CN108537365A - A kind of prediction technique and device of dispatching duration - Google Patents
A kind of prediction technique and device of dispatching duration Download PDFInfo
- Publication number
- CN108537365A CN108537365A CN201810218771.6A CN201810218771A CN108537365A CN 108537365 A CN108537365 A CN 108537365A CN 201810218771 A CN201810218771 A CN 201810218771A CN 108537365 A CN108537365 A CN 108537365A
- Authority
- CN
- China
- Prior art keywords
- dispatching
- parameter values
- combining
- duration
- combining parameter
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/0838—Historical data
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of prediction techniques and device of dispatching duration.The method includes：After at least one combining parameter values for obtaining order to be measured, it can be according to any combining parameter values and combining parameter values and with reference to the correspondence of dispatching duration, it is corresponding with reference to dispatching duration to obtain the combining parameter values, and then at least one combining parameter values of the order to be measured and at least one combining parameter values are corresponding with reference to dispatching duration input dispatching duration prediction model, the estimated dispatching duration of order to be measured can be obtained.Since dispatching duration prediction model is built to the combining parameter values of multiple History Orders and practical dispatching duration by random forests algorithm, and combining parameter values include the parameter value of at least one dispatching duration for influencing order to be measured, therefore, the dispatching duration prediction model can accurately reflect influence of the parameters value to dispatching duration, improve the accuracy of prediction dispatching duration.
Description
Technical field
The present invention relates to logistics distribution technical field more particularly to a kind of prediction techniques and device of dispatching duration.
Background technology
With the development of internet and offline business model (Online To Offline, O2O), more and more persons
Immediate distribution service is selected, immediate distribution service includes suscribing to the clothes such as meal, online purchase vegetable and fruit, online purchase articles for daily use on the net
Business.Although the dispatching distance of these service requests is shorter, the requirement to distribution time is very high, this is to a certain degree to dispatching
More stringent requirements are proposed for the dispatching duration of platform Accurate Prediction dispatching person.
The time is usually divided by distance, speed by the prior art when predicting that dispatching person dispenses the time needed for order
The time of riding of degree influence dispenses the short distance food delivery time that difficulty is influenced with by target location.Wherein, the short distance food delivery time
Including dispatching person park time needed for electric vehicle, into needed for building food delivery time, go out building and ride needed for the action such as electric vehicle
Time, it is difficult to be predicted, thereby reduces prediction dispatching person and dispenses order institute since the influence factor that these actions are subject to is more
The time accuracy needed.
Based on this, there is an urgent need for a kind of prediction techniques of dispatching duration at present, for solving the prior art due to unpredictable close
The problem of causing to be difficult to the time needed for Accurate Prediction dispatching order apart from the used time of food delivery period.
Invention content
The embodiment of the present invention provides a kind of prediction technique and device of dispatching duration, to solve the prior art due to can not be pre-
The technical issues of surveying the used time of short distance food delivery period causes to be difficult to the time needed for Accurate Prediction dispatching order.
The embodiment of the present invention provides a kind of prediction technique of dispatching duration, the method includes：
Obtain at least one combining parameter values of order to be measured, any parameter value at least one combining parameter values
Combination includes the parameter value of at least one dispatching duration for influencing order to be measured；
For the first combining parameter values, according to first combining parameter values and combining parameter values and with reference to dispatching duration
Correspondence, obtain first combining parameter values it is corresponding with reference to dispatching duration；The combining parameter values and reference dispatching
The correspondence of duration is counted according to the combining parameter values and practical dispatching duration of multiple History Orders；Described first
Combining parameter values are any combining parameter values at least one combining parameter values；
By at least one combining parameter values of the order to be measured and the corresponding reference of at least one combining parameter values
Duration input dispatching duration prediction model is dispensed, the estimated dispatching duration of the order to be measured is obtained；The dispatching duration prediction
Model is to the combining parameter values of the multiple History Order and practical dispatching duration build by random forests algorithm
It arrives.
Optionally, a first kind parameter value, the first kind ginseng are included at least in any combining parameter values
Numerical value is the parameter value that influence power is more than first threshold in multiple parameter values for dispensing durations for influencing order to be measured.
Optionally, the first kind parameter value includes dispatching address.
Optionally, at least one combining parameter values include any one of following or arbitrary combination：
Dispense address and distribution time；
Dispense address and date of delivery；
Dispense address and dispatching weather condition；
Dispense address, distribution time and date of delivery；
Dispense address, distribution time and dispatching weather condition；
Dispense address, date of delivery and dispatching weather condition；
Dispense address, distribution time, date of delivery and dispatching weather condition.
The embodiment of the present invention provides a kind of prediction meanss of dispatching duration, and described device includes：
Acquiring unit, at least one combining parameter values for obtaining order to be measured, at least one combining parameter values
In any combining parameter values include at least one dispatching duration for influencing order to be measured parameter value；
Processing unit, for being directed to the first combining parameter values, according to first combining parameter values and combining parameter values
With the correspondence with reference to dispatching duration, it is corresponding with reference to dispatching duration to obtain first combining parameter values；The parameter value
The correspondence of combination and reference dispatching duration is counted according to the combining parameter values and practical dispatching duration of multiple History Orders
It obtains；First combining parameter values are any combining parameter values at least one combining parameter values；
Predicting unit is used at least one combining parameter values of the order to be measured and at least one parameter value group
It closes corresponding inputted with reference to dispatching duration and dispenses duration prediction model, obtain the estimated dispatching duration of the order to be measured；It is described
Dispatching duration prediction model is when being dispensed to the combining parameter values of the multiple History Order and reality by random forests algorithm
What length was built.
Optionally, a first kind parameter value, the first kind ginseng are included at least in any combining parameter values
Numerical value is the parameter value that influence power is more than first threshold in multiple parameter values for dispensing durations for influencing order to be measured.
Optionally, the first kind parameter value includes dispatching address.
Optionally, at least one combining parameter values include any one of following or arbitrary combination：
Dispense address and distribution time；
Dispense address and date of delivery；
Dispense address and dispatching weather condition；
Dispense address, distribution time and date of delivery；
Dispense address, distribution time and dispatching weather condition；
Dispense address, date of delivery and dispatching weather condition；
Dispense address, distribution time, date of delivery and dispatching weather condition.
The embodiment of the present invention provides a kind of computer readable storage medium, and the storage medium is stored with instruction, when described
When instruction is run on computers so that computer, which is realized, executes method as discussed above.
The embodiment of the present invention provides a kind of computer equipment, including：
Memory, for storing program instruction；
Processor executes described above for calling the program instruction stored in the memory according to the program of acquisition
Method.
It, can be according to any ginseng after at least one combining parameter values for obtaining order to be measured in the embodiment of the present invention
The correspondence of combinations of values and combining parameter values and reference dispatching duration, it is corresponding with reference to dispatching to obtain the combining parameter values
Duration, and then the corresponding reference of at least one combining parameter values of the order to be measured and at least one combining parameter values is matched
Duration input dispatching duration prediction model is sent, the estimated dispatching duration of order to be measured can be obtained.In the embodiment of the present invention, due to
Dispatching duration prediction model is when being dispensed to the combining parameter values of the multiple History Order and reality by random forests algorithm
What length was built, and combining parameter values include the parameter value of at least one dispatching duration for influencing order to be measured, because
This, which can accurately reflect influence of the parameters value to dispatching duration so that when the dispatching
Long prediction model has higher confidence level, so as to improve the accuracy of prediction dispatching duration.
Description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without having to pay creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 for the embodiment of the present invention provide it is a kind of dispatching duration prediction technique corresponding to flow diagram；
Fig. 2 is the structural schematic diagram corresponding to a kind of prediction meanss of dispatching duration provided in an embodiment of the present invention.
Specific implementation mode
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that the described embodiments are only some of the embodiments of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
All other embodiment, shall fall within the protection scope of the present invention.
It should be noted that " dispatching duration " involved in the embodiment of the present invention can be to be dispensed difficulty by target location
The short distance food delivery period of influence, or may be the time needed for dispatching person's dispatching order.For the ease of data statistics,
Hereafter by taking " dispatching duration " is to be dispensed the short distance food delivery period that difficulty is influenced by target location as an example, it is specifically described.
Further, after predicting the dispatching duration using method provided in an embodiment of the present invention, can in conjunction with dispatching address with
The riding speed of the distance between seller addresses and dispatching person can predict the time needed for dispatching person's dispatching order.
Fig. 1 illustrate the embodiment of the present invention provide it is a kind of dispatching duration prediction technique corresponding to flow signal
Figure, as shown in Figure 1, specifically comprising the following steps：
Step 101, at least one combining parameter values of order to be measured are obtained, appointing at least one combining parameter values
One combining parameter values include the parameter value of at least one dispatching duration for influencing order to be measured.
Step 102, for the first combining parameter values, according to first combining parameter values and combining parameter values and reference
It is corresponding with reference to dispatching duration to obtain first combining parameter values for the correspondence for dispensing duration.
Step 103, by least one combining parameter values of the order to be measured and at least one combining parameter values pair
The reference dispatching duration input dispatching duration prediction model answered, obtains the estimated dispatching duration of the order to be measured.
Since dispatching duration prediction model is the combining parameter values by random forests algorithm to the multiple History Order
It is built with practical dispatching duration, and combining parameter values include at least one dispatching duration for influencing order to be measured
Parameter value, therefore, the dispatching duration prediction model can accurately reflect parameters value to dispense duration influence, make
Obtaining the dispatching duration prediction model has higher confidence level, so as to improve the accuracy of prediction dispatching duration.
Specifically, in step 101, the parameter value of order to be measured refers to the parameter for the dispatching duration for influencing order to be measured
Value, for example, parameter value may include dispatching address.Wherein, dispatching address is the destination of order dispatching, for example, dispatching address
This parameter value can be the areas xx of the cities the xx roads the xx buildings A Room 3011.
During actual implementation, generally specific to floor, dispatching duration can be by story height for dispatching address
It influences, for the different floors of same storied building, floor is higher, and distribution time is longer.And the floor of some dispatchings address is more, is
It reduces the complexity of data processing, in the embodiment of the present invention, floor can be sorted out.But it is accounted for story height
After certain numerical value, which is generally fitted with elevator.Therefore, whether the embodiment of the present invention pacifies according to dispatching address
Equipped with elevator, floor is classified, is the floor classification example for not installing elevator, wherein floor 1 and building as shown in table 1a
Layer 2 can be classified as one kind, and the category can be indicated with A1；Floor 3 and floor 4 can be classified as one kind, and the category can be indicated with A2；Building
Layer 5 and floor 6 can be classified as one kind, and the category can be indicated with A3；The floor of floor 7 and 7 or more floor can be classified as one kind, should
Classification can be indicated with A4.As shown in table 1b, to install the floor classification example of elevator, wherein floor 1 and floor 2 can be classified as
One kind, the category can be indicated with B1；Floor 3 to floor 7 can be classified as one kind, and the category can be indicated with B2；Floor 8 is to floor 12
It can be classified as one kind, the category can be indicated with B3；Floor 13 to floor 17 can be classified as one kind, and the category can be indicated with B4, building
The floor of layer 18 and 18 or more floor can be classified as one kind, and the category can be indicated with B5.
Table 1a：A kind of example of the floor classification of elevator is not installed
| Floor | Floor is classified |
| Floor 1, floor 2 | A1 |
| Floor 3, floor 4 | A2 |
| Floor 5, floor 6 | A3 |
| Floor 7 and 7 or more floor | A4 |
Table 1b：A kind of example of the floor classification of elevator is installed
| Floor | Floor is classified |
| Floor 1, floor 2 | B1 |
| Floor 3 is to floor 7 | B2 |
| Floor 8 is to floor 12 | B3 |
| Floor 13 is to floor 17 | B4 |
| Floor 18 and 18 or more floor | B5 |
In this way, may include regional location and floor position with the dispatching relevant parameter in address, as shown in table 2, for with
It is the areas xx of the cities the xx roads the xx buildings A Room 3011 to send a kind of example of the relevant parameter value in address, dispatching address 1, is equipped with elevator, then
The parameter value of the regional location of the dispatching address is the areas xx of the cities the x roads the xx buildings A, and the parameter value of floor position is B2 (according to table 1b
It obtains)；Dispatching address 2 is the areas xx of the cities xx No. 1 Room 102 of the roads xx xx cells, does not install elevator, then the region position a of the dispatching address
Parameter value be the areas xx of the cities the x roads xx xx cells 1, the parameter value of floor position is A1 (being obtained according to table 1b)；Dispatching address 3 is
The areas xx of the cities the xx roads the xx mansions B Room 1615, is equipped with elevator, then the parameter value of the regional location of the dispatching address is the areas xx of the cities x xx
The parameter value of the road mansions B, floor position is B4 (being obtained according to table 1b).
Table 2：With a kind of example of the dispatching relevant parameter value in address
| Number | Dispense address | Regional location | Floor position |
| 1 | The areas xx of the cities the xx roads the xx buildings A Room 3011 | The areas xx of the cities the xx roads the xx buildings A | B2 |
| 2 | The areas xx of the cities xx No. 1 Room 102 of the roads xx xx cells | The areas xx of the cities the xx roads xx xx cells 1 | A1 |
| 3 | The areas xx of the cities the xx roads the xx mansions B Room 1615 | The areas xx of the cities the xx roads the xx mansions B | B4 |
Further, parameter value can also include distribution time.Wherein, distribution time can be user confirm place an order when
Between, or may be to take out delivery system to receive the time that user places an order, it does not limit specifically.The distribution time can have
Body is to the date, for example, this parameter value of distribution time can be on 2 3rd, 2,018 11:12:55.
In the actual implementation process, on dispatching duration there is certain influence in the different of distribution time, for example, distribution time is
When lunchtime or date for dinner, order volume is larger, and dispatching duration is relatively long, and the order volume of other time is less, dispatching
Time is also relatively short；For another example, for this kind of dispatching address of office building, different date of delivery dispenses duration
Difference, when date of delivery is working day, order volume is relatively more, and dispatching duration also can be relatively long, and date of delivery is inoperative
When day, order volume is relatively fewer, and dispatching duration also can be relatively short.In view of the data distribution range between dispatching is larger, to keep away
Exempt from the complexity of data processing, it, can be multiple by being divided into for distribution time according to twenty four hours system in the embodiment of the present invention
Section, for example, by distribution time [00:00:00-00:59:59] it is divided into one kind, by distribution time [01:00:00-01:
59:59] it is divided into one kind, can be divided into 24 classifications with the attribute value of exchange hour in this way；Further, it is contemplated that
It the daily schedule of user and the working time of dispatching person, can be by [20:00:00- next day 10:00:00] it is divided into one kind, is had
Body is as shown in table 3, for a kind of example of distribution time classification, specifically repeats no more.
Table 3：A kind of example of distribution time classification
In this way, may include distribution time section and date of delivery (for determining whether with the relevant parameter of distribution time
Working day), as shown in table 4, for a kind of example with the relevant parameter value of distribution time, distribution time 1 is 2018-2-2 17:
22:34, then the distribution time is working day, and corresponding distribution time section is 7 (being obtained according to table 3)；Distribution time 2 is
2018-2-2 22:10:50, then the distribution time is working day, and corresponding distribution time section is 10 (being obtained according to table 3)；Match
It is 2018-2-3 11 to send the time 3:12:55, then the distribution time be working day, and corresponding distribution time section be 1 (according to
Table 3 obtains).
Table 4：With a kind of example of the relevant parameter value of distribution time
| Number | Distribution time | Distribution time section | Whether it is working day |
| 1 | 2018-2-2 17:22:34 | 7 | It is |
| 2 | 2018-2-2 22:10:50 | 10 | It is |
| 3 | 2018-2-3 11:12:55 | 1 | It is no |
Further, parameter value can also include dispatching weather condition.Wherein, dispatching weather condition may include fine day,
The weather such as cloudy, light rain, slight snow, heavy rain, heavy snow.The dispatching duration of different weather conditions, dispatching person is also different, for example, fine
It and cloudy weather, dispatching duration are relatively short；The weather of light rain and slight snow, dispatching duration are slightly longer；Heavy rain and big
The weather of snow, distribution time are relatively long.Based on this, dispatching weather condition can be classified, it is specific as shown in table 5, match
When weather being sent to be fine day or is cloudy, the weather condition is preferable；When dispatching weather is light rain or slight snow, the weather condition is general；Match
Send weather be heavy rain or heavy snow when, the weather condition is poor.
Table 5：Dispense a kind of example of weather condition classification
| Dispense weather condition | Weather condition is classified |
| It is fine day, cloudy | Preferably |
| Light rain, slight snow | Generally |
| Heavy rain, heavy snow | It is poor |
It should be noted that the content included by parameter value described above is only a kind of exemplary illustration, this field
Technical staff can rule of thumb modify to it with actual conditions, not limit specifically.
It is dispatching address, distribution time, date of delivery, dispatching weather feelings with parameter value according to content as described above
For condition, the combining parameter values being worth to according to these parameters are as follows：Dispense address；Distribution time；Date of delivery；Dispense weather
Situation；Dispense address and distribution time；Dispense address and date of delivery；Dispense address and dispatching weather condition；Distribution time and
Date of delivery；Distribution time and dispatching weather condition；Date of delivery and dispatching weather condition；It dispenses address, distribution time and matches
Send the date；Dispense address, distribution time and dispatching weather condition；Dispense address, date of delivery and dispatching weather condition；When dispatching
Between, date of delivery and dispatching weather condition；Dispense address, distribution time, date of delivery and dispatching weather condition.
Further, the combining parameter values can also according to dispatching address (or distribution time, or dispatching weather
Situation) relevant parameter is combined, for example, the combining parameter values can also be regional location；Regional location and floor position；
Regional location, floor position and distribution time；When regional location, floor position, dispatching, date of delivery and dispatching weather condition etc.
Combination, does not limit specifically.
Further, it is contemplated that during actual implementation, each parameter value is different the influence power for dispensing duration.
For example, order 1 to be measured：The parameter value for dispensing the regional location of address is the areas xx of the cities the x roads the xx buildings A, the ginseng of floor position
Numerical value is B2, and the parameter value of distribution time is 1, and the parameter value of date of delivery is working day, and the parameter value for dispensing weather condition is
Preferably；Order 2 to be measured：The parameter value for dispensing the regional location of address is the areas xx of the cities the x roads the xx mansions B, the parameter value of floor position
Parameter value for B2, distribution time is 1, and the parameter value of date of delivery is working day, and the parameter value for dispensing weather condition is preferable；
Order 3 to be measured：The parameter value for dispensing the regional location of address is the areas xx of the cities the x roads the xx mansions B, and the parameter value of floor position is B1,
The parameter value of distribution time is 2, and the parameter value of date of delivery is working day, and the parameter value for dispensing weather condition is preferable.As it can be seen that
Between order 1 and order to be measured 2 to be measured, other than the parameter value difference of the regional location of dispatching address, remaining parameter value is equal
It is identical, but when due to regional location difference, the corresponding dispatching situation in the position can be very different, such as Parking situation, region
Therefore position complex situations etc. in the two estimated orders, are obtained in the case where not considering the regional location of dispatching address
Prediction result be clearly inaccurate；And between order 2 to be measured and order to be measured 3, although the parameter value of floor position and matching
Send the parameter value of time different, but dispense address regional location parameter value be it is identical, it is therefore, identical in regional location
In the case of, the prediction dispatching duration of order 2 and order to be measured 3 to be measured is similar.
Based on this, in the embodiment of the present invention, a first kind parameter value is included at least in any combining parameter values, it is described
First kind parameter value is the parameter that influence power is more than first threshold in multiple parameter values for dispensing durations for influencing order to be measured
Value, the first threshold can be default determining according to practical experience by those skilled in the art, and the embodiment of the present application is to tool
Body method of determination does not limit.Further, which may include dispatching address.It so, it is possible so that institute
Obtained combining parameter values are more accurate, to effectively improve the accuracy of prediction dispatching duration.
Involved combining parameter values and the correspondence with reference to dispatching duration can obtain in several ways in step 102
It arrives.A kind of possible realization method is to count to obtain institute according to the combining parameter values of multiple History Orders and practical dispatching duration
State combining parameter values and the correspondence with reference to dispatching duration.
Specifically, as shown in table 6, it is a kind of example of multiple History Orders.Wherein, the parameter value of History Order includes
Regional location, distribution time section and weather condition, correspondingly, combining parameter values are regional location；Regional location and distribution time
Section；Regional location and weather condition；Regional location, distribution time section and weather condition.
Table 6：A kind of example of multiple History Orders
Further, in order to improve combining parameter values and the accuracy of the correspondence with reference to dispatching duration, present invention reality
History Order can be screened by applying example, for example, the check-in distance to History Order is screened, if the check-in distance refers to
Dispatching person clicks confirmation at the t1 moment and is sent to, at this point, t1 moment corresponding position should be the dispatching address of the order, passes through acquisition
The location information that dispatching person sends in real time during dispensing order determines that the t2 moment matches from these real-time location informations
The location of the person of sending, then t1 moment corresponding position should be the location of dispatching address and t2 moment dispatching persons of the order
The distance between for check-in distance；Wherein, the t2 moment be the distance t1 moment recently and position before time tl.Further
Check-in distance can be less than or equal to the order of pre-determined distance threshold value as reliable sample by ground after obtaining check-in distance.Such as
This, can effectively be avoided due to dispatching person in advance or delay click and confirm to be sent to so as to cause practical this data of dispatching duration not
Accurate problem to improve the accuracy of dispatching duration prediction model, and then improves the accuracy of prediction dispatching duration.
Content shown by table 6 can obtain reference value combination shown in table 7 and be closed with reference to the corresponding of dispatching duration
System, wherein it can be that the corresponding multiple reality of reference value combination dispense that each reference value, which combines corresponding reference dispatching duration,
The average value of duration.
Table 7：Reference value combines a kind of example with the correspondence with reference to dispatching duration
In other examples, it may be the median of multiple practical dispatching durations with reference to dispatching duration, or can be
60% quantile of practical dispatching duration, or can be the average and median of practical dispatching duration, it does not limit specifically.
Further, it is contemplated that the quantity of the corresponding History Order of different parameter combinations is different, for example, according to table
6 and table 7 shown in content it is found that combining parameter values be " A+2+ is preferable " corresponding History Order be that History Order 3 and history are ordered
Single 7, i.e. " A+2+ is preferable " corresponding sample number.Combining parameter values be " A+1+ is preferable " corresponding History Order be History Order 6,
History Order 8 and History Order 10, i.e. " A+1+ is preferable " corresponding sample number are 4.That is, regional location A is at the 2nd
Between section weather it is preferable in the case of be sent to 2 single, with reference to dispatching duration 305s, regional location A is in the 1st preferable feelings of period weather
4 lists are sent under condition, with reference to dispatching duration 275s, it is clear that " A+1+ is preferable " is corresponding right with reference to dispatching time length ratio " A+1+ is preferable "
The reference dispatching duration confidence level higher answered.
Based on this, in the base for the correspondence for determining combining parameter values and reference dispatching duration according to method as discussed above
On plinth, the quantity of the corresponding History Order of each combining parameter values can be further obtained, the quantity of History Order is less than pre-
If amount threshold combining parameter values exclude, so as to improve combining parameter values and with reference to dispatching duration correspondence can
Reliability, and then improve the accuracy of prediction dispatching duration.
In order to clearly describe a kind of prediction technique for dispatching duration that the embodiment of the present invention is provided, below to this
It is illustrated.
In one example, if the regional location of order to be measured is A, distribution time section is 1, and weather condition is preferable, then should
The combining parameter values of order to be measured are：Regional location (A)；Regional location and distribution time section (A+1)；Regional location and weather feelings
Condition (A+ is preferable)；Regional location, distribution time section and weather condition (A+1+ is preferable)；Content shown by table 7 is it is found that area
Domain position (A) is corresponding with reference to a length of 295s when dispensing, and regional location and distribution time section (A+1) are corresponding with reference to dispatching duration
It is 288, regional location and weather condition (A+ is preferable) are corresponding with reference to a length of 285s, regional location, distribution time section when dispensing
It is 275s with weather condition (A+1+ is preferable).
In step 103, dispatching duration prediction model can be obtained previously according to various ways, for example, can be by random
Forest algorithm is built to obtain the dispatching duration pre- to the combining parameter values of multiple History Orders and practical dispatching duration
Survey model.Specifically, when being dispensed to the combining parameter values determined in step 102 and corresponding reference using random forests algorithm
It is long to carry out operation, to build dispatching duration prediction model.Since random forests algorithm is a kind of algorithm based on decision tree, because
This, the dispatching duration prediction model built using this algorithm can generate different decisions according to different combining parameter values
Tree, and vote these decision trees to obtain prediction result, so as to effectively improve the accuracy of prediction result, ensure
Dispense the stability of duration prediction model.
In other possible realization methods, dispatching duration prediction model can also be built otherwise, such as
Algorithm with regress analysis method etc., does not limit specifically.
It should be noted that：(1) in specific implementation process, History Order can choose the preset time period before current date
Interior order, so that waiting for for current date can be more accurately predicted in the dispatching duration prediction model that structure obtains
Survey the dispatching duration of order.(2) in the embodiment of the present invention, determine that combining parameter values and the correspondence with reference to dispatching duration are adopted
Multiple History Orders with structure dispense duration prediction model used by multiple History Orders can be it is identical,
Can be that part is identical, the embodiment of the present invention is not specifically limited.
Based on same inventive concept, the embodiment of the present invention also provides a kind of prediction meanss of dispatching duration, described device
Including acquiring unit 201, processing unit 202, predicting unit 203；Wherein,
Acquiring unit 201, at least one combining parameter values for obtaining order to be measured, at least one parameter value group
Any combining parameter values closed include the parameter value of at least one dispatching duration for influencing order to be measured；
Processing unit 202, for being directed to the first combining parameter values, according to first combining parameter values and parameter value group
It closes and with reference to the correspondence for dispensing duration, it is corresponding with reference to dispatching duration to obtain first combining parameter values；The parameter
Value combines and the correspondence of reference dispatching duration is united according to the combining parameter values and practical dispatching duration of multiple History Orders
What meter obtained；First combining parameter values are any combining parameter values at least one combining parameter values；
Predicting unit 203 is used at least one combining parameter values of the order to be measured and at least one parameter
Value combination is corresponding with reference to dispatching duration input dispatching duration prediction model, obtains the estimated dispatching duration of the order to be measured；
The dispatching duration prediction model is matched to the combining parameter values of the multiple History Order and actually by random forests algorithm
Duration is sent to be built.
Optionally, a first kind parameter value, the first kind ginseng are included at least in any combining parameter values
Numerical value is the parameter value that influence power is more than first threshold in multiple parameter values for dispensing durations for influencing order to be measured.
Optionally, the first kind parameter value includes dispatching address.
Optionally, at least one combining parameter values include any one of following or arbitrary combination：
Dispense address and distribution time；
Dispense address and date of delivery；
Dispense address and dispatching weather condition；
Dispense address, distribution time and date of delivery；
Dispense address, distribution time and dispatching weather condition；
Dispense address, date of delivery and dispatching weather condition；
Dispense address, distribution time, date of delivery and dispatching weather condition.
The embodiment of the present invention provides a kind of computer readable storage medium, and the storage medium is stored with instruction, when described
When instruction is run on computers so that computer, which is realized, executes method as discussed above.
The embodiment of the present invention provides a kind of computer equipment, including：
Memory, for storing program instruction；
Processor executes described above for calling the program instruction stored in the memory according to the program of acquisition
Method.
In the embodiment of the present invention, since dispatching duration prediction model is ordered to the multiple history by random forests algorithm
What single combining parameter values and practical dispatching duration were built, and combining parameter values include that at least one influence is to be measured
The parameter value of the dispatching duration of order, therefore, which can accurately reflect parameters value to matching
Send the influence of duration so that the dispatching duration prediction model has higher confidence level, so as to improve prediction dispatching duration
Accuracy.
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, the present invention can be used in one or more wherein include computer usable program code computer
The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real
The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
God and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of prediction technique of dispatching duration, which is characterized in that the method includes：
Obtain at least one combining parameter values of order to be measured, any combining parameter values at least one combining parameter values
It include the parameter value of at least one dispatching duration for influencing order to be measured；
For the first combining parameter values, according to first combining parameter values and combining parameter values and with reference to pair of dispatching duration
It should be related to, it is corresponding with reference to dispatching duration to obtain first combining parameter values；The combining parameter values and reference dispatching duration
Correspondence be to be counted according to the combining parameter values of multiple History Orders and practical dispatching duration；First parameter
Value is combined as any combining parameter values at least one combining parameter values；
At least one combining parameter values of the order to be measured and at least one combining parameter values are corresponding with reference to dispatching
Duration input dispatching duration prediction model, obtains the estimated dispatching duration of the order to be measured；The dispatching duration prediction model
It is that the combining parameter values of the multiple History Order and practical dispatching duration are built by random forests algorithm.
2. according to the method described in claim 1, it is characterized in that, including at least one first in any combining parameter values
Type parameter value, the first kind parameter value are more than for influence power in the parameter value of multiple dispatching durations for influencing orders to be measured
The parameter value of first threshold.
3. according to the method described in claim 2, it is characterized in that, the first kind parameter value includes dispatching address.
4. method according to any one of claims 1 to 3, which is characterized in that at least one combining parameter values include
Any one of following or arbitrary combination：
Dispense address and distribution time；
Dispense address and date of delivery；
Dispense address and dispatching weather condition；
Dispense address, distribution time and date of delivery；
Dispense address, distribution time and dispatching weather condition；
Dispense address, date of delivery and dispatching weather condition；
Dispense address, distribution time, date of delivery and dispatching weather condition.
5. a kind of prediction meanss of dispatching duration, which is characterized in that described device includes：
Acquiring unit, at least one combining parameter values for obtaining order to be measured, at least one combining parameter values
Any combining parameter values include the parameter value of at least one dispatching duration for influencing order to be measured；
Processing unit, for being directed to the first combining parameter values, according to first combining parameter values and combining parameter values and ginseng
It is corresponding with reference to dispatching duration to obtain first combining parameter values for the correspondence for examining dispatching duration；The combining parameter values
It is to count to obtain according to the combining parameter values and practical dispatching duration of multiple History Orders with the correspondence with reference to dispatching duration
's；First combining parameter values are any combining parameter values at least one combining parameter values；
Predicting unit is used at least one combining parameter values of the order to be measured and at least one combining parameter values pair
The reference dispatching duration input dispatching duration prediction model answered, obtains the estimated dispatching duration of the order to be measured；The dispatching
Duration prediction model is progress when being dispensed to the combining parameter values of the multiple History Order and reality by random forests algorithm
Row structure obtains.
6. device according to claim 5, which is characterized in that include at least one first in any combining parameter values
Type parameter value, the first kind parameter value are more than for influence power in the parameter value of multiple dispatching durations for influencing orders to be measured
The parameter value of first threshold.
7. device according to claim 6, which is characterized in that the first kind parameter value includes dispatching address.
8. according to claim 5 to 8 any one of them device, which is characterized in that at least one combining parameter values include
Any one of following or arbitrary combination：
Dispense address and distribution time；
Dispense address and date of delivery；
Dispense address and dispatching weather condition；
Dispense address, distribution time and date of delivery；
Dispense address, distribution time and dispatching weather condition；
Dispense address, date of delivery and dispatching weather condition；
Dispense address, distribution time, date of delivery and dispatching weather condition.
9. a kind of computer readable storage medium, which is characterized in that the storage medium is stored with instruction, when described instruction is being counted
When being run on calculation machine so that computer realizes that perform claim requires the method described in any one of 1 to 4.
10. a kind of computer equipment, which is characterized in that including：
Memory, for storing program instruction；
Processor, for calling the program instruction stored in the memory, according to acquisition program execute as claim 1 to
Method described in 4 any claims.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810218771.6A CN108537365A (en) | 2018-03-16 | 2018-03-16 | A kind of prediction technique and device of dispatching duration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810218771.6A CN108537365A (en) | 2018-03-16 | 2018-03-16 | A kind of prediction technique and device of dispatching duration |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108537365A true CN108537365A (en) | 2018-09-14 |
Family
ID=63484090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810218771.6A Pending CN108537365A (en) | 2018-03-16 | 2018-03-16 | A kind of prediction technique and device of dispatching duration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108537365A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109544076A (en) * | 2018-11-28 | 2019-03-29 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN109615122A (en) * | 2018-11-27 | 2019-04-12 | 拉扎斯网络科技（上海）有限公司 | Dispense generation method, device, electronic equipment and the storage medium of range |
| CN109636013A (en) * | 2018-11-27 | 2019-04-16 | 拉扎斯网络科技（上海）有限公司 | Dispense generation method, device, electronic equipment and the storage medium of range |
| CN109741076A (en) * | 2018-12-28 | 2019-05-10 | 拉扎斯网络科技（上海）有限公司 | Trade company's execution of contract duration determines method and device, electronic equipment and storage medium |
| CN109993367A (en) * | 2019-04-04 | 2019-07-09 | 拉扎斯网络科技（上海）有限公司 | Dispense estimation method, estimation device, storage medium and the electronic equipment of duration |
| CN110009155A (en) * | 2019-04-08 | 2019-07-12 | 上海拉扎斯信息科技有限公司 | Estimation method, device and the electronic equipment of service area dispatching difficulty |
| CN110119847A (en) * | 2019-05-14 | 2019-08-13 | 拉扎斯网络科技（上海）有限公司 | A kind of prediction technique, device, storage medium and electronic equipment dispensing duration |
| CN110210946A (en) * | 2019-06-10 | 2019-09-06 | 网易无尾熊（杭州）科技有限公司 | Data processing method and device, medium and calculating equipment |
| CN110599078A (en) * | 2019-07-26 | 2019-12-20 | 平安科技（深圳）有限公司 | Logistics distribution information processing method and device and computer equipment |
| CN111260151A (en) * | 2020-02-12 | 2020-06-09 | 上海东普信息科技有限公司 | Multi-frequency dispatch duration prediction method, device, equipment and storage medium |
| CN111401818A (en) * | 2020-04-07 | 2020-07-10 | 上海东普信息科技有限公司 | Express delivery achievement rate calculation method, device, equipment and storage medium |
| CN111754051A (en) * | 2020-07-23 | 2020-10-09 | 拉扎斯网络科技（上海）有限公司 | Traffic duration prediction processing method and device |
| CN111915072A (en) * | 2020-07-20 | 2020-11-10 | 上海燕汐软件信息科技有限公司 | Courier attendance amount prediction method, device and equipment |
| CN112802269A (en) * | 2020-12-31 | 2021-05-14 | 成都希福生物科技有限公司 | Ice powder online sale system and method |
| CN112862133A (en) * | 2019-11-12 | 2021-05-28 | 北京三快在线科技有限公司 | Order processing method and device, readable storage medium and electronic equipment |
| CN113159685A (en) * | 2021-04-26 | 2021-07-23 | 拉扎斯网络科技（上海）有限公司 | Distribution time length updating method, distribution time length updating device, electronic equipment, medium and program product |
| CN113537680A (en) * | 2020-04-20 | 2021-10-22 | 北京京东振世信息技术有限公司 | Method and device for determining completion time of transportation task |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103794053A (en) * | 2014-03-05 | 2014-05-14 | 中商商业发展规划院有限公司 | Vague predicting method and system for city short-distance logistics simple target delivering time |
| CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
| US20170206621A1 (en) * | 2016-01-14 | 2017-07-20 | Alibaba Group Holding Limited | Systems and Methods for Determining the Effectiveness of Warehousing |
| CN107092974A (en) * | 2016-11-29 | 2017-08-25 | 北京小度信息科技有限公司 | Dispense pressure prediction method and device |
| CN107633254A (en) * | 2017-07-25 | 2018-01-26 | 平安科技（深圳）有限公司 | Establish device, method and the computer-readable recording medium of forecast model |
| CN107798502A (en) * | 2017-10-26 | 2018-03-13 | 无锡七百二十度科技有限公司 | A kind of vegetable and fruit allocator based on cloud |
-
2018
- 2018-03-16 CN CN201810218771.6A patent/CN108537365A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103794053A (en) * | 2014-03-05 | 2014-05-14 | 中商商业发展规划院有限公司 | Vague predicting method and system for city short-distance logistics simple target delivering time |
| CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
| US20170206621A1 (en) * | 2016-01-14 | 2017-07-20 | Alibaba Group Holding Limited | Systems and Methods for Determining the Effectiveness of Warehousing |
| CN107092974A (en) * | 2016-11-29 | 2017-08-25 | 北京小度信息科技有限公司 | Dispense pressure prediction method and device |
| CN107633254A (en) * | 2017-07-25 | 2018-01-26 | 平安科技（深圳）有限公司 | Establish device, method and the computer-readable recording medium of forecast model |
| CN107798502A (en) * | 2017-10-26 | 2018-03-13 | 无锡七百二十度科技有限公司 | A kind of vegetable and fruit allocator based on cloud |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109615122B (en) * | 2018-11-27 | 2021-02-02 | 拉扎斯网络科技（上海）有限公司 | Distribution range generation method and device, electronic equipment and storage medium |
| CN109615122A (en) * | 2018-11-27 | 2019-04-12 | 拉扎斯网络科技（上海）有限公司 | Dispense generation method, device, electronic equipment and the storage medium of range |
| CN109636013A (en) * | 2018-11-27 | 2019-04-16 | 拉扎斯网络科技（上海）有限公司 | Dispense generation method, device, electronic equipment and the storage medium of range |
| CN109636013B (en) * | 2018-11-27 | 2021-06-29 | 拉扎斯网络科技（上海）有限公司 | Distribution range generation method and device, electronic equipment and storage medium |
| CN109544076A (en) * | 2018-11-28 | 2019-03-29 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN109544076B (en) * | 2018-11-28 | 2021-06-18 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN109741076A (en) * | 2018-12-28 | 2019-05-10 | 拉扎斯网络科技（上海）有限公司 | Trade company's execution of contract duration determines method and device, electronic equipment and storage medium |
| CN109993367A (en) * | 2019-04-04 | 2019-07-09 | 拉扎斯网络科技（上海）有限公司 | Dispense estimation method, estimation device, storage medium and the electronic equipment of duration |
| CN110009155A (en) * | 2019-04-08 | 2019-07-12 | 上海拉扎斯信息科技有限公司 | Estimation method, device and the electronic equipment of service area dispatching difficulty |
| CN110009155B (en) * | 2019-04-08 | 2021-07-09 | 上海拉扎斯信息科技有限公司 | Method and device for estimating distribution difficulty of service area and electronic equipment |
| CN110119847B (en) * | 2019-05-14 | 2021-07-09 | 拉扎斯网络科技（上海）有限公司 | Distribution time length prediction method and device, storage medium and electronic equipment |
| CN110119847A (en) * | 2019-05-14 | 2019-08-13 | 拉扎斯网络科技（上海）有限公司 | A kind of prediction technique, device, storage medium and electronic equipment dispensing duration |
| CN110210946A (en) * | 2019-06-10 | 2019-09-06 | 网易无尾熊（杭州）科技有限公司 | Data processing method and device, medium and calculating equipment |
| CN110599078A (en) * | 2019-07-26 | 2019-12-20 | 平安科技（深圳）有限公司 | Logistics distribution information processing method and device and computer equipment |
| CN112862133A (en) * | 2019-11-12 | 2021-05-28 | 北京三快在线科技有限公司 | Order processing method and device, readable storage medium and electronic equipment |
| CN111260151A (en) * | 2020-02-12 | 2020-06-09 | 上海东普信息科技有限公司 | Multi-frequency dispatch duration prediction method, device, equipment and storage medium |
| CN111260151B (en) * | 2020-02-12 | 2022-06-24 | 上海东普信息科技有限公司 | Multi-frequency dispatch duration prediction method, device, equipment and storage medium |
| CN111401818A (en) * | 2020-04-07 | 2020-07-10 | 上海东普信息科技有限公司 | Express delivery achievement rate calculation method, device, equipment and storage medium |
| CN111401818B (en) * | 2020-04-07 | 2023-09-26 | 上海东普信息科技有限公司 | Express delivery achievement rate calculation method, device, equipment and storage medium |
| CN113537680A (en) * | 2020-04-20 | 2021-10-22 | 北京京东振世信息技术有限公司 | Method and device for determining completion time of transportation task |
| CN113537680B (en) * | 2020-04-20 | 2023-12-05 | 北京京东振世信息技术有限公司 | Method and device for determining completion time of transportation task |
| CN111915072A (en) * | 2020-07-20 | 2020-11-10 | 上海燕汐软件信息科技有限公司 | Courier attendance amount prediction method, device and equipment |
| CN111754051A (en) * | 2020-07-23 | 2020-10-09 | 拉扎斯网络科技（上海）有限公司 | Traffic duration prediction processing method and device |
| CN112802269A (en) * | 2020-12-31 | 2021-05-14 | 成都希福生物科技有限公司 | Ice powder online sale system and method |
| CN113159685A (en) * | 2021-04-26 | 2021-07-23 | 拉扎斯网络科技（上海）有限公司 | Distribution time length updating method, distribution time length updating device, electronic equipment, medium and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108537365A (en) | A kind of prediction technique and device of dispatching duration | |
| Boyacı et al. | An integrated optimization-simulation framework for vehicle and personnel relocations of electric carsharing systems with reservations | |
| Vaze et al. | Modeling airline frequency competition for airport congestion mitigation | |
| Caicedo et al. | Prediction of parking space availability in real time | |
| CN104102953B (en) | A kind of logistics delivery line optimization generation method and system | |
| CN108364085A (en) | A kind of take-away distribution time prediction technique and device | |
| CN108776852A (en) | Without stake vehicle dispatching method and system | |
| CN109636121A (en) | Dispense Transport capacity dispatching method, order allocation method and device, electronic equipment | |
| CN108647927A (en) | A kind of order allocation method and device | |
| CN109816128B (en) | Method, device and equipment for processing network taxi appointment orders and readable storage medium | |
| Wu et al. | Predicting peak load of bus routes with supply optimization and scaled Shepard interpolation: A newsvendor model | |
| CN109636213A (en) | Order splitting, evaluation method and device, electronic equipment and storage medium | |
| CN111695842B (en) | Distribution scheme determining method, distribution scheme determining device, electronic equipment and computer storage medium | |
| CN107491986A (en) | For controlling the method and device of advertising budget | |
| CN109146203A (en) | Order distribution information prediction technique, device, electronic equipment and storage medium | |
| CN112036696A (en) | Task allocation method, task allocation device, storage medium, and electronic apparatus | |
| CN111507667A (en) | Order allocation method and server applied to short-distance logistics | |
| CN108470261A (en) | A kind of ordering method and device | |
| CN109993475B (en) | Cold chain logistics timing distribution method, system and equipment | |
| CN109583634A (en) | A kind of take-away Distribution path selection method based on Modern Portfolio Theory | |
| CN108694549A (en) | The rental method of service is sent in full-automatic logistics with charge free | |
| CN111275305B (en) | Fair assessment method for traditional taxi and network appointment service in peak time | |
| CN110111055A (en) | A kind of method, apparatus of Order splitting, readable storage medium storing program for executing and electronic equipment | |
| Percoco | Spaces of competition in the sharing economy: taxi markets and Uber entry in NYC. | |
| CN111833595B (en) | Shared automobile auxiliary vehicle configuration method, electronic device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180914 |
|
| RJ01 | Rejection of invention patent application after publication |