Urban industry-by-industry employment population prediction method and device, electronic equipment and storage medium

Abstract

The invention provides a city industry-divided employment population prediction method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining city historical population data, city historical land utilization data and city historical employment data of a target city; calculating the total predicted employment population of the target city in the target prediction year according to the urban historical population data and the urban historical employment data; calculating the predicted industry population of each target industry category in the target prediction year according to the urban historical land utilization data, a plurality of preset target industry categories and the predicted total employment population; and according to preset street and town unit planning, urban historical land utilization data and predicted industry population, calculating predicted street and town industry population corresponding to each target industry category of each street and town unit in the target prediction year. According to the invention, the multi-source city data can be combined to realize high-precision industry-by-industry employment population prediction at the street and town level.

Description

Technical Field

[0001] The embodiments of the present application relate to, but are not limited to, the field of urban planning, and in particular, to a method and device for predicting the employment population by industry in a city, an electronic device, and a storage medium. Background Art

[0002] As the core carrier of employment and economic activities, the distribution of the employed population in a city directly affects industrial layout, transportation planning, public service allocation, and urban sustainable development. The distribution of the urban employed population is affected by complex multi-dimensional factors, including changes in population structure, land use types, economic development level, industrial structure adjustment, historical employment trends, etc. These factors are interrelated and evolve dynamically, jointly constituting a multi-level and non-linear urban complex system.

[0003] In the related art, traditional methods usually only rely on land use data or simple demographic indicators, and fail to fully integrate multi-source data such as economy and employment, resulting in the prediction results being difficult to reflect the true complexity of the urban system. Moreover, traffic census tracts or rail census tracts are mostly used as analysis units, which are disconnected from administrative divisions, resulting in difficult data acquisition and low prediction results. Summary of the Invention

[0004] The present application aims to at least solve one of the technical problems existing in the prior art. For this purpose, the present application provides a method and device for predicting the employment population by industry in a city, an electronic device, and a storage medium. The present application can combine multi-source urban data to achieve high-precision prediction of the employment population by industry at the sub-district and town level.

[0005] To achieve the above object, a first aspect of the embodiments of the present application proposes a method for predicting the employment population by industry in a city, the method including: Obtaining the historical urban population data, historical urban land use data, and historical urban employment data of the target city; Calculating the total predicted employment population of the target city in the target prediction year according to the historical urban population data and the historical urban employment data; Calculating the predicted industry population of each target industry category in the target prediction year according to the historical urban land use data, a plurality of preset target industry categories, and the total predicted employment population; Calculating the predicted sub-district and town industry population corresponding to each target industry category in each sub-district and town unit in the target prediction year according to the preset sub-district and town unit plan, the historical urban land use data, and the predicted industry population.

[0006] In some embodiments, the calculating the total predicted employment population of the target city in the target prediction year according to the historical urban population data and the historical urban employment data includes: Construct a target parameter regression equation based on the urban historical population data and the urban historical employment data; wherein, the urban historical population data includes the total population by year and the dependency ratio by year for each historical year, and the urban historical employment data includes the total employed population by year. Based on the total population by year and the dependency ratio by year for multiple historical years, predict the total predicted population and the predicted dependency ratio for the target prediction year. Substitute the total predicted population and the predicted dependency ratio into the target parameter regression equation to calculate the total predicted employed population.

[0007] In some embodiments, before calculating the predicted industry population for each target industry category in the target prediction year according to the urban historical land use data, multiple preset target industry categories, and the total predicted employed population, it further includes: Obtain multiple original industry categories. Merge the multiple original industry categories based on a preset industry merging rule to obtain multiple target industry categories. For each target industry category, determine the corresponding land use type in a preset list of land use types based on the corresponding industry characteristics to obtain an industry land use mapping relationship table.

[0008] In some embodiments, calculating the predicted industry population for each target industry category in the target prediction year according to the urban historical land use data, multiple preset target industry categories, and the total predicted employed population includes: For each target industry category, calculate the predicted land use area for the target industry category in the target prediction year according to the industry land use mapping relationship table and the urban historical land use data. For each target industry category, construct an employment population ratio prediction model based on the urban historical population data and the urban historical employment data; wherein, the employment population ratio prediction model is used to reflect the non-linear relationship between the first input parameter and the industry employment population ratio of the target industry category. For each target industry category, input the predicted land use area, the urban historical population data, and the urban historical employment data as the first input parameter into the employment population ratio prediction model to obtain the predicted employment population ratio output by the employment population ratio prediction model. Multiply the total predicted employed population by each predicted employment population ratio to obtain the predicted industry population for each target industry category.

[0009] Before calculating the predicted street-town industry population corresponding to each target industry category in each street-town unit in the target prediction year based on the preset street-town unit plan, the urban historical land use data, and the predicted industry population, the following steps are also included: According to the street-town unit plan, classify the urban historical population data, the urban historical land use data, and the urban historical employment data at the street-town level to obtain the street-town historical population data, street-town historical land use data, and street-town historical employment data corresponding to each street-town unit.

[0010] In some embodiments, calculating the predicted street-town industry population corresponding to each target industry category in each street-town unit in the target prediction year based on the preset street-town unit plan, the urban historical land use data, and the predicted industry population includes: According to the industry land mapping relationship table and the street-town historical land use data, calculate the predicted street-town land area of each target industry category in each street-town unit in the target prediction year; For each target industry category, construct a predicted proportion model of street-town employed population based on the street-town historical population data and the street-town historical employment data of each street-town unit; wherein, the predicted proportion model of street-town employed population is used to reflect the non-linear relationship between the second input parameter and the predicted proportion of street-town industry population corresponding to the target industry category in each street-town unit. For each target industry category in each street unit, input the street-town historical employment data, the street-town historical population data, and the predicted street-town land area as the second input parameter into the predicted proportion model of street-town employed population to obtain the predicted proportion of street-town industry population of the target industry category in the street-town unit output by the predicted proportion model of street-town employed population. According to the predicted industry population corresponding to each target industry category and the predicted proportion of street-town industry population, calculate the predicted street-town industry population of each street-town unit in each target industry category.

[0011] In some embodiments, after obtaining the predicted street-town industry population corresponding to each target industry category in each street-town unit in the target prediction year, the following steps are also included: Sum up the predicted street-town industry populations corresponding to multiple target industry categories in each street-town unit in the target prediction year to obtain the predicted total population after summation; Conduct a verification calculation on the predicted total population after summation according to the predicted total employed population.

[0012] Second aspect, an embodiment of the present application provides an urban employment population prediction device by industry, including: An acquisition module, configured to acquire the urban historical population data, urban historical land use data, and urban historical employment data of a target city; A first calculation module, configured to calculate the total predicted employment population of the target city in a target prediction year according to the urban historical population data and the urban historical employment data; A second calculation module, configured to calculate the predicted industry population of each target industry category in the target prediction year according to the urban historical land use data, multiple preset target industry categories, and the total predicted employment population; A third calculation module, configured to calculate the predicted street-town industry population corresponding to each target industry category of each street-town unit in the target prediction year according to the preset street-town unit plan, the urban historical land use data, and the predicted industry population.

[0013] Third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, it implements the urban employment population prediction method by industry according to any one of the embodiments in the first aspect of the present application.

[0014] Fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the storage medium stores a program, and when the program is executed by a processor, it implements the urban employment population prediction method by industry according to any one of the embodiments in the first aspect of the present application.

[0015] The urban employment population prediction method by industry proposed in the embodiment of the present application includes: acquiring the urban historical population data, urban historical land use data, and urban historical employment data of a target city; calculating the total predicted employment population of the target city in a target prediction year according to the urban historical population data and the urban historical employment data; calculating the predicted industry population of each target industry category in the target prediction year according to the urban historical land use data, multiple preset target industry categories, and the total predicted employment population; calculating the predicted street-town industry population corresponding to each target industry category of each street-town unit in the target prediction year according to the preset street-town unit plan, the urban historical land use data, and the predicted industry population.

[0016] The urban employment population prediction method by industry proposed in this application first constructs a multi-dimensional input covering population distribution, spatial functions, and industry characteristics by integrating urban historical population data, land use data, and employment data, avoiding the bias of a single data source and providing comprehensive data support for prediction. Then, based on the correlation between historical population and employment data, the total predicted employment population at the city level is calculated to ensure that the macro total conforms to the urban development trend. Next, combined with land use data and industry classification, the total population is decomposed into each target industry to reflect the spatial demand differences of different industries. Finally, based on the preset street-town unit plan, historical land use data, and predicted industry population, the predicted street-town industry population of each target industry category in each street-town unit in the target prediction year is calculated, achieving refined prediction at the street-town level. Therefore, this application can combine multi-source urban data to achieve high-precision employment population prediction by industry at the street-town level.

[0017] Other features and advantages of this application will be described in the following specification, and, in part, will become apparent from the specification or will be understood by implementing this application. The objectives and other advantages of this application can be realized and obtained through the structures specifically pointed out in the specification, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a schematic flowchart of the urban employment population prediction method by industry provided in an embodiment of this application; Figure 2 is a schematic flowchart of the urban employment population prediction method by industry provided in another embodiment of this application; Figure 3 is a schematic flowchart of the urban employment population prediction method by industry provided in another embodiment of this application; Figure 4 is a schematic flowchart of the urban employment population prediction method by industry provided in another embodiment of this application; Figure 5 is a schematic flowchart of the urban employment population prediction method by industry provided in another embodiment of this application; Figure 6 is a schematic flowchart of the urban employment population prediction method by industry provided in another embodiment of this application; Figure 7 is a schematic flowchart of the urban employment population prediction method by industry provided in another embodiment of this application; Figure 8 is a schematic diagram of the urban employment population prediction device by industry provided in an embodiment of this application; Figure 9 is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0020] It should be noted that although functional module division is performed in the device schematic diagram and the logical sequence is shown in the flowchart, in some cases, the steps shown or described may be executed in a different module division in the device or a different sequence in the flowchart. Terms such as "first" and "second" in the description, claims and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0022] As the core carrier of economic activities and employment, the distribution of the employed population in cities has an important impact on industrial layout, transportation planning, public service allocation, and urban sustainable development. The distribution of the urban employed population is affected by complex multi-dimensional factors, including changes in population structure, land use types, economic development level, industrial structure adjustment, historical employment trends, etc. These factors are interrelated and dynamically evolving, jointly constituting a multi-level and non-linear urban complex system.

[0023] In related technologies, traditional employed population prediction methods usually rely on simple linear regression models or single data sources and fail to fully integrate multi-source data. The main drawbacks of these methods are that the linear regression model makes predictions by establishing a linear relationship between independent variables and dependent variables. Although it is simple and easy to use, it cannot capture the non-linear characteristics of the urban employed population distribution, resulting in relatively low prediction accuracy. In addition, the Logistic model is often used to describe the growth of biological population sizes. Although this model can handle non-linear relationships, its application scope is relatively narrow and it is usually only applicable to specific types of data and cannot comprehensively reflect the complexity of the urban employed population. Moreover, existing technologies mostly use traffic zones or rail transit zones as analysis units, lacking consideration of urban administrative divisions, resulting in insufficient generality and difficulty in data acquisition. To sum up, existing technologies have drawbacks such as limited variable selection and inappropriate selection of regional units in urban employed population prediction and cannot effectively cope with the dynamic changes of urban complex systems.

[0024] Based on this, the embodiments of the present application provide a method and apparatus for predicting the employed population by industry in a city, an electronic device, and a storage medium, which can combine multi-source city data to achieve high-precision prediction of the employed population by industry at the street-town level.

[0025] The method and apparatus for predicting the employed population by industry in a city, the electronic device, and the storage medium provided by the embodiments of the present application will be specifically described through the following embodiments. First, the method for predicting the employed population by industry in the embodiments of the present application will be described.

[0026] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0027] It should be noted that in each specific embodiment of the present application, when it comes to relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or redirecting to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of the embodiments of the present application will be obtained.

[0028] Figure 1 is an optional flowchart of the method for predicting the employed population by industry in the embodiments of the present application. Figure 1 The method in may include but is not limited to steps 101 to 104.

[0029] Step 101, obtain the historical population data, historical land use data, and historical employment data of the target city.

[0030] Step 102: Calculate the total predicted employed population of the target city in the target prediction year based on the historical urban population data and the historical urban employment data.

[0031] Step 103: Calculate the predicted industrial population of each target industry category in the target prediction year based on the historical urban land use data, multiple preset target industry categories, and the total predicted employed population.

[0032] Step 104: Calculate the predicted sub-district industrial population corresponding to each target industry category of each sub-district unit in the target prediction year based on the preset sub-district unit plan, the historical urban land use data, and the predicted industrial population.

[0033] In steps 101 to 104 illustrated in the embodiments of the present application, first, by integrating the historical urban population data, land use data, and employment data, a multi-dimensional input covering population distribution, spatial function, and industry characteristics is constructed, avoiding the deviation of a single data source. Then, based on the correlation between the historical population and employment data, the total predicted employed population at the city level is calculated to ensure that the macro total conforms to the urban development trend. Next, in combination with the land use data and industry classification, the total population is decomposed into each target industry to reflect the spatial demand differences of different industries. Finally, based on the preset sub-district unit plan, the historical land use data, and the predicted industrial population, the predicted sub-district industrial population of each target industry category of each sub-district unit in the target prediction year is calculated, achieving refined prediction at the sub-district level. Therefore, the present application can combine multi-source urban data to achieve high-precision sub-district-level employment population prediction by industry.

[0034] In step 101 of some embodiments, first, basic historical record information needs to be collected for the specified prediction target, i.e., the target city. This information forms the basis for the subsequent establishment and calculation of the prediction model, specifically including the historical urban population data of the target city, such as statistical information on the total population and age structure (such as the dependency ratio) over the years, which is used to reflect the evolution of the urban population size and structure; the historical urban land use data, such as the land area, spatial distribution, and its changes over time of different planned plot types (such as industrial land, commercial service facility land, residential land, etc.), which is used to reflect the physical spatial layout of the target city; and the historical urban employment data, such as the total number of employed population over the years and the employment population structure by industry classified according to specific industry classification standards. These multi-source historical data are sourced from authoritative channels such as official statistical yearbooks, population census materials, economic census data, or land survey results, aiming to ensure the accuracy, reliability, and integrity of the input information used for model training and prediction.

[0035] In step 102 of some embodiments, it is necessary to explore and utilize the inherent relevance and regularity between the historical urban population data and the historical urban employment data, and perform calculations to obtain the total predicted employment population of the target city at a specified future time point, that is, the target prediction year. The core of this step lies in understanding and quantifying the impact of the population on the overall employment demand, and it is necessary to construct and solve a mathematical model that can reflect this impact relationship, such as a parametric regression equation. By analyzing the relationship between the population characteristics in historical years and the corresponding historical urban employment data, the model parameters can be calibrated. Then, using the predicted value of the population situation in the target prediction year and substituting it into the calibrated model, the corresponding total predicted employment population can be calculated.

[0036] Please refer to Figure 2 , in some embodiments, step 102 may include but is not limited to steps 201 to 203.

[0037] Step 201, construct a target parametric regression equation based on the historical urban population data and the historical urban employment data.

[0038] Step 202, predict the total predicted population and the predicted population dependency ratio of the target prediction year based on the total annual population and the annual population dependency ratio of multiple historical years.

[0039] Step 203, substitute the total predicted population and the predicted population dependency ratio into the target parametric regression equation to calculate the total predicted employment population.

[0040] In step 201 of some embodiments, it is necessary to establish a target parametric regression equation for predicting the total future employment population based on historical data. This step utilizes the historical urban population data obtained in step 101 (specifically including the "total annual population" recorded in each historical year and the "annual population dependency ratio" reflecting the population age structure) and the historical urban employment data (specifically including the "total annual employed population" recorded in the corresponding historical years). Through regression analysis methods, an equation that can describe the historical quantitative relationship between the total population, the population dependency ratio, and the total employed population is fitted and determined, in the following form:

[0041] Among them, represents the total predicted employment population of the target prediction year, represents the total predicted population of the target prediction year, represents the predicted population dependency ratio of the target prediction year, are model parameters obtained by fitting historical data using the least squares method. The "population dependency ratio" refers to the ratio of the non-working-age population (such as children and the elderly) to the working-age population, and is an important indicator reflecting the potential impact of the population structure on economic activities.

[0042] In step 202 of some embodiments, after constructing the target parameter regression equation that connects the relationship between population and employment, it is necessary to prepare the input data required by the target parameter regression equation for the target prediction year. Specifically, this step is based on the time series data of the "total population by year" and the "dependency ratio of the population by year" in multiple past historical years, and uses population prediction techniques to calculate and obtain the "predicted total population" and the "predicted dependency ratio of the population" in the target prediction year. The purpose of this step is to ensure that the subsequent calculation of the total employed population is based on a reasonable expectation of the future population situation.

[0043] In step 203 of some embodiments, the two key predicted values of the "predicted total population" and the "predicted dependency ratio of the population" in the future target prediction year obtained in step 202 are substituted into the "target parameter regression equation" whose parameters have been constructed and determined in step 201. The equation will output a specific value based on the quantitative relationship reflected by the historical data and combined with the prediction of the future population situation. This value is the "predicted total employed population" of the target city in the target prediction year.

[0044] Through steps 201 to 203, the embodiments of the present application first quantify the influence degree of the historical urban total population and population structure on the total employment scale through the parameter regression method; then, predict the two key driving factors of the total population and the dependency ratio in the future target year; finally, substitute the two predicted key driving factors into the established relationship model for calculation. This embodiment uses the statistical law of historical data to establish a prediction model and combines the prediction of the future population development trend, so as to obtain a quantifiable predicted value of the future total employed population driven by population factors, providing a reliable total employed population basis for more detailed sub-industry and sub-region predictions in the future.

[0045] Please refer to Figure 3 , in some embodiments, before step 103, it may further include, but is not limited to, steps 301 to 303.

[0046] Step 301, obtain multiple original industry categories.

[0047] Step 302, merge the multiple original industry categories based on a preset industry merging rule to obtain multiple target industry categories.

[0048] Step 303, for each target industry category, determine the corresponding land use type in a preset list of land use types based on the corresponding industry characteristics to obtain an industry-land use mapping relationship table.

[0049] In step 301 of some embodiments, multiple original industrial categories are first obtained. These "original industrial categories" generally refer to a relatively detailed and basic economic activity classification system derived from national standards or industry general specifications. For example, the 20 industrial sectors classified based on the national standard GB / T 4754—2017 Classification of National Economic Activities.

[0050] In step 302 of some embodiments, based on the obtained original industrial categories, purposeful industrial integration is required according to specific research or prediction needs, that is, multiple original industrial categories are merged based on preset industrial merger rules to obtain multiple target industrial categories with fewer numbers and stronger generalization ability. The "preset industrial merger rules" are classification combination schemes formulated according to specific principles, which comprehensively consider factors such as the economic activity characteristics of each industry (such as the attribution of the three industries), land use characteristics, demographic characteristics, and urban development strategies. For example, in terms of the characteristics of the three industries, agriculture, forestry, animal husbandry, and fishery belong to the primary industry. Although the mining industry belongs to the secondary industry, it generally belongs to the primary industry in other economies because the mining industry is a direct utilization of natural resources and the number of mining industry jobs in most cities is very limited. Taking Guangzhou as an example, the number of employees in the mining industry in 2018 was less than 500. Therefore, it is classified into the same category as agriculture, forestry, animal husbandry, and fishery. In terms of land use characteristics, the economic activities of agriculture, forestry, animal husbandry, and fishery and the mining industry generally occur on non-construction land. Therefore, these two industries are classified into the same category. In terms of demographic characteristics, accommodation and catering; residents' services, repair and other services generally belong to the non-basic sectors of the urban economy, and the number of employed people often increases with the increase in the total urban population. Therefore, they are classified into the same category. In terms of urban development needs, information transmission, software and information technology services; finance; leasing and business services are the tertiary industries that the city attaches importance to, and the manufacturing industry is the secondary industry that the city attaches importance to. Moreover, the land use types of the former are generally commercial service facilities land, and the latter is industrial land. Therefore, they are classified into separate categories respectively. By performing the above merger operations, the 20 sectors are reclassified into 9 categories as follows: ESAUM: Production and supply of electric power, heat power, gas and water; Water conservancy, environment and public facilities management; REABI: Real estate; Construction; PSI: Education; Health and social work; Culture, sports and entertainment; Public management, social security and social organizations; Scientific research and technical services; International organizations; TWPS: Transportation, warehousing and postal services; AFHFMI: Agriculture, forestry, animal husbandry, and fishery; Mining; WARB: Wholesale and retail trade; PS: Information transmission, software and information technology services; finance; leasing and business services; MI: Manufacturing; ACRS: Accommodation and catering services; residential services, repair and other services.

[0051] In step 303 of some embodiments, in order to establish the connection between industrial activities and urban space utilization, for each "target industry category" obtained in the previous step, based on its corresponding industry characteristics, its main or typical land use type needs to be determined in the preset land use type list, and finally a clear corresponding relationship record is formed, that is, the industry-land use mapping relationship table is obtained. The "industry characteristics" here mainly refer to the nature of the land on which the economic activities of this type of industry usually occur, and the "preset land use type list" is the standard land classification system used in urban planning or land management. For example, mapping manufacturing (MI) to industrial land, and mapping producer services (PS) to commercial service facilities land, etc. For details, refer to Table 1 below:

[0052] Table 1 Industry-Land Use Mapping Relationship Table The mapping relationship established in this step is the key link for using land use data to predict the employment population by industry in subsequent steps, connecting the abstract industry classification with the concrete land use data.

[0053] Through steps 301 to 303, the embodiments of the present application obtain the standardized original industry classification, merge them according to specific rules to obtain the simplified target industry categories that are more in line with the prediction requirements, and further clarify the mapping relationship between these target industry categories and specific land use types. This not only makes the industry classification more focused and practical, but also successfully constructs the mapping relationship connecting industrial economic activities and the urban physical space, enabling the subsequent model to effectively use land use data as a prediction factor, and improving the operability and pertinence of the prediction method.

[0054] In step 103 of some embodiments, after determining the total predicted employed population in the target prediction year, it is necessary to further decompose this total according to the industrial structure to estimate the employed population in each specific industry. This step utilizes the urban historical land use data and combines multiple target industry categories (the result of adapting or merging the standard industry classification), and at the same time takes the total predicted employed population calculated in step 102 as the total constraint condition to calculate the predicted industry population of each target industry category in the target prediction year. The calculation process here needs to reflect the complex relationship between a specific industry and the land use types it depends on (for example, the association between manufacturing and industrial land, information service industry and commercial service facility land, etc. clarified through the industry land use mapping relationship), historical employment data, population structure changes, and other factors that may affect the industry's employment demand. This complex relationship can be achieved by constructing a prediction model for the proportion of employed population in each target industry category, and this model can capture the non-linear relationship between these factors and the proportion of industry employment.

[0055] Please refer to Figure 4 , in some embodiments, step 103 may include, but is not limited to, steps 401 to 404.

[0056] Step 401, for each target industry category, calculate the predicted land area in the target prediction year according to the industry land use mapping relationship table and the urban historical land use data.

[0057] Step 402, for each target industry category, construct a prediction model for the proportion of employed population according to the urban historical population data and the urban historical employment data.

[0058] Step 403, for each target industry category, take the predicted land area, the urban historical population data, and the urban historical employment data as the first input parameters and input them into the prediction model for the proportion of employed population to obtain the predicted proportion of employed population output by the prediction model for the proportion of employed population.

[0059] Step 404, multiply the total predicted employed population by each predicted proportion of employed population to obtain the predicted industry population of each target industry category.

[0060] In step 401 of some embodiments, in order to quantify the land use factor and incorporate it into the prediction model, it is necessary to estimate the "predicted land area" corresponding to each target industry category b at the target prediction year t, denoted as . This step calculates this value through an appropriate prediction method based on the previously determined industry land use mapping relationship and the obtained urban historical land use data. The predicted land area represents the land area allocated to industry b in the future target prediction year t, which will be used as one of the key spatial factors affecting the employment scale of this industry and input into the subsequent prediction model.

[0061] In step 402 of some embodiments, for each target industry category b, an "employment population proportion prediction model" is constructed to predict the proportion of the employed population in the target industry in the target prediction year t to the total employed population in the city (i.e., the "proportion of employed population in the industry", denoted as ). A Logistic regression model can be used to construct this prediction relationship, and its mathematical form is:

[0062] The selection of this model aims to capture the complex "non-linear relationship" between the input variables and the employment proportion. Here, X is a comprehensive input term, which is a function composed of multiple prediction factors, specifically expressed as:

[0063] where is the proportion of the number of employed people in the b-th industry in the city at time t, is the aging rate of the urban resident population at time t, is the percentage of minors in the urban resident population at time t. , are respectively the number and proportion of employed people in the -th industry in the city at time (t - 1), , are respectively the number and proportion of employed people in the -th industry in the city at time (t - 2).

[0064] In step 403 of some embodiments, for each target industry category b, first, the values of each variable required for the input term X at time t need to be prepared. This includes obtaining the predicted population dependency ratio in the target prediction year t using the population prediction method in step 202 and converting it into the aging rate and the percentage of minors , the predicted land area obtained in step 401, and the known historical employment data at times t - 1 and t - 2 , , , . Substitute these specific values into the employment population proportion prediction model fitted for industry b in step 402, calculate the value of X, and then through the Logistic function conversion, the predicted proportion of the employed population in the target industry category b in the target prediction year t can be obtained , this calculation is performed for all 9 target industry categories.

[0065] In step 404 of some embodiments, the "total predicted employed population" of the whole city calculated in step 102 (denoted as ) is multiplied by the "predicted proportion of employed population" calculated for each target industry category b in step 403 to obtain the specific "predicted industry population" quantity of each target industry category b in the target prediction year t, denoted as . This method ensures that the sum of the predicted populations of all sub - industries is equal to the previously predicted total employed population of the whole city by first determining the proportion of each part and then multiplying by the total amount, maintaining the internal consistency of the prediction results.

[0066] Through steps 401 to 404, in this embodiment, the predicted land area of each industry in the target prediction year is first predicted, and then a non - linear prediction model is constructed for each industry. This model comprehensively considers multiple factors such as future population structure, land use, and historical employment to predict the proportion of each industry in the total employment. Finally, the predicted proportion is multiplied by the predicted total employed population of the city to obtain the specific predicted number of employed people in each industry. This method not only models the non - linear complex influence of multiple factors on the industry employment proportion but also ensures the coordination and unity of the sub - item prediction and the overall prediction through the proportion prediction mechanism, providing a more refined and reliable prediction result.

[0067] Please refer to Figure 5 , in some embodiments, before step 104, it may further include, but is not limited to, step 501.

[0068] Step 501: According to the street - town unit plan, the urban historical population data, urban historical land use data, and urban historical employment data are divided at the street - town level to obtain the street - town historical population data, street - town historical land use data, and street - town historical employment data corresponding to each street - town unit.

[0069] In step 501 of some embodiments, in order to perform subsequent employment predictions at a finer spatial scale, it is necessary to first spatially process the various historical data that has been obtained. Specifically, in this step, according to the pre-defined "sub-district unit plan" (i.e., the administrative or functional area division plan at the levels of streets and towns within the city), the previously obtained "urban historical population data", "urban historical land use data", and "urban historical employment data" covering the entire city are classified geographically, and the information related to specific sub-district units in the original data is extracted, summarized, or allocated to the corresponding sub-district units. For example, the census data of the whole city is statistically analyzed by sub-district, the land use data of the whole city is cut according to the sub-district boundaries and the area is statistically analyzed, and the employment data with address information in the economic census is grouped to the sub-district where it is located, generating corresponding historical time series data for each independent "sub-district unit", including the "sub-district historical population data" (such as total population, structure, etc.), "sub-district historical land use data" (such as the area of various types of land use), and "sub-district historical employment data" (such as total employment, employment by industry, etc.) of each sub-district over the years. This data provides the necessary historical data with spatial attributes for constructing and applying the prediction model at the sub-district level in subsequent steps.

[0070] In step 104 of some embodiments, in order to achieve a refined prediction of the employment distribution within the city, the municipal predicted industry population of each target industry category obtained in step 103 is further spatially processed and allocated to smaller geographical units within the city. According to the pre-set sub-district unit plan (which defines the administrative division boundaries or functional areas within the city, such as units at the levels of streets and towns), and in combination with the characteristics of the historical land use data at the sub-district unit level and the municipal predicted industry population of each target industry category calculated in step 103 (as the total control of the industry within the whole city), it is calculated that in the target prediction year, the number of employed people expected to be in each specific sub-district unit for each target industry category, that is, the predicted sub-district industry population. This allocation process needs to consider the attractiveness or repulsion of location factors such as the geographical location, resource differences, existing industrial base, current and planned land use, population distribution, and traffic accessibility of each sub-district unit to the spatial layout of employment positions in different industries. Based on these characteristics, a prediction model for the proportion of sub-district employed population is constructed, and this model also needs to have the ability to reflect the non-linear relationship between the input parameters and the proportion of predicted sub-district industry population, thus completing the employment population prediction from the overall city-wide prediction to the local sub-district distribution.

[0071] Please refer to Figure 6 , in some embodiments, step 104 may include, but is not limited to, steps 601 to 604.

[0072] Step 601: Calculate the predicted land area of each target industry category in each sub-district unit in the target prediction year based on the industry land mapping relationship table and the historical land use data of the sub-districts and towns.

[0073] Step 602: For each target industry category, construct a prediction model for the proportion of employed population in sub-districts and towns based on the historical population data and historical employment data of each sub-district unit.

[0074] Step 603: For each target industry category in each sub-district unit, input the historical employment data, historical population data, and predicted land area of the sub-district as the second input parameters into the prediction model for the proportion of employed population in sub-districts and towns, and obtain the predicted proportion of the target industry population in the sub-district unit output by the prediction model for the proportion of employed population in sub-districts and towns.

[0075] Step 604: Calculate the predicted sub-district industry population of each sub-district unit in each target industry category based on the corresponding predicted industry population and the predicted proportion of the sub-district industry population of each target industry category.

[0076] In step 601 of some embodiments, in order to consider land use factors at a finer spatial level, it is necessary to predict the land use scale of different industries in each future sub-district unit. Specifically, first, based on the previously established "industry land mapping relationship table" and the "historical land use data of sub-districts and towns" of each sub-district unit processed in step 501, for each "target industry category" b and each "sub-district unit" k, calculate the "predicted land area of the sub-district" of this industry in this sub-district unit in the target prediction year t, denoted as This step can be completed based on the historical land use change trend of this sub-district.

[0077] In step 602 of some embodiments, the core task is to construct a prediction model for the proportion of employed population in sub-districts and towns to predict what proportion of the total urban employment in a specific industry will be distributed in a specific sub-district unit. For each "target industry category" b, use the "historical population data of sub-districts and towns" (such as the historical population quantity ) and the "historical employment data of sub-districts and towns" (such as the total number of historical employment positions in this sub-district , and the historical proportion of employed population of this industry b in this sub-district k ) obtained in step 501 to construct a prediction model for the proportion of employed population in sub-districts and towns. This model aims to reflect the non-linear relationship between a set of defined "second input parameters" and the corresponding "predicted proportion of sub-district industry population" of the target industry category b in the sub-district unit k. The "predicted proportion of sub-district industry population" here It refers to the proportion of the employed population in industry b in street-town k in the target prediction year t to the total employed population in industry b in the whole city. To achieve this non-linear fitting, a general multi-linear model nested with the ReLU activation function can be used. The ReLU function is a commonly used activation function in deep learning neural network models, and the activation function is the essence for the neural network model to fit non-linear relationships, which is specifically expressed as:

[0078] In step 603 of some embodiments, the constructed prediction model of the proportion of employed population in street-towns will be used for actual prediction calculations. For each "target industry category" b in each "street-town unit" k, the specific values of the "second input parameters" required by the model are prepared. These values include: the historical data at the known time point t - 1 , , and the "predicted land area for industry b in street-town k in the target prediction year t" calculated in step 601 . Substitute these values into the "prediction model of the proportion of employed population in street-towns" (i.e., the ReLU nested linear equation) fitted for this industry b and street-town k for calculation. The result output after the model operation is the "predicted proportion of industry population in street-town" of the target industry category b in street-town unit k in the target prediction year t . This calculation needs to be performed for all combinations of k and b

[0079] In step 604 of some embodiments, based on the "predicted industry population" of each "target industry category" b at the city level calculated in step 404 , and the "predicted proportion of industry population in street-town" corresponding to this industry calculated for each street-town unit k in step 603 , multiply the two to calculate the specific "predicted industry population in street-town" of each street-town unit k in the target industry category b . In this way, the total predicted amount by industry at the city level is spatially allocated according to the relative attractiveness of each street-town to this industry (quantified by ), ensuring that the sum of the predicted populations of the same industry in all street-towns is equal to the total predicted population of this industry in the whole city , maintaining the consistency of the prediction results between levels

[0080] Through steps 601 to 604, in this embodiment, the predicted land area of each sub-district and town for a specific industry in the future is first predicted. Then, for each industry, a non-linear model (ReLU nested model) that can reflect the influence of the characteristics of the sub-district and town itself on its attractiveness in the city-wide industry is constructed. Next, using this model, the allocation ratio of employment in each sub-district and town for each industry is predicted. Finally, this ratio is applied to the city-level industry prediction total, and the specific predicted number of employed people in each industry within each sub-district and town unit is calculated. This process realizes the spatial downward allocation from the city to the sub-district and town, providing employment prediction results by industry with clear spatial location pointers. The results not only consider the non-linear influence of local factors but also ensure the logical consistency with the upper-level prediction total, providing high-precision prediction data for more specific regional planning and policy-making.

[0081] Please refer to Figure 7 , in some embodiments, after step 104, it may further include, but is not limited to, steps 701 to 702.

[0082] Step 701: Sum up the predicted sub-district and town industry populations corresponding to multiple target industry categories of each sub-district and town unit in the target prediction year to obtain the total predicted population after summation.

[0083] Step 702: Perform a verification calculation on the total predicted population after summation according to the predicted total employment population.

[0084] In step 701 of some embodiments, after calculating the predicted sub-district and town industry populations of each target industry category within each sub-district and town unit (k), it is necessary to integrate the prediction results within each sub-district and town. The specific operation is to perform an arithmetic sum on the predicted sub-district and town industry populations of all target industry categories included in each independent sub-district and town unit in the target prediction year. The result of this summation calculation is the "total predicted population after summation" of the sub-district and town unit in the target prediction year.

[0085] In step 702 of some embodiments, in order to ensure the numerical consistency and accuracy of the entire prediction system at different levels, a verification calculation needs to be performed. This step uses the "predicted total employment population" of the entire target city obtained in step 102 (or its refined step 203) to check the "total predicted population after summation" of each sub-district and town unit calculated in step 701. The specific verification calculation process can be to sum up the total predicted populations after summation of all sub-district and town units again to obtain a predicted value of the total employment population of the whole city based on the bottom-level summation, and then compare this value with the directly predicted total employment population of the whole city at the top level. Ideally, the two should be equal or the difference should be within an acceptable error range. This step is to perform a final internal consistency verification on the entire prediction process, especially the process of decomposing the city-level total to the sub-district and town-level details and then summarizing.

[0086] Steps 701 and 702 together constitute an important post - processing verification step, which is used to ensure and verify the internal consistency and numerical accuracy of the prediction results across different spatial scales and structural levels. In step 701, the prediction results at the finest - granularity (sub - district - industry level) are first effectively aggregated over spatial units (sub - districts) to generate the total employment prediction values for each sub - district with practical significance. Subsequently, in step 702, by further summing up these sub - district - level total employment prediction values and comparing them with the initial, independent total urban employment prediction value, it helps to detect possible cumulative errors or model - setting problems in the calculation process, thereby enhancing the rigor of the entire prediction system and the credibility of the final output results.

[0087] The method for predicting the employment population by industry in a city proposed in this application first constructs a multi - dimensional input covering population distribution, spatial function, and industry characteristics by integrating the historical population data, land - use data, and employment data of the city, avoiding the bias of a single data source and providing comprehensive data support for the prediction. Then, based on the correlation between historical population and employment data, the total predicted employment population at the city level is calculated to ensure that the macro - total conforms to the urban development trend. Next, in combination with land - use data and industry classification, the total population is decomposed into each target industry to reflect the spatial demand differences of different industries. Finally, based on the pre - set sub - district unit plan, historical land - use data, and predicted industry population, the predicted sub - district industry population for each target industry category in each sub - district unit in the target prediction year is calculated, achieving refined prediction at the sub - district level. Therefore, this application can combine multi - source urban data to achieve high - precision prediction of the employment population by industry at the sub - district level.

[0088] Please refer to Figure 8 , the embodiment of this application also provides a device for predicting the employment population by industry in a city, which can implement the above - mentioned method for predicting the employment population by industry in a city, including: An acquisition module, which is used to acquire the historical population data, historical land - use data, and historical employment data of the target city; A first calculation module, which is used to calculate the total predicted employment population of the target city in the target prediction year according to the historical population data and historical employment data of the city; A second calculation module, which is used to calculate the predicted industry population of each target industry category in the target prediction year according to the historical land - use data of the city, multiple pre - set target industry categories, and the total predicted employment population; A third calculation module, which is used to calculate the predicted sub - district industry population corresponding to each target industry category in each sub - district unit in the target prediction year according to the pre - set sub - district unit plan, historical land - use data of the city, and predicted industry population.

[0089] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the urban sub-industry employed population prediction method according to any one of the embodiments in the first aspect of the present application.

[0090] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. The storage medium stores a program, and when the program is executed by a processor, it implements the urban sub-industry employed population prediction method according to any one of the embodiments in the first aspect of the present application.

[0091] Please refer to Figure 9 , Figure 9 which schematically shows the hardware structure of an electronic device in another embodiment. The electronic device includes: A processor 901, which can be implemented in ways such as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present application; A memory 902, which can be implemented in forms such as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 902, and the processor 901 is called to execute the urban sub-industry employed population prediction method of the embodiments of the present application; An input / output interface 903, which is used to implement information input and output; A communication interface 904, which is used to implement communication interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.); A bus 905, which transmits information between various components of the device (such as the processor 901, the memory 902, the input / output interface 903, and the communication interface 904); Among them, the processor 901, the memory 902, the input / output interface 903, and the communication interface 904 achieve communication connections with each other inside the device through the bus 905.

[0092] An embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned urban sub-industry employment population prediction method is implemented.

[0093] As a non-transitory computer-readable storage medium, a memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0094] The embodiments described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0095] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than those shown in the figures, or combine certain steps, or different steps.

[0096] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and appropriate combinations thereof.

[0098] In the description of this application and the above-mentioned drawings, terms such as "first", "second", "third", "fourth", etc. (if any) are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of this application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that comprises a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0099] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or similar expressions refer to any combination of these items, including any combination of single items (ones) or plural items (ones). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0100] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the above-mentioned division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0101] The units described above as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0102] In addition, in each embodiment of the present application, the functional units may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0103] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present application. The foregoing storage medium includes: various media that can store programs, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0104] The preferred embodiments of the embodiments of the present application have been described above with reference to the accompanying drawings, which does not limit the scope of rights of the embodiments of the present application. Any modification, equivalent replacement, and improvement made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of rights of the embodiments of the present application.

Claims

1. A method for predicting the employed population by industry in a city, characterized in that, The method includes: Obtaining the urban historical population data, urban historical land use data, and urban historical employment data of the target city; Calculating the total predicted employed population of the target city in the target prediction year according to the urban historical population data and the urban historical employment data; Calculating the predicted industry population of each target industry category in the target prediction year according to the urban historical land use data, multiple preset target industry categories, and the total predicted employed population; Calculating the predicted street-town industry population corresponding to each target industry category of each street-town unit in the target prediction year according to the preset street-town unit plan, the urban historical land use data, and the predicted industry population.

2. The urban sub-industry employed population prediction method according to claim 1, wherein The calculating the total predicted employed population of the target city in the target prediction year according to the urban historical population data and the urban historical employment data includes: Constructing a target parameter regression equation according to the urban historical population data and the urban historical employment data; wherein, the urban historical population data includes the total annual population and the annual population dependency ratio for each historical year, and the urban historical employment data includes the total annual employed population; Based on the total annual population and the annual population dependency ratio for multiple historical years, predicting the total predicted population and the predicted population dependency ratio in the target prediction year; Substituting the total predicted population and the predicted population dependency ratio into the target parameter regression equation to calculate the total predicted employed population.

3. The urban sub-industry employed population prediction method according to claim 1, characterized in that, Before calculating the predicted industry population of each target industry category in the target prediction year according to the urban historical land use data, multiple preset target industry categories, and the total predicted employed population, it further includes: Obtaining multiple original industry categories; Merging the multiple original industry categories based on a preset industry merging rule to obtain multiple target industry categories; For each target industry category, determining the corresponding land use type in a preset land use type list based on the corresponding industry characteristics to obtain an industry-land use mapping relationship table.

4. The urban sub - industry employed population prediction method according to claim 3, wherein The calculating the predicted industry population of each target industry category in the target prediction year according to the urban historical land use data, multiple preset target industry categories, and the total predicted employed population includes: For each target industry category, calculating the predicted land use area of the target industry category in the target prediction year according to the industry-land use mapping relationship table and the urban historical land use data; For each target industry category, constructing an employed population ratio prediction model according to the urban historical population data and the urban historical employment data; wherein, the employed population ratio prediction model is used to reflect the non-linear relationship between the first input parameter and the industry employed population ratio of the target industry category. For each of the target industry categories, input the predicted land area, the historical population data of the city, and the historical employment data of the city as the first input parameters into the predicted employment population ratio model to obtain the predicted employment population ratio output by the predicted employment population ratio model; Multiply the predicted total employment population by each of the predicted employment population ratios to obtain the predicted industry population of each of the target industry categories.

5. The urban employment population prediction method by industry according to claim 4, characterized in that Before calculating the predicted street-town industry population corresponding to each target industry category in each street-town unit in the target prediction year according to the preset street-town unit plan, the historical land use data of the city, and the predicted industry population, it further includes: According to the street-town unit plan, divide the historical population data of the city, the historical land use data of the city, and the historical employment data of the city at the street-town level to obtain the street-town historical population data, street-town historical land use data, and street-town historical employment data corresponding to each street-town unit.

6. The urban sub-industry employed population prediction method according to claim 5, characterized in that The calculating the predicted street-town industry population corresponding to each target industry category in each street-town unit in the target prediction year according to the preset street-town unit plan, the historical land use data of the city, and the predicted industry population includes: According to the industry land mapping relation table and the street-town historical land use data, calculate the predicted street-town land area of each target industry category in each street-town unit in the target prediction year; For each of the target industry categories, construct a street-town employment population ratio prediction model according to the street-town historical population data and the street-town historical employment data of each street-town unit; wherein, the street-town employment population ratio prediction model is used to reflect the non-linear relationship between the second input parameter and the predicted street-town industry population ratio corresponding to the target industry category in each street-town unit. For each target industry category in each street-town unit, input the street-town historical employment data, the street-town historical population data, and the predicted street-town land area as the second input parameters into the street-town employment population ratio prediction model to obtain the predicted street-town industry population ratio of the target industry category of the street-town unit output by the street-town employment population ratio prediction model; According to the predicted industry population and the predicted street-town industry population ratio corresponding to each target industry category, calculate the predicted street-town industry population of each street-town unit in each target industry category.

7. The urban employment population prediction method by industry according to claim 1, characterized in that After obtaining the predicted street-town industry population corresponding to each target industry category in each street-town unit in the target prediction year, it further includes: Sum up the predicted street-town industry populations corresponding to multiple target industry categories in each street-town unit in the target prediction year to obtain the sum predicted total population; Conduct a verification calculation on the sum predicted total population according to the predicted total employment population.

8. An urban employment population prediction device by industry, characterized in that It includes: An acquisition module, configured to acquire the historical population data of the target city, the historical land use data of the city, and the historical employment data of the city; The first calculation module is configured to calculate the total predicted employed population of the target city in the target prediction year according to the historical population data of the city and the historical employment data of the city; The second calculation module is configured to calculate the predicted industrial population of each target industrial category in the target prediction year according to the historical land use data of the city, a plurality of preset target industrial categories, and the total predicted employed population; The third calculation module is configured to calculate the predicted street-town industrial population corresponding to each target industrial category in each street-town unit in the target prediction year according to the preset street-town unit plan, the historical land use data of the city, and the predicted industrial population.

9. An electronic device, characterized in that, Comprising: A memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for predicting the employed population by industry of a city according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program, and when the program is executed by the processor, the method for predicting the employed population by industry of a city according to any one of claims 1 to 7 is implemented.

Images