Prediction classification method based on resident travel influence factors and traffic resource demands

Abstract

The invention discloses a prediction classification method based on resident travel influence factors and traffic resource demands, and the method comprises the steps: obtaining multi-source data involved in a city development process, and constructing a resident travel analysis database under city development based on the multi-source data; based on the database, calculating resident travel traffic resource demands, and constructing a resident traffic resource demand influence factor set; constructing a resident travel traffic resource demand prediction model according to the resident travel traffic resource demand and the influence factors; and according to the resident travel traffic resource demand prediction model, calculating the resident travel influence factor importance degree, predicting the resident traffic resource demand under the influence factor change according to the resident travel influence factor importance degree, and obtaining a prediction classification result. According to the method, the resident travel traffic resource demand under the multi-factor change is accurately predicted, the traffic efficiency can be improved, and the sustainable development of urban traffic is promoted.

Description

Technical Field

[0001] The present invention belongs to the field of urban traffic travel prediction classification, and particularly relates to a prediction classification method based on factors influencing residents' travel and traffic resource demand. Background Art

[0002] With the acceleration of the global urbanization process, the urban population is continuously growing, the urban scale is continuously expanding, and urban traffic is facing increasingly severe challenges. Developing sustainable cities has become a global consensus, and the sustainable development of urban traffic is crucial, which is related to the quality of life of residents, the economic activities of cities, and environmental protection. In this context, deeply understanding the impact of various factors such as land use, travel scenarios, socio-economic attributes, and traffic convenience on the demand for traffic resources for residents' travel under urban development, and accurately predicting the demand for traffic resources for residents' travel, is of key significance for formulating scientific and reasonable traffic policies, optimizing traffic services, and promoting the sustainable development of cities.

[0003] In the process of urban development, life events (such as marriage, childbirth, employment changes, etc.), built environment (such as land use, traffic infrastructure, public transport accessibility, etc.), and scenario factors (such as weather, air pollution, major public health events, etc.) have spatio-temporal heterogeneous impacts on residents' travel behavior. For example, with the development of cities, new transportation modes such as shared bicycles, electric vehicles, and online car-hailing have emerged continuously, changing residents' travel choices; the improvement of public transport accessibility and the increase in the ownership of private cars have also significantly affected residents' travel patterns. At the same time, land use changes, economic level improvement, social norm evolution, and climate change during the urban development process will indirectly affect the employment-residence balance, values, and behavioral norms of residents, and thus have an impact on travel behavior.

[0004] Although a large number of studies have focused on the mechanism of residents' travel behavior, most of them focus on the impact of a certain type of factor on cross-sectional travel behavior, lacking a comprehensive quantitative analysis of the changes in travel behavior at different times, still lacking a comprehensive framework to systematically analyze the spatio-temporal heterogeneous impacts of various factors on residents' travel behavior during the urban development process, having insufficient understanding of the changes in the importance of multi-factors on residents' travel behavior during the urban development process, and having low accuracy in predicting the demand for traffic resources involving multiple transportation modes during residents' travel. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a prediction classification method based on factors influencing residents' travel and traffic resource demand, including:

[0006] Obtain multi-source data involved in the process of urban development, and construct a resident travel analysis database under urban development based on the multi-source data; the multi-source data includes resident travel data, resident household characteristic data, resident personal characteristic data, urban built environment data, and resident travel scenario data;

[0007] Based on the database, calculate the demand for resident travel traffic resources, and construct a set of influencing factors for resident traffic resource demand;

[0008] According to the resident travel traffic resource demand and influencing factors, construct a prediction model for resident travel traffic resource demand;

[0009] According to the prediction model for resident travel traffic resource demand, calculate the importance of influencing factors for resident travel, and predict the resident traffic resource demand under the change of influencing factors according to the importance of influencing factors for resident travel, so as to obtain a prediction classification result.

[0010] Preferably, the process of obtaining multi-source data involved in the process of urban development and constructing a resident travel analysis database under urban development based on the multi-source data includes:

[0011] According to the two-section or multi-section conditions in multiple time dimensions during the process of urban development, sample and collect urban resident travel data representing the travel characteristics of residents under a specific section of urban development, as well as the corresponding resident household characteristics and resident personal characteristic data;

[0012] According to the urban resident travel data under the collected corresponding section, determine the spatio-temporal range of resident travel, obtain the urban built environment data and resident travel scenario data under the spatio-temporal range, and combine them to obtain multi-source data;

[0013] According to the multi-source data, construct an association matrix between the multi-source data, and obtain a resident travel analysis database covering multi-source heterogeneous data under urban development.

[0014] Preferably, the sampling methods include random sampling, stratified sampling, and address-based sampling methods, and sample data representative of the current section and the current region are obtained by sampling based on the sampling methods.

[0015] Preferably, the spatio-temporal range of resident travel is the combined range of time and space covered by urban resident travel data; the formula expression is:

[0016]

[0017] In the formula, TSR represents the spatio-temporal range, T represents the time dimension, which is between the earliest travel time T_min and the latest travel time T_max, S represents the space dimension, which belongs to the research area A, and A is the convex hull or the minimum circumscribed rectangle formed by the origin and destination of all resident travels in each section.

[0018] Preferably, the association matrix is the association relationship between the travel time of residents in multiple cross-sections and the weather data at a specific time in the scenario data, and the association relationship between the travel location information of residents and the land use data in the corresponding spatial range; the formula expression is:

[0019]

[0020] In the formula, is the association matrix between datasets i and j, is the k-th attribute of dataset i, is the l-th attribute of dataset j, is the mapping function between attribute k and attribute l, which is a mapping of time relationship or spatial relationship.

[0021] Preferably, based on the database, the process of calculating the demand for residents' travel traffic resources and constructing a set of influencing factors that have a significant impact on the demand for residents' traffic resources includes:

[0022] According to the association matrix between multi-source data, extract the complete set of influencing factors of the travel traffic resources demand of residents in multiple cross-sections in a day, family characteristics, personal characteristics, scenario characteristics, and land use characteristics;

[0023] According to the complete set of influencing factors, based on the analysis algorithm, calculate the correlation between the influencing factors and the demand for residents' traffic resources;

[0024] According to the correlation and the preset threshold of the correlation, extract the set of influencing factors for the demand of residents' traffic resources.

[0025] Preferably, the demand for residents' travel traffic resources in a day is the distance traveled by residents using various transportation modes in a day; the formula expression is:

[0026]

[0027] In the formula, is the set of traffic resources required for resident i's one-day travel, is the distance that resident i uses transportation mode M in a day.

[0028] Preferably, the formula expression for extracting the complete set of influencing factors is:

[0029]

[0030] In the formula, is the extracted set of influencing factor features, including family characteristics, personal characteristics, scenario characteristics, and land use characteristics, represents the k-th feature of the j-th type of influencing factor of resident i, is the association matrix between the traffic resource demand of resident i and the j-th type of influencing factor.

[0031] Preferably, according to the demand for residents' travel traffic resources and influencing factors, the process of constructing a prediction model for residents' travel traffic resources includes:

[0032] Construct a deterministic utility function for residents' traffic resources demand under multiple cross-sections according to the set of residents' traffic resources demand and influencing factors;

[0033] According to the deterministic utility function, simulate the usage behavior of discrete-continuous traffic resources of residents within a day under multiple cross-sections of urban development, and construct a prediction model for residents' travel traffic resources demand under multiple cross-sections of urban development.

[0034] Preferably, the formula expression of the deterministic utility function is:

[0035]

[0036] In the formula, is the utility of individual i choosing travel mode M, is the household characteristic vector of individual i, is the personal characteristic vector of individual i, is the characteristic vector of travel scenarios involved by resident i within a day, is the characteristic vector of the built environment involved in resident i's one-day travel, , , and are the coefficient vectors of the corresponding characteristic vectors, is the random error term.

[0037] Compared with the prior art, the present invention has the following advantages and technical effects:

[0038] Based on multi-source heterogeneous data such as residents' travel data, residents' household characteristic data, residents' personal characteristic data, urban built environment data, and residents' travel scenario data involved in the process of urban development, the present invention constructs a complete database to support the analysis of the importance of influencing factors for residents' travel and the prediction of traffic resources demand in the process of urban development; through algorithms such as correlation analysis, an influencing factor set that has a significant impact on residents' traffic resources demand is accurately established; subsequently, a utility function for residents' travel resource demand is established to accurately simulate the usage behavior of traffic resources covering the discrete-continuous characteristics of residents; finally, a matching mechanism between prediction models for residents' travel traffic resources demand under multiple cross-sections is constructed, so as to accurately analyze the change in the importance of various influencing factors for residents' travel traffic resources demand; according to the variable range of various influencing factors, classified prediction of residents' travel traffic resources demand under the change of multiple factors is realized.

[0039] The present invention can effectively calculate the importance change of multiple factors on the demand for residents' travel traffic resources during the urban development process, accurately predict the demand for residents' travel traffic resources under the change of multiple factors, and can better assist the management department in formulating traffic supply optimization and demand management policies, improving traffic efficiency, and promoting the sustainable development of urban traffic. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings forming a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation of this application. In the drawings:

[0041] Figure 1 is a schematic flowchart of the method according to an embodiment of the present invention;

[0042] Figure 2 is a schematic diagram of the absolute value change of traffic resource demand under the change of influencing factors according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The following will refer to the drawings and combine the embodiments to detail this application.

[0044] It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0045] As Figure 1 and Figure 2 shown, an embodiment of the present invention provides a prediction and classification method based on influencing factors of residents' travel and traffic resource demand, including the following steps:

[0046] S1. Obtain multi-source data involved in the urban development process, and construct a residents' travel analysis database based on the multi-source data; the multi-source data includes residents' travel data, residents' family characteristic data, residents' personal characteristic data, urban built environment data, and residents' travel scenario data;

[0047] S2. Based on the database, calculate the demand for residents' travel traffic resources, and construct a set of influencing factors for residents' traffic resource demand;

[0048] S3. According to the demand for residents' travel traffic resources and the influencing factors, construct a prediction model for residents' travel traffic resource demand;

[0049] S4. Calculate the importance of factors affecting residents' travel according to the residents' travel traffic resource demand prediction model, predict the residents' traffic resource demand under the change of influencing factors according to the importance of factors affecting residents' travel, and obtain the predicted classification results.

[0050] Furthermore, obtaining multi-source data involved in the process of urban development, and the process of constructing a database for analyzing residents' travel under urban development based on multi-source data includes:

[0051] S11. According to the two-section or multi-section conditions in multiple time dimensions during the process of urban development, sample and collect urban residents' travel data representing the travel characteristics of residents under specific sections of urban development, as well as the corresponding resident family characteristics and resident personal characteristics data;

[0052] The two-section or multi-section in multiple time dimensions can be the key periods in the process of urban development, such as the start year and end year of various plans. In this embodiment, 2014 when the fifth resident travel survey in a certain city was conducted and 2023 when the sixth resident travel survey in a certain city was conducted are used as the two key sections.

[0053] The urban residents' travel data representing the travel characteristics of residents under specific sections, as well as the corresponding resident family characteristics and resident personal characteristics data are obtained from the resident travel survey data organized by the transportation commissions of each city. In this embodiment, the resident travel data, the corresponding resident family characteristics and resident personal characteristics data in the fifth and sixth resident travel surveys in a certain city are used as the data basis.

[0054] S12. According to the collected urban residents' travel data under the corresponding sections, determine the spatio-temporal range of residents' travel, obtain the urban built environment data and residents' travel scenario data within the spatio-temporal range, and combine them to obtain multi-source data;

[0055] S13. According to the multi-source data, construct an association matrix between the multi-source data, and obtain a database for analyzing residents' travel covering multi-source heterogeneous data under urban development.

[0056] Furthermore, the sampling methods include random sampling, stratified sampling, and address-based sampling methods. Based on the sampling methods, sample and obtain representative sample data including the current section and the current area.

[0057] Furthermore, the spatio-temporal range of residents' travel is the combined range of time and space covered by urban residents' travel data; the formula expression is:

[0058]

[0059] In the formula, TSR represents the spatio-temporal range, T represents the time dimension, which is between the earliest travel time T_min and the latest travel time T_max, and S represents the spatial dimension, which belongs to the research area A. A is the convex hull or the minimum bounding rectangle formed by the origin and destination of all residents' trips at each section.

[0060] Multi-source data such as urban built environment data and residents' travel scenario data under the spatio-temporal range can be obtained from public data such as crawling from Amap, data from weather websites, and public data from air quality monitoring stations.

[0061] Furthermore, the correlation matrix is the correlation relationship between the travel times of residents at multiple sections and the weather data at specific times in the scenario data, as well as the correlation relationship between the residents' travel location information and the land use data within the corresponding spatial range; the formula expression is:

[0062]

[0063] In the formula, is the correlation matrix between datasets i and j, is the k-th attribute of dataset i, is the l-th attribute of dataset j, is the mapping function between attribute k and attribute l, which is a mapping of time relationship or spatial relationship.

[0064] Furthermore, based on the database, the process of calculating the demand for residents' travel traffic resources and constructing a set of influencing factors that have a significant impact on the demand for residents' traffic resources includes:

[0065] S21. According to the correlation matrix between multi-source data, extract the complete set of influencing factors of the travel traffic resource demand of residents at multiple sections and family characteristics, personal characteristics, scenario characteristics, and land use characteristics;

[0066] S22. According to the complete set of influencing factors, based on the analysis algorithm, calculate the correlation between the influencing factors and the demand for residents' traffic resources;

[0067] The correlation analysis algorithms include methods such as Pearson correlation coefficient and Spearman correlation coefficient to measure the correlation between continuous influencing factors and the demand for residents' travel traffic resources, and can also be methods such as Cohen's d and KL divergence to analyze the differences in the demand for residents' travel traffic resources under multiple types of influencing factors.

[0068] S23. According to the correlation degree and the preset threshold of the correlation degree, extract the set of influencing factors for the demand for residents' traffic resources.

[0069] The preset threshold of the correlation degree can be a correlation threshold such as ±0.6 to measure whether there is a large correlation, or can also be significance indicators such as t-test and P-value to measure whether there are significant differences in the demand for residents' travel traffic resources under multiple types of influencing factors.

[0070] Furthermore, the daily travel traffic resource demand of residents is the distance traveled by residents using various transportation modes within a day; the formula expression is:

[0071]

[0072] In the formula, is the set of traffic resources required for resident i's daily travel, is the distance that resident i uses transportation mode M within a day.

[0073] Furthermore, the formula expression for extracting the complete set of influencing factors is:

[0074]

[0075] In the formula, is the extracted set of influencing factor features, including household features, personal features, scenario features, and land use features, represents the k-th feature of the j-th type of influencing factor for resident i, is the correlation matrix between resident i's traffic resource demand and the j-th type of influencing factor.

[0076] Furthermore, the process of constructing a prediction model for residents' travel traffic resource demand based on residents' travel traffic resource demand and influencing factors includes:

[0077] S31. According to the traffic resource demand of residents and the set of influencing factors, construct a deterministic utility function for residents' traffic resource demand under multiple cross-sections;

[0078] S32. According to the deterministic utility function, simulate the usage behavior of discrete-continuous traffic resources of residents within a day under multiple cross-sections of urban development, and construct a prediction model for residents' travel traffic resource demand under multiple cross-sections of urban development.

[0079] Furthermore, the formula expression for the deterministic utility function is:

[0080]

[0081] In the formula, is the utility of individual i choosing travel mode M, is the household feature vector of individual i, is the personal feature vector of individual i, is the vector of travel scenario features involved by resident i within a day, is the vector of built environment features involved in resident i's daily travel, , , and are the coefficient vectors corresponding to the feature vectors, is the random error term.

[0082] The discrete - continuous traffic resource usage behavior of residents within a day under multiple cross - sections can be fitted by multiple methods such as the multinomial discrete - continuous extreme value model, two - stage decision - making model, Markov chain model, game theory model, etc. In this embodiment, the multinomial discrete - continuous extreme value model is used to simulate the discrete - continuous traffic resource usage behavior of residents within a day under multiple cross - sections.

[0083] The multinomial discrete - continuous extreme value model aims to maximize the utility of resident i's traffic resource usage within a day. The formula expression of the utility is:

[0084]

[0085] In the formula, is a quasi - concave, monotonically increasing, and continuously differentiable function with respect to the resource vector of various transportation modes; is the resource usage amount of transportation mode m. In this embodiment, the unit is km; and are the saturation parameters of mode m. The difference is that plays an important role in adjusting the indifference curve and making the corner solution (i.e., the resource consumption of mode m is zero) possible. The intuitive interpretation of is that the higher the value of , the stronger the tendency of residents to use mode m. Different from this, controls the saturation by exponentiating the resource consumption of mode m, that is, as the resource consumption of mode m increases, the marginal utility decreases; represents the baseline marginal utility of mode m. In other words, it is the marginal utility at the zero - resource - consumption point of mode m. Usually, adopts the form of where is a determinant of the basic utility of each mode, is an independent and identically - distributed error term that follows the Gumbel distribution. In addition, is a function that captures the influence of the decision - maker and choice - option characteristics, including a constant to capture the general preference for mode m, while

[0086] To simulate the discrete - continuous traffic resource usage behavior of residents within a day under multiple cross - sections in urban development, in the multinomial discrete - continuous extreme value model adopted in this embodiment, it is necessary to maximize the utility of resident i's use of various transportation mode resources, and the form is as follows:

[0087]

[0088] In the formula, is the unit amount of using mode m, which is km in this embodiment; Let \(R_i\) be the total amount of resources consumed by resident \(i\) in one day using various modes, which is the total travel distance of resident \(i\) in one day in this embodiment. To obtain the optimal traffic resource allocation for resident \(i\), the above optimization problem can be solved by constructing a Lagrangian function and using the Kuhn - Tucker conditions, and further generating the following expressions for the probability of resource consumption for each mode.

[0089]

[0090] In the formula, \(N\) is the number of consumed traffic modes;

[0091] , .

[0092] According to the expressions for the probability of resource consumption of each traffic mode used by resident \(i\), in this embodiment, parameter estimation is carried out by methods such as maximum likelihood estimation and Bayesian estimation. In this embodiment, maximum likelihood estimation is used for estimation, and the parameter estimation results are shown in Table 1:

[0093] Table 1

[0094] Variable Impact on the 2014 mode Coefficient estimation results (t-values in parentheses) Impact on the 2023 mode Coefficient estimation results (t-values in parentheses) Gender: Male Private car 0.721（29.994） Private car 0.742（22.733） Age: 26 - 50 Private car 0.463(16.988) Private car 0.900(22.030) Annual household income: within 100,000 Walking 0.069(3.374) Walking 0.222(10.149) Family has a bicycle Surface bus 0.024(1.169) Surface bus -0.073(-2.046) Living in the suburbs Subway -0.074(-1.848) Subway 0.274(4.795) Full-day subway travel time (min) Subway -0.002(-19.822) Subway -0.001(-11.374) Severe air pollution Private car 0.085(2.423) Private car 0.960(3.136) Rainy day Surface bus -0.057(-2.557) Surface bus 0.105(2.725)

[0095] Furthermore, according to the prediction model of residents' travel traffic resource demand, calculating the importance of factors affecting residents' travel, and predicting residents' traffic resource demand under the change of influencing factors to obtain the prediction classification result includes:

[0096] S41. According to the prediction model of residents' travel traffic resource demand for multiple sections under urban development, design a matching mechanism for the prediction models between multiple sections, and calculate the importance of influencing factors between comparable multiple sections of urban development.

[0097] The matching mechanism of the prediction model of residents' traffic resource demand between multiple sections in this embodiment is Markov state transition estimation, variable value standardization according to the GDP growth rate, marginal rate of substitution calculation according to time equivalence, etc. In this embodiment, it is considered that 1 minute of residents between 2014 and 2023 is equally important. Taking the full - day subway travel time (min) as the matching mechanism for residents' travel traffic resource demand in multiple sections, calculate the marginal rate of substitution of multiple influencing factors as the importance of influencing factors between multiple sections of urban development. Since personal and household economic attribute variables are not within the controllable range of urban traffic management departments, the calculation results of the importance of household vehicle ownership, built environment, and scenario variables are shown in Table 2:

[0098] Table 2

[0099] Variable Impact on the 2014 mode Coefficient estimation results (t-values in parentheses) Impact on the 2023 mode Coefficient estimation results (t-values in parentheses) Family has a bicycle Surface bus -12.073 (-1.190) Surface bus 69.159 (2.003) Living in the suburbs Subway 291.777 (15.888) Subway -11.112 (-0.314) Full-day subway travel time (min) Subway 1 (benchmark value) Subway 1 (benchmark value) Severe air pollution Private car -42.465 (-2.365) Private car -915.99 (-2.947) Rainy day Surface bus 28.132 (2.585) Surface bus -100.46 (-2.649)

[0100] S42. According to the multi-section resident travel traffic resource demand prediction model under urban development, simulate the possible changes in the influencing factors of resident travel traffic resource demand, predict the resident traffic resource demand under the change of influencing factors, and classify it to obtain the predicted classification result.

[0101] The possible changes in the influencing factors of resident travel traffic resource demand may include the redistribution of residents' residential areas and the change of job-housing balance brought about by the land use layout, or the improvement of road network density and the improvement of public transport accessibility brought about by the optimization of urban traffic infrastructure. In this embodiment, taking the improvement of the full-day subway travel time as an example, calculate the number of people using the subway in the whole district of a certain city and the multiple change and absolute value change of traffic resource demand respectively, as shown in Figure 2 shown.

[0102] The above is only a preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A prediction classification method based on factors affecting residents' travel and traffic resource demand, characterized in that Including: Obtain multi-source data involved in the process of urban development, and construct a resident travel analysis database under urban development based on the multi-source data; the multi-source data includes resident travel data, resident household characteristic data, resident personal characteristic data, urban built environment data, and resident travel scenario data; Based on the database, calculate the demand for resident travel traffic resources, and construct a set of influencing factors for the demand of resident traffic resources; According to the demand for resident travel traffic resources and the influencing factors, construct a prediction model for the demand of resident travel traffic resources; According to the prediction model for the demand of resident travel traffic resources, calculate the importance degree of the influencing factors of resident travel, and predict the demand for resident traffic resources under the change of influencing factors according to the importance degree of the influencing factors of resident travel, so as to obtain a prediction classification result.

2. The method according to claim 1, wherein: The process of obtaining multi-source data involved in the process of urban development and constructing a resident travel analysis database under urban development based on the multi-source data includes: According to the two-section or multi-section situations in multiple time dimensions during the urban development process, sample and collect urban resident travel data representing the travel characteristics of residents under a specific section of urban development, as well as the corresponding resident household characteristics and resident personal characteristic data; According to the collected urban resident travel data under the corresponding section, determine the spatio-temporal range of resident travel, obtain the urban built environment data and resident travel scenario data within the spatio-temporal range, and combine them to obtain multi-source data; According to the multi-source data, construct an association matrix between the multi-source data, and obtain a resident travel analysis database covering multi-source heterogeneous data under urban development.

3. The method according to claim 2, wherein: The sampling method includes random sampling, stratified sampling, and address-based sampling method. Based on the sampling method, sample and obtain representative sample data of the current section and the current region.

4. The method according to claim 2, wherein: The spatio-temporal range of resident travel is the combined range of time and space covered by urban resident travel data; the formula expression is: In the formula, TSR represents the spatio-temporal range, T represents the time dimension, which is between the earliest travel time T_min and the latest travel time T_max, S represents the space dimension, which belongs to the research area A, and A is the convex hull or the minimum circumscribed rectangle formed by the starting and ending points of all resident travels in each section.

5. The method according to claim 2, wherein: The association matrix is the association relationship between the travel time of multi-section residents and the weather data in the scenario data, and the association relationship between the resident travel location information and the land use data in the corresponding spatial range; the formula expression is: wherein, is the association matrix between datasets i and j, is the k-th attribute of dataset i, is the l-th attribute of dataset j, is the mapping function between attribute k and attribute l, which is a mapping of temporal relationship or spatial relationship.

6. The method according to claim 1, wherein: The process of calculating the demand for resident travel traffic resources based on the database and constructing a set of influencing factors that have a significant impact on the demand for resident traffic resources includes: According to the association matrix between the multi-source data, extract the complete set of influencing factors of the one-day travel traffic resource demand of multi-section residents and the household characteristics, personal characteristics, scenario characteristics, and land use characteristics; According to the complete set of influencing factors, based on the analysis algorithm, calculate the correlation degree between the influencing factors and the demand for resident traffic resources; Extract the set of influencing factors for residents' transportation resource demands according to the relevance and the preset threshold of relevance.

7. The method according to claim 6, wherein the transportation resource demand for residents' one-day trips is the distance traveled by residents using various transportation modes within one day; the formula expression is: wherein, is the set of transportation resources required for resident i's one-day travel, is the distance that resident i travels by transportation mode M within one day.

8. The method according to claim 6, wherein the formula expression for extracting the complete set of influencing factors is: In the formula, is the extracted set of influencing factor features, including household features, personal features, scenario features, and land use features, represents the k-th feature of the j-th type of influencing factor for resident i, is the correlation matrix between the transportation resource demand of resident i and the j-th type of influencing factor.

9. The method according to claim 1, wherein The process of constructing a prediction model for residents' transportation resource demands based on the transportation resource demands and influencing factors of residents' trips includes: Construct a deterministic utility function for residents' transportation resource demands under multiple cross-sections according to the set of residents' transportation resource demands and influencing factors; Based on the deterministic utility function, simulate the usage behavior of discrete-continuous transportation resources of residents within one day under multiple cross-sections of urban development, and construct a prediction model for residents' transportation resource demands for trips under multiple cross-sections of urban development.

10. The method according to claim 9, wherein the formula expression of the deterministic utility function is: wherein, is the utility of individual i choosing travel mode M, is the household characteristic vector of individual i, is the personal characteristic vector of individual i, is the characteristic vector of travel scenarios involved in a day for resident i, is the characteristic vector of the built environment involved in the one-day travel of resident i, , , and are the coefficient vectors corresponding to the characteristic vectors, is the random error term.

Images