CN108197748B - People flow prediction method based on thought evolution algorithm - Google Patents
People flow prediction method based on thought evolution algorithm Download PDFInfo
- Publication number
- CN108197748B CN108197748B CN201810015168.8A CN201810015168A CN108197748B CN 108197748 B CN108197748 B CN 108197748B CN 201810015168 A CN201810015168 A CN 201810015168A CN 108197748 B CN108197748 B CN 108197748B
- Authority
- CN
- China
- Prior art keywords
- day
- evolution algorithm
- data format
- prediction
- weather
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 230000004069 differentiation Effects 0.000 abstract description 2
- 238000009472 formulation Methods 0.000 abstract description 2
- 239000000203 mixture Substances 0.000 abstract description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000003672 processing method Methods 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a people flow prediction method based on a thought evolution algorithm, which is based on a neural network prediction model, comprehensively considers the factors influencing the people flow of a power supply business hall, takes the input data of the prediction model as the corresponding time point, the weather of the day and whether the day is a working day, and outputs the people flow prediction value at the expected time. The method optimizes the traditional neural network structure through a thinking evolution algorithm, optimizes the hidden layer weight and the threshold through convergence and differentiation operations, and reduces the prediction error caused by random generation of the hidden layer weight and the threshold, thereby constructing a prediction model with higher precision, improving the people flow prediction level of the power supply business hall and providing more accurate scientific basis for the scheme formulation of the power supply business hall for improving the self service level.
Description
Technical Field
The invention relates to a people flow prediction method, and belongs to the technical field of intelligent prediction.
Background
With the gradual introduction of the electric power enterprise business into deeper market economic environment, the improvement of the electric power marketing business by using high-quality service becomes necessary work for the current electric power enterprise to carry out daily operation and management. The power supply business hall is used as a window unit directly facing power consumers, and the quality of the service level directly influences the impression of power consumers on enterprises.
The flow of people in the power supply business hall is the core reference basis of the staffs and equipment in the power supply business hall, and is a key influence factor for the service quality of the power supply business hall. Although the traditional neural network can be used for numerical prediction of the human flow, the prediction accuracy is not high and still needs to be improved, so that a more accurate human flow prediction modeling method needs to be designed.
Disclosure of Invention
The invention aims to solve the technical problem of providing a new people flow prediction method aiming at the defects related to the background technology and improving the prediction precision.
In order to solve the technical problems, the invention adopts the following technical scheme:
a people flow prediction method based on a thought evolution algorithm comprises the following steps:
the method comprises the following steps: respectively setting a corresponding time point data format, a day weather data format and whether the data format is a working day data format;
step two: constructing a model input data feature vector:
E=[T i , W i , K i ]
whereiniThe day's weather of the moment is recordedW i Whether it is a working diaryK i Corresponding time point is recorded asT i ；
Step three: setting parameters for the thought evolution algorithm, wherein the set parameters comprise a population size, a winner sub-population, a temporary sub-population, a hidden layer and iteration times;
step four: and performing convergence operation on the thought evolution algorithm, stopping the convergence operation when the score of the temporary sub-population is lower than that of the dominant sub-population, and otherwise, continuing the convergence operation.
Step five: when the convergence operation is stopped, acquiring the optimal weight and threshold of the BP neural network;
step six: inputting historical data, training a BP neural network, and obtaining a prediction model;
step seven: and inputting the corresponding time point to be predicted, the weather of the day and whether the day is a working day into the prediction model, so that the pedestrian volume of the time point to be predicted can be obtained.
By adopting the technical scheme, the invention has the following technical effects:
the method is based on a neural network prediction model, optimizes the traditional neural network structure through a thought evolution algorithm to obtain a prediction model with higher prediction precision, improves the people flow prediction level of the power supply business hall, and provides more accurate scientific basis for the scheme formulation of the power supply business hall for improving the service level of the power supply business hall.
Drawings
FIG. 1 is a flow chart of the present invention.
Fig. 2 is a schematic diagram of the present invention.
Detailed Description
The technical scheme of the invention is further explained in detail by combining the attached drawings:
it will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The invention provides a human flow prediction modeling method based on a thought evolution algorithm. The thought evolution algorithm is an optimization algorithm which is continuously evolved through iteration, and the method can realize the optimization of a neural network prediction model: and optimizing the hidden layer weight and the threshold through convergence and differentiation operations, and reducing prediction errors caused by random generation of the hidden layer weight and the threshold, thereby constructing a prediction model with higher precision.
As shown in fig. 2, the people flow prediction modeling method based on the thought evolution algorithm comprehensively considers factors affecting the people flow of the power supply business hall, takes input data of the prediction model as corresponding time points, weather of the day and whether the day is a working day, and outputs a people flow prediction value at an expected time.
Corresponding time point data format: according to the investigation and analysis of the business handling condition, the sampling period is taken as 5 minutes. The processing method for the corresponding time point comprises the following steps: the preparation is carried out for 24 hours,Mtime of flightNIs divided intoM+NAnd/60), in 14 hours and 15 minutes, 14+15/60= 14.25.
The weather data format of the day: according to the degree of weather influence trip, the trip is divided into 5 levels, and each level is assigned with a code: (clear = 1), (cloudy = 2), (light rain = 3), (medium/light/heavy snow = 4), (heavy/heavy snow = 5), (heavy/heavy rain/snow or typhoon = 6).
Whether it is in the working day data format: working day is 1, non-working day is 0: (monday to friday = 1), (saturday/sunday = 0).
Constructing a model input data feature vector:ithe weather condition of the moment is recordedW i The working day is recordedK i The time point at this time is recorded asT i . The model input feature vector is then:
E=[T i , W i , K i ]。
and setting parameters for the thought evolution algorithm. The thought evolution algorithm is an algorithm which continuously evolves through iteration, the set of all individuals of each generation is called a group during evolution, and the group is divided into a plurality of sub-groups. The set parameters include population size, winner sub-population, temporary sub-population, hidden layer, and iteration number.
Performing convergence operation on the thought evolution algorithm (within the sub-population range, the competing process of the individuals for becoming the winner is convergence), stopping the convergence operation when the score of the temporary sub-population is lower than that of the winning sub-population, and otherwise, continuing the convergence operation.
And when the convergence operation is stopped, acquiring the optimal weight and the threshold of the BP neural network, namely the prediction model reaches the optimal structure.
And inputting historical data, training a BP neural network, and obtaining a prediction model.
And inputting the time point to be predicted, the weather of the day and whether the day is a working day into the prediction model, so that the flow of people at the expected moment of the power supply business hall can be obtained.
The model is based on a BP neural network, specifically as shown in FIG. 1, and the BP neural network structure is optimized by introducing a thought evolution algorithm, so that the prediction precision is improved.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (5)
1. A people flow prediction method based on a thought evolution algorithm is characterized by comprising the following steps:
the method comprises the following steps: respectively setting a corresponding time point data format, a day weather data format and whether the data format is a working day data format;
step two: constructing a prediction model input data feature vector:
E=[T i , W i , K i ]
whereinW i Is composed ofiWhether the day weather of the moment is a work diaryK i Corresponding time point is recorded asT i ；
Step three: setting parameters for the thought evolution algorithm, wherein the set parameters comprise a population size, a winner sub-population, a temporary sub-population, a hidden layer and iteration times;
step four: performing convergence operation on the thought evolution algorithm, stopping the convergence operation when the score of the temporary sub-population is lower than that of the dominant sub-population, and otherwise, continuing the convergence operation;
step five: when the convergence operation is stopped, acquiring the optimal weight and threshold of the BP neural network;
step six: inputting historical data, training a BP neural network, and obtaining a prediction model;
step seven: and inputting the corresponding time point to be predicted, the weather of the day and whether the day is a working day into the prediction model, so that the pedestrian volume of the time to be predicted can be obtained.
2. The method of claim 1, wherein the sampling period of the data is 5 minutes.
3. The method for predicting human traffic based on the thought evolution algorithm as claimed in claim 1, wherein the data format for the corresponding time point in the step one is: the preparation is carried out for 24 hours,Mtime of flightNIs divided intoM+N/60）。
4. The method for predicting human traffic based on the thought evolution algorithm as claimed in claim 1, wherein the data format for the weather of the day in the first step is: according to the degree of weather influence traveling, the method is divided into K levels, and each level is assigned with one code.
5. The method for predicting human traffic based on the thought evolution algorithm as claimed in claim 1, wherein the data format of whether the data format is the working day in the step one is: working days were scored as 1 and non-working days as 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810015168.8A CN108197748B (en) | 2018-01-08 | 2018-01-08 | People flow prediction method based on thought evolution algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810015168.8A CN108197748B (en) | 2018-01-08 | 2018-01-08 | People flow prediction method based on thought evolution algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108197748A CN108197748A (en) | 2018-06-22 |
| CN108197748B true CN108197748B (en) | 2020-11-24 |
Family
ID=62588213
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810015168.8A Active CN108197748B (en) | 2018-01-08 | 2018-01-08 | People flow prediction method based on thought evolution algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108197748B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111026624B (en) * | 2019-11-11 | 2023-06-02 | 国网甘肃省电力公司信息通信公司 | Fault prediction method and device of power grid information system |
| CN116822965B (en) * | 2023-08-28 | 2023-11-21 | 中铁七局集团电务工程有限公司武汉分公司 | Subway construction risk early warning method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991208A (en) * | 2017-02-28 | 2017-07-28 | 浙江工业大学 | Forecasting Methodology based on the injector performance using the BP artificial neural networks for improving mind evolutionary |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10937102B2 (en) * | 2015-12-23 | 2021-03-02 | Aetna Inc. | Resource allocation |
-
2018
- 2018-01-08 CN CN201810015168.8A patent/CN108197748B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991208A (en) * | 2017-02-28 | 2017-07-28 | 浙江工业大学 | Forecasting Methodology based on the injector performance using the BP artificial neural networks for improving mind evolutionary |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108197748A (en) | 2018-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107844915B (en) | Automatic scheduling method of call center based on traffic prediction | |
| CN108564227B (en) | Rail transit passenger flow volume prediction method based on space-time characteristics | |
| CN108734357A (en) | Weather prognosis system and method | |
| CN108197748B (en) | People flow prediction method based on thought evolution algorithm | |
| CN106600463B (en) | Local shape similarity ultra-short term load prediction method and device | |
| CN104156594B (en) | Dynamic flight station-crossing time estimation method based on Bayes network | |
| CN108539738A (en) | A kind of short-term load forecasting method promoting decision tree based on gradient | |
| CN103500365A (en) | Photovoltaic power generation power prediction method and system | |
| CN110210648B (en) | Gray long-short term memory network-based control airspace strategic flow prediction method | |
| CN106384175B (en) | A kind of electric car real-time control method based on schedulable ability | |
| CN104851051A (en) | Dynamic-modification-combined storm rainfall fine alarming method for power grid zone | |
| CN105243461A (en) | Short-term load forecasting method based on artificial neural network improved training strategy | |
| CN111325380A (en) | Method and system for determining flight passenger seat rate based on multi-granularity time attention mechanism | |
| CN103002165B (en) | Method for predicting short-term telephone traffic of power supply service center | |
| CN117410981A (en) | Multi-region electric power energy intelligent scheduling method and system based on big data | |
| CN113537596B (en) | Short-time passenger flow prediction method for new line station of urban rail transit | |
| Wang | The short-term passenger flow forecasting of urban rail transit based on holt-winters' seasonal method | |
| CN110533220A (en) | A kind of airport departure from port delay distribution method for digging of data-driven | |
| CN110533480A (en) | A kind of market passenger flow forecasting based on big data | |
| CN117909888A (en) | Intelligent artificial intelligence climate prediction method | |
| CN109685242B (en) | Photovoltaic ultra-short term combined prediction method based on Adaboost algorithm | |
| CN116227738B (en) | Method and system for predicting traffic interval of power grid customer service | |
| CN116865232A (en) | Wind speed error correction-based medium-and-long-term wind power prediction method and system | |
| CN114358667A (en) | Scenic spot risk prediction model construction method based on RBF (radial basis function) network learning | |
| CN115526398A (en) | Attention mechanism-based charging load prediction method for charging station |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |