CN112949886A - Traffic prediction method, traffic prediction device, electronic device, and storage medium - Google Patents
Traffic prediction method, traffic prediction device, electronic device, and storage medium Download PDFInfo
- Publication number
- CN112949886A CN112949886A CN201911267341.4A CN201911267341A CN112949886A CN 112949886 A CN112949886 A CN 112949886A CN 201911267341 A CN201911267341 A CN 201911267341A CN 112949886 A CN112949886 A CN 112949886A
- Authority
- CN
- China
- Prior art keywords
- traffic
- target
- holiday
- sequence
- time period
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000002354 daily effect Effects 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 230000003203 everyday effect Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 13
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013145 classification model Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000000638 stimulation Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- GVVPGTZRZFNKDS-JXMROGBWSA-N geranyl diphosphate Chemical compound CC(C)=CCC\C(C)=C\CO[P@](O)(=O)OP(O)(O)=O GVVPGTZRZFNKDS-JXMROGBWSA-N 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a traffic prediction method, a traffic prediction device, electronic equipment and a storage medium. The traffic prediction method comprises the following steps: determining a target area and a target holiday of traffic to be predicted; acquiring historical traffic of a target area on a target holiday; calculating a traffic difference value proportional sequence of a target holiday according to the historical traffic; and predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence. The embodiment of the application realizes the prediction of the traffic by calculating the traffic difference ratio sequence of the target area on the target holiday, and the process predicts the traffic for the difference ratio data of a certain holiday of a certain area.
Description
Technical Field
The present application relates to the field of logistics technologies, and in particular, to a traffic prediction method, an apparatus, an electronic device, and a storage medium.
Background
With the continuous deepening of the information management reform of the logistics industry. Facing mass data of the logistics industry, information management of the logistics industry faces how to effectively extract useful information from a large amount of complex data. Data mining techniques can extract useful information from large, fuzzy data that is implicit in the data to analyze and predict future developments.
In the field of logistics, holiday and festival piece quantity prediction is a pending problem of the express delivery industry. The existing time sequence model and analysis method can achieve relatively accurate estimation of weekday quantities, but cannot estimate the quantity mutation amplitude and rhythm during holidays. The sudden change of the holiday data amount can be influenced by many factors, but the data amount which can be generally mastered as a predictor is quite limited, after all, the data amount of holidays is far smaller than that of weekday data, the requirement of a model is difficult to support, and the relevance of the data and the final mutation result is difficult to predict. The clustering method is an idea for increasing available samples of the model, but at present, a clustering method aiming at festival and city characteristics is lacked in the industry, and the consumption habits of a city in festival and holiday cannot be classified through simple component composition.
In conclusion, the component prediction in the prior art has limitations, which results in inaccurate component prediction.
Disclosure of Invention
The embodiment of the application provides a traffic prediction method and device, electronic equipment and a storage medium, so that traffic prediction is closer to an actual scene, and the accuracy of the traffic prediction is improved.
In one aspect, the present application provides a traffic prediction method, including:
determining a target area and a target holiday of traffic to be predicted;
acquiring historical traffic of the target area on the target holiday;
calculating a traffic difference value proportional sequence of the target holidays according to the historical traffic;
and predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence.
In some embodiments of the present application, the calculating a traffic difference value proportional sequence of the target holiday according to the historical traffic includes:
determining a festival observation time period and a peacetime observation time period corresponding to the target festival and holiday;
acquiring the historical traffic of the target area in the holiday observation time period each day from the historical traffic;
acquiring historical traffic of the target area in the daily observation time period at ordinary times from the historical traffic;
and calculating the traffic difference value proportional sequence of the target holiday according to the daily historical traffic in the holiday observation time period and the daily historical traffic in the ordinary observation time period.
In some embodiments of the present application, the determining a holiday observation time period and a peacetime observation time period corresponding to the target holiday includes:
filling the target holidays with a first preset number of days forward and a second preset number of days backward respectively to enable the total number of days to reach the target number of days, and obtaining holiday observation time periods corresponding to the target holidays;
and taking the first third preset number of days of each day in the festival observation time period to obtain the ordinary observation time period with the same time length as the festival observation time period.
In some embodiments of the present application, the calculating a traffic difference value proportional sequence of the target holiday according to the historical traffic of each day in the holiday observation time period and the historical traffic of each day in the ordinary observation time period includes:
generating a first traffic sequence according to the historical traffic of each day in the holiday observation time period;
generating a second traffic sequence according to the daily historical traffic of the ordinary observation time period;
calculating a single-day difference value proportion sequence corresponding to the target holiday according to the first traffic sequence and the second traffic sequence;
and calculating the traffic difference ratio sequence of the target holidays according to the single-day difference ratio sequence.
In some embodiments of the present application, the calculating a traffic difference ratio sequence of the target holiday according to the single-day difference ratio sequence includes:
acquiring a first total historical traffic volume in the festival observation time period;
acquiring a second total historical traffic of the ordinary observation time period;
calculating the total difference ratio corresponding to the target holiday according to the first total historical traffic and the second total historical traffic;
and calculating the traffic difference ratio sequence of the target holiday according to the single-day difference ratio sequence and the total difference ratio.
In some embodiments of the present application, the predicting traffic of the target area on the target holiday according to the traffic difference value ratio sequence includes:
determining a target traffic prediction model for predicting the traffic of the target area on the target holiday according to the target area and the target holiday;
and inputting the traffic difference value proportion sequence into the target traffic prediction model to predict the traffic of the target area on the target holiday.
In some embodiments of the present application, before determining the target traffic prediction model predicting the traffic of the target area on the target holiday according to the target area and the target holiday, the method further includes:
performing holiday clustering on all holidays to divide the holidays into a plurality of holiday classifications;
performing region clustering on a region to be planned so as to divide each region in the region to be planned into a plurality of region classifications, wherein the region to be planned comprises the target region;
forming a plurality of holiday and city classifications according to the plurality of holiday classifications and the plurality of region classifications;
collecting historical traffic data of the plurality of holidays and city classifications;
and training a preset model based on the historical traffic data of the classification of the plurality of holiday cities to obtain a traffic prediction model of the plurality of holiday cities.
In another aspect, the present application provides a traffic prediction apparatus, including:
the determining unit is used for determining a target area and a target holiday of the traffic to be predicted;
the acquisition unit is used for acquiring the historical traffic of the target area on the target holiday;
the calculating unit is used for calculating a traffic difference value proportion sequence of the target holiday according to the historical traffic;
and the prediction unit is used for predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence.
In some embodiments of the present application, the computing unit is specifically configured to:
determining a festival observation time period and a peacetime observation time period corresponding to the target festival and holiday;
acquiring the historical traffic of the target area in the holiday observation time period each day from the historical traffic;
acquiring historical traffic of the target area in the daily observation time period at ordinary times from the historical traffic;
and calculating the traffic difference value proportional sequence of the target holiday according to the daily historical traffic in the holiday observation time period and the daily historical traffic in the ordinary observation time period.
In some embodiments of the present application, the computing unit is specifically configured to:
filling the target holidays with a first preset number of days forward and a second preset number of days backward respectively to enable the total number of days to reach the target number of days, and obtaining holiday observation time periods corresponding to the target holidays;
and taking the first third preset number of days of each day in the festival observation time period to obtain the ordinary observation time period with the same time length as the festival observation time period.
In some embodiments of the present application, the computing unit is specifically configured to:
generating a first traffic sequence according to the historical traffic of each day in the holiday observation time period;
generating a second traffic sequence according to the daily historical traffic of the ordinary observation time period;
calculating a single-day difference value proportion sequence corresponding to the target holiday according to the first traffic sequence and the second traffic sequence;
and calculating the traffic difference ratio sequence of the target holidays according to the single-day difference ratio sequence.
In some embodiments of the present application, the computing unit is specifically configured to:
acquiring a first total historical traffic volume in the festival observation time period;
acquiring a second total historical traffic of the ordinary observation time period;
calculating the total difference ratio corresponding to the target holiday according to the first total historical traffic and the second total historical traffic;
and calculating the traffic difference ratio sequence of the target holiday according to the single-day difference ratio sequence and the total difference ratio.
In some embodiments of the present application, the prediction unit is specifically configured to:
determining a target traffic prediction model for predicting the traffic of the target area on the target holiday according to the target area and the target holiday;
and inputting the traffic difference value proportion sequence into the target traffic prediction model to predict the traffic of the target area on the target holiday.
In some embodiments of the present application, the apparatus further comprises a training unit, the training unit being configured to:
before determining a target traffic prediction model for predicting the traffic of the target region on the target holiday according to the target region and the target holiday, performing holiday clustering on all holidays so as to divide the holidays into a plurality of holiday classifications;
performing region clustering on a region to be planned so as to divide each region in the region to be planned into a plurality of region classifications, wherein the region to be planned comprises the target region;
forming a plurality of holiday and city classifications according to the plurality of holiday classifications and the plurality of region classifications;
collecting historical traffic data of the plurality of holidays and city classifications;
and training a preset model based on the historical traffic data of the classification of the plurality of holiday cities to obtain a traffic prediction model of the plurality of holiday cities.
In another aspect, the present application further provides an electronic device, including a memory and a processor, where the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to perform the following steps:
determining a target area and a target holiday of traffic to be predicted;
acquiring historical traffic of the target area on the target holiday;
calculating a traffic difference value proportional sequence of the target holidays according to the historical traffic;
and predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence.
In another aspect, the present application further provides a computer readable storage medium, on which a computer program is stored, the computer program being loaded by a processor to execute the steps in the traffic prediction method.
The method comprises the steps of determining a target area and a target holiday of the traffic to be predicted; acquiring historical traffic of the target area on the target holiday; calculating a traffic difference value proportion sequence of the holidays of the target festival according to the historical traffic; and predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence. According to the embodiment of the application, in the prior art, the component prediction is limited due to the fact that the component is classified through simple component composition, the traffic is predicted through calculating the traffic difference value proportion sequence of the target area on the target holiday on the basis of inaccurate component prediction, the process predicts the traffic for the difference value proportion data of a certain holiday of a certain area, and compared with the process of simply observing the component number of each period, the difference value proportion sequence corresponding to each holiday can better draw the consumption habit of an area facing the stimulation of the certain holiday, so that the traffic prediction is closer to the actual scene, and the accuracy of the traffic prediction is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic view of a scenario of a traffic prediction system provided in an embodiment of the present invention;
fig. 2 is a flow chart illustrating an embodiment of a traffic prediction method provided in an embodiment of the present invention;
FIG. 3 is a flowchart illustrating an embodiment of step 203 in an embodiment of the present invention;
fig. 4 is a schematic flow chart of an embodiment of predicting traffic of a target area on the target holiday according to a traffic difference value ratio sequence provided in the embodiment of the present invention;
FIG. 5 is a schematic flow chart of a training process of a traffic prediction model for a plurality of holiday cities according to an embodiment of the present invention;
FIG. 6 is a scene diagram of an embodiment of holiday clustering and city clustering in an embodiment of the invention;
fig. 7 is a schematic structural diagram of an embodiment of a traffic prediction apparatus provided in the embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without inventive exercise, are within the scope of the present invention.
In the description that follows, specific embodiments of the present invention are described with reference to steps and symbols executed by one or more computers, unless otherwise indicated. Accordingly, these steps and operations will be referred to, several times, as being performed by a computer, the computer performing operations involving a processing unit of the computer in electronic signals representing data in a structured form. This operation transforms the data or maintains it at locations in the computer's memory system, which may be reconfigured or otherwise altered in a manner well known to those skilled in the art. The data maintains a data structure that is a physical location of the memory that has particular characteristics defined by the data format. However, while the principles of the invention have been described in the foregoing context, which is not intended to be limiting, those of skill in the art will appreciate that various of the steps and operations described below may also be implemented in hardware.
The term "module" or "unit" as used herein may be considered a software object executing on the computing system. The various components, modules, engines, and services described herein may be viewed as objects implemented on the computing system. While the apparatus and methods described herein are preferably implemented in software, it is certainly within the purview of the present invention to be implemented in hardware.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
The embodiment of the invention provides a traffic prediction method, a traffic prediction device, a server and a storage medium.
Referring to fig. 1, fig. 1 is a schematic view of a scenario of a traffic prediction system according to an embodiment of the present invention, where the traffic prediction system may be implemented based on a service platform, such as a logistics service platform, and the traffic prediction system may include an electronic device 100, and a traffic prediction apparatus is integrated in the electronic device 100.
The electronic device 100 in the embodiment of the present invention is mainly used for determining a target area and a target holiday of a traffic volume to be predicted; acquiring historical traffic of the target area on the target holiday; calculating a traffic difference value proportional sequence of the target holidays according to the historical traffic; and predicting the traffic of the target area on the target holiday according to the traffic difference ratio sequence.
In this embodiment of the present invention, the server may be an independent server, or may be a server network or a server cluster composed of servers, for example, the server described in this embodiment of the present invention includes, but is not limited to, a computer, a network host, a single network server, a plurality of network server sets, or a cloud server composed of a plurality of servers. Among them, the Cloud server is constituted by a large number of computers or web servers based on Cloud Computing (Cloud Computing). In the embodiment of the present invention, the server and the client may implement communication through any communication manner, including but not limited to mobile communication based on the third Generation Partnership Project (3 GPP), Long Term Evolution (LTE), Worldwide Interoperability for Microwave Access (WiMAX), or computer network communication based on the TCP/IP Protocol Suite (TCP/IP), User Datagram Protocol (UDP) Protocol, and the like.
Those skilled in the art will understand that the application environment shown in fig. 1 is only one application scenario related to the present application, and does not constitute a limitation on the application scenario of the present application, and that other application environments may further include more or fewer electronic devices than those shown in fig. 1, for example, only 1 electronic device is shown in fig. 1, and it is understood that the traffic prediction system may further include one or more other services, which are not limited herein.
In addition, as shown in fig. 1, the traffic prediction system may further include a memory 200 for storing data, such as logistics data, for example, various data of the logistics platform, such as logistics transportation information of the transition, specifically, express information, delivery vehicle information, logistics site information, and the like.
It should be noted that the scenario diagram of the traffic prediction system shown in fig. 1 is merely an example, and the traffic prediction system and the scenario described in the embodiment of the present invention are for more clearly illustrating the technical solution of the embodiment of the present invention, and do not form a limitation on the technical solution provided in the embodiment of the present invention.
The following is a detailed description of specific embodiments.
In the present embodiment, description will be made from the perspective of a traffic prediction apparatus, which may be specifically integrated in the electronic device 100.
The invention provides a traffic prediction method, which comprises the following steps: determining a target area and a target holiday of the traffic to be predicted; acquiring the historical traffic of the target area on the target holiday; calculating a traffic difference value proportional sequence of the target holidays according to the historical traffic; and predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence.
Referring to fig. 2, a schematic flow chart of an embodiment of a traffic prediction method according to an embodiment of the present invention is shown, where the traffic prediction method includes:
201. and determining a target area and a target holiday of the traffic to be predicted.
In some embodiments of the present invention, the traffic may be a piece quantity, specifically, an express piece quantity, and it needs to be explained, and in some embodiments of the present invention, the traffic may be further limited to a piece receiving quantity or a piece sending quantity. It is understood that in other embodiments of the present invention, the traffic volume may also be the renting and selling volume of other products, such as the selling volume of a certain target product, specifically, the selling volume of air conditioners with type a in city B, which is not limited herein.
In addition, the target area refers to an area where traffic needs to be predicted, and the target area may be in units of one or more countries or include only one country; the target area may also be one or more provinces in China, or only comprise one province; the target area may also be one or more cities; the target area may also be one or more market-level areas; the target area may also be one or more streets or towns below the urban area, and it is understood that the above-mentioned target area is only an example, and the actual size of the target area may be set according to an actual scene, and is not limited herein.
The target holiday may be a holiday in a certain section of the year, and may be any holiday in any country according to the actual application requirements, for example, the holiday may be the mid-autumn section of china, or easter in the west, and the like, and the specific description is not limited herein.
202. And acquiring the historical traffic of the target area on the target holiday.
Specifically, the historical traffic of the target area on the target holiday may be historical traffic of the target area on preset days before the target holiday, for example, the historical traffic of the previous year, or may be one year, a half year, or two years, or all the stored historical traffic, and specifically, the historical traffic is not limited herein, since the service platform continuously generates service data in the service process, for example, the logistics platform continuously generates the biometric data, and stores the biometric data in a corresponding memory, for example, the memory 200 shown in fig. 1, at this time, the electronic device 100 may directly obtain the historical traffic of the target area on the target holiday from the memory 200.
203. And calculating the traffic difference value proportional sequence of the target holidays according to the historical traffic.
The traffic difference proportion sequence is a sequence generated by calculating traffic difference proportions according to historical traffic of a plurality of preset observation time periods. Specifically, as shown in fig. 3, the calculating a traffic difference value proportional sequence of the target holiday according to the historical traffic may include:
301. and determining a holiday observation time period and a peacetime observation time period corresponding to the target holiday.
Wherein the determining the holiday observation time period and the peacetime observation time period corresponding to the target holiday includes:
(1) and respectively filling the target holiday forward with a first preset number of days and filling the target holiday backward with a second preset number of days to enable the total number of days to reach the target number of days, and obtaining the holiday observation time period corresponding to the target holiday.
Specifically, the target days may be set as required, for example, the target days are 10 days, 14 days or 21 days, and it should be noted that, according to the determination of actual tests, the inventors are easier to calculate when the target days are integer multiples of the number of days per week (7 days), so in the embodiment of the present invention, the target days are integer multiples of the number of days per week (7 days), for example, 14 days.
In the embodiment of the invention, the following requirements are met: the target holiday days + the first preset days + the second preset days are the target days, and the time period corresponding to the target days is the holiday observation time period corresponding to the target holiday.
In one embodiment, assuming the first predetermined number of days is Pf, the second predetermined number of days is Pt, and the target number of days is 14 days, then:
target Holiday (Holiday): h { H1, H2.,. hi.,. H14}
The festival observation time period corresponding to the target festival and holiday is as follows: pf + H + Pt
For example, in mid-autumn holiday of 3 days (9/11-9/13), H is { H1 ═ 9-11, H2 ═ 9-12, and H3 ═ 9-13 }.
Pre-filling (Front Padding) for a first preset number of days: pf
Post-filling (Tail Padding) for a second preset number of days: pt
Pf and Pt days were filled before and after the normal target holiday period H, respectively, so that the total length of the holiday observation period was 14 days (two weeks).
Filling the conditions to be met:
Pf+H+Pt＝14
the time period corresponding to the target holiday should be within the observation time period of 14 days:
pf Floor ((14-H)/2) (rounded down);
pt ═ Cell ((14-H)/2) (rounded up);
for example, mid-autumn holiday is 3 days (9/11-9/13), that Pf ═ Floor ((14-3)/2) ═ 5 days, i.e., 9/6-9/10;
Pt-Cell ((14-3)/2) -6 days, 9/14-9/19.
In a specific application, one holiday is filled forwards, and other holidays can be encountered in the process of filling backwards, and the other holidays can influence the traffic of the target holiday, so that in the process of prediction, the situation needs to be eliminated, and particularly,
if Pf and Pt contain other holidays, then Pf will take days by pushing one week forward for holiday-coincident dates and Pt will take days by pushing one week backward for holiday-coincident dates. For example, in mid-autumn holidays 9/26-9/28, and normal Pt (9/29-10/4) would include national celebrations (10/1-10/7), Pt would normally take 9/29-9/30, and 10/8-10/11 would replace 10/1-10/4 for the coincident date. And finally, the value of Pt is 9/29-9/30+10/8-10/11, so that the aim of eliminating the interference of other festivals as much as possible is fulfilled, and the influence of the target festival on the traffic is better analyzed.
(2) And taking the first third preset number of days of each day in the festival observation time period to obtain the ordinary observation time period with the same time length as the festival observation time period.
In the embodiment of the invention, the third preset number of days can be directly pushed forward every day in the festival observation time period to obtain the ordinary observation time period with the same time length as the festival observation time period, and the ordinary observation time period is the same time length as the festival observation time period, for example, 14 days. The third preset number of days may be set according to the actual scene to avoid holidays as much as possible, and is preferably an integral multiple of the number of days per week (7 days) and not as close as possible, for example, 42 days (6 weeks).
In one embodiment, it is assumed that the Normal observation period (Normal) is also 14 days, specifically: n { N1, N2.,. ni.,. N14}
And after filling of the festival observation time period corresponding to the target festival and holiday is finished, taking the corresponding date 6 weeks ago (42 days ago) of each date to form a normal observation time period, wherein the normal observation time period is 14 days as the festival observation time period.
The method aims to select a set of fluctuation samples of the ordinary traffic for comparison with a target holiday.
Selecting conditions as follows: ni-hi-42
Similarly, if there are festivals in N, it takes 2 weeks further forward (which can be adjusted according to the actual situation, and is preferably an integral multiple of days of the week), i.e., ni is hi-56. If the festival is touched after two weeks in advance, the festival is started again for two weeks, and so on.
In other embodiments of the present invention, in addition to taking the number of days in two weeks, the data of the observation period may be selected to correspond to the average number of days per week in the first half year, i.e., the average number of days in all mondays in the half year, the average number of days in all tuesdays, etc.
302. And acquiring the daily historical traffic of the target area in the holiday observation time period from the historical traffic.
The historical traffic volume includes the daily historical traffic volume of the target area in the holiday observation time period, so that the daily historical traffic volume of the target area in the holiday observation time period can be obtained from the historical traffic volume.
303. And acquiring the historical traffic of the target area in the daily observation time period from the historical traffic.
The historical traffic volume includes the daily historical traffic volume of the target area in the ordinary observation time period, so that the daily historical traffic volume of the target area in the ordinary observation time period can be obtained from the historical traffic volume.
304. And calculating the traffic difference value proportional sequence of the target holiday according to the daily historical traffic in the holiday observation time period and the daily historical traffic in the ordinary observation time period.
Wherein, the calculating the traffic difference value proportional sequence of the target holiday according to the daily historical traffic in the holiday observation time period and the daily historical traffic in the ordinary observation time period comprises: generating a first traffic sequence according to the historical traffic of each day in the holiday observation time period; generating a second traffic sequence according to the daily historical traffic of the ordinary observation time period; calculating a single-day difference value proportion sequence corresponding to the target holiday according to the first traffic sequence and the second traffic sequence; and calculating the traffic difference ratio sequence of the target holidays according to the single-day difference ratio sequence.
In one particular embodiment, the single-day difference ratio series: d { D1, D2.,. di.,. D14}
The formula for each value in D: di (traffic (hi) -traffic (ni))/traffic (ni), i is 1 ≦ 14;
the benefits of using this dimension are as follows:
(1) observe the duration of the effect of holidays on traffic (know how many days ahead the holiday will have an effect on the area and how long the effect lasts by starting with the absolute value of d)
(2) Observing the impact (the impact of the festival on the traffic per time period can be seen by the magnitude of each d value, or the sensitivity of the area to the type of festival)
(3) Observation of the impact type (the impact type for this festival can be seen by the fluctuation of the d value)
Not affected by the amount of traffic (it should be observed that it is proportional, so large traffic may also be grouped with small traffic, as long as the consumption habits of the two regions are similar).
Further, the calculating a traffic difference ratio sequence of the target holiday according to the single-day difference ratio sequence includes: acquiring a first total historical traffic volume in the festival observation time period; acquiring a second total historical traffic of the ordinary observation time period; calculating the total difference ratio corresponding to the target holiday according to the first total historical traffic and the second total historical traffic; and calculating the traffic difference ratio sequence of the target holiday according to the single-day difference ratio sequence and the total difference ratio.
In one embodiment, the calculating of the total difference ratio corresponding to the holiday of the target festival according to the first total historical traffic and the second total historical traffic is as follows:
the ratio of the total amount difference: c
C ═ first total historical traffic-second total historical traffic)/second total historical traffic
The purpose of this dimension is to observe whether this holiday increases/decreases traffic in total or just changes the time of traffic distribution.
If the subsequent analysis or the observation in the multi-disk shows that C has strong positive influence on effective clustering, dimension enhancement on C can also be considered.
After the single-day difference ratio sequence and the total difference ratio are determined, the traffic difference ratio sequence of the target holiday can be calculated according to the single-day difference ratio sequence and the total difference ratio.
Taking the single-day difference ratio sequence as D ═ D1, D2,. the.,. di,. the., D14}, and the total difference ratio as C as an example, the single-day difference ratio sequence is added with the total difference ratio, i.e., D1, D2,. the., D14, and C is added, so as to obtain the 15-dimensional traffic difference ratio sequence.
204. And predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence.
The method comprises the steps of determining a target area and a target holiday of the traffic to be predicted; acquiring historical traffic of the target area on the target holiday; calculating a traffic difference value proportion sequence of the holidays of the target festival according to the historical traffic; and predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence. According to the embodiment of the application, in the prior art, the component prediction is limited due to the fact that the component is classified through simple component composition, the traffic is predicted through calculating the traffic difference value proportion sequence of the target area on the target holiday on the basis of inaccurate component prediction, the process predicts the traffic for the difference value proportion data of a certain holiday of a certain area, and compared with the process of simply observing the component number of each period, the difference value proportion sequence corresponding to each holiday can better draw the consumption habit of an area facing the stimulation of the certain holiday, so that the traffic prediction is closer to the actual scene, and the accuracy of the traffic prediction is improved.
In other embodiments of the present invention, as shown in fig. 4, the predicting the traffic of the target area on the target holiday according to the traffic difference value proportion sequence may further include:
401. and determining a target traffic prediction model for predicting the traffic of the target area on the target holiday according to the target area and the target holiday.
The target traffic prediction model may be a Neural Network model, such as a Convolutional Neural Network (CNN) model, a Recurrent Neural Network (RNN) model, or the like.
402. And inputting the traffic difference value proportion sequence into the target traffic prediction model to predict the traffic of the target area on the target holiday.
It can be understood that, in step 401, before determining the target traffic prediction model for predicting the traffic of the target area on the target holiday according to the target area and the target holiday, a target traffic prediction model needs to be obtained by training.
Specifically, in the embodiment of the present invention, as shown in fig. 5, before determining the target traffic prediction model for predicting the traffic of the target area on the target holiday according to the target area and the target holiday, the method further includes:
501. and performing holiday clustering on all holidays to divide the holidays into a plurality of holiday classifications.
In the embodiment of the present invention, all holidays may refer to all holidays in a preset area in a natural year, for example, all holidays in china in a natural year.
Specifically, the holiday clustering may be performed on all holidays based on the holiday traffic data, the holiday clustering may be performed on all holidays by using a holiday classification model, and the holiday classification model may consider a Fuzzy C-Means clustering (FCM) model or a K-Mean model which is trained in advance. The goal is to differentiate all holidays into several categories. If 2 is taken, the festivals with a large increase in traffic will generally be grouped together, with the festivals having little impact on traffic. The holiday classification model may also subdivide the holiday based on other characteristics if more classifications are taken.
Overall, if the number of holiday samples is small, then fewer classifications are taken in the embodiments of the present invention, which may ensure that there are sufficient data learning features under each holiday classification. If the sample size of the holiday is larger, a plurality of classifications can be selected to ensure that the holiday learnability of the collected holidays is strong. Of course, the holiday category cannot exceed the total number of holidays.
502. And carrying out region clustering on the region to be planned so as to divide each region in the region to be planned into a plurality of region classifications, wherein the region to be planned comprises the target region.
After the holiday clustering, the expression of each region in 15 dimensions is clustered by using a region clustering model according to a certain class of holiday traffic data. The purpose of this is to screen out areas that respond similarly in the face of similar consumer stimuli. Also, such region clustering can provide more valuable data combinations for subsequent models. Meanwhile, the problem that data is insufficient or the quantity of models is too large when a single region is used for modeling is avoided. Similarly, the area clustering model may also adopt a pre-trained FCM model or K-Mean model.
503. And forming a plurality of holiday and city classifications according to the plurality of holiday classifications and the plurality of region classifications.
After the dual clustering of the holidays and the regions is completed, a plurality of holiday and city classifications can be formed according to the plurality of holiday classifications and the plurality of region classifications. For example, as shown in fig. 6, assuming that a holiday of a house is a holiday and a region is a city, after completing the dual clustering of the holiday and the region, the holiday and the region can be classified into a class a holiday 1 city, a class a holiday 2 city, and the like as shown in fig. 6.
504. And collecting historical traffic data of the plurality of holidays and city classifications.
In the embodiment of the invention, the historical service volume data of the plurality of holidays and the city classification are directly collected through the service platform, for example, the service platform stores the historical service volume data in the operation process, and the historical service volume data of the plurality of holidays and the city classification can be collected through accessing the corresponding memory of the service platform.
505. And training a preset model based on the historical traffic data of the classification of the plurality of holiday cities to obtain a traffic prediction model of the plurality of holiday cities.
Specifically, the service volume data of the good holiday-city class is modeled by a machine learning method (obtained by training an initial machine learning model), so that each "holiday class-city class" has a prediction model for learning the data, such as the "class a holiday class 1 city model" shown in fig. 6, where the initial machine learning model may be the CNN model or the RNN model described in the above embodiments.
In some embodiments of the present invention, after completing the holiday clustering and the regional clustering, the distribution ratio thereof is recorded for determining the weight ratio of each model result in the subsequent prediction. For example, a given holiday has 60% of data categorized as class A, 30% as class B, and 10% as class C. A city has 70% of data categorized into class 1, 30% categorized into class 2, etc.
In other embodiments of the present invention, since different holiday starting days have different influences on traffic volume, different intra-week starting day weights may be used, and the intra-week starting day weights may include: the official starting time was seven kinds of monday, tuesday up to sunday, and 9 kinds of holidays in the previous week and holidays in the next week.
The time in the week starting on the same type of holidays is different, and the influence on the traffic in the holidays is different. For example, when certain holiday starting times are in the week, the consumption habits of people are different from the holidays that begin on weekends. In addition, if two festivals are near (such as mid-autumn and national day), the same city will have different consumption curves. Therefore, it is necessary to classify holiday data gathered together after holiday clustering by the starting intra-week time of the holiday, and a weight is determined by comparing the growth rate of these nine cases to the holiday average growth baseline. For example, in class B holiday clustering, the official second balance of class B holidays increases by a ratio of y compared to weekdays, and when the official starting time for class B holiday is Friday, the official second day increases by a ratio of y 'compared to weekdays, where the weight for the start of class B holiday Friday is ((y'/y) + c-1)/c. Here, c is a coefficient set by us and used for adjusting the influence of the weight on the final result, the value is between 1 and positive infinity, the larger c is, the weight is approximately close to 1, and the influence on the whole prediction model is smaller.
In order to better implement the traffic prediction method provided by the embodiment of the present invention, an embodiment of the present invention further provides a device based on the traffic prediction method. The terms are the same as those in the traffic prediction method, and details of implementation may refer to the description in the method embodiment.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a traffic prediction apparatus according to an embodiment of the present invention, wherein the traffic prediction apparatus 700 may include a determining unit 701, an obtaining unit 702, a calculating unit 703 and a predicting unit 704, where:
a determining unit 701, configured to determine a target area and a target holiday of traffic to be predicted;
an obtaining unit 702, configured to obtain historical traffic of the target area on the target holiday;
a calculating unit 703, configured to calculate a traffic difference ratio sequence of the target holiday according to the historical traffic;
a predicting unit 704, configured to predict traffic of the target area on the target holiday according to the traffic difference value proportion sequence.
In some embodiments of the present application, the calculating unit 703 is specifically configured to:
determining a festival observation time period and a peacetime observation time period corresponding to the target festival and holiday;
acquiring the historical traffic of the target area in the holiday observation time period each day from the historical traffic;
acquiring historical traffic of the target area in the daily observation time period at ordinary times from the historical traffic;
and calculating the traffic difference value proportional sequence of the target holiday according to the daily historical traffic in the holiday observation time period and the daily historical traffic in the ordinary observation time period.
In some embodiments of the present application, the calculating unit 703 is specifically configured to:
filling the target holidays with a first preset number of days forward and a second preset number of days backward respectively to enable the total number of days to reach the target number of days, and obtaining holiday observation time periods corresponding to the target holidays;
and taking the first third preset number of days of each day in the festival observation time period to obtain the ordinary observation time period with the same time length as the festival observation time period.
In some embodiments of the present application, the calculating unit 703 is specifically configured to:
generating a first traffic sequence according to the historical traffic of each day in the holiday observation time period;
generating a second traffic sequence according to the daily historical traffic of the ordinary observation time period;
calculating a single-day difference value proportion sequence corresponding to the target holiday according to the first traffic sequence and the second traffic sequence;
and calculating the traffic difference ratio sequence of the target holidays according to the single-day difference ratio sequence.
In some embodiments of the present application, the calculating unit 703 is specifically configured to:
acquiring a first total historical traffic volume in the festival observation time period;
acquiring a second total historical traffic of the ordinary observation time period;
calculating the total difference ratio corresponding to the target holiday according to the first total historical traffic and the second total historical traffic;
and calculating the traffic difference ratio sequence of the target holiday according to the single-day difference ratio sequence and the total difference ratio.
In some embodiments of the present application, the prediction unit 704 is specifically configured to:
determining a target traffic prediction model for predicting the traffic of the target area on the target holiday according to the target area and the target holiday;
and inputting the traffic difference value proportion sequence into the target traffic prediction model to predict the traffic of the target area on the target holiday.
In some embodiments of the present application, the apparatus further comprises a training unit, the training unit being configured to:
before determining a target traffic prediction model for predicting the traffic of the target region on the target holiday according to the target region and the target holiday, performing holiday clustering on all holidays so as to divide the holidays into a plurality of holiday classifications;
performing region clustering on a region to be planned so as to divide each region in the region to be planned into a plurality of region classifications, wherein the region to be planned comprises the target region;
forming a plurality of holiday and city classifications according to the plurality of holiday classifications and the plurality of region classifications;
collecting historical traffic data of the plurality of holidays and city classifications;
and training a preset model based on the historical traffic data of the classification of the plurality of holiday cities to obtain a traffic prediction model of the plurality of holiday cities.
In the embodiment of the application, a determining unit 701 determines a target area and a target holiday of traffic to be predicted; an obtaining unit 702 obtains the historical traffic of the target area on the target holiday; the calculation unit 703 calculates a traffic difference value proportional sequence of the target holiday according to the historical traffic; the prediction unit 704 predicts the traffic of the target area on the target holiday according to the traffic difference value proportional sequence. According to the embodiment of the application, in the prior art, the traffic prediction is limited due to the fact that the traffic is classified through simple traffic composition, the traffic prediction is achieved through calculating the traffic difference ratio sequence of the target area on the target holiday on the basis of inaccurate traffic prediction, the traffic is predicted through the process on the difference ratio data of a certain holiday of a certain area, compared with the fact that the traffic of each period is simply observed, the consumption habit of one area facing to the stimulation of the certain holiday can be better defined through the difference ratio sequence corresponding to the certain holiday, the traffic prediction is closer to the actual scene, and the accuracy of the traffic prediction is improved.
An embodiment of the present invention further provides an electronic device, as shown in fig. 8, which shows a schematic structural diagram of the electronic device according to the embodiment of the present invention, specifically:
the electronic device may include components such as a processor 801 of one or more processing cores, memory 802 of one or more computer-readable storage media, a power supply 803, and an input unit 804. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 8 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:
the processor 801 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, and performs various functions of the electronic device and processes data by operating or executing software programs and/or modules stored in the memory 802 and calling data stored in the memory 802, thereby performing overall monitoring of the electronic device. Alternatively, processor 801 may include one or more processing cores; preferably, the processor 801 may integrate an application processor and a modem processor, wherein the application processor mainly handles operations of storage media, user interfaces, application programs, and the like, and the modem processor mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 801.
The memory 802 may be used to store software programs and modules, and the processor 801 executes various functional applications and data processing by operating the software programs and modules stored in the memory 802. The memory 802 may mainly include a storage program area and a storage data area, wherein the storage program area may store an application program (such as a sound playing function, an image playing function, etc.) required for operating a storage medium, at least one function, and the like; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 802 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 802 may also include a memory controller to provide the processor 801 access to the memory 802.
The electronic device further comprises a power supply 803 for supplying power to each component, and preferably, the power supply 803 can be logically connected with the processor 801 through a power management storage medium, so that functions of managing charging, discharging, power consumption management and the like can be realized through the power management storage medium. The power supply 803 may also include any component including one or more of a dc or ac power source, a rechargeable storage medium, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.
The electronic device may further include an input unit 804, the input unit 804 being operable to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the electronic device may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 801 in the electronic device loads an executable file corresponding to a process of one or more application programs into the memory 802 according to the following instructions, and the processor 801 runs the application programs stored in the memory 802, thereby implementing various functions as follows:
determining a target area and a target holiday of traffic to be predicted; acquiring historical traffic of the target area on the holidays of the target festival; calculating a traffic difference value proportion sequence of the target holiday according to the historical traffic; and predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence.
It will be understood by those skilled in the art that all or part of the steps in the methods of the above embodiments may be performed by instructions or by instructions controlling associated hardware, and the instructions may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, the embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program is loaded by a processor to execute the steps in any one of the traffic prediction methods provided by the embodiment of the present invention. For example, the computer program may be loaded by a processor to perform the steps of:
determining a target area and a target holiday of traffic to be predicted; acquiring historical traffic of the target area on the holidays of the target festival; calculating a traffic difference value proportion sequence of the target holiday according to the historical traffic; and predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
Wherein the computer-readable storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
Since the computer program stored in the computer-readable storage medium can execute the steps in any traffic prediction method provided in the embodiments of the present invention, beneficial effects that can be achieved by any traffic prediction method provided in the embodiments of the present invention can be achieved, which are detailed in the foregoing embodiments and will not be described herein again.
The traffic prediction method, the traffic prediction device, the electronic device, and the storage medium according to the embodiments of the present invention are described in detail above, and a specific example is applied in the description to explain the principle and the implementation of the present invention, and the description of the embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A traffic prediction method, characterized in that the method comprises:
determining a target area and a target holiday of traffic to be predicted;
acquiring historical traffic of the target area on the target holiday;
calculating a traffic difference value proportional sequence of the target holidays according to the historical traffic;
and predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence.
2. The traffic prediction method of claim 1, wherein said calculating a traffic difference value proportional sequence of said target holiday according to said historical traffic comprises:
determining a festival observation time period and a peacetime observation time period corresponding to the target festival and holiday;
acquiring the historical traffic of the target area in the holiday observation time period each day from the historical traffic;
acquiring the historical traffic of the target area in the observation time period at ordinary times every day from the historical traffic;
and calculating the traffic difference value proportional sequence of the target holiday according to the daily historical traffic in the holiday observation time period and the daily historical traffic in the ordinary observation time period.
3. The traffic prediction method according to claim 2, wherein the determining the holiday observation time period and the average observation time period corresponding to the target holiday comprises:
filling the target holidays with a first preset number of days forward and a second preset number of days backward respectively to enable the total number of days to reach the target number of days, and obtaining holiday observation time periods corresponding to the target holidays;
and taking the first third preset number of days of each day in the festival observation time period to obtain the ordinary observation time period with the same time length as the festival observation time period.
4. The traffic prediction method according to claim 2, wherein the calculating a traffic difference ratio sequence of the target holiday according to the historical traffic of each day in the holiday observation period and the historical traffic of each day in the ordinary observation period comprises:
generating a first traffic sequence according to the historical traffic of each day in the holiday observation time period;
generating a second traffic sequence according to the daily historical traffic of the ordinary observation time period;
calculating a single-day difference value proportion sequence corresponding to the target holiday according to the first traffic sequence and the second traffic sequence;
and calculating the traffic difference ratio sequence of the target holidays according to the single-day difference ratio sequence.
5. The traffic prediction method of claim 4, wherein the calculating the traffic difference ratio sequence for the target holiday according to the single-day difference ratio sequence comprises:
acquiring a first total historical traffic volume in the festival observation time period;
acquiring a second total historical traffic of the ordinary observation time period;
calculating the total difference ratio corresponding to the target holiday according to the first total historical traffic and the second total historical traffic;
and calculating the traffic difference ratio sequence of the target holiday according to the single-day difference ratio sequence and the total difference ratio.
6. The traffic prediction method according to any one of claims 1 to 5, wherein the predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence comprises:
determining a target traffic prediction model for predicting the traffic of the target area on the target holiday according to the target area and the target holiday;
and inputting the traffic difference value proportion sequence into the target traffic prediction model to predict the traffic of the target area on the target holiday.
7. The traffic prediction method of claim 1, wherein prior to said determining a target traffic prediction model that predicts traffic of the target region on the target holiday based on the target region and the target holiday, the method further comprises:
performing holiday clustering on all holidays to divide the holidays into a plurality of holiday classifications;
performing region clustering on a region to be planned so as to divide each region in the region to be planned into a plurality of region classifications, wherein the region to be planned comprises the target region;
forming a plurality of holiday and city classifications according to the plurality of holiday classifications and the plurality of region classifications;
collecting historical traffic data of the plurality of holidays and city classifications;
and training a preset model based on the historical traffic data of the classification of the plurality of holiday cities to obtain a traffic prediction model of the plurality of holiday cities.
8. An apparatus for traffic prediction, the apparatus comprising:
the determining unit is used for determining a target area and a target holiday of the traffic to be predicted;
the acquisition unit is used for acquiring the historical traffic of the target area on the target holiday;
the calculating unit is used for calculating a traffic difference value proportional sequence of the target holiday according to the historical traffic;
and the prediction unit is used for predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence.
9. An electronic device comprising a memory and a processor, the memory having stored therein a computer program that, when executed by the processor, causes the processor to perform the steps of:
determining a target area and a target holiday of traffic to be predicted;
acquiring historical traffic of the target area on the target holiday;
calculating a traffic difference value proportional sequence of the target holidays according to the historical traffic;
and predicting the traffic of the target area on the target holiday according to the traffic difference value proportional sequence.
10. A computer-readable storage medium, having stored thereon a computer program which is loaded by a processor to perform the steps of the traffic prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911267341.4A CN112949886A (en) | 2019-12-11 | 2019-12-11 | Traffic prediction method, traffic prediction device, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911267341.4A CN112949886A (en) | 2019-12-11 | 2019-12-11 | Traffic prediction method, traffic prediction device, electronic device, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112949886A true CN112949886A (en) | 2021-06-11 |
Family
ID=76233994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911267341.4A Pending CN112949886A (en) | 2019-12-11 | 2019-12-11 | Traffic prediction method, traffic prediction device, electronic device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949886A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108364092A (en) * | 2018-01-29 | 2018-08-03 | 西安理工大学 | A kind of catering trade vegetable Method for Sales Forecast method based on deep learning |
| CN109657831A (en) * | 2017-10-11 | 2019-04-19 | 顺丰科技有限公司 | A kind of Traffic prediction method, apparatus, equipment, storage medium |
| WO2019109756A1 (en) * | 2017-12-05 | 2019-06-13 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for cheat examination |
-
2019
- 2019-12-11 CN CN201911267341.4A patent/CN112949886A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657831A (en) * | 2017-10-11 | 2019-04-19 | 顺丰科技有限公司 | A kind of Traffic prediction method, apparatus, equipment, storage medium |
| WO2019109756A1 (en) * | 2017-12-05 | 2019-06-13 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for cheat examination |
| CN108364092A (en) * | 2018-01-29 | 2018-08-03 | 西安理工大学 | A kind of catering trade vegetable Method for Sales Forecast method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105849998B (en) | Electric power demand forecasting device and prediction technique, power supply system and recording medium | |
| Pfaffenbichler et al. | The integrated dynamic land use and transport model MARS | |
| CN105183870B (en) | A kind of urban function region detection method and system using microblogging location information | |
| CN109325640A (en) | User's Value Prediction Methods, device, storage medium and equipment | |
| CN107609147B (en) | Method and system for automatically extracting features from log stream | |
| CN105897616B (en) | Resource allocation method and server | |
| CN103092699A (en) | Cloud computing resource pre-distribution achievement method | |
| CN103971170A (en) | Method and device for forecasting changes of feature information | |
| CN110880127B (en) | Consumption level prediction method and device, electronic equipment and storage medium | |
| CN109815631A (en) | A kind for the treatment of method and apparatus of game data | |
| CN106063067A (en) | Electricity-demand prediction device, electricity supply system, electricity-demand prediction method, and program | |
| CN106611366A (en) | Method and device for automatically selecting article | |
| CN110363427A (en) | Model quality evaluation method and apparatus | |
| CN109697637A (en) | Object type determines method, apparatus, electronic equipment and computer storage medium | |
| CN105786711A (en) | Data analysis method and device | |
| CN109685255A (en) | A kind of method and apparatus for predicting customer churn | |
| Bai et al. | A forecasting method of forest pests based on the rough set and PSO-BP neural network | |
| CN111680382A (en) | Grade prediction model training method, grade prediction device and electronic equipment | |
| CN112613637A (en) | Method and device for processing charging load | |
| CN103186575A (en) | Clustering analysis method and system of sensing data | |
| CN113268403A (en) | Time series analysis and prediction method, device, equipment and storage medium | |
| CN104993966B (en) | A kind of electric integrated service network method for predicting | |
| CN111415027A (en) | Method and device for constructing component prediction model | |
| CN115829124A (en) | Charging pile address selection method, device, equipment and storage medium | |
| CN112395499B (en) | Information recommendation method and device, electronic equipment 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 |