System and method for predicting urban rental housing demand scale based on multi-source data

Abstract

The present invention relates to the field of urban multi-source data mining and analysis, and in particular to a system and method for predicting the scale of urban rental housing demand based on multi-source data. The system includes a data acquisition module, a storage module, an input module, a rental population prediction module, and a rental housing demand scale module, wherein the rental population prediction module determines the target city housing rental population through collaborative prediction by multiple prediction submodules; the rental housing demand scale module predicts the number of housing sources required in the urban housing rental market in the forecast year based on the rental population prediction module and the storage module. The present invention predicts the urban housing rental population from multiple angles, which not only eliminates the possible deviations of a single prediction method, but also further improves the accuracy and reliability of the overall prediction; at the same time, the present invention also overcomes the defect of using fixed values ​​in traditional prediction methods, making the prediction results more scientific, reasonable and practical, and further improving the accuracy of the prediction.

Description

Technical Field

[0001] The present invention relates to the field of urban multi-source data mining and analysis, and in particular to a system and method for predicting the scale of urban rental housing demand based on multi-source data. Background Art

[0002] The housing rental market consists of supply and demand. The supply side includes individuals, government and housing rental enterprises. In the process of urbanization, the rural population has transformed into the urban population. These new influxes have greatly stimulated the demand for urban rental housing. In addition, the increasing number of college graduates each year, the renting of houses for their children to go to school, and the increased demolition and reconstruction of shanty towns and old communities have all given rise to a huge demand for rental housing. However, due to the non-permanence and instability of housing rental relationships, the current housing rental market has problems such as strong mobility of the rental population, unclear rental housing supply, and unknown scale.

[0003] At present, the calculation of urban housing rental demand is mainly based on the calculation of the rental population. The commonly used methods are the floating population size method and the home ownership rate method. Among them, the floating population size method requires the use of the floating population number in previous years, which is difficult to obtain; the home ownership rate method uses a unified fixed value when calculating the proportion of the population that solves the housing demand through leasing in the city, ignoring the impact of different levels of urban economic development on the home ownership rate, and lacks quantitative measurement of the urban home ownership rate. In addition, when calculating the scale of rental housing sources based on the size of the rental population, the average household size uses a fixed value, ignoring the trend of the average household size of residents gradually shrinking with the dynamic changes in the urban social economy. Therefore, the existing calculation method needs to be revised and improved.

[0004] Therefore, in order to promote the standardized development of the urban housing rental market, it is urgent to find a scientific and reasonable method to predict the scale of housing demand in the urban housing rental market, so as to provide support for strengthening housing rental supervision, formulating housing rental policies, stabilizing and standardizing the order of the housing rental market, and cultivating and developing the housing rental market. Summary of the invention

[0005] In view of the shortcomings of the above-mentioned prior art, the present invention provides a system and method for predicting the scale of urban rental housing demand based on multi-source data, aiming to provide an innovative technical solution to overcome the defects of the existing prediction methods, such as the difficulty in obtaining the number of floating population and the use of fixed values ​​in the housing supply scale prediction process, which has poor flexibility and is out of touch with reality, so as to more scientifically and reasonably predict the scale of urban housing rental population and rental market housing demand.

[0006] The present invention, on the basis of fully considering the actual situation of urban housing rental, has made scientific improvements to the floating population size method and the home ownership rate method, and obtained a more accurate target urban housing rental population by collaboratively predicting the initial urban housing rental population through the comprehensive improvement of the floating population size method and the home ownership rate method; at the same time, based on multiple national census data, the trend of changes in the average urban household size is calculated, thereby predicting the average urban household size data over the years, overcoming the defects of the traditional use of fixed values, and making the predicted urban housing rental market housing demand scale more scientific, reasonable and accurate.

[0007] The present invention provides a system for predicting the scale of urban rental housing demand based on multi-source data, comprising:

[0008] The data collection module is used to collect data from national censuses, statistical yearbooks, average household size data, and retention rate data of college graduates from various regions published on relevant websites in real time;

[0009] A data processing module, used for processing the data collected by the data collection module;

[0010] A storage module, used for storing data processed by the data processing module;

[0011] An input module, used for users to input forecast demand information;

[0012] The rental population prediction module includes multiple prediction submodules. Based on the information transmitted by the input module and the data stored by the storage module, the multiple prediction submodules collaboratively predict the initial urban housing rental population, thereby determining the target urban housing rental population;

[0013] The rental housing demand scale module predicts the number of housing demand in the urban housing rental market in the forecast year based on the target city's housing rental population predicted by the rental population prediction module and the data stored in the storage module.

[0014] Preferably, the national census data includes urban permanent population data, urban registered population data, urban floating population data and housing data, wherein the housing data includes housing sources, the number of housing from each source and the housing area from each source; the statistical yearbook data includes urban permanent population data, urban registered population data and urban college graduates data;

[0015] The forecast demand information includes the forecast city, forecast year, and several consecutive national census data before the forecast year.

[0016] Preferably, the data processing mentioned in the data processing module refers to processing operations on the collected data including data cleaning, feature selection, feature conversion and data encoding.

[0017] Preferably, the rental population prediction module specifically includes a first prediction sub-module, a second prediction sub-module, and a third prediction sub-module, wherein the first prediction sub-module and the second prediction sub-module respectively predict the initial urban housing rental population based on different angles, and the third prediction sub-module determines the target city housing rental population by integrating the prediction results of the first prediction sub-module and the second prediction sub-module.

[0018] Preferably, the first prediction submodule predicts the initial urban housing rental population based on the improved floating population size method, and the specific steps are:

[0019] S11. Based on the data of the national census, the floating population coefficient of each city is calculated. The calculation formula is as follows: ”

[0020] In the formula, represents the urban floating population coefficient of the i-th national census, represents the number of urban migrant population in the i-th national census, represents the number of permanent urban residents in the i-th national census, represents the number of urban registered population in the i-th group of national census;

[0021] S12. Based on the coefficients of floating population in previous cities, the average coefficients of floating population in previous cities are obtained. The calculation formula is as follows: ”

[0022] In the formula, represents the mean value of the coefficient of floating population in cities over the years, and n represents the number of groups of national census data used;

[0023] S13. Based on the average of the urban floating population coefficients of previous years, the urban floating population in the forecast year is calculated. The calculation formula is as follows: ”

[0024] In the formula, represents the number of urban floating population in the forecast year, It represents the number of urban permanent residents predicted in the statistical yearbook data. It represents the number of urban registered population in the predicted year in the statistical yearbook data;

[0025] S14. Introduce the retention rate of college graduates into the traditional floating population scale method to calculate the initial urban housing rental population in the forecast year. The calculation formula is as follows: ”

[0026] In the formula, represents the number of urban housing rental population in the initial forecast year based on the improved floating population size method, GR represents the number of urban college graduates in the past five years including the forecast year, represents the retention rate of college graduates in the past five years, including the forecast year. Indicates the proportion of floating population renting houses.

[0027] Preferably, in step S14 The retention rate of college graduates with the largest value in the past five years, or the retention rate of college graduates with the smallest value in the past five years, or the average retention rate of college graduates in the past five years;

[0028] The proportion of migrant population renting houses is 67.3% based on the "China Migrant Population Development Report".

[0029] Preferably, the second prediction submodule predicts the initial urban housing rental population based on the improved home ownership rate method, and the specific steps are:

[0030] S21. Housing data based on the national census data closest to the forecast year, excluding the number of houses in towns and villages, and summarizing the number of houses in the central urban area;

[0031] S22. Based on the source of housing, various types of housing in the central urban area are divided into home-owning households, home-renting households and other households, so as to obtain the urban home-ownership rate. The calculation formula is as follows: ”

[0032] Where A represents the urban housing ownership rate, represents the number of households that own their own home, represents the number of households renting housing, The number of households that indicated that they solved their housing problem through other means;

[0033] S23. Based on the urban housing ownership rate, calculate the initial urban housing rental population in the forecast year. The calculation formula is as follows: ”

[0034] In the formula, represents the number of urban housing rental population in the initial forecast year based on the improved home ownership rate method, It indicates the number of permanent urban population in the predicted year from the statistical yearbook data.

[0035] Preferably, the third prediction submodule determines the housing rental population in the target city by integrating the prediction results of the first prediction submodule and the second prediction submodule, and the specific steps are:

[0036] “ ”

[0037] Where RP represents the number of people renting housing in the target city.

[0038] Preferably, the specific prediction steps of the rental housing demand scale module are:

[0039] S31. Based on the data from the national census, the average household size in the city in the forecast year is calculated using the following formula: ”

[0040] Where AFS represents the average household size in the city in the forecast year, represents the average household size of the city published by the national census of the i-th group, Y represents the forecast year, The year represents the national census year closest to the forecast year;

[0041] S32, combining the target city's housing rental population predicted by the rental population prediction module and the average household size of the city in the forecast year predicted in step S41, calculate the number of housing sources required in the city's housing rental market in the forecast year, and the calculation steps are as follows: ”

[0042] Wherein, HD represents the number of housing demand in the urban housing rental market in the forecast year.

[0043] The present invention also provides a method for predicting the demand scale of urban rental housing based on multi-source data, which is applied to a system for predicting the demand scale of urban rental housing based on multi-source data, and the specific steps are:

[0044] S41, the input module sends the predicted demand information input by the user to the rental population prediction module;

[0045] S42, after receiving the forecast demand information, the rental population forecasting module calls the data stored in the storage module, and collaboratively forecasts the initial urban housing rental population through multiple forecasting submodules, thereby determining the target urban housing rental population;

[0046] S43. The rental housing demand scale module obtains the target city's housing rental population predicted by the rental population prediction module, and at the same time calls the data stored in the storage module to predict the number of housing demand in the urban housing rental market in the forecast year.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention uses the urban permanent population data and registered population data in the statistical yearbooks of previous years to obtain the initial urban floating population data, which provides a solid foundation for prediction. At the same time, the urban floating population coefficients of previous years are obtained based on the national census data. The initial urban floating population data are corrected by introducing the average of the urban floating population coefficients of previous years, thereby realizing an improvement on the traditional floating population scale method. The improved method effectively reduces the deviation caused by differences in statistical caliber or methods, makes up for the missing data, and further increases the accuracy of the prediction results. It also provides researchers with an effective alternative, which helps to fill the gap in urban housing rental population data, and provides a new perspective and tool for urban housing rental population research, which helps to promote in-depth related research.

[0049] 2. The present invention uses the housing data of the most recent national census data to predict the urban home ownership rate, which changes the defect of the traditional home ownership rate method that uses a fixed value for the home ownership rate in the calculation process. It not only takes into account the differences in development between different cities, but also is more targeted and can more accurately reflect the current home ownership rate status of the city.

[0050] 3. The present invention predicts the initial urban housing rental population from different angles through improved floating population size method and home ownership rate method, taking into account both the changes in floating population and the source of urban household housing; then, the target urban housing rental population is obtained by integrating the prediction results from multiple angles, which not only eliminates the possible deviations of a single prediction method, thereby improving the accuracy and reliability of the overall prediction, but also helps to capture the various factors that affect the changes in the urban housing rental population, more comprehensively reflects the changing trend of the urban housing rental population, and provides a more scientific and reasonable decision-making basis for the government to formulate relevant housing policies, plan the development of the urban housing rental market, and meet the housing needs of residents.

[0051] 4. The present invention measures the changing trend of the average urban household size based on multiple national census data, thereby predicting the average urban household size data over the years, overcoming the defects of the traditional use of fixed values, making the predicted urban housing rental market demand scale more scientific, reasonable and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1A schematic block diagram of a system for predicting the scale of urban rental housing demand based on multi-source data provided by the present invention;

[0054] Figure 2 A graph showing changes in the permanent population and urbanization rate of a city provided by the present invention;

[0055] Figure 3 The average household size change trend chart of different cities from 1990 to 2010 provided by the present invention;

[0056] Figure 4 A flow chart of a method for predicting the scale of urban rental housing demand based on multi-source data provided by the present invention. DETAILED DESCRIPTION

[0057] 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 only 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 are within the scope of protection of the present invention.

[0058] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as limiting the present invention; the terms "first", "second", and "third" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance. In addition, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0059] like Figure 1-2 As shown, the present invention provides a system for predicting the scale of urban rental housing demand based on multi-source data, comprising:

[0060] The data collection module is used to collect in real time the data of national censuses, statistical yearbooks of previous years, average household size data and the retention rate data of college graduates from various regions published on relevant websites.

[0061] Preferably, the national census data includes urban permanent population data, urban registered population data, urban floating population data and housing data, wherein the housing data includes housing sources, the number of housing from each source and the housing area from each source; the statistical yearbook data includes urban permanent population data, urban registered population data and urban college graduate data.

[0062] It should be noted that the data acquired in real time in the data acquisition module is obtained by manual supplementation and automatic collection by the system.

[0063] The data processing module of the present invention is used for processing the data collected by the data collection module.

[0064] In the present application, the data processing mentioned in the data processing module refers to processing operations on the collected data including data cleaning, feature selection, feature conversion and data encoding.

[0065] The storage module involved in the present invention is used for storing data processed by the data processing module.

[0066] The input module involved in the present invention is used for users to input forecast demand information.

[0067] Preferably, the forecast demand information includes the forecast city, the forecast year, and several consecutive national census data before the forecast year.

[0068] In the embodiment of the present application, the system can be used to predict the scale of housing demand in all cities across the country in a certain year, and can also predict the scale of housing demand in a certain city in a certain year.

[0069] For example, if the forecast demand information entered by the user is "Baoding, 2023, 2", it means that the user wants to forecast the number of housing sources in the urban housing rental market in Baoding in 2023, and the two consecutive national census data before 2023 are selected for forecasting, that is, the sixth to seventh national census data; if the forecast demand information entered by the user is "National, 2023, 3", it means that the user wants to forecast the number of housing sources in the urban housing rental market in all cities in the country in 2023, and the three consecutive national census data before 2023 are selected for forecasting, that is, the fifth to seventh national census data. In actual application, the specific number of consecutive national census data before the forecast year is selected and set according to the user's needs.

[0070] The rental population prediction module involved in the present invention includes multiple prediction sub-modules. Based on the information transmitted by the input module and the data stored by the storage module, the initial urban housing rental population is predicted through the multiple prediction sub-modules to determine the target urban housing rental population.

[0071] In the present application, the rental population prediction module specifically includes a first prediction sub-module, a second prediction sub-module, and a third prediction sub-module, wherein the first prediction sub-module and the second prediction sub-module respectively predict the initial urban housing rental population based on different angles, and the third prediction sub-module determines the target city housing rental population by integrating the prediction results of the first prediction sub-module and the second prediction sub-module.

[0072] Due to the instability of the urban housing rental population, this application improves the floating population size method and the home ownership rate method respectively to enhance the scientific nature of the calculation results.

[0073] In the embodiment of the present application, the first prediction submodule predicts the initial urban housing rental population based on the improved floating population size method, and the specific steps are:

[0074] S11. Based on the data of the national census, the floating population coefficient of each city is calculated. The calculation formula is as follows: ”

[0075] In the formula, represents the urban floating population coefficient of the i-th national census, represents the number of urban migrant population in the i-th national census, represents the number of permanent urban residents in the i-th national census, represents the number of urban registered population in the i-th national census.

[0076] S12. Based on the coefficients of floating population in previous cities, the average coefficients of floating population in previous cities are obtained. The calculation formula is as follows: ”

[0077] In the formula, represents the average of the coefficient of floating population in cities over the past dynasties, and n represents the number of groups of national census data used.

[0078] In the embodiment of the present application, the national census data of all time are sorted in order from the beginning to the end according to the census time. For example, when the sixth and seventh national census data are studied, the sixth national census data is the first group of national census data, and the seventh national census data is the second group of national census data, and n=2 at this time.

[0079] It should be noted that when predicting the housing rental population in all cities across the country, the national total data from the national census data is used to calculate the coefficient of urban floating population over the past dynasties; when predicting the housing rental population in a certain city, the data of that city in the national census data is used to calculate the coefficient of urban floating population over the past dynasties.

[0080] S13. Based on the average of the urban floating population coefficients of previous years, the urban floating population in the forecast year is calculated. The calculation formula is as follows: ”

[0081] In the formula, represents the number of urban floating population in the forecast year, It represents the number of urban permanent residents predicted in the statistical yearbook data. It indicates the number of registered urban population in the predicted year from the statistical yearbook data.

[0082] When the floating population in a city can be directly obtained through the dynamic monitoring data of the floating population, researchers can directly obtain the floating population data of the city over the years. However, when the floating population data of the city over the years cannot be directly obtained, it will become a problem that hinders researchers from conducting in-depth research. This application proposes a novel method for predicting the floating population data of the city over the years to address this problem. In the absence of direct data, this application first uses the urban permanent population data and registered population data in the statistical yearbooks of previous years to obtain the initial floating population data of the city, which provides a solid foundation for prediction; secondly, based on the national census data, the floating population coefficients of previous cities are obtained, and the initial floating population data of the city are corrected by introducing the mean of the floating population coefficients of previous cities, which effectively reduces the deviation caused by differences in statistical caliber or methods, and further increases the accuracy of the prediction results. In addition, this application provides researchers with an effective alternative solution, which helps to fill the gap in urban housing rental population data, and provides new perspectives and tools for urban housing rental population research, which helps to promote the in-depth study of related research.

[0083] S14. Introduce the retention rate of college graduates into the traditional floating population scale method to calculate the initial urban housing rental population in the forecast year. The calculation formula is as follows: ”

[0084] In the formula, represents the number of urban housing rental population in the initial forecast year based on the improved floating population size method, GR represents the number of urban college graduates in the past five years including the forecast year, represents the retention rate of college graduates in the past five years, including the forecast year. Indicates the proportion of floating population renting houses.

[0085] It should be noted that most of the college graduates in the past five years are homeless and need to stay in the city for life or work, so they have a high demand for renting houses. However, five years after graduation, some college graduates can become homeowners by purchasing houses, and the proportion of these college graduates renting houses will drop significantly. Therefore, the calculation of urban housing rental population in this application only considers urban college graduates in the past five years, including the forecast year.

[0086] It should be noted that since the government will not publish the retention rate data of college graduates continuously throughout the year, the embodiment of this application obtains the retention rate of college graduates in the city based on the research reports of the Human Resources and Social Security Bureau or various websites, such as Beike.com and Lianjia.com, and uses this as a reference. This is more flexible and in line with the actual situation of the city than the traditional method of directly adopting a fixed national value.

[0087] In this application, the retention rate of college graduates is the retention rate of college graduates who stay in local employment. In addition, since there is a corresponding retention rate of college graduates every year, the step S14 in this application You can choose the college graduate retention rate with the largest value in the past five years, you can choose the college graduate retention rate with the smallest value in the past five years, or you can choose the average of the past five years. This application does not make specific restrictions. In actual use, the user can set it according to actual needs. In the embodiment of this application, Select the college graduate retention rate with the largest value in the past five years.

[0088] In the embodiment of the present application, the proportion of floating population renting houses is 67.3% based on the "China Floating Population Development Report". In actual use, users can adjust the proportion according to their actual needs.

[0089] In the embodiment of the present application, the second prediction submodule predicts the initial urban housing rental population based on the improved home ownership rate method, and the specific steps are as follows:

[0090] S21. Based on the housing data of the most recent national census data for the forecast year, the number of houses in towns and villages is excluded and the number of houses in the central urban area is summarized.

[0091] It should be noted that the housing source data is obtained through the "housing source" statistical table of the national census data, where housing sources are divided into 9 categories, specifically: renting low-rent housing / public rental housing, renting other housing, purchasing new commercial housing, purchasing second-hand housing, purchasing former public housing, purchasing affordable housing / two-limit housing, self-built housing, inheritance / donation and others, where "other" refers to situations other than the above-mentioned housing sources. Considering that the "housing source" statistical table is refined into different levels such as all, cities, towns, and villages, and towns and villages have more self-owned property rights, higher housing ownership rates, and lower rental demand, it may affect the calculation of urban housing ownership rates. In order to improve data reliability and eliminate the influence of extreme values, in the embodiment of this application, when calculating urban housing ownership rates, only the housing data of the central urban area is selected for calculation.

[0092] S22. Based on the source of housing, various types of housing in the central urban area are divided into home-owning households, home-renting households and other households, so as to obtain the urban home-ownership rate. The calculation formula is as follows: ”

[0093] Where A represents the urban housing ownership rate, represents the number of households that own their own home, represents the number of households renting housing, Indicates the number of households that solve their housing problems through other means.

[0094] In the embodiment of the present application, families in the central urban area who purchase newly built commercial housing, second-hand housing, former public housing, affordable housing / two-limit housing, self-built housing, and inherited / gifted housing are classified as housing-owner families, families in the central urban area who rent low-rent housing / public housing and other housing are classified as housing rental families, and other families in the central urban area are classified as other families.

[0095] It should be noted that those whose housing source is of the "other" type mainly live in unit dormitories or stay with relatives and friends, etc. Therefore, in the embodiments of the present application, they are separated from households with their own houses and households renting houses and classified into a separate category.

[0096] S23. Based on the urban housing ownership rate, calculate the initial urban housing rental population in the forecast year. The calculation formula is as follows: ”

[0097] In the formula, represents the number of urban housing rental population in the initial forecast year based on the improved home ownership rate method, It indicates the number of permanent urban population in the predicted year from the statistical yearbook data.

[0098] The traditional home ownership rate method uses a fixed value for the home ownership rate during the calculation process, ignoring the differences in economic and social development and housing conditions in different cities. Therefore, this application uses the housing data of the national census data closest to the forecast year to predict the urban home ownership rate, which can more accurately reflect the current home ownership rate status of the city. In addition, since the national census data is comprehensive and authoritative, it can provide detailed information on housing property rights, number of households, etc., providing a solid foundation for prediction. Compared with the traditional fixed value method, this method can better reflect the differences in development between different cities, thereby further improving the accuracy of the prediction.

[0099] In the embodiment of the present application, the third prediction submodule determines the housing rental population in the target city by integrating the prediction results of the first prediction submodule and the second prediction submodule. The specific steps are: ”

[0100] Where RP represents the number of people renting housing in the target city.

[0101] Since the data sources and statistical calibers of the floating population size method and the home ownership rate method are different, in order to avoid errors, this application first predicts the urban housing rental population from different angles as the initial urban housing rental population, which fully reflects the real scale and characteristics of the urban housing rental population; secondly, the urban housing rental population predicted from different angles is synthesized and the average is calculated as the target urban housing rental population, thereby reducing the risk of unreliable prediction results due to a single method or abnormal data source, and further enhancing the robustness and reliability of the prediction results.

[0102] In addition, the urban housing rental population predicted by this method can provide a more scientific and reasonable decision-making basis for the government to formulate relevant housing policies, plan the development of the urban housing rental market and meet the housing needs of residents. At the same time, it can also understand the real situation of the urban housing rental population, which will help the government and all sectors of society to rationally allocate rental housing resources, including the construction, management and maintenance of rental housing, so as to better meet the housing needs of the rental population.

[0103] The rental housing demand scale module involved in the present invention predicts the housing demand quantity of the urban housing rental market in the forecast year based on the housing rental population of the target city predicted by the rental population prediction module and the data stored in the storage module.

[0104] In this application, the specific prediction steps of the rental housing demand scale module are:

[0105] S31. Based on the data from the national census, the average household size in the city in the forecast year is calculated using the following formula: ”

[0106] Where AFS represents the average household size in the city in the forecast year, represents the average household size of the city published by the national census of the i-th group, Y represents the forecast year, The year representing the national census year closest to the forecast year.

[0107] As shown in Table 1, the average household size in China has been shrinking since the 1980s, and the average household size data has been released once every five years since 1990, making it impossible to obtain the average household size data for cities every year.

[0108] Table 1. Comparison of the average household size in China's censuses since 1982 and the average household size in Baoding

[0109] The first national census years Average household size in China (person / household) Changes from the previous census / sample survey (persons / households) Average household size in Baoding (person / household) first 1953 4.33 — — Second time 1964 4.43 0.10 — The third time 1982 4.41 -0.02 — 1987 4.23 -0.18 — Fourth 1990 3.96 -0.27 3.96 1995 3.70 -0.26 — Fifth 2000 3.44 -0.26 3.73 2005 3.13 -0.31 — Sixth 2010 3.10 -0.03 3.53 2015 3.10 0.00 — Seventh 2020 2.62 -0.48 2.78

[0110] Since the average household size data is only published once in a fixed period of time, the traditional method of calculating the number of housing demand in the urban housing rental market mostly uses a fixed value for the average household size data. However, due to differences in social and economic development and regional economic development, the average household size data of each year and the average household size data of each region will also have corresponding differences, such as Figure 3 The trend chart of the change in the average household size in different cities from 1990 to 2010 shows that there are differences in each city, so the method of using fixed values ​​is less flexible and unrealistic. Therefore, in this application, based on multiple national census data, the trend of the change in the average household size in the city is calculated, so as to predict the average household size data in the city over the years. For example, when calculating the average household size in the city in 2023 based on the sixth and seventh national census data in the embodiment of this application, the calculation formula is as follows:

[0111] It should be noted that the embodiment of the present application mainly performs trend estimation based on the period from the sixth to the seventh national census, but the estimation method is not limited to this period. In actual use, it can also be calculated based on the trends of the fifth to the seventh national census and the fourth to the seventh national census.

[0112] S32, combining the target city's housing rental population predicted by the rental population prediction module and the average household size of the city in the forecast year predicted in step S41, calculate the number of housing sources required in the city's housing rental market in the forecast year, and the calculation steps are as follows: ”

[0113] Wherein, HD represents the number of housing demand in the urban housing rental market in the forecast year.

[0114] It should be emphasized that when predicting the number of housing demand in the national housing rental market, the rental population prediction module and the rental housing demand scale module call the national total data stored in the storage module; when predicting the number of housing demand in a certain city's housing rental market, the rental population prediction module and the rental housing demand scale module call the city's data stored in the storage module.

[0115] like Figure 4 As shown, the present invention also provides a method for predicting the demand scale of urban rental housing based on multi-source data, which is applied to a system for predicting the demand scale of urban rental housing based on multi-source data, and the specific steps are:

[0116] S41, the input module sends the predicted demand information input by the user to the rental population prediction module;

[0117] S42, after receiving the forecast demand information, the rental population forecasting module calls the data stored in the storage module, and collaboratively forecasts the initial urban housing rental population through multiple forecasting submodules, thereby determining the target urban housing rental population;

[0118] S43. The rental housing demand scale module obtains the target city's housing rental population predicted by the rental population prediction module, and at the same time calls the data stored in the storage module to predict the number of housing demand in the urban housing rental market in the forecast year.

[0119] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A system for predicting the scale of urban rental housing demand based on multi-source data, characterized in that: include: The data collection module is used to collect data from national censuses, statistical yearbooks, average household size data, and retention rate data of college graduates from various regions published on relevant websites in real time; A data processing module, used for processing the data collected by the data collection module; A storage module, used for storing data processed by the data processing module; An input module, used for users to input forecast demand information; The rental population prediction module includes multiple prediction submodules. Based on the information transmitted by the input module and the data stored by the storage module, the multiple prediction submodules collaboratively predict the initial urban housing rental population, thereby determining the target urban housing rental population; The rental housing demand scale module predicts the number of housing demand in the urban housing rental market in the forecast year based on the target city's housing rental population predicted by the rental population prediction module and the data stored in the storage module; The national census data include urban permanent population data, urban registered population data, urban floating population data and housing data, among which the housing data include housing sources, the number of housing from each source and the housing area from each source; the statistical yearbook data include urban permanent population data, urban registered population data and urban college graduates data; The forecast demand information includes the forecast city, forecast year, and several consecutive national census data before the forecast year; The data processing mentioned in the data processing module refers to processing operations including data cleaning, feature selection, feature conversion and data encoding on the collected data; The rental population prediction module specifically includes a first prediction submodule, a second prediction submodule, and a third prediction submodule, wherein the first prediction submodule and the second prediction submodule respectively predict the initial urban housing rental population based on different angles, and the third prediction submodule determines the target urban housing rental population by integrating the prediction results of the first prediction submodule and the second prediction submodule; The first prediction submodule predicts the initial urban housing rental population based on the improved floating population size method, and the specific steps are: S11. Based on the data of the national census, the floating population coefficient of each city is calculated. The calculation formula is as follows: In the formula, a i represents the urban floating population coefficient of the i-th group of national census, L i，流 represents the number of urban migrant population in the i-th national census, L i，常 represents the number of permanent urban residents in the i-th national census, L i，户 represents the number of urban registered population in the i-th group of national census; S12. Based on the coefficients of floating population in previous cities, the average coefficients of floating population in previous cities are obtained. The calculation formula is as follows: In the formula, represents the mean value of the coefficient of floating population in cities over the years, and n represents the number of groups of national census data used; S13. Based on the average of the urban floating population coefficients of previous years, the urban floating population in the forecast year is calculated. The calculation formula is as follows: Where LP 流 represents the number of urban floating population in the forecast year, LP 常 Indicates the number of urban permanent residents predicted in the statistical yearbook data, LP 户 It represents the number of urban registered population in the predicted year in the statistical yearbook data; S14. Introduce the retention rate of college graduates into the traditional floating population scale method to calculate the initial urban housing rental population in the forecast year. The calculation formula is as follows: RP1=[LP 流 +GR×Q GR留 ]×Q LP In the formula, RP1 represents the number of urban housing rental population in the initial forecast year based on the improved floating population size method, GR represents the number of urban college graduates in the past five years including the forecast year, and Q GR留 represents the retention rate of college graduates in the past five years, including the forecast year, Q LP represents the proportion of floating population renting houses; Q GR留 is the average retention rate of college graduates in the past five years; the proportion of floating population renting houses is 67.3%; The second prediction submodule predicts the initial urban housing rental population based on the improved housing ownership rate method, and the specific steps are as follows: S21. Housing data based on the national census data closest to the forecast year, excluding the number of houses in towns and villages, and summarizing the number of houses in the central urban area; S22. Based on the source of housing, various types of housing in the central urban area are divided into home-owning households, home-renting households and other households, so as to obtain the urban home-ownership rate. The calculation formula is as follows: Where A represents the urban housing ownership rate, N 自有 N is the number of households with their own homes. 租赁 Indicates the number of households renting houses, N 其他 The number of households that indicated that they solved their housing problem through other means; S23. Based on the urban home ownership rate, calculate the initial urban housing rental population in the forecast year. The calculation formula is as follows: RP2=LP 常 ×(1-A) Where RP2 represents the number of urban housing rental population in the initial year of the forecast based on the improved home ownership rate method, and LP 常 It represents the number of urban permanent residents in the predicted year in the statistical yearbook data; The third prediction submodule determines the housing rental population in the target city by integrating the prediction results of the first prediction submodule and the second prediction submodule. The specific steps are as follows: In the formula, RP represents the number of people renting houses in the target city; The specific prediction steps of the rental housing demand scale module are: S31. Based on the data of the national census, the average household size in the city in the forecast year is calculated using the following formula: In the formula, AFS represents the average household size in the city in the forecast year, PNC i represents the average household size of the city published by the national census of the i-th group, Y represents the forecast year, and Y PNG The year represents the national census year closest to the forecast year; S32. Combining the target city's housing rental population predicted by the rental population prediction module and the average household size of the city in the forecast year predicted in step S31, the number of housing sources required in the city's housing rental market in the forecast year is calculated. The calculation steps are as follows: HD=RP / AFS Wherein, HD represents the number of housing demand in the urban housing rental market in the forecast year.

2. A method for predicting the demand scale of urban rental housing based on multi-source data, applied to the system for predicting the demand scale of urban rental housing based on multi-source data as claimed in claim 1, characterized in that: The specific steps are: S41, the input module sends the predicted demand information input by the user to the rental population prediction module; S42, after receiving the forecast demand information, the rental population forecasting module calls the data stored in the storage module, and collaboratively forecasts the initial urban housing rental population through multiple forecasting submodules, thereby determining the target urban housing rental population; S43. The rental housing demand scale module obtains the target city's housing rental population predicted by the rental population prediction module, and at the same time calls the data stored in the storage module to predict the number of housing demand in the urban housing rental market in the forecast year.

Images