CN111950753A - Scenic spot passenger flow prediction method and device - Google Patents
Scenic spot passenger flow prediction method and device Download PDFInfo
- Publication number
- CN111950753A CN111950753A CN201910402126.4A CN201910402126A CN111950753A CN 111950753 A CN111950753 A CN 111950753A CN 201910402126 A CN201910402126 A CN 201910402126A CN 111950753 A CN111950753 A CN 111950753A
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- training
- model
- scenic spot
- characteristic
- 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
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
Abstract
The invention discloses a scenic spot passenger flow prediction method and a device, wherein the method comprises the steps of obtaining parameter information of a predicted scenic spot, determining characteristic engineering of the predicted scenic spot according to the parameter information, inputting the characteristic engineering of the predicted scenic spot into a passenger flow prediction model, and predicting passenger flow of the predicted scenic spot, wherein the passenger flow prediction model is obtained by training and learning historical passenger flow under different scenes of the scenic spot, and comprises a primary training model and a secondary training model. By adding the characteristic engineering value to the passenger flow prediction model obtained by learning according to the primary training model and the secondary training model, the passenger flow of scenic spots can be accurately predicted, and the prediction accuracy is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of passenger flow prediction, in particular to a scenic spot passenger flow prediction method and device.
Background
The scenic spot passenger flow volume data can reflect historical scenic spot and current tourist carrying capacity and distribution conditions, and meanwhile, data support is provided for managers to make future decisions, and the operation efficiency is improved. And the scene manager can be helped to obtain some measures and schemes for dealing with the scene in the future by making sufficiently accurate passenger flow prediction data and analysis in advance.
Therefore, in order to obtain accurate scenic spot passenger flow prediction data and provide effective basis for scenic spot managers to implement some measures and schemes, a method for multi-dimensional scenic spot passenger flow prediction is urgently needed.
Disclosure of Invention
The embodiment of the invention provides a scenic spot passenger flow prediction method and device, which are used for improving the accuracy of scenic spot passenger flow prediction.
The embodiment of the invention provides a scenic spot passenger flow prediction method, which comprises the following steps:
acquiring parameter information of a predicted scenic spot;
determining the characteristic engineering of the predicted scenic spot according to the parameter information;
inputting the feature engineering of the forecast scenic spot into a passenger flow forecasting model, and forecasting the passenger flow of the forecast scenic spot, wherein the passenger flow forecasting model is obtained by training and learning the historical passenger flow under different scenes of the scenic spot, and comprises a primary training model and a secondary training model.
According to the technical scheme, the characteristic engineering value is added to the passenger flow prediction model obtained through learning according to the primary training model and the secondary training model, so that the passenger flow of scenic spots can be accurately predicted, and the prediction accuracy is improved.
Optionally, the training and learning passenger flows in different scenes of the scenic spot to obtain the passenger flow prediction model includes:
obtaining historical passenger flow information of scenic spots;
analyzing the historical passenger flow according to the prediction granularity in a plurality of scenes to determine a feature set;
determining a characteristic value corresponding to each characteristic aiming at each characteristic in the characteristic set to form a first characteristic project;
and performing model training on the first characteristic project and the corresponding historical passenger flow to determine the passenger flow prediction model.
Optionally, the performing model training on the first feature engineering and the historical passenger flow corresponding to the first feature engineering to determine the passenger flow prediction model includes:
forming the first characteristic project and the corresponding historical passenger flow into a data set; and separating the data set into primary training data and secondary training data;
training the primary training data by using a plurality of basic algorithms to obtain a plurality of trained basic models;
and performing secondary training according to the secondary training data and the plurality of trained base models to obtain the passenger flow prediction model.
Optionally, the performing secondary training according to the secondary training data and the trained base models to obtain the passenger flow prediction model includes:
dividing the secondary training data into a training set and a validation set;
inputting the training set to the trained models respectively to obtain a plurality of predicted values;
inputting the plurality of predicted values into a linear regression model to perform secondary training to obtain a secondary training model;
and evaluating the secondary training model by using the verification set to obtain the passenger flow prediction model.
Optionally, the evaluating the secondary training model by using the verification set to obtain the passenger flow prediction model includes:
using R according to the validation set2And evaluating the secondary training model by an error method, if the evaluation value is lower than an expected value, re-determining the first characteristic project, and then performing model training until the evaluation value is greater than or equal to the expected value to obtain the passenger flow prediction model.
Correspondingly, the embodiment of the invention also provides a device for forecasting the passenger flow in the scenic spot, which comprises the following steps:
an acquisition unit configured to acquire parameter information of a predicted scenic region;
the processing unit is used for determining the feature engineering of the predicted scenic spot according to the parameter information;
inputting the feature engineering of the forecast scenic spot into a passenger flow forecasting model, and forecasting the passenger flow of the forecast scenic spot, wherein the passenger flow forecasting model is obtained by training and learning the historical passenger flow under different scenes of the scenic spot, and comprises a primary training model and a secondary training model.
Optionally, the processing unit is specifically configured to:
obtaining historical passenger flow information of scenic spots;
analyzing the historical passenger flow according to the prediction granularity in a plurality of scenes to determine a feature set;
determining a characteristic value corresponding to each characteristic aiming at each characteristic in the characteristic set to form a first characteristic project;
and performing model training on the first characteristic project and the corresponding historical passenger flow to determine the passenger flow prediction model.
Optionally, the processing unit is specifically configured to:
forming the first characteristic project and the corresponding historical passenger flow into a data set; and separating the data set into primary training data and secondary training data;
training the primary training data by using a plurality of basic algorithms to obtain a plurality of trained basic models;
and performing secondary training according to the secondary training data and the plurality of trained base models to obtain the passenger flow prediction model.
Optionally, the processing unit is specifically configured to:
dividing the secondary training data into a training set and a validation set;
inputting the training set to the trained models respectively to obtain a plurality of predicted values;
inputting the plurality of predicted values into a linear regression model to perform secondary training to obtain a secondary training model;
and evaluating the secondary training model by using the verification set to obtain the passenger flow prediction model.
Optionally, the processing unit is specifically configured to:
using R according to the validation set2Error method for the secondary training modelAnd evaluating, if the evaluation value is lower than an expected value, re-determining the first characteristic project, and then performing model training until the evaluation value is greater than or equal to the expected value to obtain the passenger flow prediction model.
Correspondingly, an embodiment of the present invention further provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instruction stored in the memory and executing the method for predicting the scenic spot passenger flow according to the obtained program.
Accordingly, an embodiment of the present invention further provides a computer-readable non-volatile storage medium, which includes computer-readable instructions, and when the computer reads and executes the computer-readable instructions, the computer is caused to execute the above method for predicting scenic spot passenger flow.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be 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 to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic diagram of a system architecture according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for predicting the passenger flow in a scenic spot according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of feature engineering construction provided by an embodiment of the present invention;
FIG. 4 is a schematic diagram of model training according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating a primary training model according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating a secondary training model according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a device for predicting scenic spot passenger flow according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, 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 making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 illustrates an exemplary system architecture, which may be a server 100, including a processor 110, a communication interface 120, and a memory 130, to which embodiments of the present invention are applicable.
The communication interface 120 is used for communicating with a terminal device, and transceiving information transmitted by the terminal device to implement communication.
The processor 110 is a control center of the server 100, connects various parts of the entire server 100 using various interfaces and routes, performs various functions of the server 100 and processes data by operating or executing software programs and/or modules stored in the memory 130 and calling data stored in the memory 130. Alternatively, processor 110 may include one or more processing units.
The memory 130 may be used to store software programs and modules, and the processor 110 executes various functional applications and data processing by operating the software programs and modules stored in the memory 130. The memory 130 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to a business process, and the like. Further, the memory 130 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.
It should be noted that the structure shown in fig. 1 is only an example, and the embodiment of the present invention is not limited thereto.
Based on the above description, fig. 2 exemplarily shows a flow of a method for scenic spot passenger flow prediction according to an embodiment of the present invention, where the flow may be performed by a device for scenic spot passenger flow prediction, which may be located in the server 100 shown in fig. 1, or may be the server 100.
As shown in fig. 2, the process specifically includes:
In the embodiment of the present invention, the parameter information of the predicted scenic spot may be a characteristic of the predicted scenic spot, and may be information of date, weather, temperature, activity, and the like, for example.
Before the scenic spot passenger flow prediction is carried out, a passenger flow prediction model needs to be trained, the passenger flow prediction model is obtained by training and learning historical passenger flows in different scenes of the scenic spot, and the passenger flow prediction model comprises a primary training model and a secondary training model. Specifically, historical passenger flow information of scenic spots needs to be obtained first, and then the historical passenger flow is analyzed according to the prediction granularity in a plurality of scenes to determine a feature set. And finally, performing model training on the first characteristic project and the corresponding historical passenger flow to determine a passenger flow prediction model.
Therefore, feature engineering needs to be constructed first, and in the embodiment of the present invention, the feature engineering construction may be divided into three steps, namely, scene division, granularity selection, and feature selection:
1) scene partitioning
Under some special scenes, the passenger flow volume data can be greatly changed, so that the a scene division A can be carried out on the passenger flow prediction of the scenic spot according to the actual situation of the scenic spot1、A2……AaSee fig. 1. Example A1General date passenger flow prediction, A2Holiday passenger flow prediction, A3And predicting the passenger flow of the important event day.
2) Selection of particle size
Besides passenger flow prediction under condition division and multiple scenes, the passenger flow prediction method can also be divided into b prediction granularities according to actual demands, L1Hour, L2Day, L3Moon … LbAs shown in fig. 3.
3) Feature selection
By inspecting scenic spot on the spot, combining with divided scenes, selecting the needed prediction granularity, analyzing historical passenger flow data of the scenic spot, and capturing a feature set [ X ] which can influence the passenger flow of the scenic spotM]For each feature, analysis is performed, and an appropriate feature value is extracted to form a feature project [ X ]MN]As shown in fig. 3. For example, in the prediction of passenger flow at an hour level in a heavy activity scene, the extraction of partial feature values is as follows:
X1date: from historical traffic data, the date can extract a characteristic value X that can have an effect on traffic11month，X12day，X13week,X14hour,……X1N。
X2Weather: splitting the weather in the weather forecast before and after (such as cloudy turning into cloudy), giving weight values to various types of weather to show the weather quality, and thus obtaining the characteristic value X in the weather forecast21Front weather front (weather), X22Rear weather back (weather), X23Weight values front _ weather (weight), X of the previous weather24Weight value of the following weather back _ weather (weight).
X3Temperature: the temperature in the weather forecast is split (such as 15-20 ℃) before and after the temperature, and then the average temperature of the day is obtained, so that the characteristic value X is obtained31Maximum temperatures max (C), X32Minimum temperatures min (C), X33Average temperature mean (C).
X4Moving: defining the activity according to the activity scale level to obtain the characteristic value X41Such as small-sized activities (1), X42Medium-sized activity (2), X43Large-scale activities (3), etc., corresponding to various activity scale levels by corresponding numerical values.
In the way described aboveAfter the first characteristic project is obtained, a data set can be formed by the first characteristic project and the corresponding historical passenger flow, and the data set is divided into primary training data and secondary training data. And then, training the primary training data by using a plurality of basic algorithms to obtain a plurality of trained basic models. And finally, performing secondary training according to the secondary training data and the plurality of trained base models to obtain a passenger flow prediction model. When performing the secondary training, the secondary training data may be specifically divided into a training set and a validation set. And respectively inputting the training set to a plurality of trained models to obtain a plurality of predicted values. And inputting the plurality of predicted values into the linear regression model to perform secondary training to obtain a secondary training model. And evaluating the secondary training model by using the verification set to obtain a passenger flow prediction model. Further, R can be used according to a validation set2And (4) evaluating the secondary training model by an error method, if the evaluation value is lower than an expected value, re-determining the first characteristic project, and then performing model training until the evaluation value is greater than or equal to the expected value to obtain a final passenger flow prediction model.
For example, the embodiment of the invention is constructed based on a stacking ensemble learning algorithm, and the algorithm model is composed of a plurality of base models [ C ]1，C2，……Cm]And combining and training to obtain the product. Firstly, the constructed characteristic engineering [ X ]MN]And the corresponding actual passenger flow volume form a data set, the data set is divided into primary training data and secondary training data, and then primary training and secondary training are performed respectively based on the primary training data and the secondary training data, so as to finally obtain a passenger flow prediction model, as shown in fig. 4. The primary training method and the secondary training method will be described in detail below.
The first and the primary training method are as follows:
in the primary training process, m basic algorithms are selected in advance, and each selected basic algorithm is subjected to model training by using primary training data, so that m trained basic algorithm models are obtained, as shown in fig. 5.
The second and secondary training method comprises the following steps:
after the primary training is finished and the basic model is confirmed, the secondary training number is countedRespectively calling each base model as a training set to predict to obtain a predicted value PmThen all the predicted values are combined into a new training set [ P ]m]. Selecting linear regression algorithm as secondary algorithm model, and using [ P ]m]And performing linear regression algorithm model training as input, and finally training to obtain a combination of the secondary model and the base model, namely the final prediction algorithm model.
In the secondary training process, the secondary training data can be divided into a training set and a verification set, the training set is used as input to train the model, and the verification set uses R after the model training is finished2The error method evaluates the model, if the evaluation value is lower than the expected value, feature engineering reconstruction is required, and then training of the model is carried out again until the evaluation value meets the expected requirement, as shown in fig. 6.
In order to better explain the flow of the scenic spot passenger flow prediction provided by the embodiment of the present invention, the following description is provided in a specific implementation scenario.
In 2018, in 14 months 11 (day: clear to cloudy, temperature: 15-20 ℃), a large-scale activity will be held in a certain scenic spot, and the passenger flow prediction on the day can be carried out according to the following steps:
1. and (4) constructing the characteristic engineering, namely constructing the characteristic engineering according to the structure of the characteristic engineering during the training of the algorithm model, and taking the characteristic as an input value of the algorithm model. Assuming that the feature engineering constructed during the algorithm model training is [ month, day, week, former weather weight, latter weather weight, lowest temperature, highest temperature, average temperature, activity ], defining weather sunny (value: 1, weight: 0), cloudy (value: 2, weight: 0.2), large activity (value: 3) in the database, then the feature engineering at the time of prediction is constructed [11,14,3,1,0,2,0.2,15,20,17.5,3 ].
2. And (3) primary model prediction, namely assuming that the basic model selected in the primary model training is a Ridge regression algorithm model, a Lasso regression algorithm model, a random forest algorithm model, a decision tree algorithm model and an XGboost algorithm model, respectively calling the models to predict by taking the feature engineering in the step 1 as an input value, and combining the output value into a feature [ P1，P2，P3，P4，P5]。
3. And (5) predicting by using a secondary model, wherein the prediction result is a final passenger flow prediction value. The characteristics [ P ] finally obtained in the step 21，P2，P3，P4，P5]And calling the linear regression algorithm model obtained in the secondary training as input for prediction, wherein the output value of the model is the final passenger flow predicted value.
The embodiment of the invention has the advantages that the historical passenger flow data is utilized to train the prediction model, then the prediction model is used to predict the future passenger flow, and the appropriate prediction model can be trained according to different scenes, so that the scenic spot passenger flow prediction under the complex environment is met. Has the following main effects:
1. the method is easy to obtain and has no high requirements on scenic spot hardware facilities depending on scenic spot historical passenger flow data;
2. the use is flexible, and the accuracy is high.
The embodiment shows that parameter information of a predicted scenic spot is obtained, the feature engineering of the predicted scenic spot is determined according to the parameter information, the feature engineering of the predicted scenic spot is input into a passenger flow prediction model, and passenger flow of the predicted scenic spot is predicted, wherein the passenger flow prediction model is obtained by training and learning historical passenger flow under different scenes of the scenic spot, and comprises a primary training model and a secondary training model. By adding the characteristic engineering value to the passenger flow prediction model obtained by learning according to the primary training model and the secondary training model, the passenger flow of scenic spots can be accurately predicted, and the prediction accuracy is improved.
Based on the same technical concept, fig. 7 exemplarily shows a structure of a device for scenic spot passenger flow prediction, which can perform a flow of scenic spot passenger flow prediction and is located in the server 100 shown in fig. 1, or the server 100.
As shown in fig. 7, the apparatus specifically includes:
an acquisition unit 701 configured to acquire parameter information of a predicted scenic region;
a processing unit 702, configured to determine, according to the parameter information, a feature project of the predicted scenic spot;
inputting the feature engineering of the forecast scenic spot into a passenger flow forecasting model, and forecasting the passenger flow of the forecast scenic spot, wherein the passenger flow forecasting model is obtained by training and learning the historical passenger flow under different scenes of the scenic spot, and comprises a primary training model and a secondary training model.
Optionally, the processing unit 702 is specifically configured to:
obtaining historical passenger flow information of scenic spots;
analyzing the historical passenger flow according to the prediction granularity in a plurality of scenes to determine a feature set;
determining a characteristic value corresponding to each characteristic aiming at each characteristic in the characteristic set to form a first characteristic project;
and performing model training on the first characteristic project and the corresponding historical passenger flow to determine the passenger flow prediction model.
Optionally, the processing unit 702 is specifically configured to:
forming the first characteristic project and the corresponding historical passenger flow into a data set; and separating the data set into primary training data and secondary training data;
training the primary training data by using a plurality of basic algorithms to obtain a plurality of trained basic models;
and performing secondary training according to the secondary training data and the plurality of trained base models to obtain the passenger flow prediction model.
Optionally, the processing unit 702 is specifically configured to:
dividing the secondary training data into a training set and a validation set;
inputting the training set to the trained models respectively to obtain a plurality of predicted values;
inputting the plurality of predicted values into a linear regression model to perform secondary training to obtain a secondary training model;
and evaluating the secondary training model by using the verification set to obtain the passenger flow prediction model.
Optionally, the processing unit 702 is specifically configured to:
using R according to the validation set2And evaluating the secondary training model by an error method, if the evaluation value is lower than an expected value, re-determining the first characteristic project, and then performing model training until the evaluation value is greater than or equal to the expected value to obtain the passenger flow prediction model.
Based on the same technical concept, an embodiment of the present invention further provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instruction stored in the memory and executing the method for predicting the scenic spot passenger flow according to the obtained program.
Based on the same technical concept, the embodiment of the invention also provides a computer-readable non-volatile storage medium, which comprises computer-readable instructions, and when the computer-readable instructions are read and executed by a computer, the computer is enabled to execute the method for scenic spot passenger flow prediction.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method for scenic spot passenger flow prediction, comprising:
acquiring parameter information of a predicted scenic spot;
determining the characteristic engineering of the predicted scenic spot according to the parameter information;
inputting the feature engineering of the forecast scenic spot into a passenger flow forecasting model, and forecasting the passenger flow of the forecast scenic spot, wherein the passenger flow forecasting model is obtained by training and learning the historical passenger flow under different scenes of the scenic spot, and comprises a primary training model and a secondary training model.
2. The method of claim 1, wherein the training and learning of the passenger flow in different scenes of the scenic spot to obtain the passenger flow prediction model comprises:
obtaining historical passenger flow information of scenic spots;
analyzing the historical passenger flow according to the prediction granularity in a plurality of scenes to determine a feature set;
determining a characteristic value corresponding to each characteristic aiming at each characteristic in the characteristic set to form a first characteristic project;
and performing model training on the first characteristic project and the corresponding historical passenger flow to determine the passenger flow prediction model.
3. The method of claim 2, wherein said model training of said first feature engineering and its corresponding historical passenger flow to determine said passenger flow prediction model comprises:
forming the first characteristic project and the corresponding historical passenger flow into a data set; and separating the data set into primary training data and secondary training data;
training the primary training data by using a plurality of basic algorithms to obtain a plurality of trained basic models;
and performing secondary training according to the secondary training data and the plurality of trained base models to obtain the passenger flow prediction model.
4. The method of claim 3, wherein said performing secondary training based on said secondary training data and said plurality of trained base models to obtain said traffic prediction model comprises:
dividing the secondary training data into a training set and a validation set;
inputting the training set to the trained models respectively to obtain a plurality of predicted values;
inputting the plurality of predicted values into a linear regression model to perform secondary training to obtain a secondary training model;
and evaluating the secondary training model by using the verification set to obtain the passenger flow prediction model.
5. The method of claim 4, wherein said evaluating said secondary training model using said validation set to obtain said passenger flow prediction model comprises:
using R according to the validation set2And evaluating the secondary training model by an error method, if the evaluation value is lower than an expected value, re-determining the first characteristic project, and then performing model training until the evaluation value is greater than or equal to the expected value to obtain the passenger flow prediction model.
6. An apparatus for scenic spot passenger flow prediction, comprising:
an acquisition unit configured to acquire parameter information of a predicted scenic region;
the processing unit is used for determining the feature engineering of the predicted scenic spot according to the parameter information;
inputting the feature engineering of the forecast scenic spot into a passenger flow forecasting model, and forecasting the passenger flow of the forecast scenic spot, wherein the passenger flow forecasting model is obtained by training and learning the historical passenger flow under different scenes of the scenic spot, and comprises a primary training model and a secondary training model.
7. The apparatus as claimed in claim 6, wherein said processing unit is specifically configured to:
obtaining historical passenger flow information of scenic spots;
analyzing the historical passenger flow according to the prediction granularity in a plurality of scenes to determine a feature set;
determining a characteristic value corresponding to each characteristic aiming at each characteristic in the characteristic set to form a first characteristic project;
and performing model training on the first characteristic project and the corresponding historical passenger flow to determine the passenger flow prediction model.
8. The apparatus as claimed in claim 7, wherein said processing unit is specifically configured to:
forming the first characteristic project and the corresponding historical passenger flow into a data set; and separating the data set into primary training data and secondary training data;
training the primary training data by using a plurality of basic algorithms to obtain a plurality of trained basic models;
and performing secondary training according to the secondary training data and the plurality of trained base models to obtain the passenger flow prediction model.
9. The apparatus as claimed in claim 8, wherein said processing unit is specifically configured to:
dividing the secondary training data into a training set and a validation set;
inputting the training set to the trained models respectively to obtain a plurality of predicted values;
inputting the plurality of predicted values into a linear regression model to perform secondary training to obtain a secondary training model;
and evaluating the secondary training model by using the verification set to obtain the passenger flow prediction model.
10. The apparatus as claimed in claim 9, wherein said processing unit is specifically configured to:
using R according to the validation set2And evaluating the secondary training model by an error method, if the evaluation value is lower than an expected value, re-determining the first characteristic project, and then performing model training until the evaluation value is greater than or equal to the expected value to obtain the passenger flow prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910402126.4A CN111950753A (en) | 2019-05-15 | 2019-05-15 | Scenic spot passenger flow prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910402126.4A CN111950753A (en) | 2019-05-15 | 2019-05-15 | Scenic spot passenger flow prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111950753A true CN111950753A (en) | 2020-11-17 |
Family
ID=73336299
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910402126.4A Pending CN111950753A (en) | 2019-05-15 | 2019-05-15 | Scenic spot passenger flow prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111950753A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113723716A (en) * | 2021-11-02 | 2021-11-30 | 深圳市城市交通规划设计研究中心股份有限公司 | Passenger flow classification early warning abnormity warning method, device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590569A (en) * | 2017-09-25 | 2018-01-16 | 山东浪潮云服务信息科技有限公司 | A kind of data predication method and device |
| CN107895283A (en) * | 2017-11-07 | 2018-04-10 | 重庆邮电大学 | A kind of businessman's volume of the flow of passengers big data Forecasting Methodology based on Time Series |
| CN109034469A (en) * | 2018-07-20 | 2018-12-18 | 成都中科大旗软件有限公司 | A kind of tourist flow prediction technique based on machine learning |
| CN109272365A (en) * | 2018-10-15 | 2019-01-25 | 广东工业大学 | A kind of flow of restaurant guests prediction technique, device and equipment based on data mining |
-
2019
- 2019-05-15 CN CN201910402126.4A patent/CN111950753A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590569A (en) * | 2017-09-25 | 2018-01-16 | 山东浪潮云服务信息科技有限公司 | A kind of data predication method and device |
| CN107895283A (en) * | 2017-11-07 | 2018-04-10 | 重庆邮电大学 | A kind of businessman's volume of the flow of passengers big data Forecasting Methodology based on Time Series |
| CN109034469A (en) * | 2018-07-20 | 2018-12-18 | 成都中科大旗软件有限公司 | A kind of tourist flow prediction technique based on machine learning |
| CN109272365A (en) * | 2018-10-15 | 2019-01-25 | 广东工业大学 | A kind of flow of restaurant guests prediction technique, device and equipment based on data mining |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113723716A (en) * | 2021-11-02 | 2021-11-30 | 深圳市城市交通规划设计研究中心股份有限公司 | Passenger flow classification early warning abnormity warning method, device and storage medium |
| CN113723716B (en) * | 2021-11-02 | 2022-03-18 | 深圳市城市交通规划设计研究中心股份有限公司 | Passenger flow classification early warning abnormity warning method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10606862B2 (en) | Method and apparatus for data processing in data modeling | |
| CN108364085B (en) | Takeout delivery time prediction method and device | |
| US20180253637A1 (en) | Churn prediction using static and dynamic features | |
| CN111815432B (en) | Financial service risk prediction method and device | |
| CN113435770A (en) | Transaction risk assessment method and device based on block chain | |
| CN110415036B (en) | User grade determining method, device, computer equipment and storage medium | |
| CN111143685B (en) | Commodity recommendation method and device | |
| CN112632179A (en) | Model construction method and device, storage medium and equipment | |
| CN111950622A (en) | Behavior prediction method, behavior prediction device, behavior prediction terminal and storage medium based on artificial intelligence | |
| CN112446637A (en) | Building construction quality safety online risk detection method and system | |
| CN111667093B (en) | Medium-and-long-term wind power generation calculation method and device | |
| CN113408561A (en) | Model generation method, target detection method, device, equipment and storage medium | |
| CN110796366A (en) | Quality difference cell identification method and device | |
| CN108416619B (en) | Consumption interval time prediction method and device and readable storage medium | |
| CN115730947A (en) | Bank customer loss prediction method and device | |
| US9626156B2 (en) | Application architecture design method, application architecture design system, and recording medium | |
| CN111950753A (en) | Scenic spot passenger flow prediction method and device | |
| CN111090401B (en) | Storage device performance prediction method and device | |
| CN113827978A (en) | Loss user prediction method and device and computer readable storage medium | |
| CN113672375A (en) | Resource allocation prediction method, device, equipment and storage medium | |
| CN116205355A (en) | Power load prediction method, device and storage medium | |
| CN111984637B (en) | Missing value processing method and device in data modeling, equipment and storage medium | |
| CN112434648A (en) | Wall shape change detection method and system | |
| CN113807579A (en) | Flight arrival delay time prediction method based on machine learning | |
| CN112434653A (en) | Method and system for detecting building area by using remote sensing image |
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 |