CN110491124A - A kind of vehicle flow prediction technique, device, equipment and storage medium - Google Patents
A kind of vehicle flow prediction technique, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110491124A CN110491124A CN201910765989.8A CN201910765989A CN110491124A CN 110491124 A CN110491124 A CN 110491124A CN 201910765989 A CN201910765989 A CN 201910765989A CN 110491124 A CN110491124 A CN 110491124A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- time series
- interaction data
- current type
- historical interaction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000003993 interaction Effects 0.000 claims abstract description 132
- 241001123248 Arma Species 0.000 claims abstract description 46
- 230000006399 behavior Effects 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 21
- 230000015654 memory Effects 0.000 claims description 12
- 230000015572 biosynthetic process Effects 0.000 claims description 7
- 238000003786 synthesis reaction Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 abstract description 3
- 206010019133 Hangover Diseases 0.000 description 6
- 238000007667 floating Methods 0.000 description 6
- 241000208340 Araliaceae Species 0.000 description 4
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 4
- 235000003140 Panax quinquefolius Nutrition 0.000 description 4
- 235000008434 ginseng Nutrition 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000000714 time series forecasting Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013506 data mapping Methods 0.000 description 1
- 230000009189 diving Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Chemical & Material Sciences (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a kind of vehicle flow prediction technique, device, equipment and storage mediums.This method comprises: obtaining different user to the historical interaction data of the vehicle of current type, and determine trip wish time series corresponding with current type vehicle according to each historical interaction data；It is fitted arma modeling according to trip wish time series, and is predicted according to vehicle flow of the arma modeling to current type vehicle in the following set period of time.The technical solution of the embodiment of the present invention passes through the arma modeling that user is fitted the trip wish time series of current type vehicle, it can be from trip wish time series itself, in view of the potential connection in trip wish time series between different data, establish the mapping relations between historical data and Future Data, and then in future time section when the prediction of vehicle flow, precision of prediction and forecasting efficiency are improved, to improve the usage experience of user.
Description
Technical field
The present embodiments relate to field of computer technology more particularly to a kind of vehicle flow prediction techniques, device, equipment
And storage medium.
Background technique
It is shared economical as a kind of new economic form, high frequency friendship is carried out by this information carrier of shared platform and user
Mutually, supplying party's slack resources are temporarily shifted by shared platform, asset utilization ratio is improved, provides convenience for party in request, for supply
Create value in side.
In order to provide the user with better service in shared platform of hiring a car, it will usually be gone on a journey and be believed according to the history of user
Breath, predicts the vehicle flow of different periods, to realize the rational allocation to the different types of vehicle of different periods.
When predicting in the prior art the vehicle flow of different periods, the mode for generalling use empirical analysis is subject to reality
It is existing.However, since empirical analysis process takes a long time, while its standard defines disunity, has ignored diving between different data
It is contacting, is causing the precision of prediction by the way of empirical analysis poor, to reduce the usage experience of user.
Summary of the invention
The present invention provides a kind of vehicle flow prediction technique, device, equipment and storage medium, to improve to different periods
The forecasting efficiency and precision of prediction of vehicle wandering, to promote the usage experience of user.
In a first aspect, the embodiment of the invention provides a kind of vehicle flow prediction techniques, comprising:
Different user is obtained to the historical interaction data of the vehicle of current type, and true according to each historical interaction data
Fixed trip wish time series corresponding with the current type vehicle；
It is fitted autoregressive moving average arma modeling according to the trip wish time series, and according to the arma modeling
The vehicle flow of current type vehicle described in the following set period of time is predicted.
Second aspect, the embodiment of the invention also provides a kind of vehicle flow prediction meanss, comprising:
Time series determining module, for obtaining different user to the historical interaction data of the vehicle of current type, and root
Trip wish time series corresponding with the current type vehicle is determined according to each historical interaction data；
Vehicle flow prediction module, for being fitted autoregressive moving average ARMA mould according to the trip wish time series
Type, and predicted according to vehicle flow of the arma modeling to current type vehicle described in the following set period of time.
The third aspect, the embodiment of the invention also provides a kind of electronic equipment, comprising:
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes a kind of vehicle flow prediction technique as provided by first aspect embodiment.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program, which is characterized in that a kind of vehicle flow as provided by first aspect embodiment is realized when the program is executed by processor
Prediction technique.
The embodiment of the present invention is by obtaining different user to the historical interaction data of the vehicle of current type, and according to respectively going through
History interaction data determines trip wish time series corresponding with current type vehicle；According to trip wish time series fitting
Arma modeling, and predicted according to vehicle flow of the ARAM model to current type vehicle in the following set period of time.It is above-mentioned
Technical solution carries out the fitting of arma modeling by user to the trip wish time series of current type vehicle, so that after fitting
Arma modeling can be from trip wish time series itself, it is contemplated that in trip wish time series between different data
Potential connection, establish the mapping relations between historical data and Future Data, and then the vehicle flow in future time section
When the prediction of amount, precision of prediction and forecasting efficiency are improved, to improve the usage experience of user.
Detailed description of the invention
Fig. 1 is the flow chart of one of embodiment of the present invention one vehicle flow prediction technique；
Fig. 2 is the flow chart of one of embodiment of the present invention two vehicle flow prediction technique；
Fig. 3 A is the flow chart of one of embodiment of the present invention three vehicle flow prediction technique；
Fig. 3 B is one of embodiment of the present invention three model integrated stand composition；
Fig. 3 C is one of embodiment of the present invention three vehicle time series establishment process figure；
Fig. 3 D is one of embodiment of the present invention three vehicle time series schematic diagram；
Fig. 3 E is the vehicle time series schematic diagram after one of the embodiment of the present invention three difference processing；
Fig. 3 F is one of embodiment of the present invention three auto-correlation coefficient distribution map；
Fig. 3 G is one of embodiment of the present invention three PARCOR coefficients distribution map；
Fig. 3 H is one of embodiment of the present invention three vehicle time series forecasting difference prediction result figure；
Fig. 3 I is one of embodiment of the present invention three vehicle time series forecasting actual prediction result figure；
Fig. 4 is the structure chart of one of embodiment of the present invention four vehicle flow prediction meanss；
Fig. 5 is the structure chart of one of the embodiment of the present invention five electronic equipment.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the flow chart of one of embodiment of the present invention one vehicle flow prediction technique, and the embodiment of the present invention is applicable in
In in shared platform of hiring a car, the flow of different types of vehicle corresponding to different time sections in advance is predicted the case where.
This method is executed by vehicle flow prediction meanss, and the device is by software and or hardware realization, and concrete configuration is certain in having
In the electronic equipment of data operation ability, wherein electronic equipment can be server or PC.
A kind of vehicle flow prediction technique as shown in Figure 1, comprising:
S110, different user is obtained to the historical interaction data of the vehicle of current type, and according to each history interaction
Data determine trip wish time series corresponding with the current type vehicle.
Wherein, historical interaction data characterizes user to corresponding for recording user to the interbehavior of different type vehicle
The fancy grade of type of vehicle.Wherein, trip wish time series for characterize in different time period user to different type
The fancy grade or consumption wish of vehicle, have continuity on time dimension.Wherein, user can be understood as it is shared hire a car it is flat
The a large number of users of a certain geographic area in platform, wherein geographic area can by technical staff as needed or empirical value set
It is fixed；The quantity of user can also or empirical value sets itself as needed by technical staff.In general, in order to improve vehicle flow
Precision of prediction, the quantity of user need it is as big as possible, to guarantee that history interbehavior is as more as possible.Wherein, interbehavior
It is including search behavior and/or in single file.
Illustratively, historical interaction data can be stored in advance in electronic equipment it is local, with associated by electronic equipment its
He stores in equipment or cloud；Correspondingly, obtaining user to the historical interaction data of the vehicle of current type, can be in electronics
Locally and in other storage equipment or cloud associated by electronic equipment, the lookup for carrying out historical interaction data obtains equipment.
In a kind of optional embodiment of the embodiment of the present invention, different user is obtained to the history of the vehicle of current type
Interaction data can be and directly be obtained according to the lookup that type of vehicle carries out historical interaction data；It can also be and obtain all vehicles
The corresponding historical interaction data of type, then screens historical interaction data according to type of vehicle, obtains current type
Historical interaction data corresponding to vehicle；It can also be and obtain the corresponding historical interaction data of different user, and by each user couple
The historical interaction data answered is counted according to type of vehicle, obtains the corresponding historical interaction data of different vehicle type.
Illustratively, trip wish time series corresponding with current type vehicle is determined according to each historical interaction data,
It can be and each historical interaction data is divided according to certain period of time, by the corresponding historical interaction data of different time sections
Spliced according to chronological order, obtains trip wish time series.
It is understood that in order to improve it is subsequent vehicle flow is predicted when precision of prediction, can also obtain
After user is to the historical interaction data of the vehicle of current type, the invalid data in historical interaction data can also be filtered
It removes and the operation such as logarithm type data are normalized.
S120, arma modeling is fitted according to the trip wish time series, and future is set according to the arma modeling
The vehicle flow of the current type vehicle is predicted in section of fixing time.
Wherein, ARMA (Autoregressive moving average model, autoregressive moving average) model is used for
Transition research is carried out to the consumer behavior of current type vehicle or using wish to user, namely excavates trip wish time series
Incidence relation between middle different time sections, it is right to pass through the interbehavior of the current type vehicle of previous time period user couple
User predicts the interbehavior of current type vehicle in future time section, to obtain current in the following set period of time
The vehicle flow of type of vehicle.
It should be noted that by the prediction for the vehicle flow of current vehicle type in the following set period of time, it can
Vehicle scheduling is carried out to all types of vehicles, so that corresponding according to the corresponding vehicle flow prediction result of different type vehicle
Each candidate vehicle shared in platform of hiring a car in period can match the demand of user to greatest extent, and then promote user and use
Shared platform of hiring a car carries out the experience of vehicle rental.
It is understood that since arma modeling is used to carry out rational spectrum research to stationary random process, so in basis
Before wish time series of going on a journey fitting autoregressive moving average arma modeling, the trip wish time series can also be determined
Steady type, and the steady type be it is unstable when to the trip wish time series progress tranquilization processing.Phase
It answers, arma modeling is fitted according to the trip wish time series after smoothing techniques, and set to future according to arma modeling
The vehicle flow of current type vehicle is predicted in period.
In a kind of optional embodiment of the embodiment of the present invention, determine that the steady type of trip wish time series can be with
It is realized in the following ways: determining the auto-correlation coefficient distribution and PARCOR coefficients distribution of trip wish time series；
If auto-correlation coefficient distribution and PARCOR coefficients distribution be truncation or hangover, it is determined that trip wish time series it is steady
Type is steady；It otherwise, is unstable.
In a kind of optional embodiment of the embodiment of the present invention, tranquilization processing is carried out to trip wish time series,
It can be realized by the way of difference processing, and cooperate corresponding curve type.For example, if to trip wish time series
It is roughly the same to carry out each numerical value obtained after first difference processing, then can cooperate trends of straight line；If to trip wish time sequence
Each numerical value obtained after column progress second order difference processing is roughly the same, then can cooperate conic section；If to the trip wish time
Each numerical value that sequence progress logarithm first difference is handled is roughly the same, then can cooperate exponential curve；If to trip wish
Time series carries out first difference, and treated that ring ratio is roughly the same, can cooperate Prediction by Modified Index Curve；If to trip wish
The ring ratio that time series carries out each numerical value obtained after the processing of logarithm first difference is roughly the same, then can cooperate Gang Pazi
(Gompertz) curve；If to the ring ratio for each numerical value that trip wish time series obtain after first difference processing reciprocal
It is roughly the same, then it can match logical (Logistic) curve.It is, of course, also possible to using other processing modes to trip wish
Time series carries out tranquilization processing, and details are not described herein.
The embodiment of the present invention is by obtaining different user to the historical interaction data of the vehicle of current type, and according to respectively going through
History interaction data determines trip wish time series corresponding with current type vehicle；According to trip wish time series fitting
Arma modeling, and predicted according to vehicle flow of the ARAM model to current type vehicle in the following set period of time.It is above-mentioned
Technical solution carries out the fitting of arma modeling by user to the trip wish time series of current type vehicle, so that after fitting
Arma modeling can be from trip wish time series itself, it is contemplated that in trip wish time series between different data
Potential connection, establish the mapping relations between historical data and Future Data, and then the vehicle flow in future time section
When the prediction of amount, precision of prediction and forecasting efficiency are improved, to improve the usage experience of user.
Embodiment two
Fig. 2 is the flow chart of one of embodiment of the present invention two vehicle flow prediction technique, and the embodiment of the present invention is upper
It states and improvement is optimized on the basis of the technical solution of each embodiment.
Further, operation is " corresponding with the current type vehicle out according to each historical interaction data determination
Row wish time series " is refined as " dividing each historical interaction data according to the preset reference cycle, obtaining multiple
With reference to historical interaction data；Count comprehensive interaction time of all users to the current type vehicle in each reference cycle
Number, and statistical result is spliced sequentially in time and generates the trip wish time series " to improve trip wish time sequence
The determination mechanism of column.
A kind of vehicle flow prediction technique as shown in Figure 2, comprising:
S210, user is obtained to the historical interaction data of the vehicle of current type.
S220, each historical interaction data is divided according to the preset reference cycle, is obtained multiple with reference to history
Interaction data.
Illustratively, historical interaction data can be divided according to day, week, the moon or season etc., obtains multiple references and goes through
History interaction data.Wherein, the selection mode in reference cycle can be according to the practical need for the user for having vehicle flow forecast demand
It asks and is determined.Correspondingly, following set period of time when subsequent progress vehicle flow prediction is corresponding with the reference cycle.Example
Such as, when needing to predict the vehicle flow of the following month daily current type vehicle, it can will be set as day in the reference cycle；When
Need to predict following one month weekly the vehicle flow of current type vehicle when, can will be set as week the reference cycle；Work as needs
In prediction following 1 year monthly the vehicle flow of current type vehicle when, can will be set as the moon in the reference cycle；When needing to predict
In 1 year following when the vehicle flow of every season current type vehicle, it can will be set as season in the reference cycle.
S230, in statistics each reference cycle all users to the synthesis interaction times of the current type vehicle, and
Statistical result is spliced sequentially in time and generates the trip wish time series.
Illustratively, counting all users in each reference cycle can be the synthesis interaction times of current type vehicle
One of user is chosen as active user, for different interbehaviors, determines the ginseng of the active user respectively
Examine the corresponding statistic of each interbehavior in historical interaction data；According to the corresponding weight of each interbehavior and statistic, determine
Interaction times of the active user to the current type vehicle in each reference cycle；To own in the reference cycle
The corresponding interaction times adduction of user, obtains the comprehensive interaction times.
Specifically, can determine that the active user is to the current type in each reference cycle using following formula
The interaction times c of vehicle:
Wherein, ajFor the corresponding weight of jth kind interbehavior；cijIt is corresponding for i-th of active user's jth kind interbehavior
Statistic.
Optionally, interbehavior includes search behavior and/or is in single file.Wherein, in single file to can be understood as paying
Successfully lower single act.
It is understood that needing to filter out invalid interbehavior to improve the confidence level of data.Wherein, nothing
Effect interbehavior can be understood as really reflecting user to the consumption wish of current type vehicle or can not really reflect use
The interbehavior of family trip wish.
It, can be in determination if interbehavior includes search behavior in a kind of optional embodiment of the embodiment of the present invention
In the reference historical interaction data of the active user before the corresponding statistic of search behavior, according to the active user
The change on date is recorded during carrying out vehicle search, screening is with reference to effective search behavior in historical interaction data；Phase
It answers, determines the corresponding statistic of effective search behavior in the reference historical interaction data of the active user.
When user carries out vehicle search, there is the case where searching only for browsing, has no actual vehicle and rent demand, therefore
Search behavior at this time can regard as invalid search behavior；When user, which has actual vehicle, rents demand, it will usually choose
Certain time period carries out the search and browsing of information of vehicles, therefore search behavior at this time can regard as effective search behavior.Institute
Can carry out the screening of effective search behavior by date change situation of the user in search process or be searched in vain
Suo Hangwei's filters out.
It, can also be true if user behavior includes lower single act in another optional embodiment of the embodiment of the present invention
Surely before with reference to the corresponding statistic of single act lower in historical interaction data, according to branch of user during carrying out vehicle rental
Record is paid, screening is with reference to effective lower single act in historical interaction data；Correspondingly, determining with reference to effective in historical interaction data
The corresponding statistic of lower single act.Wherein, corresponding lower single act is effectively lower single act when paying successfully, namely in single file
For.
It should be noted that due to each user within each reference cycle it is corresponding go out line frequency and trip radix not
Together, therefore according to the corresponding weight of each interbehavior and statistic, the active user couple in each reference cycle is determined
Before the interaction times of the current type vehicle, it is also necessary to the described of the active user be referred to historical interaction data respectively
In the corresponding statistic of each interbehavior be normalized, to update corresponding statistic of each reference cycle.
Optionally, historical interaction data can be referred to using deviation standardization is corresponding to every kind of interbehavior of each user
It is normalized；Or it is optional, it can also be standardized using mean value to the corresponding ginseng of every kind of interbehavior of each user
Historical interaction data is examined to be normalized
Illustratively, for a kind of interbehavior of each user, can using following at least one normalization modes into
Row deviation standardization, which may is that, obtains the corresponding each maximum value with reference in historical interaction data of current interbehavior and most
Small value；It is corresponding each with reference to historical interaction data for current interbehavior, determine this with reference to historical interaction data and minimum
The floating difference of value, and determine the ratio of the difference between floating difference and maximum value and minimum value, using determining ratio as
The reference historical interaction data obtained after normalized.It is handed over alternatively, available current interbehavior is corresponding with reference to history
Maximum value, minimum value and average value in mutual data；It is corresponding each with reference to historical interaction data for current interbehavior, really
Fixed this refers to the floating difference of historical interaction data and average value, and determines the difference between floating difference and maximum value and minimum value
The ratio of value, using determining ratio as the reference historical interaction data obtained after normalized.
Specifically, being updated to each with reference to the corresponding statistic of interbehavior each in historical interaction data, can use
Following formula is realized:
Wherein, x is the corresponding any statistical value with reference to historical interaction data of current interbehavior；X' is to obtain after normalizing
To the updated statistical value with reference to historical interaction data；xminAnd xmaxFor the minimum with reference to each statistical value in historical interaction data
Value and maximum value.
Alternatively, being updated to each with reference to the corresponding statistic of interbehavior each in historical interaction data, can also use
Following formula is realized:
Wherein, x is the corresponding any statistical value with reference to historical interaction data of current interbehavior；X' is to obtain after normalizing
To the updated statistical value with reference to historical interaction data；xminAnd xmaxFor the minimum with reference to each statistical value in historical interaction data
Value and maximum value；μ is the average value with reference to statistical value each in historical interaction data.
Illustratively, for a kind of interbehavior of each user, can using following at least one normalization modes into
Row mean value standardization, which may is that, can also obtain the corresponding mean value of the corresponding reference historical interaction data of current interbehavior
And standard deviation；For current interbehavior it is corresponding it is each refer to historical interaction data, determine this with reference to historical interaction data with
The floating difference of mean value, and determine the ratio of floating difference and standard deviation, using determining ratio as being obtained after normalized
Reference historical interaction data.
Specifically, being updated to each with reference to the corresponding statistic of interbehavior each in historical interaction data, can also adopt
It is realized with following formula:
Wherein, x is the corresponding any statistical value with reference to historical interaction data of current interbehavior；X' is to obtain after normalizing
To the updated statistical value with reference to historical interaction data；μ is the mean value with reference to statistical value each in historical interaction data；σ is ginseng
Examine the standard deviation of each statistical value in historical interaction data.
S240, arma modeling is fitted according to the trip wish time series, and future is set according to the arma modeling
The vehicle flow of the current type vehicle is predicted in section of fixing time.
The embodiment of the present invention will be by that will determine trip wish corresponding with current type vehicle according to each historical interaction data
Time series is refined as dividing each historical interaction data according to the preset reference cycle, obtains multiple with reference to history friendship
Mutual data；All users in each reference cycle are counted to the synthesis interaction times of current type vehicle, and by statistical result according to
Time sequencing splicing generates trip wish time series, and the determination mechanism of perfect trip wish time series passes through different ginsengs
Period corresponding division and statistics with reference to historical interaction data is examined, is established between user mutual behavior on time dimension
Incidence relation and hiding cycle information, and then improve to precision of prediction when vehicle flow is predicted in future time section
And forecasting efficiency.
Embodiment three
Fig. 3 A is the flow chart of one of embodiment of the present invention three vehicle flow prediction technique, and the embodiment of the present invention is upper
It states and improvement is optimized on the basis of the technical solution of each embodiment, and combine model integrated stand composition shown in Fig. 3 B, into
Row exemplary illustration
Referring to a kind of vehicle flow prediction technique shown in Fig. 3 A, comprising:
S301, the different user search log of user and at odd-numbered day will whithin a period of time is obtained.
S302, the search log that user does not change search date is deleted, to be updated to search log.
S303, the reference search frequency for counting day part according to the reference cycle is set and reference are at single-frequency number.
S304, place is normalized at single-frequency number in the corresponding reference search frequency of different time sections and reference in each user
Reason, obtains searching statistical amount and at single statistic.
It is normalized specifically, searching for frequency or reference to reference according to the following formula at single-frequency number:
Wherein, x is with reference to search frequency or with reference at single-frequency number；X' is the searching statistical amount obtained after normalizing or Cheng Dan
Statistic；xminAnd xmaxFrequency is searched for or with reference at the corresponding minimum value of single-frequency number and maximum for the reference in each reference cycle
Value.
For example, when the reference cycle is the moon, xminAnd xmaxFrequency is searched for for reference monthly or with reference in single-frequency number
Minimum value and maximum value.
S305, for each user to the searching statistical amount of day part and at single statistic, form the corresponding trip of user and anticipate
It is willing to statistic.
Specifically, certain period goes on a journey, wish statistic=T* searching statistical amount+(1-T) * is at single statistic.
Wherein, T is weight.
The corresponding trip wish statistic of user of [period, vehicle, wish statistic of going on a journey] is ultimately formed, convenient for subsequent
Statistical operation.Wherein, the period is specially the section period.
S306, each user trip wish statistic corresponding to day part is obtained each by vehicle progress aggregation operator
The corresponding trip wish statistic of vehicle.
For details, reference can be made to Fig. 3 C, [the period 1: user volume 1 is ultimately formed；Period 2: user volume 2；…；Period N: user volume N]
The corresponding trip wish statistic of vehicle.
S307, according to forecast demand, retrodict the corresponding trip wish statistic of vehicle in several continuous whole periods, structure
Build vehicle time series.
Wherein, the corresponding vehicle time series of different automobile types is different.Subsequent different automobile types carry out arma modeling fitting respectively.
Fig. 3 D is exemplary to give a kind of vehicle corresponding vehicle time sequence within this period of in April, 2018 in December, 2018
Column.Wherein, abscissa is the month in April, 2018 in December, 2018；Ordinate indicates actual vehicle flow, unit.
S308, the stationarity for judging different automobile types time series, and jiggly vehicle time series is carried out at difference
Reason, obtains stable vehicle time series.
The auto-correlation coefficient distribution and PARCOR coefficients distribution for calculating each vehicle time series, if auto-correlation coefficient is distributed
It is truncation or hangover with PARCOR coefficients distribution, it is determined that vehicle time series is stationary sequence, is otherwise unstable sequence
Column.
If roughly the same to each numerical value obtained after the progress first difference processing of vehicle time series, straight line can be cooperated
Trend；If roughly the same to each numerical value obtained after the progress second order difference processing of vehicle time series, secondary song can be cooperated
Line；It, can be bent with hop index if each numerical value handled vehicle time series progress logarithm first difference is roughly the same
Line；If carrying out first difference to vehicle time series, treated that ring ratio is roughly the same, Prediction by Modified Index Curve can be cooperated；If
It is roughly the same to the ring ratio of each numerical value obtained after the progress logarithm first difference processing of vehicle time series, then it can cooperate ridge
Pa Zi (Gompertz) curve；If to the ring ratio for each numerical value that vehicle time series obtain after first difference processing reciprocal
It is roughly the same, then it can match logical (Logistic) curve.
The vehicle time series as shown in Fig. 3 D is non-stationary series, after carrying out difference processing to it, obtains Fig. 3 E
Shown in vehicle time series.Wherein, abscissa is the month in April, 2018 in December, 2018；Ordinate indicates difference vehicle
Flow, unit.
S309, the corresponding vehicle time series of each vehicle is fitted respectively, obtains arma modeling.
Fitting obtains arma modeling can be realized using following steps:
1) the auto-correlation coefficient distribution and the distribution of partial autocorrelation number of words for calculating vehicle time series, determine order.
If auto-correlation coefficient is hangover, PARCOR coefficients are the truncation of p rank, then use AR (p) model:
If auto-correlation coefficient is the truncation of q rank, PARCOR coefficients are hangover, then use MA (q) model:
If auto-correlation coefficient is hangover, PARCOR coefficients are hangover, then use ARMA (p, q) model:
Wherein, p, q choose distribution downward trend and convert most apparent order, and model order is user to same kind vehicle
The parametrization for generating interbehavior correlation indicates, to a certain extent for the regularity of user behavior and to following influence
Have well and modeling acts on.Wherein, xtFor the vehicle time sequence of day part, for the value for predicting vehicle time sequence；φiFor
The parameter of AR department pattern, to the incidence relation between p value before being fitted；μtFor the white noise item of various time points, use
The parameter θ of MA department patternjTo be fitted.
Fig. 3 F and Fig. 3 G are that the corresponding auto-correlation coefficient of vehicle time series after calm disposing is distributed and partial autocorrelation system
Number distribution.
2) according to setting rule, the reference value of computation model selects the smallest model of reference value.
Setting rule includes AIC (akaike information criterion, red pond information criterion), BIC
(bayesian information criterion, bayesian information criterion) and HQIC (Hannan-Quinn
At least one of information criterion is celebrated in information criterion, Chinese south).
Wherein, different rules correspond to reference value calculation it is as follows:
AIC=-2ln (L)+2k；
BIC=-2ln (L)+ln (n) * k；
HQIC=-2ln (L)+ln (ln (n)) * k；
Wherein, L is the maximum likelihood number of model, and n is data bulk, and k is the variable number of model.
3) parameter Estimation and adaptive test are carried out using the model of selection.
S310, the vehicle time series for predicting the following complete cycle, obtain the corresponding vehicle flow of each vehicle.
By counting the peak period corresponding vehicle time series of each vehicle prediction, the traffic trends of vehicle are estimated.
Referring to actual vehicle model time series shown in the corresponding difference vehicle time series of Fig. 3 H and Fig. 3 I, schematically provide
In January, 2019 corresponding vehicle flow prediction result.Wherein, abscissa is the month in April, 2018 in January, 2019；It is vertical
The difference vehicle flow and actual vehicle flow of coordinate representation prediction, unit.
Example IV
Fig. 4 is the structure chart of one of embodiment of the present invention four vehicle flow prediction meanss, and the embodiment of the present invention is applicable in
In in shared platform of hiring a car, the flow of different types of vehicle corresponding to different time sections in advance is predicted the case where.
The device is by software and or hardware realization, and concrete configuration is in the electronic equipment for having certain data operation ability, wherein
Electronic equipment can be server or PC.
A kind of vehicle flow prediction meanss as shown in Figure 4, comprising: time series determining module 410 and vehicle flow
Prediction module 420.
Wherein, time series determining module 410, for obtaining different user to the history interaction number of the vehicle of current type
According to, and trip wish time series corresponding with the current type vehicle is determined according to each historical interaction data；
Vehicle flow prediction module 420, for being fitted autoregressive moving average according to the trip wish time series
Arma modeling, and carried out in advance according to vehicle flow of the arma modeling to current type vehicle described in the following set period of time
It surveys.
The embodiment of the present invention obtains different user by time series determining module and hands over the history of the vehicle of current type
Mutual data, and trip wish time series corresponding with current type vehicle is determined according to each historical interaction data；Pass through vehicle
Volume forecasting module is fitted arma modeling according to trip wish time series, and according to ARAM model in the following set period of time
The vehicle flow of current type vehicle is predicted.When above-mentioned technical proposal passes through trip wish of the user to current type vehicle
Between sequence carry out arma modeling fitting, enable fitting after arma modeling from trip wish time series,
In view of the potential connection in trip wish time series between different data, establish between historical data and Future Data
Mapping relations, and then precision of prediction and forecasting efficiency are improved when the prediction of vehicle flow in future time section, to mention
The usage experience of user is risen.
Further, time series determining module 410, including time series determination unit, for according to each history
Interaction data determines trip wish time series corresponding with the current type vehicle；
Correspondingly, time series determination unit, specifically includes:
Reference cycle divides subelement, for being drawn each historical interaction data according to the preset reference cycle
Point, it obtains multiple with reference to historical interaction data；
Interaction times count subelement, for counting in each reference cycle all users to the current type vehicle
Synthesis interaction times, and statistical result is spliced sequentially in time and generates the trip wish time series.
Further, interaction times count subelement, and all users are to institute in each reference cycle is completely counted in execution
The synthesis interaction times for stating current type vehicle, are specifically used for:
One of user is chosen as active user, for different interbehaviors, determines the active user respectively
It is described with reference to the corresponding statistic of interbehavior each in historical interaction data；
According to the corresponding weight of each interbehavior and statistic, determine that the active user is to institute in each reference cycle
State the interaction times of current type vehicle；
By the corresponding interaction times adduction of users all in the reference cycle, the comprehensive interaction times are obtained.
Further, the interbehavior includes search behavior and/or is in single file.
Further, if the interbehavior includes search behavior, interaction times count subelement and work as described in the determination
In the reference historical interaction data of preceding user before the corresponding statistic of search behavior, it is also used to:
The change on date is recorded during carrying out vehicle search according to the active user, is screened described with reference to history
Effective search behavior in interaction data；
Correspondingly, interaction times, which count subelement, is executing the described with reference to historical interaction data of the determining active user
When the corresponding statistic of middle search behavior, it is specifically used for:
Determine that the active user's is described with reference to the corresponding statistic of effective search behavior in historical interaction data.
Further, interaction times count subelement, according to the corresponding weight of each interbehavior and statistic, determine each
Before the active user is to the interaction times of the current type vehicle in the reference cycle, it is also used to:
The described of the active user is carried out with reference to the corresponding statistic of interbehavior each in historical interaction data respectively
Normalized, to update corresponding statistic of each reference cycle.
Further, which further includes tranquilization processing module, is specifically included:
Steady type determining units, for being fitted autoregressive moving average ARMA according to the trip wish time series
Before model, the steady type of the trip wish time series is determined, and when the steady type is unstable to described
Wish time series of going on a journey carries out tranquilization processing；
Correspondingly, vehicle flow prediction module 420, sliding according to trip wish time series fitting autoregression executing
When dynamic average arma modeling, it is specifically used for:
Autoregressive moving average arma modeling is fitted according to the trip wish time series after smoothing techniques.
Further, which further includes that scheduler module is used for:
According to the corresponding vehicle flow prediction result of different type vehicle, vehicle scheduling is carried out to all types of vehicles.
Vehicle flow prediction technique provided by any embodiment of the invention can be performed in above-mentioned vehicle flow prediction meanss, tool
It is standby to execute the corresponding functional module of vehicle flow prediction technique and beneficial effect.
Embodiment five
Fig. 5 is the structure chart of one of the embodiment of the present invention five electronic equipment.The electronic equipment can be server.Such as
Electronic equipment shown in fig. 5, comprising: input unit 510, processor 520 and storage device 530.
Wherein, input unit 510, for obtaining user to the historical interaction data of the vehicle of current type；
One or more processors 520；
Storage device 530, for storing one or more programs.
In Fig. 5 by taking a processor 520 as an example, input unit 510 in the electronic equipment can by bus or other
Mode is connected with, processor 520 and storage device 530, and processor 520 and storage device 530 also by bus or other
Mode connects, in Fig. 5 for being connected by bus.
In the present embodiment, the processor 520 in electronic equipment can control input unit 510 and obtain different user to working as
The historical interaction data of the vehicle of preceding type；It can also and the current type vehicle determining according to each historical interaction data
Corresponding trip wish time series；Autoregressive moving average ARMA mould can also be fitted according to the trip wish time series
Type；It can also be carried out according to vehicle flow of the arma modeling to current type vehicle described in the following set period of time pre-
It surveys.
Storage device 530 in the electronic equipment is used as a kind of computer readable storage medium, can be used for storing one or
Multiple programs, described program can be software program, computer executable program and module, such as vehicle in the embodiment of the present invention
Corresponding program instruction/the module of method for predicting is (for example, attached time series determining module 410 shown in Fig. 4 and vehicle flow
Measure prediction module 420).Software program, instruction and the module that processor 520 is stored in storage device 530 by operation, from
And execute the various function application and data processing of electronic equipment, i.e. vehicle flow prediction in realization above method embodiment
Method.
Storage device 530 may include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function；It storage data area can (the history interaction in such as above-described embodiment such as storing data
Data, trip wish time series, arma modeling and vehicle flow etc.).In addition, storage device 530 may include high speed with
Machine access memory, can also include nonvolatile memory, a for example, at least disk memory, flush memory device or its
His non-volatile solid state memory part.In some instances, storage device 530 can further comprise remote relative to processor 520
The memory of journey setting, these remote memories can pass through network connection to server.The example of above-mentioned network includes but not
It is limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Embodiment six
The embodiment of the present invention six also provides a kind of computer readable storage medium, is stored thereon with computer program, the journey
Realize that the present invention implements a kind of vehicle flow prediction technique provided when sequence is executed by vehicle flow prediction meanss, comprising: obtain
Different user to the historical interaction data of the vehicle of current type, and according to each historical interaction data it is determining with it is described current
The corresponding trip wish time series of type of vehicle；Autoregressive moving average ARMA is fitted according to the trip wish time series
Model, and predicted according to vehicle flow of the arma modeling to current type vehicle described in the following set period of time.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) executes method described in each embodiment of the present invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of vehicle flow prediction technique characterized by comprising
Different user is obtained to the historical interaction data of the vehicle of current type, and according to each historical interaction data determine with
The corresponding trip wish time series of the current type vehicle；
It is fitted autoregressive moving average arma modeling according to the trip wish time series, and according to the arma modeling to not
The vehicle flow for carrying out the current type vehicle in set period of time is predicted.
2. the method according to claim 1, wherein determining and described current according to each historical interaction data
The corresponding trip wish time series of type of vehicle, comprising:
Each historical interaction data is divided according to the preset reference cycle, is obtained multiple with reference to historical interaction data；
All users in each reference cycle are counted to the synthesis interaction times of the current type vehicle, and by statistical result
Splicing generates the trip wish time series sequentially in time.
3. according to the method described in claim 2, all users are to the current type in statistics each reference cycle
The synthesis interaction times of vehicle, comprising:
One of user is chosen as active user, for different interbehaviors, determines the institute of the active user respectively
It states with reference to the corresponding statistic of interbehavior each in historical interaction data；
According to the corresponding weight of each interbehavior and statistic, determine that the active user works as to described in each reference cycle
The interaction times of preceding type of vehicle；
By the corresponding interaction times adduction of users all in the reference cycle, the comprehensive interaction times are obtained.
4. according to the method described in claim 3, it is characterized in that, the interbehavior includes search behavior and/or in single file
For.
5. according to the method described in claim 4, it is characterized in that, if the interbehavior includes search behavior, in determination
In the reference historical interaction data of the active user before the corresponding statistic of search behavior, further includes:
The change on date is recorded during carrying out vehicle search according to the active user, is screened described with reference to history interaction
Effective search behavior in data；
Correspondingly, determining that the active user's is described with reference to the corresponding statistic of search behavior in historical interaction data, comprising:
Determine that the active user's is described with reference to the corresponding statistic of effective search behavior in historical interaction data.
6. according to the method described in claim 3, it is characterized in that, according to the corresponding weight of each interbehavior and statistic,
Before determining that the active user is to the interaction times of the current type vehicle in each reference cycle, further includes:
The described of the active user is subjected to normalizing with reference to the corresponding statistic of interbehavior each in historical interaction data respectively
Change processing, to update corresponding statistic of each reference cycle.
7. method according to claim 1-6, which is characterized in that quasi- according to the trip wish time series
Before conjunction autoregressive moving average arma modeling, further includes:
It determines the steady type of the trip wish time series, and anticipates when the steady type is unstable to the trip
It is willing to that time series carries out tranquilization processing；
Correspondingly, being fitted autoregressive moving average arma modeling according to the trip wish time series, comprising:
Autoregressive moving average arma modeling is fitted according to the trip wish time series after smoothing techniques.
8. a kind of vehicle flow prediction meanss characterized by comprising
Time series determining module is gone through for obtaining user to the historical interaction data of the vehicle of current type, and according to described
History interaction data determines trip wish time series corresponding with the current type vehicle；
Vehicle flow prediction module, for being fitted autoregressive moving average arma modeling according to the trip wish time series,
And it is predicted according to vehicle flow of the arma modeling to current type vehicle described in the following set period of time.
9. a kind of electronic equipment characterized by comprising
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as a kind of described in any item vehicle flow prediction techniques of claim 1-7.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
A kind of such as claim 1-7 described in any item vehicle flow prediction techniques are realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910765989.8A CN110491124B (en) | 2019-08-19 | 2019-08-19 | Vehicle flow prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910765989.8A CN110491124B (en) | 2019-08-19 | 2019-08-19 | Vehicle flow prediction method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110491124A true CN110491124A (en) | 2019-11-22 |
| CN110491124B CN110491124B (en) | 2020-09-08 |
Family
ID=68552039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910765989.8A Active CN110491124B (en) | 2019-08-19 | 2019-08-19 | Vehicle flow prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110491124B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145537A (en) * | 2019-12-02 | 2020-05-12 | 东南大学 | Travel generation amount prediction method and system |
| CN111626589A (en) * | 2020-05-21 | 2020-09-04 | 北京骑胜科技有限公司 | Siltation area determination method and device and vehicle scheduling method and device |
| CN111966897A (en) * | 2020-08-07 | 2020-11-20 | 上海新共赢信息科技有限公司 | Travel willingness sensing method and device, terminal and storage medium |
| CN112465546A (en) * | 2020-11-26 | 2021-03-09 | 中诚信征信有限公司 | User identification method, device and equipment |
| CN114283590A (en) * | 2021-09-02 | 2022-04-05 | 青岛海信网络科技股份有限公司 | Traffic flow peak prediction method and device and electronic equipment |
| CN116502019A (en) * | 2023-04-27 | 2023-07-28 | 广东花至美容科技有限公司 | Skin collagen protein lifting rate calculation method, storage medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170372235A1 (en) * | 2016-06-28 | 2017-12-28 | International Business Machines Corporation | Dynamic Transportation Pooling |
| CN108536652A (en) * | 2018-03-15 | 2018-09-14 | 浙江大学 | A kind of short-term vehicle usage amount prediction technique based on arma modeling |
| CN108960590A (en) * | 2018-06-15 | 2018-12-07 | 平安科技（深圳）有限公司 | Vehicle leasing method, apparatus, computer equipment and storage medium |
| CN109829649A (en) * | 2019-01-31 | 2019-05-31 | 北京首汽智行科技有限公司 | A kind of vehicle dispatching method |
| CN110046788A (en) * | 2019-01-17 | 2019-07-23 | 阿里巴巴集团控股有限公司 | Vehicle Demand Forecast method and device, vehicle supply amount prediction technique and device |
-
2019
- 2019-08-19 CN CN201910765989.8A patent/CN110491124B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170372235A1 (en) * | 2016-06-28 | 2017-12-28 | International Business Machines Corporation | Dynamic Transportation Pooling |
| CN108536652A (en) * | 2018-03-15 | 2018-09-14 | 浙江大学 | A kind of short-term vehicle usage amount prediction technique based on arma modeling |
| CN108960590A (en) * | 2018-06-15 | 2018-12-07 | 平安科技（深圳）有限公司 | Vehicle leasing method, apparatus, computer equipment and storage medium |
| CN110046788A (en) * | 2019-01-17 | 2019-07-23 | 阿里巴巴集团控股有限公司 | Vehicle Demand Forecast method and device, vehicle supply amount prediction technique and device |
| CN109829649A (en) * | 2019-01-31 | 2019-05-31 | 北京首汽智行科技有限公司 | A kind of vehicle dispatching method |
Non-Patent Citations (1)
| Title |
|---|
| 罗利: "基于粒子群算法的汽车租赁短期车辆配置问题研究", 《运筹与管理》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145537A (en) * | 2019-12-02 | 2020-05-12 | 东南大学 | Travel generation amount prediction method and system |
| CN111145537B (en) * | 2019-12-02 | 2021-06-15 | 东南大学 | Travel generation amount prediction method and system |
| CN111626589A (en) * | 2020-05-21 | 2020-09-04 | 北京骑胜科技有限公司 | Siltation area determination method and device and vehicle scheduling method and device |
| CN111966897A (en) * | 2020-08-07 | 2020-11-20 | 上海新共赢信息科技有限公司 | Travel willingness sensing method and device, terminal and storage medium |
| CN111966897B (en) * | 2020-08-07 | 2023-07-21 | 凹凸乐享(苏州)信息科技有限公司 | Method, device, terminal and storage medium for sensing travel willingness |
| CN112465546A (en) * | 2020-11-26 | 2021-03-09 | 中诚信征信有限公司 | User identification method, device and equipment |
| CN112465546B (en) * | 2020-11-26 | 2024-04-19 | 中诚信征信有限公司 | User identification method, device and equipment |
| CN114283590A (en) * | 2021-09-02 | 2022-04-05 | 青岛海信网络科技股份有限公司 | Traffic flow peak prediction method and device and electronic equipment |
| CN114283590B (en) * | 2021-09-02 | 2023-03-21 | 青岛海信网络科技股份有限公司 | Traffic flow peak prediction method and device and electronic equipment |
| CN116502019A (en) * | 2023-04-27 | 2023-07-28 | 广东花至美容科技有限公司 | Skin collagen protein lifting rate calculation method, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110491124B (en) | 2020-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110491124A (en) | A kind of vehicle flow prediction technique, device, equipment and storage medium | |
| CN110163474A (en) | A kind of method and apparatus of task distribution | |
| CN109974735B (en) | Arrival time estimation method and device and computer equipment | |
| Kliewer et al. | Multiple depot vehicle and crew scheduling with time windows for scheduled trips | |
| US20180107987A1 (en) | Meeting service with meeting time and location optimization | |
| EP4290824A1 (en) | Task allocation method and apparatus based on internet-of-things device, and network training method and apparatus | |
| CN106209967B (en) | A kind of video monitoring cloud resource prediction technique and system | |
| CN113254840B (en) | Artificial intelligence application service pushing method, pushing platform and terminal equipment | |
| US20130268941A1 (en) | Determining an allocation of resources to assign to jobs of a program | |
| CN110444008B (en) | Vehicle scheduling method and device | |
| CN111832869A (en) | Vehicle scheduling method and device, electronic equipment and storage medium | |
| Park et al. | Investigating a machine breakdown genetic programming approach for dynamic job shop scheduling | |
| CN105491079B (en) | The method and device of the required resource of adjustment application in cloud computing environment | |
| CN110262863A (en) | A kind of methods of exhibiting and device of terminal main interface | |
| JPH10228463A (en) | Demand prediction model evaluating method | |
| CN108449411A (en) | Cloud resource dispatching method towards heterogeneous expense under a kind of stochastic demand | |
| CN114841451A (en) | Driver travel subsidy method and device and storage medium | |
| Zhao et al. | Reverse-auction-based competitive order assignment for mobile taxi-hailing systems | |
| CN113298120A (en) | User risk prediction method and system based on fusion model and computer equipment | |
| Yadav et al. | Workload prediction for cloud resource provisioning using time series data | |
| Guo et al. | Exploration on the optimal application of Mobile cloud computing in Enterprise financial management under 5G network architecture | |
| CN109684549A (en) | Target data prediction method and device, electronic equipment and computer storage medium | |
| Wang et al. | A service composition approach for the fulfillment of temporally sequential requirements | |
| Na et al. | An adaptive replanning mechanism for dependable service-based systems | |
| US11922310B1 (en) | Forecasting activity in software applications using machine learning models and multidimensional time-series data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 587, building 3, 333 Hongqiao Road, Xuhui District, Shanghai 200030 Patentee after: Shanghai Lexiang Sijin Technology Co.,Ltd. Address before: Room 587, building 3, 333 Hongqiao Road, Xuhui District, Shanghai 200030 Patentee before: Shanghai xinwin Information Technology Co.,Ltd. |