CN111612223A - Population employment distribution prediction method and device based on land and traffic multi-source data - Google Patents

Population employment distribution prediction method and device based on land and traffic multi-source data Download PDF

Info

Publication number
CN111612223A
CN111612223A CN202010372082.8A CN202010372082A CN111612223A CN 111612223 A CN111612223 A CN 111612223A CN 202010372082 A CN202010372082 A CN 202010372082A CN 111612223 A CN111612223 A CN 111612223A
Authority
CN
China
Prior art keywords
employment
traffic
data
population
year
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010372082.8A
Other languages
Chinese (zh)
Other versions
CN111612223B (en
Inventor
钟鸣
任智
崔革
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan University of Technology WUT
Original Assignee
Wuhan University of Technology WUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan University of Technology WUT filed Critical Wuhan University of Technology WUT
Priority to CN202010372082.8A priority Critical patent/CN111612223B/en
Publication of CN111612223A publication Critical patent/CN111612223A/en
Application granted granted Critical
Publication of CN111612223B publication Critical patent/CN111612223B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • 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
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a population and employment distribution prediction method and device based on land and traffic multi-source data, and belongs to the technical field of traffic. The realization method comprises the following steps: calculating the per capita space ratio according to the population and employment data of the reference year and the classified building area data of the reference year; calculating reachability data of the traffic community according to travel time and traveling expenses; acquiring standard year classified building rate data, planned year classified building area data, planned year population and employment data; establishing a population and employment distribution model; calibrating parameters of population and employment distribution models according to per-capita space ratio, accessibility data, classified building room price data, population and employment data of reference years and planning years and classified building area data; and predicting the population and employment distribution in the future year according to the calibrated population and employment distribution model. The invention systematically considers land utilization and traffic accessibility at the traffic community level to accurately predict the future population and employment change trend.

Description

Population employment distribution prediction method and device based on land and traffic multi-source data
Technical Field
The invention belongs to the technical field of traffic, and particularly relates to a population and employment distribution prediction method and device based on land and traffic multi-source data.
Background
Along with the rapid development of economy and the continuous promotion of urbanization, urban population and employment are rapidly increased. This not only causes the imbalance of city expansion and land utilization, but also causes the problems of traffic jam, traffic accident and environmental pollution. However, mastering the urban population and employment change trend is a premise of land utilization planning, traffic planning and traffic management, and if the distribution situation of the urban traffic community population and employment in the future can not be accurately predicted, the problems of land utilization, traffic jam, traffic accidents, environmental pollution and the like can not be fundamentally solved.
Traditional population and employment distribution data are mainly obtained through population and economic census, which consumes a great deal of time, manpower and material resources. In addition, the population census of China is performed once every ten years, the economic census is performed once every five years, and the cycle interval time of the census is too long to meet the requirement of acquiring population and employment distribution conditions of a certain future year. Moreover, the census in the prior art is totally dependent on manpower and cannot be realized by technical means.
With the increasing development of Geographic Information System (GIS) and Remote Sensing (RS) technologies, studies for calculating population and employment data by using GIS and RS data are increasing. However, the levels of these studies are generally macroscopic and do not systematically take into account the impact of land use, traffic accessibility, on population and employment. On one hand, the actual conditions of population and employment cannot be reflected; on the other hand, it is difficult to capture dynamic changes of population and employment distribution, and technical support cannot be provided for population mobility management and planning at the traffic cell level.
Population and employment distribution greatly influence population flow among traffic districts, and if the population and employment distribution cannot be scientifically predicted, congestion is inevitably caused in the peak period of population flow, so that serious potential safety hazards exist. The existing traffic guidance technology, such as the realization of various navigation APPs on congestion phenomena and path planning, mainly judges whether traffic is congested in real time based on the acquisition of GPS signals of a mobile phone, so that a route with light congestion is screened and added into recommended navigation. The method only relies on real-time data acquisition to calculate the traffic population distribution, and does not have the function of advance and accurate prediction; in addition, users tend to walk non-blocking routes recommended by the APP, so that the traffic congestion is caused at the traffic peak, and originally non-blocking roads are also blocked. Therefore, the situation that the user is blocked on a half road after changing the route according to the navigation often occurs, and the user is not beneficial to going out and traffic dispersion.
If a technical means can be provided, population and employment distribution on the traffic cell level can be accurately predicted, corresponding changes can be made to control of traffic signals and path induction in navigation software in advance, scientific and dynamic real-time management of population flow between traffic cells is further realized, traffic jam is reduced, and potential safety hazards are reduced.
Disclosure of Invention
Aiming at the defects or improvement requirements of the prior art, the invention provides a population and employment distribution prediction method and device based on land and traffic multi-source data, and the land utilization and traffic accessibility are systematically considered at the traffic community level to accurately predict the future population and employment change trend.
To achieve the above object, according to one aspect of the present invention, there is provided a population and employment distribution prediction method based on land and traffic multi-source data, comprising:
s1: calculating the per-capita occupation space rate according to population and employment data of each traffic cell in the reference year and classified building area data of each traffic cell in the reference year;
s2: calculating traffic cell reachability data according to travel time and traveling expenses among traffic cells, wherein the traffic cell reachability data is used for expressing the convenience degree of arriving at the traffic cells;
s3: acquiring classified building rate data of each traffic cell in a reference year, classified building area data of each traffic cell in a planning year and population and employment data of each traffic cell in the planning year;
s4: establishing a population and employment distribution model;
s5: carrying out parameter calibration on the population and employment distribution model according to the per-capita space ratio, the reachability data, the classified building rate data of each traffic cell of the reference year, the population and employment data of each traffic cell of the planning year and the classified building area data of each traffic cell of the planning year;
s6: and predicting the population and employment distribution in the future year according to the calibrated population and employment distribution model.
Preferably, step S1 includes:
s1.1: acquiring population and employment data of each traffic cell in a reference year, wherein the employment data comprises commercial finance, industrial warehousing, administrative office, educational scientific research, public service and other employment data;
s1.2: obtaining classified building area data of each traffic cell of a reference year, wherein the building area data comprises: residential, commercial finance, industrial warehousing, administrative offices, educational research, public services, and other building area data;
s1.3: calculating the occupied space ratio of the residents according to the population data of each traffic cell in the reference year and the residential building area data of each traffic cell in the reference year:
Figure BDA0002478704190000031
Figure BDA0002478704190000032
wherein ,SUreThe occupied space ratio of all the residents is obtained, N is the total number of the traffic districts,
Figure BDA0002478704190000033
for the residential building area of the reference year traffic cell i,
Figure BDA0002478704190000034
is the population of the traffic cell i of the benchmark year;
s1.4: according to the baseAnd calculating the employment occupation space rate of each employment person according to employment data of each traffic district in the quasi-year and the employment building area data of each traffic district in the reference year:
Figure BDA0002478704190000035
Figure BDA0002478704190000036
wherein ,
Figure BDA0002478704190000037
the occupation space rate of the kth employment people is, N is the total number of traffic districts,
Figure BDA0002478704190000038
is the area of the k-th employment of the traffic district i of the reference year,
Figure BDA0002478704190000039
is the employment quantity of the kth employment of the traffic community i of the benchmark year.
Preferably, step S2 includes: by
Figure BDA00024787041900000310
Deducing traffic cell reachability, wherein ACiFor accessibility of traffic cell i, TIijmTravel time, FA, required for using the transportation means m from the transportation cell i to the transportation cell jijmThe driving cost for using the traffic mode M from the traffic cell i to the traffic cell j, N is the total number of the traffic cells, M is the number of the traffic modes, a1、a2Are the corresponding tuning parameters.
Preferably, step S3 includes:
s3.1: obtaining classified building rate data of each traffic cell in a reference year, wherein the classified building rate data comprises residential, commercial and financial, industrial warehousing, administrative office, educational scientific research, public service and other building rate data;
s3.2: obtaining classified building area data of each traffic cell in a planning year, wherein the classified building area data comprises residential, commercial and financial, industrial warehousing, administrative office, educational scientific research, public service and other building area data;
s3.3: and acquiring population and employment data of each traffic cell in the planning year, wherein the employment data comprises commercial finance, industrial warehousing, administrative office, educational scientific research, public service and other employment data.
Preferably, step S4 includes:
s4.1: the population distribution model is:
Figure BDA0002478704190000041
wherein ,
Figure BDA0002478704190000042
to plan the population of the annual traffic cell i,
Figure BDA0002478704190000043
is the population of the traffic cell i of the reference year,
Figure BDA0002478704190000044
to plan the residential building area of the annual traffic sector i,
Figure BDA0002478704190000045
is the residential building area of the year-based traffic district i, SUreOccupancy of space for the average resident, ACiFor the reachability of the traffic cell i,
Figure BDA0002478704190000046
residential building rates, AR, for traffic districts iplTo plan the total area of the residential building of the year, ARbaIs the total area of the residential buildings of the reference year, N is the total number of the traffic districts, b1、b2、b3Corresponding parameters to be calibrated;
s4.2: the employment distribution model is as follows:
Figure BDA0002478704190000051
wherein ,
Figure BDA0002478704190000052
to plan the employment volume of the annual traffic sector i,
Figure BDA0002478704190000053
for the employment amount of the traffic cell i of the reference year,
Figure BDA0002478704190000054
to plan the area of the buildings in the kth employment of the annual traffic sector i,
Figure BDA0002478704190000055
is the area of the k-th employment of the traffic district i of the reference year,
Figure BDA0002478704190000056
average occupancy of space for k-th employment, ACiFor the reachability of the traffic cell i,
Figure BDA0002478704190000057
the building rate of the kth employment of the traffic community i,
Figure BDA0002478704190000058
to plan the total area of buildings for the kth employment of the year,
Figure BDA0002478704190000059
the total area of the K-th employment of the benchmark year, N is the total number of traffic districts, K is the number of employment types, c1、c2、c3And the parameters are corresponding to be calibrated.
Preferably, step S5 includes:
s5.1: converting the population and employment distribution model into an objective function by using a genetic algorithm, and setting related constraints;
s5.2: and respectively substituting the reachability data, the classified building rate data, the standard year, the planning year population and employment data, the classified building area data and the per-capita space ratio of each traffic cell into the objective function to obtain the calibration values of the parameters.
Preferably, step S6 includes:
and respectively inputting the per-capita space rate, the accessibility data, the classified building room price data, the reference year population and employment data and the reference year and future year classified building area data into the calibrated population and employment distribution model, and predicting the future year population and employment distribution condition.
According to another aspect of the present invention, there is provided a population and employment distribution prediction apparatus based on land and traffic multi-source data, comprising:
the average occupied space rate calculating module is used for calculating the average occupied space rate according to population and employment data of each traffic cell in the reference year and classified building area data of each traffic cell in the reference year;
the system comprises a reachability calculation module, a traffic cell reachability calculation module and a traffic cell reachability calculation module, wherein the reachability calculation module is used for calculating reachability data of the traffic cells according to travel time and traveling expenses among the traffic cells, and the reachability data is used for expressing convenience degree of arriving at the traffic cells;
the data acquisition module is used for acquiring classified building rate data of each traffic cell in a reference year, classified building area data of each traffic cell in a planning year and population and employment data of each traffic cell in the planning year;
the distribution model building module is used for building a population and employment distribution model;
the calibration module is used for carrying out parameter calibration on the population and employment distribution model according to the per-capita space ratio, the reachability data, the classified building room price data of each traffic cell of the reference year, the population and employment data of each traffic cell of the planning year and the classified building area data of each traffic cell of the planning year;
and the prediction module is used for predicting the population and employment distribution in the future year according to the calibrated population and employment distribution model.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects: the invention fully considers the influence of land utilization and traffic accessibility, utilizes population and employment data, classified building area data, accessibility data and classified building price data to construct a population and employment distribution model based on multi-source data, carries out parameter calibration on the population and employment distribution model through real data, and finally obtains the population and employment distribution model to realize population and employment distribution prediction.
Drawings
FIG. 1 is a schematic flow chart of a method for predicting the employment distribution of a population based on land and traffic multi-source data according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of an embodiment of calibrating population and employment distribution model parameters using a genetic algorithm according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Fig. 1 is a schematic flow chart of a population and employment distribution prediction method based on land and traffic multi-source data according to an embodiment of the present invention, which includes the following steps:
s1: calculating the per capita space ratio according to the population and employment data of the reference year and the classified building area data of the reference year;
in the embodiment of the present invention, in step S1, the method for calculating the per-capita space ratio according to the reference year population, employment data and the reference year classified building area data specifically includes the following steps:
s1.1: acquiring population and employment data of each traffic cell in a benchmark year;
the reference year should be a year from the historical years according to the availability of data, but it is not preferable that the reference year is too long, and 2008 may be selected as the reference year in the embodiment of the present invention. The employment data may be classified into business finance, industrial warehousing, administrative office, educational scientific research, public service, and other employment data according to the type of employment, wherein the other employment data represents remaining employment data except for the business finance, industrial warehousing, administrative office, educational scientific research, and public service.
The method comprises the steps of drawing a traffic cell map layer and calculating the area of each traffic cell in a reference year through a GIS technology, and combining population and employment data of each administrative area in a statistical yearbook to obtain population and various employment data in each traffic cell in the reference year.
S1.2: acquiring classified building area data of each traffic cell in a reference year;
the classified building area data and the population and employment data correspond to each other and can be divided into residential, commercial finance, industrial warehousing, administrative office, educational scientific research, public service and other building area data, wherein the other building area data represent the remaining building area data except for residential, commercial finance, industrial warehousing, administrative office, educational scientific research and public service.
And performing superposition analysis on the building map layer and the land utilization map layer of the reference year by using a GIS technology, so as to obtain the classified building area data of each traffic cell of the reference year.
S1.3: calculating the occupied space ratio of the residents according to population data of each traffic cell in the reference year and residential building area data of each traffic cell in the reference year;
the occupied space ratio of the residents is the concept of how much residential building space each resident occupies, and is equal to the quotient of the residential building area and the corresponding population, as shown in the following formula:
Figure BDA0002478704190000081
wherein ,SUreThe occupied space ratio of all the residents is obtained, N is the total number of the traffic districts,
Figure BDA0002478704190000082
for the residential building area of the reference year traffic cell i,
Figure BDA0002478704190000083
is the population of the traffic cell i of the benchmark year.
S1.4: calculating the occupation space rate of employment people according to employment data of each traffic district in the reference year and employment building area data of each traffic district in the reference year;
wherein, the per employment occupation space rate is the concept of how much corresponding employment building space each kind of employment post occupies, and it is equal to the quotient of each kind of employment building area and corresponding employment amount, as shown in the following formula:
Figure BDA0002478704190000084
wherein ,
Figure BDA0002478704190000085
the occupation space rate of the kth employment people is, N is the total number of traffic districts,
Figure BDA0002478704190000086
is the area of the k-th employment of the traffic district i of the reference year,
Figure BDA0002478704190000087
is the employment quantity of the kth employment of the traffic community i of the benchmark year.
The employment data of each traffic cell related in the embodiment of the present invention includes six types of business finance, industrial warehousing, administrative office, educational scientific research, public service and other employment data, and the classified building area data includes seven types of residential, business finance, industrial warehousing, administrative office, educational scientific research, public service and other building area data, and it should be understood that the division of the employment data and the building area data is not limited to the types listed in the embodiment of the present invention, and may also include other more detailed divisions.
S2: calculating traffic cell reachability data according to travel time and traveling expenses, wherein the traffic cell reachability data is used for expressing the convenience degree of arriving at a traffic cell;
in the embodiment of the present invention, in step S2, the reachability data of the transportation cell is calculated according to the travel time and the traveling cost, which may be specifically implemented by:
s2.1: acquiring travel time and traveling expenses among traffic districts;
where travel time between traffic cells represents the time spent from one traffic cell to another. Taking private car travel as an example, a road network Map layer is acquired in an Open Street Map through a GIS technology, the travel distance between traffic cells can be acquired by combining a traffic cell mass center Map layer, and the travel time between traffic cells can be acquired by setting the average travel speed.
Where the driving cost between traffic cells is the cost spent from one traffic cell to another. Taking private car travel as an example, on the basis of travel distance between traffic districts, the driving cost between the traffic districts can be obtained through oil consumption per kilometer.
S2.2: calculating the accessibility of the traffic cell according to the travel time and the traveling expense;
wherein, accessibility is the convenience of reaching a location through the transportation system, as shown in the following formula:
Figure BDA0002478704190000091
wherein ,ACiFor accessibility of traffic cell i, TIijmTravel time, FA, required for using the transportation means m from the transportation cell i to the transportation cell jijmThe driving cost for using the traffic mode M from the traffic cell i to the traffic cell j, N is the total number of the traffic cells, M is the number of the traffic modes, a1、a2In the embodiment of the present invention, a is preferably selected for adjusting the parameters accordingly1Is 0.02, a2Is 0.039.
S3: acquiring standard year classified building rate data, planned year classified building area data, planned year population and employment data;
in the embodiment of the present invention, in step S3, obtaining reference year classified building rate data, planned year classified building area data, planned year population and employment data may specifically be implemented by:
s3.1: acquiring building rate data of each traffic cell classification in a reference year;
the classified building rate data corresponds to population and employment data, and comprises residential, commercial finance, industrial warehousing, administrative office, educational scientific research, public service and other building rate data, wherein the other building rate data represents the rest building rate data except for residential, commercial finance, industrial warehousing, administrative office, educational scientific research and public service.
The building rate data of each traffic cell of the reference year can be obtained by clustering and counting the building rate of the reference year according to the traffic cells through a GIS technology.
S3.2: acquiring classified building area data of each traffic cell in a planning year;
wherein, a planned year should be a certain year after the reference year according to actual needs and data support, and 2013 is selected as the planned year in the embodiment of the present invention. The classified building area data of each traffic cell in the planning year is consistent with the classified building area data of each traffic cell in the reference year in type, and comprises residential, commercial finance, industrial warehousing, administrative office, educational scientific research, public service and other building area data, wherein the other building area data represent the residual building area data except the residential, commercial finance, industrial warehousing, administrative office, educational scientific research and public service.
And performing superposition analysis on the building map layer and the land utilization map layer in the planning year by using a GIS technology, so as to obtain the classified building area data of each traffic cell in the planning year.
S3.3: acquiring population and employment data of each traffic cell in a planning year;
the planning year traffic cell population and employment data and the reference year traffic cell population and employment data are kept consistent in type, the planning year traffic cell population and employment data comprise business finance, industrial warehousing, administrative office, educational scientific research, public service and other employment data, and the other employment data represent the remaining employment data except the business finance, industrial warehousing, administrative office, educational scientific research and public service.
The area of each traffic cell in the planning year is calculated through a GIS technology, and population and employment data of each traffic cell in the planning year can be obtained by combining population and employment data of each administrative region in the statistical yearbook.
S4: establishing a population and employment distribution model;
in the embodiment of the present invention, in step S4, the established population and employment distribution model is:
s4.1: establishing a population distribution model as shown in the following formula:
Figure BDA0002478704190000111
wherein ,
Figure BDA0002478704190000112
to plan the population of the annual traffic cell i,
Figure BDA0002478704190000113
is the population of the traffic cell i of the reference year,
Figure BDA0002478704190000114
to plan the residential building area of the annual traffic sector i,
Figure BDA0002478704190000115
is the residential building area of the year-based traffic district i, SUreOccupancy of space for the average resident, ACiFor the reachability of the traffic cell i,
Figure BDA0002478704190000116
residential building rates, AR, for traffic districts iplTo plan the total area of the residential building of the year, ARbaIs the total area of the residential buildings of the reference year, N is the total number of the traffic districts, b1、b2、b3And the parameters are corresponding to be calibrated.
S4.2: establishing a employment distribution model as shown in the following formula:
Figure BDA0002478704190000117
wherein ,
Figure BDA0002478704190000118
to plan the employment volume of the annual traffic sector i,
Figure BDA0002478704190000119
for the employment amount of the traffic cell i of the reference year,
Figure BDA00024787041900001110
to plan the area of the buildings in the kth employment of the annual traffic sector i,
Figure BDA00024787041900001111
is the area of the k-th employment of the traffic district i of the reference year,
Figure BDA00024787041900001112
average occupancy of space for k-th employment, ACiFor the reachability of the traffic cell i,
Figure BDA00024787041900001113
the building rate of the kth employment of the traffic community i,
Figure BDA00024787041900001114
to plan the total area of buildings for the kth employment of the year,
Figure BDA00024787041900001115
the total area of the K-th employment of the benchmark year, N is the total number of traffic districts, K is the number of employment types, c1、c2、c3And the parameters are corresponding to be calibrated.
S5: calibrating parameters of population and employment distribution models according to per-capita space ratio, accessibility data, classified building room price data, population and employment data of reference years and planning years and classified building area data;
in the embodiment of the present invention, in step S5, the population and employment distribution model is subjected to parameter calibration according to the per-capita space ratio, the reachability data, the classified building room price data, the benchmark year and planned year population and employment data, and the classified building area data, as shown in fig. 2, the specific method is as follows:
s5.1: transforming population and employment distribution models into objective functions by using a genetic algorithm, and setting related constraints;
in order to conveniently calibrate parameters in the population distribution model, the population distribution model is converted into an objective function, which is shown as the following formula:
Figure BDA0002478704190000121
calling a getpy genetic algorithm module in Python, and setting related constraints as follows:
in the embodiment of the invention, the target dimension is set to be 1, the decision variable dimension is set to be 3, and the parameter b1Has an upper limit of 1 and a lower limit of 0, and a parameter b2、b3Has an upper limit of 10 and a lower limit of 0, and a parameter b1、b2、b3The upper limit of (1) is a closed interval, the lower limit is an open interval, and the feasibility rule is adoptedAnd (4) physical constraint, namely enabling the objective function value to be less than or equal to 0.001, enabling the coding mode to be real integer coding, selecting the probability as a default value, the cross probability as a default value, the mutation probability as a default value, enabling the population scale to be 50 and enabling the maximum evolution algebra to be 200.
To facilitate calibrating the parameters in the employment distribution model, the employment distribution model is converted into an objective function, as shown in the following formula:
Figure BDA0002478704190000131
calling a getpy genetic algorithm module in Python, and setting related constraints as follows:
in the embodiment of the invention, the target dimension is set to be 1, the decision variable dimension is set to be 3, and the parameter c1Has an upper limit of 1 and a lower limit of 0, and a parameter c2、c3Has an upper limit of 10 and a lower limit of 0, and a parameter c1、c2、c3The upper limit of the target function value is a closed interval, the lower limit of the target function value is an open interval, the feasibility rule is adopted to process constraint, the target function value is less than or equal to 0.001, the coding mode is real integer coding, the selection probability is a default value, the cross probability is a default value, the variation probability is a default value, the population scale is 50, and the maximum evolution algebra is 200.
S5.2: respectively substituting reachability data, classified building room price data, population and employment data of the reference year and the planning year, classified building area data and per-capita space ratio of each traffic cell into target functions of the population distribution model and the employment distribution model, solving the target functions of the population distribution model and the employment distribution model through a genetic algorithm, finding out an individual with the target function value of the population distribution model and the employment distribution model being minimum, and obtaining an optimal parameter calibration value b of the population distribution model1、b2、b3And optimal parameter values c of employment distribution model1、c2、c3。
S6: and predicting the population and employment distribution in the future year according to the calibrated population and employment distribution model.
In the embodiment of the present invention, in step S6, the population and employment distribution in the future year is predicted according to the calibrated population and employment distribution model, and the specific method is as follows:
and respectively inputting the per-capita space rate, the accessibility data, the classified building room price data, the reference year population and employment data and the reference year and future year classified building area data into the calibrated population and employment distribution model, so that the future year population and employment distribution condition can be predicted.
Fig. 3 is a schematic structural diagram of an apparatus according to an embodiment of the present invention, including:
the average occupied space ratio calculating module 301 is used for calculating the average occupied space ratio according to population and employment data of each traffic cell in the reference year and classified building area data of each traffic cell in the reference year;
a reachability calculation module 302, configured to calculate reachability data of traffic cells according to travel time and traveling cost between the traffic cells, where the reachability data is used to indicate convenience degree of reaching the traffic cells;
the data acquisition module 303 is configured to acquire classified building rate data of each traffic cell in the reference year, classified building area data of each traffic cell in the planning year, and population and employment data of each traffic cell in the planning year;
a distribution model building module 304, configured to build a population and employment distribution model;
a calibration module 305, configured to perform parameter calibration on the population and employment distribution model according to the per-capita space ratio, the reachability data, the classified building rate data of each traffic cell in the reference year, the population and employment data of each traffic cell in the planning year, and the classified building area data of each traffic cell in the planning year;
and the prediction module 306 is used for predicting the population and employment distribution in the future year according to the calibrated population and employment distribution model.
The specific implementation of each module may refer to the description of the above method embodiment, and the embodiment of the present invention will not be repeated.
It should be noted that, according to the implementation requirement, each step/component described in the present application can be divided into more steps/components, and two or more steps/components or partial operations of the steps/components can be combined into new steps/components to achieve the purpose of the present invention.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (8)

1. A population and employment distribution prediction method based on land and traffic multi-source data is characterized by comprising the following steps:
s1: calculating the per-capita occupation space rate according to population and employment data of each traffic cell in the reference year and classified building area data of each traffic cell in the reference year;
s2: calculating traffic cell reachability data according to travel time and traveling expenses among traffic cells, wherein the traffic cell reachability data is used for expressing the convenience degree of arriving at the traffic cells;
s3: acquiring classified building rate data of each traffic cell in a reference year, classified building area data of each traffic cell in a planning year and population and employment data of each traffic cell in the planning year;
s4: establishing a population and employment distribution model;
s5: carrying out parameter calibration on the population and employment distribution model according to the per-capita space ratio, the reachability data, the classified building rate data of each traffic cell of the reference year, the population and employment data of each traffic cell of the planning year and the classified building area data of each traffic cell of the planning year;
s6: and predicting the population and employment distribution in the future year according to the calibrated population and employment distribution model.
2. The method according to claim 1, wherein step S1 includes:
s1.1: acquiring population and employment data of each traffic cell in a reference year, wherein the employment data comprises commercial finance, industrial warehousing, administrative office, educational scientific research, public service and other employment data;
s1.2: obtaining classified building area data of each traffic cell of a reference year, wherein the building area data comprises: residential, commercial finance, industrial warehousing, administrative offices, educational research, public services, and other building area data;
s1.3: calculating the occupied space ratio of the residents according to the population data of each traffic cell in the reference year and the residential building area data of each traffic cell in the reference year:
Figure FDA0002478704180000011
Figure FDA0002478704180000021
wherein ,SUreThe occupied space ratio of all the residents is obtained, N is the total number of the traffic districts,
Figure FDA0002478704180000022
for the residential building area of the reference year traffic cell i,
Figure FDA0002478704180000023
is the population of the traffic cell i of the benchmark year;
s1.4: calculating the occupation space ratio of employment people according to the employment data of each traffic district in the reference year and the employment building area data of each traffic district in the reference year:
Figure FDA0002478704180000024
Figure FDA0002478704180000025
wherein ,
Figure FDA0002478704180000026
the occupation space rate of the kth employment people is, N is the total number of traffic districts,
Figure FDA0002478704180000027
is the area of the k-th employment of the traffic district i of the reference year,
Figure FDA0002478704180000028
is the employment quantity of the kth employment of the traffic community i of the benchmark year.
3. The method according to claim 2, wherein step S2 includes: by
Figure FDA0002478704180000029
Deducing traffic cell reachability, wherein ACiFor accessibility of traffic cell i, TIijmTravel time, FA, required for using the transportation means m from the transportation cell i to the transportation cell jijmThe driving cost for using the traffic mode M from the traffic cell i to the traffic cell j, N is the total number of the traffic cells, M is the number of the traffic modes, a1、a2Are the corresponding tuning parameters.
4. The method according to claim 2 or 3, wherein step S3 includes:
s3.1: obtaining classified building rate data of each traffic cell in a reference year, wherein the classified building rate data comprises residential, commercial and financial, industrial warehousing, administrative office, educational scientific research, public service and other building rate data;
s3.2: obtaining classified building area data of each traffic cell in a planning year, wherein the classified building area data comprises residential, commercial and financial, industrial warehousing, administrative office, educational scientific research, public service and other building area data;
s3.3: and acquiring population and employment data of each traffic cell in the planning year, wherein the employment data comprises commercial finance, industrial warehousing, administrative office, educational scientific research, public service and other employment data.
5. The method according to claim 4, wherein step S4 includes:
s4.1: the population distribution model is:
Figure FDA0002478704180000031
wherein ,
Figure FDA0002478704180000032
to plan the population of the annual traffic cell i,
Figure FDA0002478704180000033
is the population of the traffic cell i of the reference year,
Figure FDA0002478704180000034
to plan the residential building area of the annual traffic sector i,
Figure FDA0002478704180000035
is the residential building area of the year-based traffic district i, SUreOccupancy of space for the average resident, ACiFor the reachability of the traffic cell i,
Figure FDA0002478704180000036
residential building rates, AR, for traffic districts iplTo plan the total area of the residential building of the year, ARbaIs the total area of the residential buildings of the reference year, N is the total number of the traffic districts, b1、b2、b3Corresponding parameters to be calibrated;
s4.2: the employment distribution model is as follows:
Figure FDA0002478704180000037
wherein ,
Figure FDA0002478704180000038
to plan the employment volume of the annual traffic sector i,
Figure FDA0002478704180000039
for the employment amount of the traffic cell i of the reference year,
Figure FDA00024787041800000310
to plan the area of the buildings in the kth employment of the annual traffic sector i,
Figure FDA00024787041800000311
is the area of the k-th employment of the traffic district i of the reference year,
Figure FDA00024787041800000312
average occupancy of space for k-th employment, ACiFor the reachability of the traffic cell i,
Figure FDA00024787041800000313
the building rate of the kth employment of the traffic community i,
Figure FDA00024787041800000314
to plan the total area of buildings for the kth employment of the year,
Figure FDA00024787041800000315
the total area of the K-th employment of the benchmark year, N is the total number of traffic districts, K is the number of employment types, c1、c2、c3And the parameters are corresponding to be calibrated.
6. The method according to claim 5, wherein step S5 includes:
s5.1: converting the population and employment distribution model into an objective function by using a genetic algorithm, and setting related constraints;
s5.2: and respectively substituting the reachability data, the classified building rate data, the standard year, the planning year population and employment data, the classified building area data and the per-capita space ratio of each traffic cell into the objective function to obtain the calibration values of the parameters.
7. The method according to claim 6, wherein step S6 includes:
and respectively inputting the per-capita space rate, the accessibility data, the classified building room price data, the reference year population and employment data and the reference year and future year classified building area data into the calibrated population and employment distribution model, and predicting the future year population and employment distribution condition.
8. A population and employment distribution prediction apparatus based on land and traffic multisource data, comprising:
the average occupied space rate calculating module is used for calculating the average occupied space rate according to population and employment data of each traffic cell in the reference year and classified building area data of each traffic cell in the reference year;
the system comprises a reachability calculation module, a traffic cell reachability calculation module and a traffic cell reachability calculation module, wherein the reachability calculation module is used for calculating reachability data of the traffic cells according to travel time and traveling expenses among the traffic cells, and the reachability data is used for expressing convenience degree of arriving at the traffic cells;
the data acquisition module is used for acquiring classified building rate data of each traffic cell in a reference year, classified building area data of each traffic cell in a planning year and population and employment data of each traffic cell in the planning year;
the distribution model building module is used for building a population and employment distribution model;
the calibration module is used for carrying out parameter calibration on the population and employment distribution model according to the per-capita space ratio, the reachability data, the classified building room price data of each traffic cell of the reference year, the population and employment data of each traffic cell of the planning year and the classified building area data of each traffic cell of the planning year;
and the prediction module is used for predicting the population and employment distribution in the future year according to the calibrated population and employment distribution model.
CN202010372082.8A 2020-05-06 2020-05-06 Population employment distribution prediction method and device based on land and traffic multisource data Active CN111612223B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010372082.8A CN111612223B (en) 2020-05-06 2020-05-06 Population employment distribution prediction method and device based on land and traffic multisource data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010372082.8A CN111612223B (en) 2020-05-06 2020-05-06 Population employment distribution prediction method and device based on land and traffic multisource data

Publications (2)

Publication Number Publication Date
CN111612223A true CN111612223A (en) 2020-09-01
CN111612223B CN111612223B (en) 2023-05-02

Family

ID=72201870

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010372082.8A Active CN111612223B (en) 2020-05-06 2020-05-06 Population employment distribution prediction method and device based on land and traffic multisource data

Country Status (1)

Country Link
CN (1) CN111612223B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112954623A (en) * 2021-02-02 2021-06-11 苏州丽景智行交通工程咨询有限公司 Resident occupancy rate estimation method based on mobile phone signaling big data
CN113393353A (en) * 2021-06-11 2021-09-14 中国测绘科学研究院 Building commuting population estimation method based on IC card data and storage medium thereof
CN117252404A (en) * 2023-11-20 2023-12-19 武汉市规划研究院 Method and system for measuring and calculating population and post scale of city updating unit

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2008201962A1 (en) * 2008-05-02 2009-11-19 Lend Lease Corporation Limited Computational apparatus and method for modelling employment
JP2012160143A (en) * 2011-02-03 2012-08-23 Nippon Telegr & Teleph Corp <Ntt> Future population prediction device, method, and program
US8346586B1 (en) * 2006-05-02 2013-01-01 Macroeconomic Advisers, LLC Systems and methods for estimating employment levels
CN110222886A (en) * 2019-05-28 2019-09-10 东南大学 A kind of commercial building by when density of personnel prediction technique
CN110222959A (en) * 2019-05-23 2019-09-10 河南大学 A kind of urban employment accessibility measuring method and system based on big data
CN110309952A (en) * 2019-05-28 2019-10-08 同济大学 A kind of urban employment spatial configuration optimal auxiliary system based on commuting model

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8346586B1 (en) * 2006-05-02 2013-01-01 Macroeconomic Advisers, LLC Systems and methods for estimating employment levels
AU2008201962A1 (en) * 2008-05-02 2009-11-19 Lend Lease Corporation Limited Computational apparatus and method for modelling employment
JP2012160143A (en) * 2011-02-03 2012-08-23 Nippon Telegr & Teleph Corp <Ntt> Future population prediction device, method, and program
CN110222959A (en) * 2019-05-23 2019-09-10 河南大学 A kind of urban employment accessibility measuring method and system based on big data
CN110222886A (en) * 2019-05-28 2019-09-10 东南大学 A kind of commercial building by when density of personnel prediction technique
CN110309952A (en) * 2019-05-28 2019-10-08 同济大学 A kind of urban employment spatial configuration optimal auxiliary system based on commuting model

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
郭莉等: "基于土地利用的人口岗位分布预测研究" *
钱振伟,刘丽华: "就业增长测度模型构建及实证研究――以云南省就业状况为例" *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112954623A (en) * 2021-02-02 2021-06-11 苏州丽景智行交通工程咨询有限公司 Resident occupancy rate estimation method based on mobile phone signaling big data
CN113393353A (en) * 2021-06-11 2021-09-14 中国测绘科学研究院 Building commuting population estimation method based on IC card data and storage medium thereof
CN113393353B (en) * 2021-06-11 2022-03-22 中国测绘科学研究院 Building commuting population estimation method based on IC card data and storage medium thereof
CN117252404A (en) * 2023-11-20 2023-12-19 武汉市规划研究院 Method and system for measuring and calculating population and post scale of city updating unit
CN117252404B (en) * 2023-11-20 2024-02-23 武汉市规划研究院 Method and system for measuring and calculating population and post scale of city updating unit

Also Published As

Publication number Publication date
CN111612223B (en) 2023-05-02

Similar Documents

Publication Publication Date Title
Li et al. The varying patterns of rail transit ridership and their relationships with fine-scale built environment factors: Big data analytics from Guangzhou
CN109978224B (en) Method for analyzing and acquiring traffic trip rates of buildings with different properties
CN111612223B (en) Population employment distribution prediction method and device based on land and traffic multisource data
Shen et al. Optimized public parking location modelling for green intelligent transportation system using genetic algorithms
Li et al. Explore the recreational service of large urban parks and its influential factors in city clusters–Experiments from 11 cities in the Beijing-Tianjin-Hebei region
CN106408984B (en) Urban traffic flow induction system based on Internet of things
CN113112068A (en) Method and system for addressing and layout of public facilities in villages and small towns
Qu et al. Location optimization for urban taxi stands based on taxi GPS trajectory big data
CN114548811B (en) Airport reachability detection method and device, electronic equipment and storage medium
CN113222271B (en) Medium and small airport site selection layout method under comprehensive transportation system
CN112288311A (en) Convenient and fast residential area supporting facility metering method based on POI data
CN113868492A (en) Visual OD (origin-destination) analysis method based on electric police and checkpoint data and application
Aydinoglu et al. Determining parking demand and locating parking areas using geographic analytics methods
CN111009140A (en) Intelligent traffic signal control method based on open-source road condition information
CN110288125A (en) It is a kind of based on the commuting method for establishing model of mobile phone signaling data and application
CN106980942A (en) Calculate method of the bicycle free way to the coverage of public bicycles lease point
Zhu et al. The impact of road functions on road congestions based on poi clustering: an empirical analysis in xi’an, china
Steenberghen et al. Support study on data collection and analysis of active modes use and infrastructure in Europe
Mehdian et al. A data-driven functional classification of urban roadways based on geometric design, traffic characteristics, and land use features
CN116797045A (en) Urban pattern analysis method for night lamplight fusion multi-source data
Sten Hansen Analysing the role of accessibility in contemporary urban development
CN115146840A (en) Data-driven rail transit new line access passenger flow prediction method
Willumsen Urban traffic modelling with limited data
CN113408867A (en) City burglary crime risk assessment method based on mobile phone user and POI data
Bramson et al. Social and economic flows across multimodal transportation networks in the Greater Tokyo Area

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