Map-based crowd income monitoring method, apparatus and device, and storage medium

Abstract

The invention discloses a crowd income monitoring method and device based on a map, equipment and a storage medium, and relates to the technical field of data prediction, and the method comprises the steps: collecting original feature information, and carrying out the ETL processing of the original feature information, so as to obtain the feature information of each target; constructing a target file, obtaining map data, and generating a target map image according to the map data and the target file; obtaining an initial crowd aggregation degree and a relative crowd aggregation degree based on the target map image, predicting an income growth trend of the target crowd by using the initial crowd aggregation degree and a target income prediction model, and determining a financial service according to the crowd aggregation degree and the income growth trend; and executing the financial service on the target crowd to obtain execution feedback by using the second preset application programming interface, and monitoring an income increase condition of the target crowd based on the execution feedback. The feature information and financial service execution feedback of the target crowd are obtained by using the application programming interface, so that the working efficiency is greatly improved, and the human resource cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data prediction, and particularly relates to a method, device, equipment and storage medium for monitoring the income of the population based on a map. Background Art

[0003] Traditional methods for investigating the income growth of low-income populations rely on a large amount of human resources. Through grid personnel of the government and banks, on-site visits and investigations are carried out in each township and street. This method has low work efficiency, takes a long time, and has a high human resource cost. Therefore, how to propose an efficient and low-cost method for predicting the income situation of low-income populations is a problem to be solved at present. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method, device, equipment and storage medium for detecting the income of the population based on a map, which can obtain the characteristic information of the target population and the execution feedback of financial services by using an application programming interface, greatly improving the work efficiency and reducing the human resource cost. The specific solutions are as follows:

[0005] In the first aspect, the present application provides a method for monitoring the income of the population based on a map, including:

[0006] Collecting the original characteristic information corresponding to the target population from each target data source by using a first preset application programming interface, and performing ETL processing on the obtained original characteristic information to obtain each target characteristic information corresponding to the target population;

[0007] Constructing a target file corresponding to the target population according to each target characteristic information, obtaining map data corresponding to the target population from a target map source, and generating a target map image according to the map data and the target file;

[0008] Obtaining the initial population aggregation degree and relative population aggregation degree corresponding to the target population based on the target map image, predicting the income growth trend corresponding to the target population by using the initial population aggregation degree and a target income prediction model, and determining the financial service corresponding to the target population according to the relative population aggregation degree and the income growth trend;

[0009] Performing the financial service on the target population to obtain the corresponding execution feedback by using a second preset application programming interface, and monitoring the income growth situation of the target population based on the execution feedback.

[0010] Optionally, before performing ETL processing on the obtained original characteristic information, it further includes:

[0011] Determine whether the original feature information is private data. If the original feature information is private data, perform an encryption operation on the original feature information to obtain the original feature information in a desensitized state;

[0012] If the original feature information is not private data, jump to the step of performing ETL processing on the obtained original feature information.

[0013] Optionally, the performing ETL processing on the obtained original feature information to obtain the respective target feature information corresponding to the target population includes:

[0014] Perform a data cleaning operation on the original feature information to obtain the de-duplicated feature information, and perform a data aggregation operation on the de-duplicated feature information from each of the target data sources to obtain the corresponding aggregated feature information;

[0015] Perform data verification on the aggregated feature information to obtain the respective target feature information corresponding to the target population.

[0016] Optionally, the generating the target map image according to the map data and the target file includes:

[0017] Perform data processing on the vector data and raster data in the map data to obtain the processed map data, and generate the target map image corresponding to the target population based on the processed map data and the target file.

[0018] Optionally, the generating the target map image corresponding to the target population based on the processed map data and the target file includes:

[0019] Perform a coordinate reference system conversion operation on the processed map data to obtain the corresponding converted map data, and generate the target map image corresponding to the target population by using the converted map data and the target file.

[0020] Optionally, before predicting the income growth trend corresponding to the target population by using the relative population aggregation degree and the target income prediction model, it further includes:

[0021] Obtain the historical income data corresponding to the target population from each of the target data sources, and perform a model training operation on the initial income prediction model by using the historical income data, and update the model parameters of the initial income prediction model based on the corresponding training results to obtain the target income prediction model.

[0022] Optionally, the obtaining the initial population aggregation degree and the relative population aggregation degree corresponding to the target population based on the target map image includes:

[0023] Divide the aggregation blocks corresponding to the target population according to the target map image, and use the aggregation blocks and a preset aggregation degree calculation formula to calculate the initial population aggregation degree corresponding to the target population;

[0024] Use the initial population aggregation degree corresponding to the target population and a preset hot spot analysis technique to obtain the relative population aggregation degree corresponding to the target population.

[0025] In a second aspect, the present application provides a map-based population income monitoring device, including:

[0026] A feature information acquisition module, configured to collect original feature information corresponding to the target population from various target data sources by using a first preset application programming interface, and perform ETL processing on the acquired original feature information to obtain each target feature information corresponding to the target population;

[0027] A map image generation module, configured to construct a target profile corresponding to the target population according to each target feature information, obtain map data corresponding to the target population from a target map source, and generate a target map image according to the map data and the target profile;

[0028] A financial service determination module, configured to obtain the relative population aggregation degree corresponding to the target population based on the target map image, predict the income growth trend corresponding to the target population by using the relative population aggregation degree and a target income prediction model, and determine the financial service corresponding to the target population according to the population aggregation degree and the income growth trend;

[0029] A feedback acquisition module, configured to execute the financial service on the target population, so as to obtain corresponding execution feedback by using a second preset application programming interface, and monitor the income growth of the target population based on the execution feedback.

[0030] In a third aspect, the present application provides an electronic device, including:

[0031] A memory, configured to store a computer program;

[0032] A processor, configured to execute the computer program to implement the foregoing map-based population income monitoring method.

[0033] In a fourth aspect, the present application provides a computer-readable storage medium, configured to store a computer program, and when the computer program is executed by a processor, the foregoing map-based population income monitoring method is implemented.

[0034] This application first collects the original feature information corresponding to the target population from various target data sources by using the first preset application programming interface, and performs ETL processing on the obtained original feature information to obtain the respective target feature information corresponding to the target population. Then, according to each of the target feature information, a target profile corresponding to the target population is constructed, map data corresponding to the target population is obtained from the target map source, and a target map image is generated based on the map data and the target profile. After that, the initial population aggregation degree and the relative population aggregation degree corresponding to the target population are obtained based on the target map image, the income growth trend corresponding to the target population is predicted by using the initial population aggregation degree and the target income prediction model, and the financial service corresponding to the target population is determined according to the population aggregation degree and the income growth trend. Finally, the financial service is executed for the target population to obtain the corresponding execution feedback by using the second preset application programming interface, and the income growth situation of the target population is monitored based on the execution feedback. Thus, it can be seen that this application obtains the feature information corresponding to the target population by using the program programming interface, and predicts the income growth trend of the target population based on the feature information, avoiding the problems of low work efficiency and high investigation cost caused by obtaining data through manual investigation; by using the program programming interface to obtain feedback information and monitoring the income of the target population in real time according to the feedback information, the monitoring efficiency is improved, and the monitoring cost is greatly reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.

[0036] Figure 1 It is a flowchart of a method for monitoring population income based on a map disclosed in this application;

[0037] Figure 2 It is a schematic diagram of a specific method for monitoring population income disclosed in this application;

[0038] Figure 3 It is a flowchart of a method for processing privacy data disclosed in this application;

[0039] Figure 4 It is a schematic diagram of file information disclosed in this application;

[0040] Figure 5 It is a schematic diagram of a map image disclosed in this application;

[0041] Figure 6Flowchart of a financial service execution method disclosed in this application;

[0042] Figure 7 Schematic diagram of a specific financial service execution method flow disclosed in this application;

[0043] Figure 8 Schematic diagram of a visualization monitoring platform disclosed in this application;

[0044] Figure 9 Schematic diagram of a visualization monitoring platform disclosed in this application;

[0045] Figure 10 Schematic diagram of the structure of a population income monitoring device disclosed in this application;

[0046] Figure 11 Schematic diagram of the structure of an electronic device disclosed in this application. Detailed implementation manners

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0048] Currently, the method for monitoring the income growth status of low-income populations is through on-site visits and investigations by manual labor. This method has problems such as low investigation efficiency and high cost consumption. For this reason, this application provides a map-based population income monitoring method, which greatly improves work efficiency and reduces human resource costs by using application programming interfaces to obtain the characteristic information of the target population and the feedback of financial service execution.

[0049] See Figure 1 As shown, the embodiments of the present invention disclose a map-based population income monitoring method, including:

[0050] Step S11: Collect the original characteristic information corresponding to the target population from each target data source by using a first preset application programming interface, and perform ETL processing on the obtained original characteristic information to obtain each target characteristic information corresponding to the target population.

[0051] In this embodiment, the process of monitoring the income of low-income populations, that is, the target population, is as Figure 2As shown in the figure, first, it is necessary to use the API (Application Programming Interface) to achieve cross-institutional data integration, extract and store the data of low-income people. That is, use the first preset application programming interface to collect the original feature information corresponding to the target population from each target data source. Specifically, first, through the application programming interface, that is, the first preset application programming interface, extract the data related to low-income people, that is, the original feature information, from multiple dispersed data sources, that is, each target data source, such as regional operation centers, big data management bureaus, poverty alleviation offices, and tax authorities, etc., to complete the external data access. It should be noted that in the embodiment of this application, the data acquisition weights corresponding to each target data source can be set according to the actual data application requirements, and according to the above weights, the target population, that is, the original feature information corresponding to the low-income population, is obtained from each target data source in corresponding proportions. For example, 60% of the data is obtained from the poverty alleviation office, 30% of the data is obtained from the regional operation center, and 10% of the data is obtained from the tax authority. The specific weights and data acquisition ratios can be determined according to the actual application requirements and will not be elaborated here. And, in the process of obtaining the data, in addition to using the API to obtain data from the databases of relevant institutions, a crawler program can also be used to obtain policy information, enterprise layoff information, etc. corresponding to low-income people from other network data platforms, such as official accounts, mini-programs, and other video or text data platforms, and use the large language model to extract the feature information of the data to enrich the initial feature information corresponding to the obtained low-income population. After the original feature information is accessed, it is necessary to perform ETL (Extract-Load-Transform) processing on the obtained original feature information to obtain the target feature information corresponding to the target population.

[0052] It can be understood that according to the requirements for the data protection of low-income people, for external data sources, that is, the obtained original feature information, it is necessary to distinguish whether the specific data fields belong to the scope of data protected by personal privacy. In this embodiment, before performing ETL processing on the obtained original feature information, it also includes: judging whether the original feature information is private data. If the original feature information is private data, then perform an encryption operation on the original feature information to obtain the original feature information in a desensitized state; if the original feature information is not private data, then jump to the step of performing ETL processing on the obtained original feature information. Specifically, such as Figure 3As shown, it is first necessary to determine whether the obtained original feature information is the privacy data of low-income people; in a specific implementation, if the obtained original feature information is the privacy data of low-income people, the module responsible for processing privacy data in the income monitoring system corresponding to the population income monitoring method in this embodiment is used to perform MPC (Multi-party Computation, i.e., multi-party security) calculation on the obtained privacy data to encrypt the privacy data and obtain the encrypted data corresponding to the privacy data, that is, the original feature information in the desensitized state, which is also the data in the intermediate result state; in another specific implementation, if the obtained original feature information is not the privacy data of low-income people, no encryption processing is required, and the data is directly subjected to ETL processing; that is, the sensitive data of low-income people specific to individuals enters the data mart in the intermediate result state through the data encryption of this module and directly participates in the operation of the algorithm in the subsequent process; the non-sensitive data and the intermediate result data in the desensitized state are uniformly stored and aggregated in the system data mart. Finally, the system performs unified ETL processing on these external data sources.

[0053] In this embodiment, the process of performing ETL processing on the original feature information to obtain the respective target feature information corresponding to the target population may specifically include: performing data cleaning operations on the original feature information to obtain the de-duplicated feature information, and performing data aggregation operations on the de-duplicated feature information from each target data source to obtain the corresponding aggregated feature information; performing data verification on the aggregated feature information to obtain the respective target feature information corresponding to the target population; specifically, the above ETL processing process includes data cleaning (removing duplicate and inconsistent data), data mapping (mapping fields from different data sources to a unified data model), and data aggregation (merging data from different sources), and loading the transformed data into the target database or data warehouse to achieve persistent storage of the data. It should be noted that in the entire ETL process, ensuring the consistency and integrity of the data is crucial. Consistency means that the data maintains the same value at different time points and in different systems, while integrity refers to the accuracy and reliability of the data. To maintain the consistency and integrity of the data of low-income people, mechanisms such as data verification, error handling, and data auditing also need to be implemented to ensure the reliability of the processed data. By performing operations such as data cleaning, data mapping, and data aggregation on the obtained original feature information, duplicate data and inconsistent data are removed, improving the reliability of the data; by using application programming interfaces to call data from each data source, the problem of low efficiency caused by manual on-site visits is avoided.

[0054] Step S12: Construct a target profile corresponding to the target population based on each piece of the target feature information, obtain the map data corresponding to the target population from the target map source, and generate a target map image based on the map data and the target profile.

[0055] In this embodiment, first, it is necessary to construct a target profile corresponding to the target population containing geographical markers as shown in Figure 4 . This process includes operations such as data deduplication, outlier identification and processing, and data format standardization. At this stage, information filing for low-income populations is completed. Specifically, the above information filing process also requires a detailed classification of the types of low-income populations (such as: households with unstable poverty alleviation, marginally poverty-prone households, households facing sudden severe difficulties, poverty-alleviated households, rural subsistence allowance households, urban subsistence allowance households, households receiving special hardship assistance, low-income margin households), a detailed classification of the reasons for low income (such as: due to illness, due to schooling, due to disability, due to natural disasters, lack of resources, lack of labor force, lack of technology, lack of endogenous motivation, others), and for those impoverished due to natural disasters, a classification of the types of natural disasters (such as: flood disasters, geological disasters, drought disasters, biological disasters (pest disasters), meteorological disasters, earthquake disasters, others); the system makes a detailed portrait of the living and production conditions of low-income populations (such as: cultivated land area, water surface area, forest land area, area of returning farmland to forest (grass), fruit forest area, type of access road, distance from the main village road, type of housing, type of drinking water, whether joining a professional cooperative, whether driven by a leading enterprise, whether having access to domestic electricity, whether having access to radio and television, family asset situation, etc.); based on the population geographical location information corresponding to the target population, the system finally converts the data into a GIS (Geographic Information System) compatible format, such as GeoJSON (Geography JavaScript Object Notation, a data encoding format) or GML (Geography Markup Language, a data encoding format); it can be understood that the above population geographical location information is the data contained in the aforementioned target feature information.

[0056] In this embodiment, the process of obtaining the map data corresponding to the target population from the target map source, that is, obtaining the map data from the remote sensing center and the online API of external map plugin suppliers. The process of generating the target map image based on the map data and the target file may specifically include: performing data processing on the vector data and raster data in the map data to obtain the processed map data, and generating the target map image corresponding to the target population based on the processed map data and the target file; the process of storing and processing the point, line, and surface vector data and raster data is to ensure that all data uses a unified spatial reference framework. The process of generating the target map image corresponding to the target population based on the processed map data and the target file may specifically include: performing a coordinate reference system conversion operation on the processed map data to obtain the corresponding converted map data, and generating the target map image corresponding to the target population by using the converted map data and the target file; it should be noted that the above operation of performing coordinate system conversion is to adapt to different map projection requirements. By processing the vector data and raster data, the reliability of the processed map data is ensured; by performing coordinate system conversion, different map projection requirements can be adapted, and the applicability of the obtained map image is improved; by using the application programming interface to obtain data, the method of obtaining data through on-site investigation is avoided, thereby reducing the labor cost.

[0057] Step S13, obtain the initial population aggregation degree and relative population aggregation degree corresponding to the target population based on the target map image, predict the income growth trend corresponding to the target population by using the initial population aggregation degree and the target income prediction model, and determine the financial service corresponding to the target population according to the relative population aggregation degree and the income growth trend.

[0058] In this embodiment, before predicting the income growth trend corresponding to the target population by using the initial population aggregation degree and the target income prediction model, it further includes: obtaining the historical income data corresponding to the target population from each target data source, and performing a model training operation on the initial income prediction model by using the historical income data, and updating the model parameters of the initial income prediction model based on the corresponding training results to obtain the target income prediction model; the trained target income prediction model can predict the income growth trend of the target population according to the population aggregation degree corresponding to the target population, that is, the initial population aggregation degree.

[0059] In this embodiment, the system needs to perform spatial analysis and dynamic prediction on the aggregation of low-income populations carried by the map, apply spatial analysis algorithms to evaluate the spatial aggregation degree of low-income populations, that is, the above-mentioned initial aggregation degree, predict their income growth trends, and visually display the analysis results through a dynamic monitoring large screen or other visualization tools to assist in decision-making. Correspondingly, the process of obtaining the initial population aggregation degree and relative population aggregation degree corresponding to the target population based on the target map image may specifically include: dividing the aggregation blocks corresponding to the target population according to the target map image, and using the aggregation blocks and a preset aggregation degree calculation formula to calculate the initial population aggregation degree corresponding to the target population; using the initial population aggregation degree corresponding to the target population and a preset hotspot analysis technology to obtain the relative population aggregation degree corresponding to the target population. Specifically, the system calculates the initial aggregation degree of low-income populations. The calculation formula for the low-income population aggregation degree (IoA) of each aggregation block, that is, the above-mentioned preset aggregation degree calculation formula, is:

[0060] ;

[0061] where i represents the i-th region or the i-th factor, and n represents the number of regions or the number of factors considered; represents the total population within the delimited map block, represents the population of low-income people within the delimited map block, represents the total area of the delimited map block, represents the living area of low-income people within the delimited map block, represents the weight. It should be noted that the map block is the smallest unit area for calculation, and the aggregation block is a set of blocks and is the unit area for displaying the aggregation degree on the map. The size of the aggregation block can be adjusted by dragging the scroll bar of the map plugin as needed, and the position and size of the aggregation block can also be set manually; as Figure 5 shown, the system can also display the initial population aggregation degree corresponding to the low-income population through a visualization map, that is, the aforementioned target map image, and mark the aggregation blocks with different low-income aggregation degrees with different shades of color; in addition, through a hotspot analysis technology (Getis-Ord Gi*) based on spatial data analysis, the relative population aggregation degree of low-income populations can be identified, and through the Figure 5 shown visualization map, it can help government and financial institution managers understand which regions have high and low value aggregations of the income levels of low-income populations; additionally, most of the time, compared with the absolute poverty aggregation degree of each region, a relative value is often more concerned about during the calculation process. If there is a region with a high aggregation degree in a set of regions with a low poverty aggregation degree, or vice versa, it belongs to the object worthy of attention, also known as a "hotspot" or "cold spot". For this, the neighborhood poverty degree Gi is introduced, which represents the average poverty aggregation degree of nearby regions, and its calculation formula is:

[0062] ;

[0063] Among them, is the poverty aggregation degree of the neighboring regions, is the spatial weight, representing the distance between this region i and the locations of each neighboring region. The farther the distance, the smaller it is. For the number of j, it can be uniformly set as needed. If j is 10, then the nearest 10 regions are selected for calculation.

[0064] Thus, the relative poverty aggregation degree of region i is expressed as follows:

[0065] ;

[0066] It can be understood that by re-rendering each region of the target map image according to the value, the "hot spots" or "cold spots" of the poverty aggregation degree and their changes in the time dimension can be visually observed.

[0067] In this embodiment, it is also necessary to use the above-mentioned initial population aggregation degree and the target income prediction model to predict the income growth trend of the target population. Specifically, the system automatically predicts the low-income aggregation degree of each aggregation block in the next few time periods (months, quarters) according to the algorithm, forming a prediction of the income growth trend of the low-income population, that is, the target population. The calculation formula is as follows:

[0068] ;

[0069] In the above formula, represents the low-income aggregation degree of the i-th aggregation block at time t, is a vector (e.g., low-income population type = marginally poverty-prone households, low-income reason = due to natural disasters, natural disaster type = natural disasters). Here, it includes the low-income aggregation degree of this aggregation block in the past 12 time periods . is the intercept term; is the coefficient vector of the explanatory variables; is the individual fixed effect, capturing the individual characteristics that are not observable for each individual (e.g., cultivated land area, water surface area, forest land area, area of returning farmland to forest (grass), fruit tree area, type of access road, distance from the main village road, housing type, drinking water type, whether to join a professional cooperative, whether there is a leading enterprise drive, whether there is access to domestic electricity, whether there is access to radio and television, family asset situation, etc.); is the time fixed effect, capturing the macroeconomic factors that change over time; is the error term, assuming that its mean is 0 and it is not correlated with the explanatory variables. After dynamic model training, the above , , Parameters such as are automatically incorporated into the aggregation degree vector of the past time period when predicting the low-income aggregation degree of a certain aggregation block i in the next time period. , and the predicted value can be obtained. For example, Figure 5 As shown, by dragging the time slider in the map plugin, the changes in the low-income aggregation degrees of each aggregation block within a certain future time period can be visually observed; refresh, reset, and configuration operations can be performed. It can be understood that the method of data analysis and calculation based on the constructed target map image in this embodiment is universal, applicable not only in this field but also extendable to fields such as real estate development and population census. In this embodiment, by re-rendering the target map image according to the relative population aggregation degree, the hot or cold spots of the poverty aggregation degree and its changes in the time dimension can be visually observed; by innovatively introducing the geographic information system and the time axis as dimensions for data display and analysis, this method can dig deeper into potential data information and business value compared with traditional data analysis means, thus providing richer insights for decision-making.

[0070] Step S14: Execute the financial service for the target population to obtain the corresponding execution feedback by using the second preset application programming interface, and monitor the income growth of the target population based on the execution feedback.

[0071] In this embodiment, it is necessary to launch the above financial service and apply it to the low-income population in order to obtain the execution feedback of the task and monitor the income growth of the low-income population in real time according to the feedback.

[0072] Thus, it can be seen that this application avoids the problem of low efficiency caused by manual on-site visits by calling data from various data sources through the application programming interface; by re-rendering the target map image according to the relative population aggregation degree, the hot or cold spots of the poverty aggregation degree and its changes in the time dimension can be visually observed; by innovatively introducing the geographic information system and the time axis as dimensions for data display and analysis, this method can dig deeper into potential data information and business value compared with traditional data analysis means, thus providing richer insights for decision-making.

[0073] Based on the foregoing embodiments, this application describes the process of obtaining the initial population aggregation degree according to the target map image and predicting the population income growth trend according to the initial population aggregation degree. To make the technical solution of this application more complete, next, this application will elaborate on the process of executing the financial service for the target population. Refer to Figure 6 As shown, the embodiments of this application provide a process for executing a financial service, including:

[0074] Step S21: Obtain the relative population aggregation degree and income growth trend corresponding to the target population.

[0075] Step S22: Select the financial services corresponding to the target population according to the relative population aggregation degree and the income growth trend, and allocate the financial services to the target execution center to execute the financial services for the target population.

[0076] In this embodiment, it is necessary to identify the low-income population areas with similar characteristics according to the relative population aggregation degree and income growth trend corresponding to the target population, select the corresponding financial services, and through an automated mechanism, achieve one-key precise delivery of policy services and financial services, and optimize the resource allocation efficiency; specifically, as Figure 7 shown in the financial policy execution flowchart, first, according to the map, circle the low-income population with consistent characteristics or areas; then select the policies and financial supporting services, that is, the above-mentioned financial services, and then the system directly connects to the urban operation center system of the district through the API interface, that is, the target execution center, and allocates it to the district urban operation center to execute the task.

[0077] Step S23: Obtain the execution feedback corresponding to the financial services, and monitor the income growth of the target population in real time according to the execution feedback.

[0078] In this embodiment, first, it is necessary to obtain the feedback on the task execution situation from the above-mentioned target execution center; finally, through the visualization cockpit such as Figure 8 and Figure 9 shown, monitor the income growth changes of the low-income population in real time, and provide key data support for government affairs services and financial services.

[0079] Among them, the specific process of the above step S21 can refer to the corresponding content disclosed in the foregoing embodiments, and will not be elaborated here.

[0080] It can be seen that this application selects financial services for the target population according to the relative population aggregation degree and income growth trend corresponding to the target population, ensuring the fit between the financial services and the actual situation of the target population, thus ensuring the effectiveness of the financial services; by using the application programming interface to issue financial services and obtaining the execution feedback of the services, it avoids obtaining information through the method of manual visits and investigations, thereby greatly improving the work efficiency and reducing the human resource cost.

[0081] See Figure 10 shown, an embodiment of this application discloses a population income monitoring device, including:

[0082] A feature information acquisition module 11, configured to collect original feature information corresponding to a target population from each target data source by using a first preset application programming interface, and perform ETL processing on the obtained original feature information to obtain each target feature information corresponding to the target population;

[0083] A map image generation module 12, configured to construct a target profile corresponding to the target population according to each target feature information, obtain map data corresponding to the target population from a target map source, and generate a target map image according to the map data and the target profile;

[0084] A financial service determination module 13, configured to obtain an initial population aggregation degree and a relative population aggregation degree corresponding to the target population based on the target map image, predict an income growth trend corresponding to the target population by using the initial population aggregation degree and a target income prediction model, and determine a financial service corresponding to the target population according to the relative population aggregation degree and the income growth trend;

[0085] A feedback acquisition module 14, configured to execute the financial service on the target population, obtain corresponding execution feedback by using a second preset application programming interface, and monitor the income growth condition of the target population based on the execution feedback.

[0086] It can be seen that, in this application, by using the application programming interface, the feature information corresponding to the target population is obtained, and based on the feature information, the income growth trend of the target population is predicted, avoiding the problems of low work efficiency and high investigation cost caused by obtaining data through manual investigation; by using the application programming interface to obtain feedback information and monitoring the income of the target population in real time according to the feedback information, the monitoring efficiency is improved, and the monitoring cost is greatly reduced.

[0087] In some specific embodiments, the feature information acquisition module 11 further includes:

[0088] An information judgment unit, configured to judge whether the original feature information is private data. If the original feature information is private data, perform an encryption operation on the original feature information to obtain the original feature information in a desensitized state;

[0089] A step jump unit, configured to, if the original feature information is not private data, jump to the step of performing ETL processing on the obtained original feature information.

[0090] In some specific embodiments, the feature information acquisition module 11 specifically includes:

[0091] A data cleaning unit for performing data cleaning operations on the original feature information to obtain de-duplicated feature information, and performing data aggregation operations on the de-duplicated feature information from each of the target data sources to obtain corresponding aggregated feature information;

[0092] A data verification unit for performing data verification on the aggregated feature information to obtain each of the target feature information corresponding to the target population.

[0093] In some specific embodiments, the map image generation module 12 specifically includes:

[0094] A map image generation sub-module for performing data processing on the vector data and raster data in the map data to obtain processed map data, and generating the target map image corresponding to the target population based on the processed map data and the target file.

[0095] In some specific embodiments, the map image generation sub-module specifically includes:

[0096] A map image generation unit for performing a coordinate reference system conversion operation on the processed map data to obtain corresponding converted map data, and generating the target map image corresponding to the target population by using the converted map data and the target file.

[0097] In some specific embodiments, the financial service determination module 13 further includes:

[0098] A model training unit for obtaining historical income data corresponding to the target population from each of the target data sources, and performing model training operations on the initial income prediction model by using the historical income data, and updating the model parameters of the initial income prediction model based on the corresponding training results to obtain the target income prediction model.

[0099] In some specific embodiments, the financial service determination module 13 specifically includes:

[0100] An image partitioning unit for partitioning the aggregation blocks corresponding to the target population according to the target map image, and calculating the initial population aggregation degree corresponding to the target population by using the aggregation blocks and a preset aggregation degree calculation formula;

[0101] An aggregation degree obtaining unit for obtaining the relative population aggregation degree corresponding to the target population by using the initial population aggregation degree corresponding to the target population and a preset hot spot analysis technique.

[0102] Furthermore, the embodiment of the present application also discloses an electronic device, Figure 11It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment. The content in the figure should not be considered as any limitation on the scope of use of this application.

[0103] Figure 11 This is a schematic structural diagram of an electronic device 20 provided by an embodiment of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the map-based population income monitoring method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0104] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of this application, and no specific limitation is imposed on it here; the input / output interface 25 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitation is made here.

[0105] In addition, as a carrier for resource storage, the memory 22 may be a read-only memory, a random access memory, a magnetic disk, or an optical disc, etc. The resources stored thereon may include an operating system 221, a computer program 222, etc., and the storage method may be temporary storage or permanent storage.

[0106] Among them, the operating system 221 is used to manage and control each hardware device and the computer program 222 on the electronic device 20, and it may be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the map-based population income monitoring method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs that can be used to complete other specific tasks.

[0107] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the map-based population income monitoring method disclosed above. For the specific steps of this method, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details are not repeated here.

[0108] In this specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description in the method section.

[0109] Those skilled in the art can further realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0110] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0111] Finally, it should also be noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0112] The above has introduced the technical solutions provided by this application in detail. Specific examples are used in this article to elaborate on the principles and implementation manners of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A method for monitoring population income based on a map, characterized in that: include: Using the first preset application programming interface to collect original feature information corresponding to the target population from each target data source, and performing ETL processing on the acquired original feature information to obtain each target feature information corresponding to the target population; Constructing a target profile corresponding to the target population according to each target feature information, acquiring map data corresponding to the target population from a target map source, and generating a target map image according to the map data and the target profile; Based on the target map image, an initial crowd concentration and a relative crowd concentration corresponding to the target population are obtained, the income growth trend corresponding to the target population is predicted using the initial crowd concentration and a target income prediction model, and the financial services corresponding to the target population are determined according to the relative crowd concentration and the income growth trend; The financial services are executed for the target population to obtain corresponding execution feedback using a second preset application programming interface, and the income growth of the target population is monitored based on the execution feedback.

2. The map-based population income monitoring method according to claim 1, characterized in that: Before performing ETL processing on the acquired original feature information, the method further includes: Determine whether the original feature information is private data, and if the original feature information is private data, encrypt the original feature information to obtain the original feature information in a desensitized state; If the original feature information is not privacy data, jump to the step of performing ETL processing on the acquired original feature information.

3. The map-based population income monitoring method according to claim 1, characterized in that: The ETL processing is performed on the acquired original feature information to obtain target feature information corresponding to the target population, including: Performing a data cleaning operation on the original feature information to obtain deduplicated feature information, and performing a data aggregation operation on the deduplicated feature information from each of the target data sources to obtain corresponding aggregated feature information; The aggregated characteristic information is subjected to data verification to obtain the target characteristic information corresponding to the target population.

4. The map-based population income monitoring method according to claim 1, characterized in that: The generating of the target map image according to the map data and the target file comprises: Data processing is performed on the vector data and raster data in the map data to obtain processed map data, and the target map image corresponding to the target population is generated based on the processed map data and the target profile.

5. The map-based population income monitoring method according to claim 4, characterized in that: The generating the target map image corresponding to the target population based on the processed map data and the target profile includes: A coordinate reference system conversion operation is performed on the processed map data to obtain corresponding converted map data, and the target map image corresponding to the target population is generated using the converted map data and the target file.

6. The map-based population income monitoring method according to claim 1, characterized in that: Before predicting the income growth trend corresponding to the target population using the initial population concentration and the target income prediction model, the method further includes: The historical income data corresponding to the target population is obtained from each of the target data sources, and the historical income data is used to perform model training operations on the initial income prediction model. The model parameters of the initial income prediction model are updated based on the corresponding training results to obtain the target income prediction model.

7. The map-based population income monitoring method according to any one of claims 1 to 6, characterized in that: The obtaining the initial crowd concentration and the relative crowd concentration corresponding to the target crowd based on the target map image includes: Divide the target population into cluster blocks according to the target map image, and calculate the initial population concentration degree corresponding to the target population using the cluster blocks and a preset concentration degree calculation formula; The relative crowd concentration degree corresponding to the target population is obtained by using the initial crowd concentration degree corresponding to the target population and a preset hot spot analysis technology.

8. A map-based crowd income monitoring device, characterized in that: include: A feature information acquisition module, used to collect original feature information corresponding to the target population from each target data source using a first preset application programming interface, and perform ETL processing on the acquired original feature information to obtain each target feature information corresponding to the target population; A map image generation module, used to construct a target profile corresponding to the target population according to each target feature information, obtain map data corresponding to the target population from a target map source, and generate a target map image according to the map data and the target profile; a financial service determination module, for obtaining an initial crowd concentration and a relative crowd concentration corresponding to the target population based on the target map image, predicting an income growth trend corresponding to the target population using the initial crowd concentration and a target income prediction model, and determining financial services corresponding to the target population based on the relative crowd concentration and the income growth trend; A feedback acquisition module is used to execute the financial services for the target population, so as to obtain corresponding execution feedback using a second preset application programming interface, and to monitor the income growth of the target population based on the execution feedback.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the map-based population income monitoring method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the map-based population income monitoring method as described in any one of claims 1 to 7.

Images