Population synthesis method considering job-housing and post constraints and electronic equipment

Abstract

The invention relates to a population synthesis method and electronic equipment considering job-housing and post constraints, and the method comprises the steps: obtaining population synthesis seed data based on resident trip survey data; fusing population census data, economic census data and mobile platform individual space-time big data with job and housing information to obtain urban street-level family statistical data, urban street-level population statistical data, urban street-level post statistical data and urban traffic large-area-level job and housing distribution data as population synthesis edge distribution constraint data; based on population synthesis edge distribution constraint data, performing family and individual sample expansion weight calculation on the population synthesis seed data by using an Extend IPU algorithm to obtain a sample expansion weight of each person; and sampling according to the sample expansion weight by using a Monte Carlo sampling algorithm to obtain a population synthesis result. Compared with the prior art, the method has the advantages that a population synthesis result better conforms to actual population distribution, synthesis is more efficient and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of population synthesis, and in particular to a population synthesis method and electronic equipment taking into account job-residence and position constraints. Background Art

[0002] With the acceleration of urbanization, urban planning and traffic management face increasingly complex challenges. Population synthesis, as an important tool for understanding and predicting urban population distribution and its behavior patterns, plays a key role in traffic demand analysis, urban planning and policy making. Traditional population synthesis methods are usually divided into two stages: first, synthesizing the population according to the attributes of the place of residence, and then selecting the place of work. However, this method has some limitations, including but not limited to 1) the traditional method separates the synthesis process of the place of residence and the place of work, which may cause the synthesis results to deviate from the actual population distribution in spatial distribution and fail to accurately reflect the balance of the population between work and residence; 2) in the synthesis process, the distribution and quantity restrictions of jobs are often ignored, resulting in unrealistic employment opportunities for the synthesized population; 3) the staged synthesis method increases the complexity of calculation and may lead to inefficiency, especially in large-scale population synthesis; 4) due to the above problems, the traditional population synthesis method may not be able to provide accurate population data for individual traffic demand models, limiting the prediction ability and application scope of the model. Although there have been many studies in the field of population synthesis at home and abroad, they mainly focus on improving the synthesis algorithm, improving the synthesis accuracy and efficiency. For example, some attempts have been made to optimize the population synthesis process through machine learning techniques, while other studies have focused on synthesis methods for specific regions or specific populations. However, most of these studies still use the traditional staged synthesis framework and fail to fundamentally solve the above problems.

[0003] After searching, China Invention Patent Publication No. CN118378013A discloses a method for synthesizing the full population and constructing travel elements based on multi-data fusion, using population census data, economic census data, resident travel survey data and Internet location data as data sources, using the iterative proportional update model IPU to generate full family information and population information, and updating the population travel element attributes based on the statistical results of multi-source data. The existing patent has the problem that population synthesis does not simultaneously consider job-residence and job constraints.

[0004] How to achieve population synthesis that takes into account work-residence and job constraints has become a technical problem that needs to be solved. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and provide a population synthesis method and electronic equipment taking into account the constraints of work, residence and position.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] According to one aspect of the present invention, a population synthesis method considering job-residence and job constraints is provided, the method comprising the following steps:

[0008] Step S1: Integrate the resident travel survey data and the urban street-level zoning spatial information data to obtain population synthetic seed data;

[0009] Step S2: Integrate population census data, economic census data, and individual spatiotemporal big data of mobile platforms with job-residence information, and combine urban street-level zoning spatial information data and urban transportation district-level spatial information data to obtain urban street-level household statistical data, urban street-level population statistical data, urban street-level job statistical data, and urban transportation district-level job-residence distribution data as population synthetic marginal distribution constraint data;

[0010] Step S3: Based on the population synthetic marginal distribution constraint data of step S2, the Extend IPU algorithm is used to calculate the household and individual expansion weights of the population synthetic seed data of step S1 to obtain the expansion weight of each person in the population synthetic seed data;

[0011] Step S4: Using the Monte Carlo sampling algorithm, sampling is performed according to the expansion weights calculated in step S3 to obtain a population synthesis result.

[0012] Preferably, the step S1 specifically comprises: merging the family table and the individual table of the residents' travel survey data, and mapping the merged data to the urban street-level zoning spatial information data to obtain population synthesis seed data.

[0013] More preferably, the population synthetic seed data includes the family number, family type, number of family members by age segment, number of family members by gender, number of family members by household registration, number of employed family members and work and residence of family members.

[0014] Preferably, the process of step S2 includes:

[0015] a) Statistical data of the population census and economic census at the urban street level to obtain urban street level household statistics, urban street level population statistics and urban street level job statistics;

[0016] b) Map the spatial location of individual spatiotemporal big data on the mobile platform to the spatial information data of the urban street-level division, and extract the user's age, gender, whether he has a job, and his place of work and residence as seed data;

[0017] c) using the result of step a) as the edge distribution constraint data, using the Extend IPU algorithm to calculate the individual sample expansion weights for the seed data of step b) to obtain the sample expansion weights for each person in the seed data;

[0018] d) Using the Monte Carlo sampling algorithm to perform sampling according to the expansion weight of each person in the seed data, the population synthesis result is obtained, and then the occupational and residential distribution data of the entire city at the transportation district level is obtained, and this data is used as the urban transportation district-level occupational and residential distribution data in step S2, so as to be used as the population synthesis marginal distribution data.

[0019] More preferably, the urban street-level household statistical data, urban street-level population statistical data and urban street-level job statistical data in step a) include the number of street household types, the number of street age segments, the number of street genders, the number of street registered residents, the number of street employed people and the total number of street jobs.

[0020] More preferably, the data in the result of step a) is used as marginal distribution constraint data, specifically: the marginal distribution constraint data only includes the number of age segments in the street, the number of genders in the street, the number of employed people in the street and the total number of jobs in the street.

[0021] Preferably, the Extend IPU algorithm is an extension of the general IPU algorithm, adding constraints of different geographic space units to obtain the expansion weight of each person in the population synthetic seed data.

[0022] Preferably, in step S3, the process of obtaining the sample expansion weight of each person in the population synthetic seed data includes:

[0023] Step S3-1: Initialize sample data and edge distribution;

[0024] Step S3-2: adjusting the weight values ​​of other indicators according to the general IPU algorithm based on the traffic area layer;

[0025] Step S3-3: adjusting the weight values ​​of households and individuals according to the general IPU algorithm based on the street layer;

[0026] Step S3-4: repeat steps S3-2 to S3-3 until convergence;

[0027] Step S3-5: Output the weight result.

[0028] Preferably, in step S4, the process of obtaining the population synthesis result includes:

[0029] Step S4-1: The weight w of each individual's family i As the individual sampling weight w pj , where j = 1, 2, 3, ... M, w iThe weight of each household is calculated for step S3;

[0030] Step S4-2: Normalize the sampling weights and treat them as the probability of being sampled:

[0031]

[0032] Step S4-3: Sampling is performed according to probability, and the differences with various constraint indicators are counted, and the result with the smallest error with various control indicators is selected as the population synthesis result.

[0033] According to another aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the method described above is implemented when the processor executes the program.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1) The present invention integrates population census data, economic census data and individual spatiotemporal big data of mobile platforms with job-residence information, and combines street-level zoning spatial information data and urban traffic region-level spatial information data to obtain urban street-level household statistical data, urban street-level population statistical data, urban street-level job statistical data and urban traffic region-level job-residence distribution data as population synthesis marginal distribution constraint data. The population synthesis data calculated using the Extend IPU algorithm and the Monte Carlo sampling algorithm are more in line with the actual population distribution because the job and job-residence constraints are taken into account at the same time. It can provide more accurate support for the individual traffic demand model, thereby improving the application value of the model, and also provides technical support for urban planning and traffic management in terms of population synthesis and population distribution prediction.

[0036] 2) Compared with the previous method of synthesizing the population according to the attributes of the place of residence and then selecting the place of work, the present invention can more easily synthesize a synthetic population with the attributes of work and residence without selecting the place of work. The synthesis process of the integrated work-residence synthesis framework simplifies the calculation steps and improves the synthesis efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of the population synthesis method considering job-residence and job constraints in the present invention;

[0038] Figure 2 This is a schematic diagram of the urban residents' job-residence distribution map obtained by expanding the sample based on the individual spatiotemporal big data of the mobile platform in the present invention;

[0039] Figure 3 It is a scatter diagram showing the statistical comparison between the family indicators of the control group and the real data in the present invention;

[0040] Figure 4 This is a scatter plot diagram showing the statistical comparison between the individual indicators of the control group and the real data in the present invention;

[0041] Figure 5 Provides a scatter plot diagram showing the statistical comparison between the experimental group family indicators and the real data;

[0042] Figure 6 It is a scatter plot diagram showing the statistical comparison between the personal indicators, employment, job and job-residence distribution indicators of the experimental group in the present invention and the real data. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0044] Example 1

[0045] This embodiment relates to a population synthesis method that takes into account job-residence and job constraints. During the synthesis process, this method simultaneously considers the attributes of the residence and the workplace, as well as the distribution and quantity constraints of the jobs, providing a simpler, more efficient and accurate solution, and providing ideas for promoting technological progress and application development in related fields.

[0046] A population synthesis method that takes into account job-residence and job constraints, such as Figure 1 ,include:

[0047] Step S1: integrating the resident travel survey data and the urban street-level zoning spatial information data (map data) to obtain population synthetic seed data;

[0048] Step S2: Integrate population census data, economic census data, mobile platform individual spatiotemporal big data with job-residence information, urban street-level zoning spatial information data, and urban transportation district-level spatial information data (map data) to obtain urban street-level household statistical data, urban street-level population statistical data, urban street-level job statistical data, and urban transportation district-level job-residence distribution data as population synthetic marginal distribution constraint data;

[0049] Step S3: Based on the population synthetic marginal distribution constraint data, the Extend IPU algorithm is used to calculate the household and individual expansion weights of the population synthetic seed data to obtain the expansion weight of each person in the population synthetic seed data;

[0050] Step S4: Using the Monte Carlo sampling algorithm, sampling is performed according to the expansion weights obtained for each person in the population synthesis seed data to obtain the final population synthesis result.

[0051] Step S1 includes: merging the family table and personal table of the residents' travel survey data, and mapping the data to the urban street-level zoning spatial information data. The integrated data information should include the family number, family type (how many people in the household), the number of family members by age segment, the number of family members by gender, the number of family members by household registration, the number of employed people in the family, and the work and residence of family members (street level), which serves as the population synthesis seed data.

[0052] Step S2 includes:

[0053] a) Statistics of population census data and economic census data at the urban street level, mainly including general household information, population information and job information, including the number of household types in the street (number of households with several people), the number of age groups in the street, the number of genders in the street, the number of people in the street by household registration, the number of employed people in the street, and the total number of jobs in the street. The fields must correspond to the seed data;

[0054] b) For individual spatiotemporal big data on mobile platforms with job and residence information, the spatial location is mapped to the spatial information data of urban street-level divisions, and the user's age, gender, whether they have a job, and job and residence information (street level) are extracted as seed data. The general family information, population information, and job information obtained from the population census data and economic census data are used as edge distribution constraint data. Considering that individual spatiotemporal big data on mobile platforms does not have family information, the relevant indicators of the edge distribution constraint data only include the number of street age segments, the number of street genders, the number of street employed people, and the total number of street jobs.

[0055] c) Based on the population synthesis marginal distribution constraint data, the Extend IPU algorithm is used to calculate the individual expansion weights of the population synthesis seed data to obtain the expansion weights of each person in the seed data. The Monte Carlo sampling algorithm is used to sample according to the expansion weights obtained for each person in the seed data to obtain the final population synthesis result, and then the traffic region-level city-wide population occupation-residence distribution data is obtained, and this data is used as the urban traffic region-level occupation-residence distribution data in step S2 to be used as the population synthesis marginal distribution data.

[0056] Step S3 includes: inputting the population synthetic seed data obtained based on the resident travel survey data and the urban street-level zoning spatial information data, and the population synthetic edge distribution constraint data obtained based on the population census data, the economic census data, the mobile platform individual spatiotemporal big data with employment and residence information, the urban street-level zoning spatial information data and the urban traffic district-level spatial information data into the Extend IPU algorithm to calculate the expansion weight of each person in the seed data.

[0057] Compared with the general IPU algorithm, the Extend IPU algorithm is an extension of the general IPU algorithm. On the basis of the original consideration of the distribution of household and population attributes, it adds constraints of different geographic space units, so as to meet the multi-layer edge distribution population synthesis model.

[0058] The general IPU algorithm steps are as follows, and the calculation diagram is shown in Table 1, including:

[0059] Step 1: Initialize sample data and marginal distribution;

[0060] Step 2: Adjust the weight values ​​by column according to the indicators of family, individual, and others, where: b is the goodness-of-fit variable in each weight adjustment process, and the formula is:

[0061]

[0062] Among them, w i is the weight of family i; d ij is the contribution value (households or people) of household i in column j; c j is the constraint boundary of column j.

[0063] The overall objective function δ can be expressed as:

[0064] δ(6j)

[0065] Step 3: Repeat step 2 until convergence;

[0066] Step 4: Weight result output.

[0067] In the process of column-by-column adjustment, all column objective functions are merged into the overall objective function, and the overall objective function is minimized to represent the optimal solution, that is, convergence is achieved.

[0068] Table 1

[0069]

[0070]

[0071] Table 2 shows the calculation of different geographical constraint spaces in the Extend IPU algorithm. Assuming that Street 1 and Street 2 are independent, and Traffic Area 1 includes Street 1 and Street 2, the Extend IPU algorithm steps are as follows:

[0072] Step 1: Initialize sample data and marginal distribution;

[0073] Step 2: Adjust the weights of other indicators according to the general IPU algorithm based on the traffic area layer;

[0074] Step 3: Adjust the weight values ​​of households and individuals according to the general IPU algorithm based on the street layer;

[0075] Step 4: Repeat steps 2-3 until convergence;

[0076] Step 5: Weight result output.

[0077] Table 2

[0078]

[0079]

[0080] Monte Carlo sampling is an algorithm based on random sampling, which is used to generate samples from probability distribution. It does not depend on the specific form of the distribution and is therefore very flexible. The basic idea of ​​Monte Carlo sampling is that by randomly sampling from a given distribution, certain characteristics of the distribution, such as the mean, variance, etc., can be approximately estimated. According to the Extend IPU algorithm, the weight w of each household can be obtained. i , the goal is to generate a population M that satisfies the marginal distribution data, where the total population in the seed data is N.

[0081] Step S4-1: The weight w of each individual's family i As the individual sampling weight w pj , j = 1, 2, 3, ... M;

[0082] Step S4-2: Normalize the sampling weights and treat them as the probability of being sampled:

[0083]

[0084] Step S4-3: Sampling is performed according to probability, and the differences with various constraint indicators are counted, and the result with the smallest error with various control indicators is selected as the population synthesis result.

[0085] Example 2

[0086] This embodiment also relates to the application and verification test of a population synthesis method that takes into account job-residence and job constraints.

[0087] like Figures 2 to 5 , taking the population data of a certain city as an example, a verification test of the population synthesis method considering job-residence and job constraints is provided.

[0088] The population data of a certain city include: street-level zoning spatial information data (map data) of a certain city, traffic region-level spatial information data (map data) of a certain city, individual spatiotemporal big data of a certain city on mobile platforms with job and residence labels (about 1.53 million people), travel survey data of a certain city (38,565 households, 70,990 people), the seventh population census data of a certain city, and the fourth economic census data of a certain city.

[0089] First, the residents' travel survey data are mapped to the street-level zoning spatial information data of a certain city, with the family as the smallest expansion unit. The data information should include the family number, family type (how many people in the household), the number of family members by age segment, the number of family members by gender, the number of family members by household registration, the number of employed people in the family, and the work and residence of family members (street level), which will be used as the population synthesis seed data.

[0090] The population census data and economic census data are counted at the urban street level, mainly including general household, population information and job information, including the number of household types in the street (number of households with several people), the number of age segments in the street, the number of genders in the street, the number of people registered in the street, the number of employed people in the street, and the total number of jobs in the street. The fields must correspond to the population synthesis seed data.

[0091] For individual spatiotemporal big data on mobile platforms with job and residence labels, the spatial location is mapped to the spatial information data of urban street-level divisions. The individual is taken as the smallest research unit, and the user's age, gender, whether he has a job, and job and residence information (street level) are extracted as seed data. The general family, population information and job information obtained from the population census data and economic census data are used as marginal distribution constraint data. Considering that the individual spatiotemporal big data on mobile platforms does not have family information, the relevant indicators of the marginal distribution constraint data only include the number of street age segments, the number of street genders, the number of street employed people, and the total number of street jobs.

[0092] Based on the population synthetic edge distribution constraint data, the Extend IPU algorithm is used to calculate the individual expansion weight of the population synthetic seed data obtained from the individual spatiotemporal big data of the mobile platform with job and residence labels, and the expansion weight of each person in the seed data is obtained; the Monte Carlo sampling algorithm is used to sample according to the expansion weight obtained by each person in the seed data to obtain the final population synthesis result, and then the population job and residence distribution data of the entire transportation area are obtained, such as Figure 2 As shown, this data is used as the edge constraint data of urban employment and residence information for subsequent population synthesis calculations.

[0093] The seed data obtained from the residents' travel survey data, the marginal distribution data obtained from the individual spatiotemporal big data of the mobile platform, the population census, and the economic census data are input into the Extend IPU algorithm to calculate the weight of each household, and then the Monte Carlo sampling algorithm is used to obtain the final population synthesis result. In order to test the effect of the proposed method, a control group and an experimental group are set up:

[0094] The seed data obtained from the residents' travel survey data, the marginal distribution data obtained from the individual spatiotemporal big data of the mobile platform, the population census, and the economic census data are input into the Extend IPU algorithm to calculate the weight of each household, and then the Monte Carlo sampling algorithm is used to obtain the final population synthesis result. In order to test the effect of the proposed method, a control group and an experimental group are set up:

[0095] Control group: Population synthesis is conducted only from the residential end, without considering job and work location constraints. Control indicators include family residence, family type, age of family members, gender of family members, and household registration status of family members. The spatial units constrained by the above indicators are all at the street level.

[0096] Experimental group: that is, the method proposed in the present invention, in addition to the control indicators considered in the control group, also includes the employment status of family members (street level), the work place of family members (traffic region level), and the total number of street positions (street level).

[0097] Figures 3-4 The results for the control group, Figures 5-6 is the result of the experimental group, and Table 3 is the comparison of the errors of each control index between the control group and the experimental group. Figure 6 and Figure 4 In comparison, there are more indicators such as street employed population, number of street jobs and job-residence distribution at the transportation district level.

[0098] contrast Figures 3 to 6 It can be found that the population synthesis results of the experimental group and the control group are not significantly different from the actual statistical data. From the goodness of fit R2, the goodness of fit of the experimental group and the control group are both 0.96 and above, indicating that the population synthesis results of the two groups are good. Although from the RMSE point of view, due to the experimental group's additional control indicators such as employment, job and job-residence distribution, the RMSE of family indicators and personal indicators has increased. Due to the increase in control indicators and the increase in the level of traffic regions in geographic space constraints, the increase in errors is a normal performance. At the same time, it can be seen that the increase in errors is not significant. Therefore, it can be proved that the population method considering job-residence and job constraints proposed in the present invention can obtain population synthesis results with job-residence information more conveniently and efficiently while ensuring the synthesis accuracy.

[0099] Table 3

[0100]

[0101] The present invention proposes an integrated work-residence synthesis framework, which can directly synthesize a population with work-residence attributes without selecting a work location, thereby simplifying the calculation steps and making population synthesis more convenient and efficient.

[0102] The present invention combines street-level zoning spatial information data and urban traffic region-level spatial information data, integrates population census data, economic census data and mobile platform individual spatiotemporal big data with job-residence information, and obtains urban street-level household statistical data, urban street-level population statistical data, urban street-level job statistical data and urban traffic region-level job-residence distribution data as population synthesis marginal distribution constraint data; takes residents' travel survey data as seed data for population synthesis, and the calculated population synthesis data takes into account job and job-residence constraints, so the population synthesis result is more in line with the actual population distribution, and can be provided for individual traffic demand models, thereby improving the application value of the model.

[0103] The method of the present invention can not only provide a scientific basis for traffic planning, management and policy formulation, but also provide technical support for population distribution prediction in urban planning.

[0104] Example 3

[0105] The electronic device of the present invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0106] Multiple components in the device are connected to the I / O interface, including: input units, such as keyboards, mice, etc.; output units, such as various types of displays, speakers, etc.; storage units, such as disks, optical disks, etc.; and communication units, such as network cards, modems, wireless communication transceivers, etc. The communication unit allows the device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunication networks.

[0107] The processing unit performs the various methods and processes described above, such as methods S1 to S4. For example, in some embodiments, methods S1 to S4 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on the device via a ROM and / or a communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more steps of methods S1 to S4 described above may be performed. Alternatively, in other embodiments, the CPU may be configured to execute methods S1 to S4 in any other appropriate manner (e.g., by means of firmware).

[0108] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0109] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0110] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0111] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A population synthesis method considering job-residence and job constraints, characterized in that: The method comprises the following steps: Step S1: Integrate the resident travel survey data and the urban street-level zoning spatial information data to obtain population synthetic seed data; Step S2: Integrate population census data, economic census data, and individual spatiotemporal big data of mobile platforms with job-residence information, and combine urban street-level zoning spatial information data and urban transportation district-level spatial information data to obtain urban street-level household statistical data, urban street-level population statistical data, urban street-level job statistical data, and urban transportation district-level job-residence distribution data as population synthetic marginal distribution constraint data; Step S3: Based on the population synthetic marginal distribution constraint data of step S2, the Extend IPU algorithm is used to calculate the household and individual expansion weights of the population synthetic seed data of step S1 to obtain the expansion weight of each person in the population synthetic seed data; Step S4: Using the Monte Carlo sampling algorithm, sampling is performed according to the expansion weights calculated in step S3 to obtain a population synthesis result.

2. A population synthesis method considering job-residence and job constraints according to claim 1, characterized in that: The step S1 is specifically as follows: merging the family table and the individual table of the residents' travel survey data, and mapping the merged data to the urban street-level zoning spatial information data to obtain population synthesis seed data.

3. A population synthesis method considering job-residence and job constraints according to claim 2, characterized in that: The population synthetic seed data include family number, family type, number of family members by age segment, number of family members by gender, number of family members by household registration, number of employed family members and work and residence of family members.

4. A population synthesis method considering job-residence and job constraints according to claim 1, characterized in that: The process of step S2 includes: a) Statistical data of the population census and economic census at the urban street level to obtain urban street level household statistics, urban street level population statistics and urban street level job statistics; b) Map the spatial location of individual spatiotemporal big data on the mobile platform to the spatial information data of the urban street-level division, and extract the user's age, gender, whether he has a job, and his place of work and residence as seed data; c) using the data in the result of step a) as the marginal distribution constraint data, and using the Extend IPU algorithm to calculate the individual sample expansion weights for the seed data in step b), to obtain the sample expansion weights for each person in the seed data; d) Using the Monte Carlo sampling algorithm to perform sampling according to the expansion weight of each person in the seed data, obtain the population synthesis result, and then obtain the occupational and residential distribution data of the entire city at the transportation district level, and use this data as the urban transportation district-level occupational and residential distribution data in step S2, so as to be used as the population synthesis marginal distribution data.

5. A population synthesis method considering job-residence and job constraints according to claim 4, characterized in that: The urban street-level household statistical data, urban street-level population statistical data and urban street-level job statistical data in step a) include the number of street household types, the number of street age segments, the number of street genders, the number of street registered residents, the number of street employed people and the total number of street jobs.

6. A population synthesis method considering job-residence and job constraints according to claim 5, characterized in that: The specific method of using the result of step a) as marginal distribution constraint data is as follows: the marginal distribution constraint data only includes the number of age segments in the street, the number of genders in the street, the number of employed people in the street and the total number of jobs in the street.

7. A population synthesis method considering job-residence and job constraints according to claim 1, characterized in that: The Extend IPU algorithm is an extension of the general IPU algorithm, adding constraints of different geographic space units to obtain the expansion weight of each person in the population synthetic seed data.

8. A population synthesis method considering job-residence and job constraints according to claim 1, characterized in that: In step S3, the process of obtaining the sample expansion weight of each person in the population synthetic seed data includes: Step S3-1: Initialize sample data and edge distribution; Step S3-2: adjusting the weight values ​​of other indicators according to the general IPU algorithm based on the traffic area layer; Step S3-3: adjusting the weight values ​​of households and individuals according to the general IPU algorithm based on the street layer; Step S3-4: repeat steps S3-2 to S3-3 until convergence; Step S3-5: Output the weight result.

9. A population synthesis method considering job-residence and job constraints according to claim 1, characterized in that: In step S4, the process of obtaining the population synthesis result includes: Step S4-1: The weight w of each individual's family i As the individual sampling weight w pj , where j = 1, 2, 3, ... M, w i The weight of each household is calculated for step S3; Step S4-2: Normalize the sampling weights and treat them as the probability of being sampled: Step S4-3: Sampling is performed according to probability, and the differences with various constraint indicators are counted, and the result with the smallest error of various control indicators is selected as the population synthesis result.

10. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the program, the method according to any one of claims 1 to 9 is implemented.

Images