Citations (2)
| Title |
|---|
| 林克 等: ""基于物联网技术的智能物流公共服务平台设计"", 《电信技术》 * |
| 甘波: ""基于海量物流轨迹数据的分析挖掘系统"", 《中国优秀硕士学位论文全文数据库 信息科技辑 （月刊 ）》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110782088A (en) * | 2019-10-25 | 2020-02-11 | 嘉应学院 | UWB-based vehicle scheduling optimization system and method thereof |
| CN110782088B (en) * | 2019-10-25 | 2022-07-05 | 嘉应学院 | UWB-based vehicle scheduling optimization system and method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10549768B2 (en) | Real time machine vision and point-cloud analysis for remote sensing and vehicle control | |
| CN107533630A (en) | For the real time machine vision of remote sense and wagon control and put cloud analysis | |
| Lewandowski et al. | Road traffic monitoring system based on mobile devices and bluetooth low energy beacons | |
| Zear et al. | Intelligent transport system: A progressive review | |
| Masino et al. | Learning from the crowd: Road infrastructure monitoring system | |
| CN103236166A (en) | Method for recognizing vehicle violation behaviors with satellite positioning technology | |
| CN104281709A (en) | Method and system for generating traffic information tiled map | |
| CN113538072A (en) | Intelligent travel chain identification method and device for freight vehicle and electronic equipment | |
| CN107622656B (en) | Cross-region data processing method and system for key operation vehicle | |
| Zhu et al. | CrowdParking: Crowdsourcing based parking navigation in autonomous driving era | |
| Iwan et al. | Impact of telematics on efficiency of urban freight transport | |
| Celes et al. | From mobility traces to knowledge: Design guidance for intelligent vehicular networks | |
| CN107958364A (en) | A kind of logistics user behavior pattern analysis and processing method and system | |
| KR101081426B1 (en) | Uses a both direction communication information integrated management system | |
| KR20230109558A (en) | Vehicular computational task allocation | |
| US11809199B2 (en) | Method and apparatus for predicting demand for personal mobility vehicle and redistributing personal mobility vehicle | |
| Yang et al. | Stochastic Parameter Identification Method for Driving Trajectory Simulation Processes Based on Mobile Edge Computing and Self‐Organizing Feature Mapping | |
| CN106887138B (en) | A kind of traffic congestion sprawling situation method for detecting and system | |
| Čolaković et al. | Adaptive Traffic Management Systems Based on the Internet of Things (IoT) | |
| CN113326958A (en) | Congestion degree determining and pushing method, route planning method, related device and system | |
| Abu-Aisha et al. | A New Methodology To Infer Travel Behavior Using Floating Car Data | |
| CN117854284B (en) | Vehicle-road cooperative monitoring method and vehicle detector device for complex road environment | |
| Kyriakou et al. | A pavement rating system based on machine learning | |
| CN112710324B (en) | Block chain traceability technology-based geomagnetic positioning and intelligent terminal construction method | |
| Arregui et al. | Data-Driven Representation Model of Urban Movement Space |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180424 |