CN103794053A - Vague predicting method and system for city short-distance logistics simple target delivering time - Google Patents
Vague predicting method and system for city short-distance logistics simple target delivering time Download PDFInfo
- Publication number
- CN103794053A CN103794053A CN201410077956.1A CN201410077956A CN103794053A CN 103794053 A CN103794053 A CN 103794053A CN 201410077956 A CN201410077956 A CN 201410077956A CN 103794053 A CN103794053 A CN 103794053A
- Authority
- CN
- China
- Prior art keywords
- time
- section
- logistics
- sample
- 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.)
- Granted
Links
Images
Abstract
The invention discloses a vague predicting method and system for city short-distance logistics simple target delivering time. First, different logistics routes are determined according to actual logistics distribution, and the logistics routes are divided into a plurality of independent road sections. Then passing time of distributing vehicles on all the road sections in different logistics routes is collected in real time through a GPS locating system. The collected road section passing time value is used for generating independent road section marks according to the time sequence. The independent road section marks generated in the logistics routes are stored in a sample base as samples in the logistic routes. Finally, a time cycle is selected, a vague predicating result of simple target distributing time is generated. The method is simple, and strong in operability. Moreover, the prediction result can be basically used as distribution time window selection in items, so that the vague predicting method and system can improve the logistics distribution service quality and reduce the on-passage time of fresh farm products.
Description
Technical field
The present invention relates to logistics field, be particularly related to a kind of city short distance logistics single goal distribution time fuzzy prediction method and system, utilize the empirical value consuming time that passes through of historical dispensing, the dispensing period that draws each job order the best, namely physical distribution window, in conjunction with path optimization, help driver's reasonable arrangement dispensing order, quickening task completes speed, guarantees the quality of kinds of goods, improves user satisfaction.
Background technology
Because road network in city is intensive, road conditions are complicated and changeable, and all kinds of factors that affect logistics Vehicle Speed are too much, cannot judge one by one, even if obtain the flow coil monitor value that Traffic Administration Bureau issues, obtain each average link speed, also cannot obtain desirable predicted time; If rely on driver self experience completely, lack again scientific basis, random strong, effect is also undesirable.
Summary of the invention
The object of the invention is to propose a kind of city short distance logistics single goal distribution time fuzzy prediction method and system, utilize the empirical value consuming time that passes through of historical dispensing, draw the dispensing period of each job order the best, namely physical distribution window, in conjunction with path optimization, help driver's reasonable arrangement dispensing order, quickening task completes speed, guarantee the quality of kinds of goods, improve user satisfaction.
To achieve these goals, technical scheme of the present invention is:
A kind of city short distance logistics single goal distribution time fuzzy prediction method, comprising:
The first step: determine logistics route according to actual logistics distribution, described logistics route is divided into multiple independently sections;
Second step: by GPS positioning system real-time collection dispensing vehicle each section in logistics route
Pass through the time;
The 3rd step: gathered each section is generated to each independent section mark by time value according to time sequencing, described mark is at least divided into four sections, first paragraph is that area code, second segment are section code, the 3rd section for time window code, the 4th section are for passing through time value in section, wherein, time window code order comprises date code, time code;
The 4th step: the each independent section mark generating in described logistics route deposits in Sample Storehouse as a sample in described logistics route respectively;
The 5th step: choose a time cycle, produce single goal distribution time fuzzy prediction result:
A. the time ambiguity of first determining the each independent section in described logistics route in the described time cycle predicts the outcome;
A1. read interior logistics route correspondence of selected time cycle in Sample Storehouse and set the each independent section sample of storing in the time cycle;
A2. when the each independent section sample of described logistics route is respectively one, the time ambiguity predicted value in each independent section directly adopts this section to pass through time value;
A3. when within the selected time cycle, the independent section sample of described logistics route is respectively two, and the time ambiguity predicted value in independent section adopts twice section by the mean value of time value;
A4. when setting in the time cycle, when the independent section sample of described logistics route is respectively more than three or three, the time ambiguity predicted value in independent section is by formula t=(t optimism+t pessimism+t most probable × 4)/6 acquisitions, wherein, t is optimistic is that minimum journey time, t pessimism are that maximum journey times, t most probable are intermediate value or maximum time of identical value;
B. by formula T
produce single goal distribution time fuzzy prediction result, the wherein whole independent section number in logistics route described in n=, the time ambiguity predicted value in t=independence section.
Be further, described method is further: in the time that in described logistics route, indivedual independent sections are blank section, the average link speed that adopts Traffic Administration Bureau to issue calculates this section and obtains this section by time value polishing sample space by time value or by field exploring.
Further, described in time cycle of choosing be spring or summer or autumn or time cycle in winter, its maximum duration cycle is no more than 180 days.
Further, in the time that the independent section of described logistics route in the time cycle of choosing sample exceeds 30, choose 30 sample numerical value of variance minimum in all time samples.
A kind of city short distance logistics single goal distribution time Fuzzy estimation system, described system comprises:
A server: described server, for determining different logistics routes according to actual logistics distribution, is divided into multiple independently sections by described logistics route;
A data acquisition unit being connected with server: described data acquisition unit is by the real-time collection dispensing vehicle of GPS positioning system the passing through the time of each section in variant logistics route;
A mark processing device arranging in server: described mark processing device generates each independent section mark by time value according to time sequencing by gathered each section, described mark is at least divided into four sections, first paragraph is that logistics route area code, second segment are section code, the 3rd section for time window code, the 4th section are for passing through time value in section, wherein, time window code order comprise date code, time code, fixing festivals or holidays code and fixing spring, summer, autumn, winter code;
A Sample Storehouse server being connected with server: described Sample Storehouse server identifies the sample in described logistics route respectively for the each independent section that described logistics route is generated and deposits in Sample Storehouse;
A treating apparatus that predicts the outcome arranging in server, described in the treating apparatus that predicts the outcome produce single goal distribution time fuzzy prediction result.
Be further, described system also comprises a supplementary treating apparatus: described supplementary treating apparatus is processed in the time that in described logistics route, indivedual independent sections are blank section, and the average link speed that adopts Traffic Administration Bureau to issue calculates this section and obtains this section by time value polishing sample space by time value or by field exploring.
Further, in described mark processing device, the selected time cycle of time window code is spring or summer or autumn or time cycle in winter, and its maximum duration cycle is no more than 180 days.
Further, described in predict the outcome in treating apparatus in the time that the independent section of described logistics route in the time cycle of choosing sample exceeds 30, choose 30 sample numerical value of variance minimum in all time samples.
The inventive method is simple, workable, and predicting the outcome substantially can be selected for distribution time window in project, can promote logistics distribution service quality, reduces the fresh agricultural products time in transit; And also have advantages of following:
1, computation model parameter is simple, and image data amount is few; Do not need to gather microcosmic road conditions, do not carry out test block analogue simulation, do not need to gather link flow coil yet, according to objective world uncertainty principle, directly ignore Various Complex factor.
2, forecast model can self-teaching, constantly adapts to the road condition change that urban economy social development brings.Utilize genetic algorithm circulation, continue to optimize sample space, method system can oneself be evolved, guarantee that forecast system is not subject to the impact of commercial circle transition, railway network planning, population growth, vehicle growth and lost efficacy gradually.
3, sample collection can be set arbitrarily time origin, because be not to lean on away power curve to predict, not limited by data volume, has certain data accumulation can predict afterwards, supports to enter fast production application, is convenient to transplant.
4, take unit, section as research object, not fixation test district, is decomposed into distribution route the combination in multiple sections, adapts to the flexible variation of distribution route, and expanded application ability is strong.At present take single goal dispensing as research object, when data accumulation to a certain extent, can support the solution of challenge more such as Distribution path optimization of multiple goal dispensing.
Below in conjunction with drawings and Examples, the present invention is described in detail.
Accompanying drawing explanation
Fig. 1 system diagram of the present invention.
Embodiment
embodiment 1:
A kind of city short distance logistics single goal distribution time fuzzy prediction method, comprising:
The first step: determine different logistics routes according to actual logistics distribution, described logistics route is divided into multiple independently sections;
Second step: by GPS positioning system real-time collection dispensing vehicle each section in variant logistics route
Pass through the time;
The 3rd step: gathered each section is generated to each independent section mark by time value according to time sequencing, described mark is at least divided into four sections, first paragraph is that area code, second segment are section code, the 3rd section for time window code, the 4th section are for passing through time value in section, wherein, time window code order comprises date code, time code;
The 4th step: the each independent section mark generating in described logistics route deposits in Sample Storehouse as a sample in described logistics route respectively;
The 5th step: choose a time cycle, produce single goal distribution time fuzzy prediction result:
A. the time ambiguity of first determining the each independent section in described logistics route in the described time cycle predicts the outcome;
A1. read interior logistics route correspondence of selected time cycle in Sample Storehouse and set the each independent section sample of storing in the time cycle;
A2. when the each independent section sample of described logistics route is respectively one, the time ambiguity predicted value in each independent section directly adopts this section to pass through time value;
A3. when within the selected time cycle, the independent section sample of described logistics route is respectively two, and the time ambiguity predicted value in independent section adopts twice section by the mean value of time value;
A4. when setting in the time cycle, when the independent section sample of described logistics route is respectively more than three or three, the time ambiguity predicted value in independent section is by formula t=(t optimism+t pessimism+t most probable × 4)/6 acquisitions, wherein, t is optimistic is that minimum journey time, t pessimism are that maximum journey times, t most probable are intermediate value or maximum time of identical value;
B. by formula T
produce single goal distribution time fuzzy prediction result, the wherein whole independent section number in logistics route described in n=, the time ambiguity predicted value in t=independence section.
In embodiment, described method is further: in the time that in described logistics route, indivedual independent sections are blank section, the average link speed that adopts Traffic Administration Bureau to issue calculates this section and obtains this section by time value polishing sample space by time value or by field exploring.
In embodiment, described in time cycle of choosing be spring or summer or autumn or time cycle in winter, its maximum duration cycle is no more than 180 days.
In embodiment, in the time that the independent section of described logistics route in the time cycle of choosing sample exceeds 30, choose 30 sample numerical value of variance minimum in all time samples.Namely use formula D (X)=E (X
2e)-[(X)]
2calculate variance, afterwards D (X) is arranged according to ascending order from small to large, get time samples numerical value corresponding to front 30 variances, namely 30 less time samples numerical value of dispersion degree, as new Sample Storehouse.
Below further illustrating said method:
The core process of method is totally 4 steps, and the 1st, initialization model, section blocking, acquisition time sample; The 2nd, user provides distribution route and distribution time window; The 3rd, calculate dispensing predicted value; The 4th, dispensing finishes rear acquisition actual value, feeds back to system, carries out sample space optimization.Wherein each step itself comprises again one or more independently treatment schemees.
(1) initialization model, distribution route blocking, acquisition time sample
1, setting sample collection initial time, for example, adopt point 1 day 0 January in 2013, is basic point if system in new urban environment operation, can select to move 0 of the same day; (explain: this method adopts historical passing through the time, by statistic algorithm, obtains forecasted future value, therefore need limit prediction, limit accumulation sample value.）
2, first specifying certain common route a is goal in research.This route is divided into some independently sections, and uses unique ID marking road section.Each section has two by direction, adopts different ID marks.Logistics time window is except according to 24 hour-symbols, is also divided into the Spring Festival, common festivals or holidays, three types on ordinary days, and spring, summer, autumn, four seasons of winter, the Link Travel Time in different logistics time window situations, adopts different ID to mark record.(explain: each section, at ordinary times with festivals or holidays vehicle flowrate be different, the vehicle flowrate of each time period is also different, adopts the similar sample of overall situation to estimate predicted value as far as possible, more approaches true effect.）
Concrete grammar is as follows: road section ID adopts IP address pattern four-part form mark, first paragraph is that division code, second segment are section code, the 3rd section for time window code, the 4th section are for section is by time value (unit be minute), every section of tens digit is no more than 255(and explains: expand for using genetic algorithm optimization Sample Storehouse to do in the future, this patent document scope wouldn't relate to).
First paragraph division code is directly 1 ~ 255 numeral.Division code, if North Star commercial circle is 001, commercial circle, Xidan is 012 etc.
Second segment section code i.e. the section serial number in this region, with 1 ~ 255 numeral.Ru Huizhong North Road, by the section of North Star commercial circle, is labeled as 003;
The 3rd section of time window code, with the numeral between 100 ~ 224, wherein the first bit digital 1 and 2, distinguishes the different logistics directions in same section, and latter two 00 to 24, what represent to be accurate to hour passes through the time.West, Ru Huizhong North Road to the dispensing of, 12 noon, is just labeled as 112 east, as east orientation west to, 12 dispensings, are just labeled as 212.(explain: same section, the different vehicle flowrates of direction differ huge, and internal system is actual is considered as different sections of highway processing.) (do not mark fixing festivals or holidays code and fixing spring, summer, autumn, winter code).
The 4th section is that this section is actual in the time, is recorded as the numeral between 1 ~ 255, take minute as unit.
As North Star commercial circle, west, Hui Zhong North Road east to, 12 30 minutes consuming time by this section, this sample value is expressed as in system:
001.003.112.030
3,, by actual logistics progress, actual acquisition arrives the distribution time Ta of route a and the journey time value t1 in each section, t2 ..., tn, one stores in road section ID, enters in Sample Storehouse.
4, newly-increased route, newly added road sections, produces Tb, Tc ..., adopt said method, be constantly accumulated to section by time samples storehouse.
5, when Sample Storehouse runs up to a certain degree, when all there is sample value in the section of logistics distribution route process in Sample Storehouse, can predict.
6, indivedual blank sections, if needed, adopt two kinds of methods to carry out initialization to journey time sample value, and the one, the average link speed that Traffic Administration Bureau issues calculates; The 2nd, field exploring.Polishing sample space.
(explain: have sample value just to utilize sample value, there is no sample value, with regard to the outer data of acquisition system, implement prediction.）
(2) user provides distribution route and distribution time window is predicted
1, user provides distribution route.
2, user provides distribution time window, year-month-day-time.(explain: distribution time window, it is exactly the time period of dispensing, same section, the different time, by consuming time be distinguishing, logistics vehicles when dispensing, answer the execution sequence of reasonably optimizing dispensing task, the simplest situation is the morning peak task of going out of the city of providing and delivering, and 10 deallocations of later going down town again send next task; The task of commercial circle, Xidan is sent the morning, and afternoon to evening, people will be more and more.）
3, judge season and type under the time providing according to the date.Season and type are two enumerated values, season { spring, summer, autumn, winter }, type { Spring Festival, common festivals or holidays on ordinary days, }.
(3) calculate dispensing predicted value
1, the distribution route that needs predicted time is decomposed into some sections; (explain: disassemble into unit, some sections, unit, each section passed through recycling that predicted value consuming time just can maximal efficiency.）
2, the 1st section operated, find qualified journey time value set according to distribution time window, this road section ID value; (explain: road section ID that Here it is adopts the meaning of four-part form, to filter in database first three section identical, obtain sample set.）
3, selecting wherein at most journey times is the most pessimistic time, and minimum journey time is the most optimistic time, and the time that identical value is maximum is most likely time, according to three point estimation method formula:
T=(T optimism+T pessimism+T most probable * 4)/6
Obtain the estimated time in this section;
Note: in the time that sample value is 1, directly adopt this value; In the time that sample value is 2, adopt arithmetic mean; In the time of sample number >=3, adopt said method.
4, by that analogy, to the 2nd section, circulation said method, obtains the predicted travel time in these all sections of route, and accumulative total obtains predicting distribution time.
T route
(the whole sections of n=number)
(4) sample space optimization
1, record in each delivery process, the reality in each section, by time value, adds to sample space.(explain: the above-mentioned predicted value that just obtains, logistics vehicles on the way all will gather the pass through consuming time situation of institute through section every day at any time, the Sample Storehouse in substantial system.）
2, in the time that said process 1 completes, judge, when single channel section exceedes 30 by time samples, be optimized by time value sample space for this section.Section, by time samples, in nearest 180 days, exceedes 180 days samples before at most, automatically gives up.(explain: logistics task always has repetition, and sample collection quantity constantly increases, can not entirely not be used for prediction, consider socio-economic development trend, cross the sample before long-time, comparison meaning weakens gradually, just deletes them.）
3, carry out sample optimization according to evolution strategy.Evolution strategy is: 30 numerical value that obtain all the time variance minimum in nearest half a year of interior (180 days) all time samples.All time samples should be normal distribution in its arithmetic mean both sides, utilize genetic algorithm, loop Selecting operation, obtain one group of higher 30 time samples of fitness, offer prediction next time and use.(explain: certainly having some samples is individual cases, calculating variance is the simplest method that reduces sample error, constantly rejects exception, obtains the sample value consuming time of passing through that can reflect actual conditions.This is an application of genetic algorithm, if too complicated, can not include in this patent.）
the feature of this method is:
1, utilize fuzzy prediction theory, head direct for theme, challenge is simplified;
2, utilize genetic algorithm circulation to continue to optimize historical trend sample space, make the method system can self-teaching, keep and urban traffic situation changes synchronous variation;
3, the four-part form section coding method of similar IP geocoding mode, had both guaranteed the uniqueness of road section ID to be worth integrated storage by road section ID with by time prediction, was convenient to searching and managing, was convenient to be scaled scale-of-two genotype coding, carried out genetic algorithm computing.
4, this method, according to the close feature of historical trend, is used fuzzy theory, does not consider microcosmic road conditions, do not carry out test block analogue simulation, do not need to gather link flow coil, obtain the variablees such as Vehicle Speed variation tendency, but directly predict according to historical journey time sample value yet.Method is simple, workable, and predicting the outcome substantially can be selected for distribution time window in project, can promote logistics distribution service quality, reduces the fresh agricultural products time in transit.
Although 5 is the fuzzy predictions that carry out according to Probability Statistics Theory, but still consider Various Seasonal, on ordinary days with the variation that festivals or holidays, even Spring Festival brought to urban traffic situation, Link Travel Time is carried out to statistic of classification, filter as far as possible sample noise.
embodiment 2:
Realize a system for city short distance logistics single goal distribution time fuzzy prediction method described in embodiment 1,
Referring to Fig. 1, described system comprises:
A predictive server 1: described server, for determining different logistics routes according to actual logistics distribution, is divided into multiple independently sections by described logistics route;
A data acquisition unit being connected with server 2: described data acquisition unit is by the real-time collection dispensing vehicle of GPS positioning system the passing through the time of each section in variant logistics route;
A mark processing device 1-1 who arranges in server: described mark processing device generates each independent section mark by time value according to time sequencing by gathered each section, described mark is at least divided into four sections, first paragraph is that logistics route area code, second segment are section code, the 3rd section for time window code, the 4th section are for passing through time value in section, wherein, time window code order comprise date code, time code, fixing festivals or holidays code and fixing spring, summer, autumn, winter code;
A Sample Storehouse server 3 being connected with server: described Sample Storehouse server identifies the sample in described logistics route respectively for the each independent section that described logistics route is generated and deposits in Sample Storehouse;
A treating apparatus 1-2 that predicts the outcome arranging in server, described in the treating apparatus that predicts the outcome produce single goal distribution time fuzzy prediction result.
In embodiment, described system also comprises a supplementary treating apparatus: described supplementary treating apparatus is processed in the time that in described logistics route, indivedual independent sections are blank section, and the average link speed that adopts Traffic Administration Bureau to issue calculates this section and obtains this section by time value polishing sample space by time value or by field exploring.
In embodiment, in described mark processing device, the selected time cycle of time window code is spring or summer or autumn or time cycle in winter, and its maximum duration cycle is no more than 180 days.
In embodiment, described in predict the outcome in treating apparatus in the time that the independent section of described logistics route in the time cycle of choosing sample exceeds 30, choose 30 sample numerical value of variance minimum in all time samples.
Claims (8)
1. a city short distance logistics single goal distribution time fuzzy prediction method, is characterized in that, described method comprises:
The first step: determine logistics route according to actual logistics distribution, described logistics route is divided into multiple independently sections;
Second step: by GPS positioning system real-time collection dispensing vehicle each section in logistics route
Pass through the time;
The 3rd step: gathered each section is generated to each independent section mark by time value according to time sequencing, described mark is at least divided into four sections, first paragraph is that area code, second segment are section code, the 3rd section for time window code, the 4th section are for passing through time value in section, wherein, time window code order comprises date code, time code;
The 4th step: the each independent section mark generating in described logistics route deposits in Sample Storehouse as a sample in described logistics route respectively;
The 5th step: choose a time cycle, produce single goal distribution time fuzzy prediction result:
A. the time ambiguity of first determining the each independent section in described logistics route in the described time cycle predicts the outcome;
A1. read interior logistics route correspondence of selected time cycle in Sample Storehouse and set the each independent section sample of storing in the time cycle;
A2. when the each independent section sample of described logistics route is respectively one, the time ambiguity predicted value in each independent section directly adopts this section to pass through time value;
A3. when within the selected time cycle, the independent section sample of described logistics route is respectively two, and the time ambiguity predicted value in independent section adopts twice section by the mean value of time value;
A4. when setting in the time cycle, when the independent section sample of described logistics route is respectively more than three or three, the time ambiguity predicted value in independent section is by formula t=(t optimism+t pessimism+t most probable × 4)/6 acquisitions, wherein, t is optimistic is that minimum journey time, t pessimism are that maximum journey times, t most probable are intermediate value or maximum time of identical value;
B. by formula T
produce single goal distribution time fuzzy prediction result, the wherein whole independent section number in logistics route described in n=, the time ambiguity predicted value in t=independence section.
2. a kind of city short distance logistics single goal distribution time fuzzy prediction method according to claim 1, it is characterized in that, described method is further: in the time that in described logistics route, indivedual independent sections are blank section, the average link speed that adopts Traffic Administration Bureau to issue calculates this section and obtains this section by time value polishing sample space by time value or by field exploring.
3. a kind of city short distance logistics single goal distribution time fuzzy prediction method according to claim 1,
It is characterized in that, described in time cycle of choosing be spring or summer or autumn or time cycle in winter, its maximum duration cycle is no more than 180 days.
4. fuzzy according to a kind of city short distance logistics single goal distribution time described in claim 1 or 2 or 3
Forecasting Methodology, is characterized in that, in the time that the independent section of described logistics route in the time cycle of choosing sample exceeds 30, chooses 30 sample numerical value of variance minimum in all time samples.
5. a city short distance logistics single goal distribution time Fuzzy estimation system, is characterized in that described system
Turnkey is drawn together:
A server: described server, for determining different logistics routes according to actual logistics distribution, is divided into multiple independently sections by described logistics route;
A data acquisition unit being connected with server: described data acquisition unit is by the real-time collection dispensing vehicle of GPS positioning system the passing through the time of each section in variant logistics route;
A mark processing device arranging in server: described mark processing device generates each independent section mark by time value according to time sequencing by gathered each section, described mark is at least divided into four sections, first paragraph is that logistics route area code, second segment are section code, the 3rd section for time window code, the 4th section are for passing through time value in section, wherein, time window code order comprise date code, time code, fixing festivals or holidays code and fixing spring, summer, autumn, winter code;
A Sample Storehouse server being connected with server: described Sample Storehouse server identifies the sample in described logistics route respectively for the each independent section that described logistics route is generated and deposits in Sample Storehouse;
A treating apparatus that predicts the outcome arranging in server, described in the treating apparatus that predicts the outcome produce single goal distribution time fuzzy prediction result.
6. a kind of city short distance logistics single goal distribution time Fuzzy estimation system according to claim 5, it is characterized in that, described system also comprises a supplementary treating apparatus: described supplementary treating apparatus is processed in the time that in described logistics route, indivedual independent sections are blank section, and the average link speed that adopts Traffic Administration Bureau to issue calculates this section and obtains this section by time value polishing sample space by time value or by field exploring.
7. a kind of city short distance logistics single goal distribution time Fuzzy estimation system according to claim 5, it is characterized in that, in described mark processing device, the selected time cycle of time window code is spring or summer or autumn or time cycle in winter, and its maximum duration cycle is no more than 180 days.
8. a kind of city short distance logistics single goal distribution time Fuzzy estimation system according to claim 5, it is characterized in that, in the described treating apparatus that predicts the outcome, in the time that the independent section of described logistics route in the time cycle of choosing sample exceeds 30, choose 30 sample numerical value of variance minimum in all time samples.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410077956.1A CN103794053B (en) | 2014-03-05 | 2014-03-05 | Vague predicting method for city short-distance logistics simple target delivering time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410077956.1A CN103794053B (en) | 2014-03-05 | 2014-03-05 | Vague predicting method for city short-distance logistics simple target delivering time |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103794053A true CN103794053A (en) | 2014-05-14 |
| CN103794053B CN103794053B (en) | 2015-04-01 |
Family
ID=50669664
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410077956.1A Expired - Fee Related CN103794053B (en) | 2014-03-05 | 2014-03-05 | Vague predicting method for city short-distance logistics simple target delivering time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103794053B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104156838A (en) * | 2014-05-16 | 2014-11-19 | 东南大学 | Pig slaughtering link retrospective method based on time window |
| CN105224994A (en) * | 2014-07-03 | 2016-01-06 | 富士通株式会社 | The apparatus and method of the prediction residence time, the equipment determining delivery route and method |
| CN105590183A (en) * | 2015-12-18 | 2016-05-18 | 苏州功路驿站网络科技有限公司 | Logistic multi-supplier in-transit management system |
| WO2016155517A1 (en) * | 2015-04-03 | 2016-10-06 | 阿里巴巴集团控股有限公司 | Logistics monitoring method and device |
| CN107169845A (en) * | 2017-06-07 | 2017-09-15 | 北京小度信息科技有限公司 | A kind of trade company's attribute query method, device and server |
| CN107203858A (en) * | 2016-03-16 | 2017-09-26 | 阿里巴巴集团控股有限公司 | Distribution time determines method and apparatus |
| CN107292418A (en) * | 2017-05-23 | 2017-10-24 | 顺丰科技有限公司 | A kind of waybill is detained Forecasting Methodology |
| CN107331149A (en) * | 2016-04-29 | 2017-11-07 | 株式会社日立制作所 | The method and apparatus for predicting time of vehicle operation |
| CN107437144A (en) * | 2017-08-01 | 2017-12-05 | 北京闪送科技有限公司 | A kind of order dispatch method, system, computer equipment and storage medium |
| CN108256685A (en) * | 2018-01-22 | 2018-07-06 | 浙江工业大学 | A kind of Hospital Logistic shipping time Forecasting Methodology based on multiple linear regression model |
| CN108364085A (en) * | 2018-01-02 | 2018-08-03 | 拉扎斯网络科技（上海）有限公司 | A kind of take-away distribution time prediction technique and device |
| CN108537365A (en) * | 2018-03-16 | 2018-09-14 | 拉扎斯网络科技（上海）有限公司 | A kind of prediction technique and device of dispatching duration |
| CN109508923A (en) * | 2018-09-30 | 2019-03-22 | 深圳春沐源控股有限公司 | Order allocator, device, server and storage medium |
| CN109858855A (en) * | 2019-01-14 | 2019-06-07 | 北京邮电大学 | A kind of express delivery Distribution path optimization method, device and electronic equipment |
| CN110503225A (en) * | 2018-05-17 | 2019-11-26 | 株式会社日立制作所 | A kind of order worksheet processing allocator |
| CN111932043A (en) * | 2020-10-12 | 2020-11-13 | 广州赛特智能科技有限公司 | Early warning method for robot distribution time |
| CN111950803A (en) * | 2020-08-24 | 2020-11-17 | 上海寻梦信息技术有限公司 | Logistics object delivery time prediction method and device, electronic equipment and storage medium |
| CN111985873A (en) * | 2020-08-21 | 2020-11-24 | 杨培 | Logistics transportation scheme acquisition method |
| CN112639904A (en) * | 2018-09-06 | 2021-04-09 | 本田技研工业株式会社 | Route subdividing device |
| CN113706874A (en) * | 2021-10-28 | 2021-11-26 | 华清科盛(北京)信息技术有限公司 | Method and device for predicting arrival time of logistics vehicles in factory in real time and electronic equipment |
| CN114418471A (en) * | 2022-03-31 | 2022-04-29 | 广州平云小匠科技有限公司 | Intelligent planning and visual management method and system for work orders |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000348296A (en) * | 1999-06-04 | 2000-12-15 | Toshiba Fa Syst Eng Corp | Vehicle allocation system |
| CN101320442A (en) * | 2007-06-05 | 2008-12-10 | 上海博拉软件有限公司 | Method for implementing real-time cargo tracing and monitoring based on logistics management platform |
-
2014
- 2014-03-05 CN CN201410077956.1A patent/CN103794053B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000348296A (en) * | 1999-06-04 | 2000-12-15 | Toshiba Fa Syst Eng Corp | Vehicle allocation system |
| CN101320442A (en) * | 2007-06-05 | 2008-12-10 | 上海博拉软件有限公司 | Method for implementing real-time cargo tracing and monitoring based on logistics management platform |
Non-Patent Citations (1)
| Title |
|---|
| 叶创鑫，谭满春: "基于SVM与人工神经网络组合模型的物流规划车辆行程时间预测", 《暨南大学学报（自然科学版）》, vol. 31, no. 5, 31 October 2010 (2010-10-31), pages 451 - 456 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104156838A (en) * | 2014-05-16 | 2014-11-19 | 东南大学 | Pig slaughtering link retrospective method based on time window |
| CN105224994A (en) * | 2014-07-03 | 2016-01-06 | 富士通株式会社 | The apparatus and method of the prediction residence time, the equipment determining delivery route and method |
| US10446023B2 (en) | 2015-04-03 | 2019-10-15 | Alibaba Group Holding Limited | Logistics monitoring method and device |
| WO2016155517A1 (en) * | 2015-04-03 | 2016-10-06 | 阿里巴巴集团控股有限公司 | Logistics monitoring method and device |
| CN106156966A (en) * | 2015-04-03 | 2016-11-23 | 阿里巴巴集团控股有限公司 | Logistics monitoring method and equipment |
| CN105590183A (en) * | 2015-12-18 | 2016-05-18 | 苏州功路驿站网络科技有限公司 | Logistic multi-supplier in-transit management system |
| CN107203858A (en) * | 2016-03-16 | 2017-09-26 | 阿里巴巴集团控股有限公司 | Distribution time determines method and apparatus |
| CN107203858B (en) * | 2016-03-16 | 2020-12-18 | 菜鸟智能物流控股有限公司 | Distribution time determining method and device |
| CN107331149B (en) * | 2016-04-29 | 2021-07-09 | 株式会社日立制作所 | Method and device for predicting vehicle running time |
| CN107331149A (en) * | 2016-04-29 | 2017-11-07 | 株式会社日立制作所 | The method and apparatus for predicting time of vehicle operation |
| CN107292418A (en) * | 2017-05-23 | 2017-10-24 | 顺丰科技有限公司 | A kind of waybill is detained Forecasting Methodology |
| CN107169845A (en) * | 2017-06-07 | 2017-09-15 | 北京小度信息科技有限公司 | A kind of trade company's attribute query method, device and server |
| CN107437144A (en) * | 2017-08-01 | 2017-12-05 | 北京闪送科技有限公司 | A kind of order dispatch method, system, computer equipment and storage medium |
| CN108364085B (en) * | 2018-01-02 | 2020-12-15 | 拉扎斯网络科技（上海）有限公司 | Takeout delivery time prediction method and device |
| CN108364085A (en) * | 2018-01-02 | 2018-08-03 | 拉扎斯网络科技（上海）有限公司 | A kind of take-away distribution time prediction technique and device |
| CN108256685A (en) * | 2018-01-22 | 2018-07-06 | 浙江工业大学 | A kind of Hospital Logistic shipping time Forecasting Methodology based on multiple linear regression model |
| CN108256685B (en) * | 2018-01-22 | 2021-02-26 | 浙江工业大学 | Hospital logistics transportation time prediction method based on multiple linear regression model |
| CN108537365A (en) * | 2018-03-16 | 2018-09-14 | 拉扎斯网络科技（上海）有限公司 | A kind of prediction technique and device of dispatching duration |
| CN110503225A (en) * | 2018-05-17 | 2019-11-26 | 株式会社日立制作所 | A kind of order worksheet processing allocator |
| CN112639904A (en) * | 2018-09-06 | 2021-04-09 | 本田技研工业株式会社 | Route subdividing device |
| CN112639904B (en) * | 2018-09-06 | 2022-10-11 | 本田技研工业株式会社 | Route subdividing device |
| CN109508923A (en) * | 2018-09-30 | 2019-03-22 | 深圳春沐源控股有限公司 | Order allocator, device, server and storage medium |
| CN109858855A (en) * | 2019-01-14 | 2019-06-07 | 北京邮电大学 | A kind of express delivery Distribution path optimization method, device and electronic equipment |
| CN111985873A (en) * | 2020-08-21 | 2020-11-24 | 杨培 | Logistics transportation scheme acquisition method |
| CN111950803A (en) * | 2020-08-24 | 2020-11-17 | 上海寻梦信息技术有限公司 | Logistics object delivery time prediction method and device, electronic equipment and storage medium |
| CN111932043A (en) * | 2020-10-12 | 2020-11-13 | 广州赛特智能科技有限公司 | Early warning method for robot distribution time |
| CN111932043B (en) * | 2020-10-12 | 2021-05-18 | 广州赛特智能科技有限公司 | Early warning method for robot distribution time |
| CN113706874A (en) * | 2021-10-28 | 2021-11-26 | 华清科盛(北京)信息技术有限公司 | Method and device for predicting arrival time of logistics vehicles in factory in real time and electronic equipment |
| CN114418471A (en) * | 2022-03-31 | 2022-04-29 | 广州平云小匠科技有限公司 | Intelligent planning and visual management method and system for work orders |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103794053B (en) | 2015-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103794053B (en) | Vague predicting method for city short-distance logistics simple target delivering time | |
| Qin et al. | Ride-hailing order dispatching at didi via reinforcement learning | |
| Tian et al. | Dynamic pricing for reservation-based parking system: A revenue management method | |
| CN109117993B (en) | Processing method for optimizing vehicle path | |
| Rajamoorthy et al. | A novel intelligent transport system charging scheduling for electric vehicles using Grey Wolf Optimizer and Sail Fish Optimization algorithms | |
| CN103747523B (en) | A kind of customer location forecasting system and method based on wireless network | |
| CN107919014B (en) | Taxi running route optimization method for multiple passenger mileage | |
| CN105303487A (en) | Method and device of travel service | |
| CN104464291A (en) | Traffic flow predicting method and system | |
| CN107330586A (en) | A kind of public bicycles dynamic dispatching method based on improvement ant group algorithm | |
| CN104102953A (en) | Logistics delivery route optimizing generation method and system | |
| CN109741626A (en) | Parking situation prediction technique, dispatching method and system | |
| CN103731916A (en) | Wireless-network-based user position predicting system and method | |
| CN108765940A (en) | Road congestion based on high-order Markov model finds method | |
| CN104282142B (en) | Bus station arrangement method based on taxi GPS data | |
| Nair et al. | Equilibrium design of bicycle sharing systems: the case of Washington DC | |
| CN107025504A (en) | A kind of service type storehouse site selecting method for considering region transportation situation | |
| Jamil et al. | Taxi passenger hotspot prediction using automatic ARIMA model | |
| CN104464280A (en) | Vehicle advance expenditure prediction method and system | |
| CN105389647A (en) | NSGA-II-based electricity fee payment place site-selecting method | |
| Xi et al. | Hmdrl: Hierarchical mixed deep reinforcement learning to balance vehicle supply and demand | |
| Yang | The nonlinear effects of multi-scale built environments on CO2 emissions from commuting | |
| CN107526815A (en) | The determination method and electronic equipment of Move Mode in the range of target area | |
| Wang et al. | Towards accessible shared autonomous electric mobility with dynamic deadlines | |
| CN109064750A (en) | Urban road network traffic estimation method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150401 Termination date: 20180305 |