Methods, devices, equipment and storage media for predicting per capita car ownership in cities

Abstract

This application provides a method, apparatus, equipment, and readable storage medium for predicting per capita car ownership in cities, belonging to the field of data prediction technology. The method includes: obtaining per capita income of urban residents, the proportion of driver's license holders, and differences in transportation accessibility, wherein the differences in transportation accessibility represent the difference in transportation convenience between having a car and not having a car; determining the saturation level of urban private car ownership; using the per capita income of urban residents, the proportion of driver's license holders, and the differences in transportation accessibility to obtain a prediction factor, wherein the prediction factor is used to predict car ownership; and calculating the per capita car ownership in cities based on the saturation level of urban car ownership and the prediction factor. This prediction method has the advantages of low data requirements, ease of understanding, and scalability.

Description

Technical Field

[0001] This application relates to the field of data prediction technology, specifically to methods, devices, equipment, and storage media for predicting per capita car ownership in cities. Background Technology

[0002] Urban car ownership is a core indicator for measuring urban motorization levels, traffic demand, energy consumption, and environmental impact. Accurate simulation and forecasting of this data are the prerequisite and foundation for urban traffic planning, infrastructure investment, congestion management, carbon emission peaking strategies, and the development of the new energy vehicle industry. The accuracy of the forecast directly affects the scientific nature of policy-making and the effectiveness of resource allocation.

[0003] Existing forecasting methods can be broadly classified into three categories: traditional statistical methods based on historical data, econometric methods based on causal relationships, and multi-agent methods based on complex system simulation.

[0004] Existing methods suffer from the following main shortcomings: First, challenges in data quality and availability. Data granularity is insufficient; macro-level statistics cannot reflect the heterogeneous behavior of micro-level individuals, and high-quality micro-level data such as household income and expenditure surveys and personal travel surveys are lacking. Data timeliness is poor; many key data (such as population censuses) have long update cycles, failing to support real-time or near-real-time forecast adjustments. Data on emerging factors is also lacking: systematic and long-term observational data on the impact of new transportation modes such as ride-hailing and car-sharing on car ownership is lacking. Second, limitations of the models themselves. All models based on historical patterns implicitly assume that the future is a continuation of the past. However, when disruptive changes occur, the models fail. Nonlinearity and interaction effects are difficult to capture: traditional regression models struggle to handle complex nonlinear relationships and interactions between variables. Although existing urban car ownership prediction models attempt to address this issue, their rule settings rely heavily on subjective assumptions, resulting in complex processing methods and hindering generalization. Summary of the Invention

[0005] In view of this, the embodiments of the present invention are committed to providing a method, apparatus, equipment and storage medium for predicting the per capita car ownership in cities, which has the advantages of small data requirements and easy understanding and promotion.

[0006] In a first aspect, the present invention provides a method for predicting the per capita car ownership in cities, comprising:

[0007] The data includes the per capita income of urban residents, the proportion of driver's license holders, and differences in transportation accessibility. Differences in transportation accessibility represent the difference in transportation convenience between having a car and not having a car.

[0008] Determine the saturation level of private car ownership in the city;

[0009] Using the per capita income of the city's residents, the proportion of driver's license holders, and the differences in transportation accessibility, a predictive factor is obtained, wherein the predictive factor is used to predict car ownership.

[0010] The per capita car ownership in the city is calculated based on the saturation level of the city's car ownership and the predictive factor.

[0011] Furthermore, the formula for calculating the difference in traffic accessibility is as follows:

[0012] Among them, A t(1+) For the accessibility of self-driving travel in year t, A t(0) For accessibility by public transport, A t(1+) and A t(0) All calculations use time cost, d t The difference in accessibility between public transportation and private vehicles.

[0013] Furthermore, the formula for calculating the predictor is as follows: Where lic is the proportion of driver's license holders, Inc is the household income, and α, β, and γ are coefficients to be determined.

[0014] Furthermore, the formula for calculating the per capita car ownership in the city is as follows: , where p t Let X be the per capita car ownership, s be the saturation level of car ownership, and X be the number of cars owned per capita. t The predictor is referred to as "the predictor".

[0015] Furthermore, the saturation level of private car ownership in the city was determined by referring to the situation in developed countries.

[0016] Secondly, the present invention provides an urban car ownership prediction device, comprising:

[0017] Acquisition Module: Used to acquire data on the per capita income of urban residents, the proportion of driver's license holders, and differences in transportation accessibility. Among these, differences in transportation accessibility represent the difference in transportation convenience between having a car and not having a car.

[0018] Determining module: Used to determine the saturation level of private car ownership in a city;

[0019] Calculation module: used to calculate a predictive factor using the per capita income of the city's residents, the proportion of driver's license holders, and the differences in transportation accessibility, wherein the predictive factor is used to predict car ownership;

[0020] Prediction module: used to calculate the per capita car ownership in the city based on the saturation level of the city's car ownership and the prediction factor.

[0021] Thirdly, the present invention provides an electronic device including a memory and a processor, the memory being used to store a computer program, and the processor being used to implement the method described in any of the preceding claims when the computer program is executed.

[0022] Fourthly, the present invention provides a storage medium storing a computer program that, when executed by a processor, implements the method described in any of the preceding claims.

[0023] This application can achieve at least the following beneficial effects: by using the above method, the number of cars can be calculated using driver's license holding data, income data and accessibility data. Compared with the existing technology, the number of cars in a city can be calculated using a small amount of indicator data, providing more methodological options when data availability is low. The data requirement is small and it is easy to understand and promote. Attached Figure Description

[0024] Figure 1 The diagram shown is a flowchart illustrating the urban per capita car ownership prediction method provided in the embodiments of this specification.

[0025] Figure 2 This is a schematic diagram illustrating the principle of the urban per capita car ownership prediction method provided in the embodiments of this specification.

[0026] Figure 3 The Stata regression results are shown in the examples provided in this specification. Detailed Implementation

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] The following describes the embodiments in conjunction with the appendix to the instruction manual. Figures 1-2 Specific details:

[0029] Example 1 of this specification provides a method for predicting the per capita car ownership in cities, including:

[0030] S1. Obtain the per capita income of urban residents, the proportion of driver's license holders, and the differences in transportation accessibility. Among them, the differences in transportation accessibility represent the differences in transportation convenience between having a car and not having a car.

[0031] In the embodiments of this specification, the per capita income of urban residents and the proportion of driver's license holders are obtained from various statistical yearbooks, while the differences in traffic accessibility need to be calculated using GIS software based on road network data. The travel time in the city under the two transportation options of public transportation and private driving is obtained by the following formula.

[0032]

[0033] Among them, A t(1+) With A t(0) Let d represent the accessibility of two travel types in year t: driving (with a car) and taking public transportation (without a car). Time cost is used for calculation. t The difference in accessibility between public transportation and private vehicles reflects the advantages of owning a car.

[0034] S2. Determine the saturation level of private car ownership in the city;

[0035] As the economy continues to develop, the number of cars owned by residents will continue to increase, but it will usually tend to reach a saturation level. This value is the limit of the model's predicted value, meaning that the model's predicted value can approach this value infinitely but will not exceed it. Specifically, the saturation level of urban private car ownership is determined by referring to the situation in developed countries.

[0036] S3. Using the per capita income of the city residents, the proportion of driver's license holders, and the difference in transportation accessibility, a prediction factor is obtained, wherein the prediction factor is used to predict the number of cars owned.

[0037] This predictor is a weighted average of multiple indicator data; therefore, a regression method is needed to determine the coefficients before calculating X. The calculation formula is as follows, where lic, d, and Inc represent the proportion of urban regression holders, the difference in accessibility (public transport vs. private car), and residents' income, respectively.

[0038]

[0039] S4. Calculate the per capita car ownership in the city based on the city's car ownership saturation level and the predictive factor. The calculation formula is as follows:

[0040]

[0041] In the formula, p t Let t represent the per capita car ownership in year t, and s be the number of cars owned per capita. t These are the saturation level of car ownership and the predictive factor calculated in the previous step, respectively.

[0042] Example 2 predicts the per capita car ownership in Shanghai. According to the method described above, the required data includes the total number of private cars in the city in historical years, the proportion of licensed drivers, the per capita income of urban residents, transportation accessibility (both with and without cars), and the average number of cars per household. The variable to be predicted (dependent variable) is the per capita car ownership.

[0043] The panel model is established as follows:

[0044] (1)

[0045] (2)

[0046] (3)

[0047] in, Let X be the number of private cars per capita, and s be the level at which household car ownership reaches saturation. t The predictor for year t is a weighted average of various influencing factors, reflecting residents' propensity to purchase cars. Predictor X t It consists of the following variables, lic t (Percentage of driver's license holders), Inc. t (Household income), d t (Accessibility differences, i.e., the difference in accessibility between households with cars and those without cars.) and The time is calculated based on whether there is a car or not. If there is a car, the time is calculated using car speed; if there is no car, the time is calculated using public transportation.

[0048] The model used in the embodiments of this specification is the Logit model. The Logit model is used because the relationship between car ownership and variables such as income is not linear. As residents' propensity to purchase cars increases (X), the number of cars owned by residents will increase, but will tend towards a saturation value. In this model, as the predictor factors continue to increase, the per capita car ownership will tend towards a saturation value S.

[0049] The specific process for predicting Shanghai's car ownership is as follows:

[0050] Step 1, Data Acquisition.

[0051] Due to the difficulty in obtaining detailed car ownership data, we used city-level data. First, we included data on Shanghai's per capita private car ownership (calculated from the number of private cars and the total population), the percentage of licensed drivers (calculated from the number of drivers and the total population), per capita disposable income, and accessibility (calculated by the time to reach downtown Shanghai from each district, including public transportation time and driving time).

[0052] The difference in accessibility can be obtained by subtracting the accessibility by public transport from that by driving, as shown in the formula below.

[0053] Shanghai Number of private cars (in ten thousand vehicles) Resident population (10,000s) Number of cars per capita Y per capita disposable income Number of drivers holding driver's licenses (in ten thousand) Percentage of driver's license holders L (%) Accessibility (by bus) (minutes) Accessibility (by car) (minutes) Difference in accessibility 2010 85.03 2302.66 0.037 3.04 189.00 0.082 128.9 51.4 77.5 2011 103.71 2356 0.044 3.47 235.60 0.100 128.9 51.4 77.5 2012 119.75 2399 0.050 4.02 524.00 0.218 128.9 51.4 77.5 2013 141.16 2448 0.058 4.39 560.00 0.229 105.5 47.1 58.4 2014 183.3 2467 0.074 4.77 616.00 0.250 105.5 47.1 58.4 2015 208.65 2458 0.085 4.99 650.67 0.265 105.5 47.1 58.4 2016 242.66 2467 0.098 5.43 679.12 0.275 89.2 43.1 46.1 2017 274.38 2466 0.111 5.90 715.68 0.290 89.2 43.1 46.1 2018 302.14 2475 0.122 6.42 751.47 0.304 89.2 43.1 46.1 2019 321.27 2481 0.129 6.94 790.06 0.318 79.5 39.4 40.1 2020 347.59 2488.22 0.140 7.22 814.51 0.327 79.5 39.4 40.1 2021 362.91 2489.43 0.146 7.80 881.00 0.354 79.5 39.4 40.1 2022 395.72 2475 0.160 7.96 930.00 0.376 69.7 40.1 29.44 2023 419.6 2487.45 0.169 8.48 966.27 0.388 69.7 40.1 29.44 2024 454.23 2480.26 0.183 8.84 1021.40 0.412 69.7 40.1 29.44

[0054] Step 2, determine the saturation level (S) of private car ownership.

[0055] This indicator represents the future saturation level of private car ownership in cities, and it is difficult to know precisely. However, we determined this value by referring to the situation in developed countries. The car ownership situation in some developed countries is shown in the table below (2023) (there are slight differences between different data sources).

[0056] Clearly, the United States has the highest per capita car ownership, followed by Italy. The European Union has a per capita car ownership of 0.55 vehicles per person. Since the EU includes multiple countries, this figure is an average across those countries; therefore, we choose 0.55 vehicles per person as the saturation level for per capita car ownership.

[0057] Country Name USA Italy Australia Canada Japan Germany EU Number of cars per person (vehicles / person) 0.864 0.694 0.747 0.670 0.49 0.58 0.55

[0058] Step 3, calculate the car ownership predictor X.

[0059] Before using the model to calculate car ownership, it is necessary to calculate the predictor factor X. The calculation of X requires determining the coefficients of each variable, as shown in formula (2). To this end, we can transform formulas (1) and (2) and take the logarithm to obtain the following formula, which is a linear formula. The coefficients α, β, γ, and ε can be obtained through regression.

[0060]

[0061] For historical years, only the coefficients α, β, γ, and ε are unknown in the above formula; all other data are known. We use the historical data to perform regression and determine the values ​​of the coefficients, as shown in the table below. Adj-R 2 =0.9922, which achieved a very good simulation effect.

[0062] α (constant) β γ ε -12.19916 3.047537 0.9166558 -0.0003778

[0063] Stata regression results are as follows Figure 3 As shown.

[0064] Step 4, Model Application: Predict the future per capita car ownership in cities.

[0065] The foregoing indicates that the method of this invention can achieve excellent results in simulating urban car ownership from 2010 to 2024. Based on this, this section applies the method to predict future car ownership in Shanghai.

[0066] To predict future urban private car ownership, we need to determine future variables including the proportion of licensed drivers (lic), income (Inc), and accessibility. We determine the variable values ​​up to 2030 based on historical data trends (see figure below). Regarding transportation accessibility, since transportation changes relatively slowly, we assume that the transportation network remains unchanged in the short term.

[0067]

[0068] After determining the indicator values ​​for each future year, substituting them into formulas (1), (2), and (3) allows us to predict the per capita car ownership for each year, as shown in the table below.

[0069] Percentage of driver's license holders Disposable income ln(I) d X Simulated value per capita car 2025 0.42313 93052 11.44 25.00 -0.53 0.204 2026 0.44159 97205 11.48 25.00 -0.43 0.216 2027 0.46005 101359 11.53 25.00 -0.34 0.229 2028 0.47849 105512 11.57 20.00 -0.23 0.244 2029 0.49693 109666 11.61 20.00 -0.13 0.257 2030 0.51535 113819 11.64 20.00 -0.04 0.269

[0070] This shows that the proportion of driver's license holders and disposable income will continue to change in the future, and by 2030, the average number of private cars owned per person in Shanghai will reach 0.269.

[0071] The predicted changes in variables such as the proportion of licensed drivers and disposable income are input items for the embodiments of this specification. Changes in these variables can be used to examine the impact of policies, for example, examining the impact on urban car ownership after income rises to a certain level; or the impact of subway construction (changing accessibility) on urban car ownership, etc.

[0072] Based on the same idea, embodiments of this specification provide an urban car ownership prediction device, comprising:

[0073] Acquisition Module: Used to acquire data on the per capita income of urban residents, the proportion of driver's license holders, and differences in transportation accessibility. Among these, differences in transportation accessibility represent the difference in transportation convenience between having a car and not having a car.

[0074] Determining module: Used to determine the saturation level of private car ownership in a city;

[0075] Calculation module: used to calculate a predictive factor using the per capita income of the city's residents, the proportion of driver's license holders, and the differences in transportation accessibility, wherein the predictive factor is used to predict car ownership;

[0076] Prediction module: used to calculate the per capita car ownership in the city based on the saturation level of the city's car ownership and the prediction factor.

[0077] Based on the same idea, this specification provides an electronic device including a memory and a processor. The memory is used to store a computer program, and the processor is used to implement the method described in any of the above-mentioned embodiments when the computer program is executed.

[0078] Based on the same idea, embodiments of this specification provide a storage medium storing a computer program that, when executed by a processor, implements the method described in any of the above-mentioned embodiments.

[0079] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the aforementioned specific details.

[0080] The block diagrams of devices, apparatuses, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0081] It should also be noted that in the apparatus, device, and method of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of the present invention.

[0082] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0083] It should be understood that the qualifying terms "first", "second", "third", "fourth", "fifth" and "sixth" used in the description of the embodiments of the present invention are only used to more clearly illustrate the technical solutions and are not intended to limit the scope of protection of the present invention.

[0084] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method of predicting the number of cars per capita in a city, characterized by, include: The data includes the per capita income of urban residents, the proportion of driver's license holders, and differences in transportation accessibility. Differences in transportation accessibility represent the difference in transportation convenience between having a car and not having a car. Determine the saturation level s of urban private car ownership; Using the per capita income of the city's residents, the proportion of driver's license holders, and the differences in transportation accessibility, a predictive factor is obtained, wherein the predictive factor is used to predict car ownership. The per capita car ownership in the city is calculated based on the saturation level of the city's car ownership and the predictive factor.

2. The method of claim 1, wherein, The formula for calculating the difference in accessibility is as follows: where A t(1+) is the accessibility of self-driving travel for t years, A t(0) is the accessibility of taking the bus, A t(1+) and A t(0) are both calculated by time cost, d t is the difference between the two types of accessibility.

3. The method according to claim 1, characterized in that, The formula for calculating the predictor is: , among which, lic t The percentage of driver's license holders in year t, Inc t Let be the family income in year t, and α, β, and γ be coefficients to be determined.

4. The method according to claim 1, characterized in that: The formula for calculating the per capita car ownership in the city is as follows: , where p t Let X be the number of cars owned per capita in year t, s be the saturation level of car ownership in year t, and X be the number of cars owned per capita in year t. t The predictor is referred to as "the predictor".

5. The method according to claim 1, characterized in that: The saturation level of private car ownership in the city was determined by referring to the situation in developed countries.

6. A device for predicting urban car ownership, characterized in that, include: Acquisition Module: Used to acquire data on the per capita income of urban residents, the proportion of driver's license holders, and differences in transportation accessibility. Among these, differences in transportation accessibility represent the difference in transportation convenience between having a car and not having a car. Determining module: Used to determine the saturation level of private car ownership in a city; Calculation module: used to calculate a predictive factor using the per capita income of the city's residents, the proportion of driver's license holders, and the differences in transportation accessibility, wherein the predictive factor is used to predict car ownership; Prediction module: used to calculate the per capita car ownership in the city based on the saturation level of the city's car ownership and the prediction factor.

7. An electronic device, characterized in that: The system includes a memory and a processor, the memory being used to store a computer program, and the processor being used to implement the method according to any one of claims 1 to 5 when the computer program is executed.

8. A storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 5.

Images