Population Prediction Method, Apparatus, Device, and Storage Medium

Abstract

An embodiment of the present invention provides a population prediction method, apparatus, device, and storage medium. The method includes: determining the household registration location of each user according to the identity card information associated with the mobile device of each user in the target area and the location information on specified holidays over the years; determining the current-year permanent residence and last-year permanent residence of each user according to the household registration location of each user and the location information of the mobile device of each user; determining the number of inflowing population of each age and the number of outflowing population of each age in the target area according to the current-year permanent residence and last-year permanent residence of each user; respectively obtaining the total predicted inflowing population and the total predicted outflowing population in the next year of the target area according to the number of inflowing population of each age and its corresponding weight coefficient, and the number of outflowing population of each age and its corresponding weight coefficient, and combining the number of surviving population in the current year and the total predicted number of newborns in the next year in the target area to achieve the prediction of the total predicted population in the next year of the target area.

Description

Technical Field

[0001] The present invention relates to the field of population prediction, and more particularly, to a population prediction method, apparatus, device, and storage medium. Background Art

[0002] Population prediction is of great significance to the planning of economic and social development. Currently, there are mainly two types of population prediction methods. One is the direct prediction method, that is, based on certain data rules, using linear growth models, geometric growth models, exponential growth models, or logistic growth models to obtain relevant parameters and coefficients for predicting population development trends, and then completing population prediction based on the given prediction time. The other is the element-based prediction method, that is, based on the law of population age progression, combined with the number of births, deaths, immigrants, emigrants, and the given prediction time, to predict the population numbers of different ages in each year within the given time. The specific implementation involves the following processes: First, the population of each age and gender in the census year is shifted to the next year according to the survival rate of the population of that age and gender. Then, the number of women of childbearing age and the age-specific fertility rate are obtained by age to calculate the number of births in one year, and the number of births is projected to the neonatal population in the next year. If migration is considered, the net migration population is added to the population numbers of each age obtained by prediction, and thus iterated year by year to complete the population prediction within the given prediction time. However, both of these two types of population prediction methods have certain defects:

[0003] For the direct prediction method, it ignores the internal law of population growth and only relies on historical data rules to predict future data, and is not applicable to population prediction in case of emergencies. And because it does not consider the influence of various complex factors, it is only applicable to the situation where population growth is relatively stable and is not applicable to population prediction in case of frequent population movement.

[0004] For the element-based prediction method, the difficulty lies in obtaining the migration population model. Because in population surveys, there is a high underreporting rate of population migration between provinces, and there are also certain biases in the samples of population surveys, resulting in difficulty in obtaining accurate population migration data and making it more difficult to obtain the migration population model.

[0005] Therefore, whether it is the direct prediction method or the element-based prediction method, there are problems of low accuracy in the results of future population prediction. Summary of the Invention

[0006] In view of this, in order to at least solve the problem of low accuracy of population prediction results in related technologies, the purpose of the present invention is to provide a population prediction method, apparatus, device, and storage medium.

[0007] To achieve the above purpose, the technical solutions adopted in the embodiments of the present invention are as follows:

[0008] In the first aspect of the embodiments of the present invention, a population prediction method is provided, including:

[0009] Determine the household registration locations of each user according to the identity card information associated with the mobile devices of each user in the target group in the target area and the location information of designated holidays over the years;

[0010] Determine the current-year permanent residence and last-year permanent residence of each user according to the household registration location of each user and the location information of the mobile device of each user;

[0011] Determine the number of inflowing population of each age and the number of outflowing population of each age in the target area according to the current-year permanent residence and last-year permanent residence of each user; the number of inflowing population of each age represents the total population corresponding to different-age users who flow out of the target area in the target group, and the number of outflowing population of each age represents the total population corresponding to different-age users who flow into the target area in the target group;

[0012] Obtain the total predicted inflowing population of the target area in the next year according to the number of inflowing population of each age and their respective weight coefficients, and obtain the total predicted outflowing population of the target area in the next year according to the number of outflowing population of each age and their respective weight coefficients; wherein, any weight coefficient is determined based on the policy factor value, environmental factor value, economic factor value, and education level value of the target area in the next year;

[0013] Determine the total predicted population of the target area in the next year according to the total predicted inflowing population in the next year, the total predicted outflowing population in the next year, the number of surviving population in the current year of the target area, and the total predicted number of newborns in the next year.

[0014] In the second aspect of the embodiments of the present invention, a population prediction device is provided, including:

[0015] A household registration location determination module, configured to: determine the household registration location of each user according to the identity card information associated with the mobile devices of each user in the target group in the target area and the location information of designated holidays over the years;

[0016] A permanent residence determination module, configured to: determine the current-year permanent residence and last-year permanent residence of each user according to the household registration location of each user and the location information of the mobile device of each user;

[0017] A floating population determination module, configured to: determine the number of inflowing population of each age and the number of outflowing population of each age in the target area according to the current-year permanent residence and last-year permanent residence of each user; the number of inflowing population of each age represents the total population corresponding to different-age users who flow out of the target area in the target group, and the number of outflowing population of each age represents the total population corresponding to different-age users who flow into the target area in the target group;

[0018] The floating population prediction module is configured to: obtain the total predicted inflow population of the target area in the next year according to the number of inflow populations of each age and their respective weight coefficients, and obtain the total predicted outflow population of the target area in the next year according to the number of outflow populations of each age and their respective weight coefficients; wherein, any weight coefficient is determined based on the policy factor value, environmental factor value, economic factor value and education level value of the target area in the next year;

[0019] The total population prediction module is configured to: determine the total predicted population of the target area in the next year according to the total predicted inflow population in the next year, the total predicted outflow population in the next year, the number of surviving populations in the current year of the target area, and the total predicted number of newborn populations in the next year.

[0020] In a third aspect of the embodiments of the present invention, there is provided an electronic device, including a processor and a memory, where the memory stores machine-executable instructions that can be executed by the processor, and the processor can execute the machine-executable instructions to implement the population prediction method provided in the first aspect above.

[0021] In a fourth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the population prediction method provided in the first aspect above is implemented.

[0022] The population prediction method, device, equipment, and storage medium provided by the embodiments of the present invention. In the first aspect, by using the ID card information associated with the mobile devices of the target group in the target area and the positioning information on specified holidays over the years, first determine the household registration locations of each user in the target group, and then based on the household registration locations and the positioning information of the mobile devices, obtain the current-year permanent residence and last-year permanent residence of each user. Furthermore, use the current-year permanent residence and last-year permanent residence of each user to obtain the number of inflowing population and the number of outflowing population in the target area. This solution for obtaining the number of inflowing population and the number of outflowing population in the target area by using mobile device signaling not only solves the problem of difficult access to migrant population, but also objectively reflects the population flow situation in the target area, and further improves the accuracy of the obtained population flow data, laying a foundation for accurately predicting the total predicted population in the target area in the following year. In the second aspect, on the premise of obtaining the population flow data in the target area, further divide and count the flow data, that is, separately count the number of inflowing population and the number of outflowing population at different ages to obtain the number of inflowing population at each age and the number of outflowing population at each age. Then, use the number of inflowing population at each age and their respective weight coefficients to predict the total predicted inflowing population in the target area in the following year, and use the number of outflowing population at each age and their respective weight coefficients to predict the total predicted outflowing population in the target area in the following year. This way of realizing the prediction of the inflowing population and the outflowing population in the following year by age stage not only can accurately reflect the population flow situation at each age, but also based on this, predicting the inflowing and outflowing population in the following year can make the total predicted inflowing population and the total predicted outflowing population in the following year obtained by prediction have higher accuracy. In the third aspect, by adding factors such as the policy factors, environmental factors, economic factors, and education level of the target area to determine the weight coefficients in the prediction process of the inflowing and outflowing population in the following year. This way of predicting the population flow situation in the target area in the following year by comprehensively considering the population flow situation in the target area in the current year and factors such as the policy factors, environmental factors, economic factors, and education level of the target area in the following year well considers the impact of the objective factors existing in the target area on population flow, and can further improve the accuracy of the total predicted population in the following year obtained based on this prediction.

[0023] In addition, the combination of the second and third aspects described above, by assigning corresponding weight coefficients to the population inflow numbers of each age group and corresponding weight coefficients to the population outflow numbers of each age group, well considers the influence of the objective factors existing in the target area on the population flow situation at different ages, realizes a more accurate prediction of the population flow situation at different ages, and further makes the total predicted inflow population and the total predicted outflow population obtained based on this prediction have higher accuracy. On this basis, further combining with the first aspect, that is, the combination of the above three aspects, can reduce the deviation between the finally predicted total population and the actually announced total population to within 1%. It can be seen that the above solution provided by the embodiments of the present invention can greatly improve the accuracy of population prediction.

[0024] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes a detailed description as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0026] Figure 1 Shows a structural block diagram of an electronic device provided by an embodiment of the present invention;

[0027] Figure 2 Shows a flowchart of a population prediction method provided by an embodiment of the present invention;

[0028] Figure 3 Shows a functional module diagram of a population prediction device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Usually, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0030] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0031] It should be noted that 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 terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0032] To at least solve the technical problem of low accuracy of the pre-stored population results caused by the difficulty in obtaining the migrant population model in the traditional technology, the present invention provides a population prediction method. In the first aspect, by using the ID card information associated with the mobile devices of the target group in the target area and the location information on designated holidays over the years, first determine the household registration locations of each user in the target group, and then based on the household registration locations and the location information of the mobile devices, obtain the current-year permanent residence and last-year permanent residence of each user. Furthermore, use the current-year permanent residence and last-year permanent residence of each user to obtain the number of inflowing population and the number of outflowing population in the target area. This solution for obtaining the number of inflowing population and the number of outflowing population in the target area by using mobile device signaling not only solves the problem of difficulty in obtaining the migrant population, but also objectively reflects the population flow situation in the target area, and further improves the accuracy of the obtained population flow data, laying a foundation for accurately predicting the total population in the next year in the target area. In the second aspect, on the premise of obtaining the population flow data in the target area, further divide and count the flow data, that is, separately count the number of inflowing population and the number of outflowing population at different ages to obtain the number of inflowing population at each age and the number of outflowing population at each age. Then, use the number of inflowing population at each age and their respective weight coefficients to predict the total number of inflowing population in the next year in the target area, and use the number of outflowing population at each age and their respective weight coefficients to predict the total number of outflowing population in the next year in the target area. This way of predicting the inflowing population and the outflowing population in the next year by age stage can not only accurately reflect the population flow situation at each age, but also make the predicted total number of inflowing population in the next year and the predicted total number of outflowing population in the next year obtained based on this have higher accuracy. In the third aspect, by adding factors such as the policy factor, environmental factor, economic factor, and education level of the target area to determine the weight coefficients in the process of predicting the inflowing and outflowing population in the next year, this way of predicting the population flow situation in the next year in the target area by comprehensively considering the population flow situation in the target area in the current year and factors such as the policy factor, environmental factor, economic factor, and education level of the target area in the next year well considers the impact of the objective factors existing in the target area on the population flow, and can further improve the accuracy of the predicted total population in the next year obtained based on this.

[0033] In addition, the combination of the second and third aspects mentioned above, by allocating corresponding weight coefficients to the population inflow numbers of different ages and corresponding weight coefficients to the population outflow numbers of different ages, well considers the influence of the objective factors existing in the target area on the population flow situation at different ages, realizes a more accurate prediction of the population flow situation at different ages, and further makes the total predicted inflow population and the total predicted outflow population obtained based on this prediction have higher accuracy. On this basis, further combining with the first aspect, that is, the combination of the above three aspects, can reduce the deviation between the finally predicted total population and the actually announced total population to within 1%. It can be seen that the above solution provided by the embodiments of the present invention can greatly improve the accuracy of population prediction.

[0034] The population prediction method provided by the present invention can be applied to an electronic device. Please refer to Figure 1 , which is a structural block diagram of the electronic device. The electronic device 100 includes a memory 110, a processor 120, and a communication module 130. The elements of the memory 110, the processor 120, and the communication module 130 are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines.

[0035] Among them, the memory is used to store programs or data. The memory can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0036] The processor is used to read / write the data or programs stored in the memory and execute corresponding functions.

[0037] The communication module is used to establish a communication connection between the electronic device and other communication terminals through a network and is used to transmit and receive data through the network.

[0038] It should be understood that Figure 1 The structure shown is only a schematic diagram of the structure of the electronic device. The electronic device may further include more or fewer components than those shown in Figure 1 , or have a different configuration from that shown in Figure 1 .Figure 1 Each component shown in FIG. may be implemented by hardware, software, or a combination thereof.

[0039] In some embodiments, the electronic device may be a personal computer or a server, and the embodiments of the present invention do not limit this.

[0040] The following Figure 2 describes the population prediction method provided by the embodiments of the present invention. Figure 2 is a flowchart of a population prediction method provided by an embodiment of the present invention. The population prediction method includes:

[0041] In step S100, according to the identity card information associated with the mobile devices of each user in the target group in the target area and the positioning information of specified holidays in multiple years, determine the household registration location of each user;

[0042] In step S200, according to the household registration location of each user and the positioning information of the mobile device of each user, determine the current year's permanent residence and last year's permanent residence of each user;

[0043] In step S300, according to the current year's permanent residence and last year's permanent residence of each user, determine the number of inflowing population of each age and the number of outflowing population of each age in the target area; the number of inflowing population of each age represents the total population corresponding to different age users who flow out of the target area in the target group, and the number of outflowing population of each age represents the total population corresponding to different age users who flow into the target area in the target group;

[0044] In step S400, according to the number of inflowing population of each age and its corresponding weight coefficient, obtain the total predicted inflowing population of the target area in the next year, and according to the number of outflowing population of each age and its corresponding weight coefficient, obtain the total predicted outflowing population of the target area in the next year; wherein, any weight coefficient is determined based on the policy factor value, environmental factor value, economic factor value, and education level value of the target area in the next year;

[0045] In step S500, according to the total predicted inflowing population in the next year, the total predicted outflowing population in the next year, the number of surviving population in the current year of the target area, and the total predicted number of newborns in the next year, determine the total predicted population of the target area in the next year.

[0046] In the population prediction scenario, if it is necessary to predict the total population of a certain place or a certain area (i.e., the target area) in the following year, the operation program of the method can be started in the electronic device loaded with the population prediction method provided by the embodiments of the present invention, so that the electronic device executes the above steps S100 to S500, thereby realizing the prediction of the total population of the target area in the following year. Among them, the target area can refer to one area or multiple areas, and the area can be at the national level, for example, China; it can also be at the provincial, municipal, district, county, or township level under the country. The embodiments of the present invention do not make any limitations in this regard. It should be understood that as long as it involves predicting the total population of a region in the following year, the population prediction method provided by the embodiments of the present invention can be used. If it is necessary to predict the total population of multiple regions in the following year, the above steps S100 to S500 can be executed for each region to obtain the predicted total population of each region in the following year.

[0047] The following describes the process of the population prediction method provided by the embodiments of the present invention to predict the total population of the target area in the following year in combination with steps S100 to S500:

[0048] First, obtain the target area for which the population needs to be predicted in the following year. The acquisition of the target area can be pre-built in the relevant program of the population prediction method provided by the embodiments of the present invention during the development stage, or can be input by relevant personnel when starting the population prediction method provided by the embodiments of the present invention. The embodiments of the present invention do not make any limitations in this regard.

[0049] After obtaining the target area, the user information associated with the mobile devices whose positioning information falls within the target area within this year can be obtained from the operator database that has been authorized and stores mobile device communication signaling, and these users are used as the target group in the target area. In short, the users who have stayed in the target area and carried mobile devices are used as the target group mentioned in step S100. The mobile device among them can be a device equipped with a normally usable SIM card, and the mobile device can be a mobile phone, a tablet computer, a portable computer, or a watch. However, at present, in fact, users have a relatively high usage frequency of mobile device of the mobile phone type and carry it basically every day. Therefore, in some examples, the mobile device can be limited to a mobile phone to ensure the accuracy and effectiveness of the target group and further improve the accuracy of the population prediction result.

[0050] After learning about the target area and target group, the ID card information associated with each user's mobile device and the location information on designated holidays over the years can be obtained from the operator database, and then step S10 is executed. Based on the ID card information of each user in the target group and the location information on designated holidays over the years, the household registration location of each user can be determined. In some examples, the household registration location can be directly obtained from the ID card information. For example, the household registration location can be directly determined as the ID card registration location, or the location designated by the location information on designated holidays over the years can be directly used as the household registration location. However, this method of determining the household registration location of users only considers the ID card registration location or only considers the place where the user stays on designated holidays over the years, lacking comprehensiveness. Because the ID card registration location may not be consistent with the actual household registration location, and the place where the user stays on designated holidays over the years may be a regular travel destination. Therefore, both of the above methods for determining the household registration location have inevitable loopholes, resulting in the lack of accuracy in the determination result of the household registration location, and further affecting the accuracy of determining the subsequent population flow situation. Therefore, to solve this technical problem, in some embodiments, the population prediction method provided by the embodiments of the present invention also provides a method for determining the household registration location with relatively high accuracy, that is, in the above step S100, the step of determining the household registration location of each user according to the ID card information associated with the mobile devices of each user in the target group in the target area and the location information on designated holidays over the years may include the following steps:

[0051] In step S110, according to the ID card information associated with the mobile devices carried by each user in the target group, obtain the ID card registration location of each user;

[0052] In step S120, according to the location information of the mobile devices carried by each user on designated holidays over the years, determine the hometown location of each user;

[0053] In step S130, for each user, if the ID card registration location and the hometown location match, determine that the household registration location is the ID card registration location; if the ID card registration location and the hometown location do not match, determine that the household registration location is the hometown location.

[0054] Through the above steps S110 to S130, in the process of determining the household registration location of each user, for each user, since the numbers at specific positions in the ID number in the ID information generally represent the ID registration location, the ID registration location of the user can be obtained from the ID information. For the convenience of computer processing, in some examples, the ID registration location can be directly expressed by the corresponding numbers in the ID information. In addition, for each user, the location information of the mobile device can also be used to obtain the location information during the specified holidays in the years before this year. For example, the location information during the specified holidays in three years or more. For the target group with the target area in the country, the specified holiday can be the Tomb-Sweeping Festival or the Spring Festival; for the target group with the target area abroad, the specified holiday can be the holiday when local families usually get together, such as Thanksgiving or Christmas. The embodiments of the present invention do not limit this.

[0055] Among them, for the convenience of description, taking the target area in the country as an example, to more accurately determine the household registration location of the user, generally speaking, the Spring Festival in the country is the most important festival for each family in a year, and users who work hard outside usually return to their hometowns during this holiday. Therefore, in this embodiment, the specified holiday can be during the Spring Festival, and the Spring Festival period can be the 5 days from two days before the first day of the first lunar month to the third day of the first lunar month, but it is not limited to this. Based on this, in step S120, for each user, the place where the user has stayed for the longest cumulative time during the Spring Festival in multiple years can be used as the hometown location of the user. The stay time can be obtained according to the positioning time recorded in the positioning information. For details, please refer to the related technology and will not be elaborated here.

[0056] For step S120, to further improve the accuracy of the determined hometown location, in some embodiments, the embodiments of the present invention also provide another solution for determining the hometown location of the user, that is, in step S120, the step of determining the hometown location of each user according to the positioning information of the mobile devices carried by each user during the specified holidays in multiple years can include the following steps:

[0057] In step S121, according to the positioning information of the mobile devices carried by each user during the specified holidays in multiple years, determine the place where each user stays for the longest time during the specified holiday each year;

[0058] In step S122, determine the number of times each user stays in the same place during the multiple years, and use the place with the most times as the hometown location.

[0059] In the process of determining the hometown location of each user, first, through step S121, for each user, the location information of the user's mobile device during the Spring Festival in each year over the years can be used to know the places where the user stays during the Spring Festival in each year. For any given year, when there are multiple places of stay, the place with the most days of stay can be further determined from multiple places of stay based on the time data included in the location information, and this place is used as the place of stay to be obtained in step S121. However, only the number of days of stay is considered here. Although the number of days of stay can also represent the stay time to a certain extent, the most days of stay does not necessarily mean the longest stay time. For example, assume that the user stays in three places, A, B, and C, during the above-mentioned 5-day Spring Festival. It may be that due to traffic congestion, the user stays in place A for 2 days and in place B for 1 day; or, the user keeps traveling back and forth between A and C and passes through place B, so the number of days of stay in place B (as long as passing through place B, it is considered that the user stays in place B on the day of passing through) may be the most. In fact, the stay time in place B is not long, and place B is not the hometown location, but at this time, place B will be misjudged as the hometown location. Therefore, to solve the above misjudgment problem, in some embodiments, the longest stay time not only includes the most days of stay but also the longest stay duration. Based on this, in step S121, in addition to obtaining the number of days of stay of each place of stay as described above, the corresponding stay duration of each place of stay can be further obtained based on the location information of the user's mobile device during the specified holiday. And this stay duration can refer to the cumulative stay duration at any time period within a day. However, to further improve the accuracy of determining the hometown location, in this embodiment, this stay duration refers to the cumulative stay duration during the normal rest period of the human body during the specified holiday. Among them, the normal rest period of the human body can be from 10 pm to 9 am the next day, or from 9 pm to 7 am the next day. Thus, the number of days of stay and the stay duration corresponding to each place of stay each year can be obtained, and the place of stay with the most days of stay and the longest stay duration can be determined from them as the place of stay to be obtained in step S121.

[0060] However, among the multiple places of stay each year, it is possible that there is no place of stay that simultaneously has the most days of stay and the longest stay duration. In this case, different stay weights can be assigned to the number of days of stay and the stay duration respectively. Among them, the stay weight of the number of days of stay is less than the stay weight of the stay duration. For example, one is 0.2 and the other is 0.8. Then, the stay duration is converted into units of days, and then the number of days of stay and the stay duration converted into units of days are weighted and processed according to their respective stay weights to obtain a stay duration value. At this time, the place of stay with the largest stay duration value can be used as the place of stay to be obtained in step S121.

[0061] After obtaining the desired stay in step S121 through any of the above embodiments, that is, obtaining a stay corresponding to the user in each year for many years, step S122 can be used to count the same stays in many years, and the stay with the most visits can be used as the hometown. For example, assuming that the user's stays in each year within 5 years are: A, B, A, C, A, it can be seen that A appears the most times, and in this case, A is used as the hometown.

[0062] After obtaining each user's ID card registration location and hometown location through steps S110 and S120, respectively, each user's registered residence location can be determined through step S130. Specifically, for each user, if the user's ID card registration location and hometown location are the same, or the distance between the ID card registration location and hometown location is within a set distance threshold (indicating that the ID card registration location and hometown location may be the same place, but the positioning result is inaccurate due to a certain positioning deviation. If the distance between the two places falls within the positioning deviation range, it indicates that the two places are most likely the same place), then the user's registered residence location is determined to be the ID card registration location. Conversely, if the user's ID card registration location and hometown location are different, and the distance between them exceeds the aforementioned distance threshold, then the user's registered residence location is determined to be the hometown location.

[0063] It should be added that step S110 and step S120 can be executed serially or in parallel, and there is no strict order in which they must be executed.

[0064] Thus, after obtaining the registered residence of each user in the target group in the target area through any embodiment of step S100, step S200 can be then executed to obtain the permanent residence of each user this year and last year based on the registered residence of each user and the positioning information of each user's mobile device. Among them, the determination method of the permanent residence in the relevant technology can be applied to step S200 to obtain the permanent residence of each user this year and last year. However, in order to further improve the determination result of the permanent residence, in some embodiments, the embodiment of the present invention also provides a method for determining the permanent residence this year, that is, in step S200, the step of determining the permanent residence of each user this year based on the registered residence of each user and the positioning information of each user's mobile device can include the following steps:

[0065] In step S211, based on the location information of each user's mobile device in the month when the current time is located, it is determined whether each user lives in their place of household registration in that month. The current time here can refer to the time when the population prediction method provided by the embodiments of the present invention is executed. As long as any one of the locations indicated by the location information in the month when the current time is located falls within the place of household registration, it is considered that the current user lives in the place of household registration in that month. Or, as long as there is a location among the locations indicated by the location information in the month when the current time is located whose distance from the place of household registration is less than or equal to the above distance threshold, it is also considered that the current user lives in the place of household registration in that month. Subsequently, it will jump to step S214; otherwise, if any one of the locations indicated by the location information in the month when the current time is located does not fall within the place of household registration, or if any one of the locations indicated by the location information in the month when the current time is located does not fall within the place of household registration and the distance between any one of the locations and the place of household registration is greater than the above distance threshold, it is considered that the current user does not live in the place of household registration in that month. Subsequently, step S212 will be executed.

[0066] In step S212, when the current user does not live in the place of household registration in that month, based on the location information of the current user's mobile device in the statistical period of this year, it is determined whether the current user has left their place of household registration for more than a preset duration. Here, the statistical period of this year can be the period starting from the beginning of the previous twelve months of the month when the current time is located and ending at the month when the current time is located; the twelve months can be adjusted to any one of nine months to eleven months as needed; in addition, the preset duration can be 6 months, but it is not limited to this. Taking the preset duration of 6 months as an example, in step S212, for each user who does not live in the place of household registration in that month, if it is known from the location information of the user's mobile device in the above statistical period of this year that the user has left the place of household registration for 6 months or more, step S213 will be executed; otherwise, step S214 will be executed.

[0067] In step S213, when the current user has left their place of household registration for more than a preset duration, based on the location information of the current user's mobile device in the statistical period of this year, the place where the current user has stayed the longest in addition to the place of household registration is determined as the usual residence of this year. The longest stay time here can refer to the relevant records above, that is, it can represent the most days of stay, or it can represent the most days of stay and the longest stay duration. Details are not elaborated here. However, in this step, the place serving as the usual residence of this year also needs to meet the following requirements: the user has stayed in this place for more than a set number of months, for example, 6 months, and the number of days the user stays in this place each month exceeds a set number of days, for example, 10 days.

[0068] In step S214, when the current user has not left his / her place of household registration for more than a preset duration, or when the current user lives in the place of household registration in the current month, determine that the current user's usual place of residence this year is the place of household registration.

[0069] Thus, through steps S211 to S214, the usual place of residence of each user this year can be obtained. In addition, the principle of obtaining the usual place of residence of each user last year is the same as that of obtaining the usual place of residence this year. That is, in step S200, the steps of determining the usual place of residence of each user last year according to the place of household registration of each user and the positioning information of the mobile devices of each user may include the following steps:

[0070] In step S221, according to the positioning information of the mobile devices of each user in the last month of the last statistical period of last year, determine whether each user lived in the place of household registration in the last month;

[0071] In step S222, when the current user did not live in the place of household registration in the last month, according to the positioning information of the mobile device of the current user in the last statistical period of last year, determine whether the current user has left his / her place of household registration for more than a preset duration;

[0072] In step S223, when the current user has left his / her place of household registration for more than a preset duration, according to the positioning information of the mobile device of the current user in the last statistical period of last year, determine that the place where the current user stayed the longest in addition to the place of household registration is the usual place of residence last year;

[0073] In step S224, when the current user has not left his / her place of household registration for more than a preset duration, or when the current user lived in the place of household registration in the last month, determine that the current user's usual place of residence last year is the place of household registration.

[0074] For the understanding of steps S221 to S224, reference can be made to the relevant descriptions of steps S211 to S214 in the above text, and details will not be elaborated here.

[0075] In addition, considering that some mobile users will cancel their SIM cards, resulting in the loss of some positioning information, it is possible that some users have no usual place of residence this year or no usual place of residence last year. To avoid this situation from affecting the smooth execution of subsequent steps, in some embodiments, for users without a usual place of residence this year, the place where they last stayed can be taken as the usual place of residence this year; for users without a usual place of residence last year, the place where they last stayed last year can be taken as the usual place of residence last year.

[0076] After obtaining the current year's usual residence and last year's usual residence of each user through any embodiment of step S200, the number of inflowing population and the number of outflowing population of each age in the target area can be obtained through step S300 based on the current year's usual residence and last year's usual residence of each user in the target group in the target area. For example, for each user, if his current year's usual residence is different from his last year's usual residence, the user is considered a mobile user. If his current year's usual residence is the same as his last year's usual residence, the user is considered a non-mobile user. Since the number of inflowing population and the number of outflowing population of each age in the target area are both statistically based on mobile users, the data of non-mobile users can be ignored.

[0077] After obtaining all the mobile users in the target group, the mobile users can be further divided to obtain inflowing users and outflowing users. Among them, the inflowing users and outflowing users are both relative to the target area. That is, if the current year's usual residence is in the target area and the last year's usual residence is not in the target area, the current user is considered an inflowing user. On the contrary, if the current year's usual residence is not in the target area and the last year's usual residence is in the target area, the current user is considered an outflowing user. In this way, the inflowing users and outflowing users can be distinguished.

[0078] Whether it is an inflowing user or an outflowing user, since their ID card information can be obtained, the age corresponding to each inflowing user can be calculated based on the ID card information of all inflowing users. Then, the inflowing users with the same age can be included in the same subset of inflowing users. In this way, different subsets of inflowing users corresponding to different ages can be obtained. For each subset of inflowing users, the number of users it contains can be further counted to obtain the number of inflowing population of each age. For example, assuming that the age range of the users in the target group is between 9 and 100 years old, the number of inflowing population of each age includes: the number of inflowing population at the age of 9, the number of inflowing population at the age of 10, the number of inflowing population at the age of 11... the number of inflowing population at the age of 100.

[0079] Similarly, the relevant data of all outflowing users can also be processed according to the above principle to obtain the number of outflowing population of each age.

[0080] As can be seen from the relevant records above, there is a certain positioning deviation in mobile devices. If the judgment of mobile users is directly based on the current year's usual residence and the previous year's usual residence with a certain positioning deviation, the judgment result will obviously be affected by this positioning deviation. For example, the boundary between regions may face the situation where the actual usual residence has not changed, but the positioning information of the mobile device determines it as two different regions, which may lead to misjudgment of mobile users. Therefore, to solve this technical problem, in some embodiments, the population prediction method provided by the embodiments of the present invention also provides a solution to correct the errors caused by the positioning deviation of the current year's usual residence and the previous year's usual residence, and reduce the phenomenon of misjudgment of mobile users. That is, in the above step S300, the step of determining the number of inflowing population of each age and the number of outflowing population of each age in the target region according to the current year's usual residence and the previous year's usual residence of each user may include the following steps:

[0081] In step S310, for each user, determine whether the distance between their current year's usual residence and the previous year's usual residence exceeds a set distance threshold;

[0082] In step S320, when the distance between the current user's current year's usual residence and the previous year's usual residence exceeds the set distance threshold, determine that the current user is a mobile user;

[0083] In step S330, when the distance between the current user's current year's usual residence and the previous year's usual residence does not exceed the set distance threshold, determine that the current user is a non-mobile user;

[0084] In step S340, according to the current year's usual residence and the previous year's usual residence of all mobile users, determine the number of inflowing population of each age and the number of outflowing population of each age in the target region.

[0085] Among them, for the understanding of step S340, reference can be made to the relevant records above. That is, in step S340, the step of determining the number of inflowing population of each age and the number of outflowing population of each age in the target region according to the current year's usual residence and the previous year's usual residence of all mobile users may include the following steps:

[0086] In step S341, for each mobile user, if the current year's usual residence of the mobile user is the target region and the previous year's usual residence is not the target region, determine that the mobile user is an inflowing user of the target region; if the previous year's usual residence of the mobile user is the target region and the current year's usual residence is not the target region, determine that the mobile user is an outflowing user of the target region;

[0087] In step S342, according to the inflowing users and the outflowing users, determine the number of inflowing population of each age and the number of outflowing population of each age in the target region.

[0088] After obtaining the number of inflowing population of each age and the number of outflowing population of each age in the target area through any of the embodiments of step S300, step S400 can be executed to obtain the total predicted inflowing population of the target area in the next year based on the number of inflowing population of each age and their respective weight coefficients; and obtain the total predicted outflowing population of the target area in the next year based on the number of outflowing population of each age and their respective weight coefficients. Among them, the total predicted inflowing population in the next year can be calculated by formula (1), and the total predicted outflowing population in the next year can be calculated by formula (2):

[0089] Formula (1)

[0090] Formula (2)

[0091] In formula (1), is the total predicted inflowing population in the next year, represents this year, represents the next year, represents the weight coefficient corresponding to the number of inflowing population of age in the next year, takes values as , and is an integer value between, represents the minimum age value among all the inflowing users recorded above, represents the maximum age value among all the inflowing users recorded above, represents age corresponding to the number of inflowing population in this year.

[0092] In formula (2), is the total predicted outflowing population in the next year, represents this year, represents the next year, represents the weight coefficient corresponding to the number of outflowing population of age in the next year, the value range of , , represents the minimum age value among all the outflowing users recorded above, represents the maximum age value among all the outflowing users recorded above, represents age corresponding to the number of outflowing population in this year.

[0093] Among the above, the weight coefficients corresponding to the inflow population numbers of each age, that is, the weight coefficients used to predict the inflow population numbers of each age in the next year, can be comprehensively considered according to the policy factors, environmental factors, economic factors, educational levels, etc. of the target area in the next year, and the corresponding values can be set by developers through experience or experiments. It can be understood that whether it is the inflow population number or the outflow population number, the weight coefficients corresponding to each age can be set by developers during the development stage.

[0094] Although the weight coefficients obtained by the developers can already express the policy factors, environmental factors, economic factors, educational levels, etc. from a relatively objective level to predict the relatively accurate total predicted inflow population and total predicted outflow population in the next year, in each year after this year, if population prediction is to be carried out, it may be necessary to reset the corresponding weights for the outflow population and inflow population of each age according to the policy factors, environmental factors, economic factors, and educational levels of the year after the current year of the target area again. This will bring a great workload to relevant personnel, and the method relying on manual setting also has problems of low efficiency and high error rate. Therefore, to solve this technical problem, in some embodiments, the population prediction method provided by the embodiments of the present invention also provides an automated acquisition solution for weight coefficients, that is, the acquisition process of the weight coefficients corresponding to the inflow population numbers of each age includes:

[0095] In step S410, according to the policies, environment, economy, and education level of the target region in the following year, obtain the policy factor value, environmental factor value, economic factor value, and education level value of the target region in the following year from the pre-constructed factor value table. Among them, the factor value table can use big data analysis methods to score based on the past policies, environment, economy, and education level of the target region before this year and unify the scoring rules. For example, for the policy factor, the semantic analysis method can be used to interpret the annual policies of the target region, extract the positive policy items with positive effects and the negative policy items with negative effects, then respectively count the first total number of positive policy items and the second total number of negative policy items, and then use the difference between the first total number and the second total number as the policy factor value; in other examples, whether it is a positive policy item or a negative policy item, corresponding values can also be assigned to each item according to the importance of the impact of each item in the policy item. Based on this, if each value is a positive number, the difference between the sum of the values corresponding to all items in the positive policy items and the sum of the values corresponding to all items in the negative policy items can be used as the policy factor value; if the values corresponding to the positive policy items are positive numbers and the values corresponding to the negative policy items are negative numbers, the sum of the values corresponding to all items in the positive policy items and the sum of the values corresponding to all items in the negative policy items can be used as the policy factor value. The environmental factor value, economic factor value, and education level value can be obtained based on the same principle. Taking the example of assigning corresponding values to each item, the constructed factor value table can include various possible items and the corresponding values of each item. For example, for the policy factor, assuming there are 20 possible policy items, each policy item and its corresponding value can be recorded in the factor value table. Thus, after learning the factors such as the policies, environmental conditions, economic conditions, and education level conditions of the target region in the following year, the content of each factor can be interpreted first through the voice analysis method, then the various items involved under each factor can be obtained, and then the corresponding values can be obtained from the factor value table based on each item and corresponding operations can be performed according to the above description, so as to obtain the policy factor value, environmental factor value, economic factor value, and education level value of the target region in the following year. Next, step S4200 can be executed.

[0096] In step S420, based on the policy factor value, environmental factor value, economic factor value, and education level value of the target area in the following year, an influence integration value is processed. After obtaining the policy factor value, environmental factor value, economic factor value, and education level value of the target area in the following year through step S410, through step S420, these four values can be integrated to obtain an influence integration value. The integration process can be weighted summation processing, weighted average processing, or mean processing. When it comes to weighted summation processing or weighted average processing, the weights of each item in the policy factor value, environmental factor value, economic factor value, and education level value can be randomly set by the electronic device executing this step, or pre-set coefficients can be used. Next, step S430 can be executed.

[0097] In step S430, for each age, the influence integration value is input into the inflow population weight curve corresponding to that age to obtain the weight coefficient corresponding to the inflow population number of each age. After obtaining the influence integration value through step S420, through step S430, for each age, the influence integration value can be input into the inflow population weight curve corresponding to each age for calculation to obtain the weight coefficient corresponding to the inflow population number of each age.

[0098] In the above, the construction process of the inflow population weight curve model can include the following steps:

[0099] In step S001, for each year in the historical years of the target area, based on the policy factor value, environmental factor value, economic factor value, and education level value corresponding to that year, an influence integration value is processed;

[0100] In step S002, for each year in the historical years of the target area, based on the actual inflow population number of each age and the predicted inflow population number of each age corresponding to that year, the weight coefficient corresponding to the predicted inflow population number of each age is calculated;

[0101] In step S003, for each year in the historical years of the target area, with the influence integration value corresponding to that year as the independent variable and the weight coefficient corresponding to the predicted inflow population number of each age in that year as the dependent variable, a first data subset corresponding to different ages in that year is formed;

[0102] In step S004, for each age in the historical years of the target area, based on all the first data subsets corresponding to that age in the historical years, the inflow population weight curve corresponding to that age is constructed to obtain the inflow population weight curves corresponding to each age of the target area.

[0103] In step S001, the origin of the policy factor value, environmental factor value, economic factor value, and education level value, as well as the relevant principle of how to process the policy factor value, environmental factor value, economic factor value, and education level value to obtain an impact integration value, can be found in the relevant records above and will not be elaborated here.

[0104] In step S002, the actual inflow population numbers of each age corresponding to each year in the historical years of the target area can be obtained from the publicly available census data, while the predicted inflow population numbers of each age are obtained based on the initial weights corresponding to the inflow population numbers of each age through the population prediction method provided by the embodiments of the present invention. The relevant principles have been recorded above and will not be elaborated here; in some examples, for the convenience of initial operation, the initial weight corresponding to the inflow population number of any age can be initialized to the value 1. Thus, for each age in each year of the historical years of the target area, the corresponding weight coefficient can be obtained based on the ratio of the actual inflow population number and the predicted inflow population number of the corresponding age. That is, assuming that in 2019, the actual inflow population number of 20-year-olds in the target area is 1 million, and the predicted inflow population number is 1.1 million, based on this, the obtained weight coefficient is 1 million / 1.1 million = 0.909. At this time, the weight coefficient corresponding to the predicted inflow population number of 20-year-olds will be adjusted from the initial value 1 to 0.909. Based on this principle, the weight coefficients corresponding to the predicted inflow population numbers of each age in each year of the historical years of the target area can be obtained.

[0105] Then, through step S003, for each year, taking the impact integration value corresponding to that year as the independent variable and the weight coefficients corresponding to the predicted inflow population numbers of each age in that year as the dependent variable, a first data subset corresponding to each age in that year is formed. The form of the first data subset can be expressed as ( , ), where represents the impact integration value of the inflow population in the kth year (such as 2019) in the above historical years, represents the weight coefficient corresponding to the predicted inflow population number of age (such as 20-year-olds in 2019) in the kth year in the above historical years. The definition of here can be found in the definition of above. It can be seen that for the same year, in the data subsets corresponding to different ages, the impact integration values can be the same because the policies, economy, environment, and education levels in the same year do not change much.

[0106] Thus, through step S003, the first data subsets corresponding to each age in each year of the historical years can be obtained.

[0107] Subsequently, step S004 can be executed to classify all the first data subsets in historical years by age and sort them by year, obtaining multiple first data subsets sorted in chronological order by year for each age. Then, for each age, curve fitting is performed using all its corresponding first data subsets. The relevant fitting principle can be referred to in the related art, and thus the inflow population weight curve corresponding to each age can be obtained. That is, for each age, there is a corresponding inflow population weight curve. After presenting this inflow population weight curve in a rectangular coordinate system, the value along the horizontal axis represents the impact fusion value for each year, and the value along the vertical axis represents the weight coefficient value corresponding to the predicted inflow population number for each year at the corresponding age.

[0108] Therefore, in subsequent applications, after obtaining the impact fusion value of the current year, the impact fusion value can be input into the inflow population weight curve of the corresponding age to output the weight coefficient corresponding to the inflow population of the corresponding age in the year after the current year.

[0109] Based on the acquisition principle of the weight coefficient corresponding to the inflow population number of each age, the acquisition process of the weight coefficient corresponding to the outflow population number of each age includes:

[0110] In step S401, according to the policies, environment, economy, and education level of the target region in the following year, the policy factor value, environmental factor value, economic factor value, and education level value of the target region are obtained from the pre-constructed factor value table;

[0111] In step S402, an impact fusion value is processed based on the policy factor value, environmental factor value, economic factor value, and education level value of the target region;

[0112] In step S403, for each age, the impact fusion value is input into the outflow population weight curve corresponding to that age to obtain the weight coefficient corresponding to the outflow population number of each age.

[0113] The implementation principle and related technical details of steps S401 to S402 can be referred to the relevant records of steps S410 to S430 above and will not be elaborated here.

[0114] Based on the construction principle of the inflow population weight curve, the construction process of the outflow population weight curve includes:

[0115] In step S011, for each year in the historical years of the target region, an impact fusion value is processed according to the policy factor value, environmental factor value, economic factor value, and education level value corresponding to that year;

[0116] In step S012, for each year in the historical years of the target area, according to the actual outflow population numbers of each age corresponding to that year and the predicted outflow population numbers of each age, the weight coefficients corresponding to the predicted outflow population numbers of each age are calculated;

[0117] In step S013, for each year in the historical years of the target area, taking the influence fusion value corresponding to that year as the independent variable and the weight coefficients corresponding to the predicted outflow population numbers of each age in that year as the dependent variable, a second data subset corresponding to different ages in that year is formed;

[0118] In step S014, for each age in the historical years of the target area, according to all the second data subsets corresponding to that age in the historical years, an outflow population weight curve corresponding to that age is constructed to obtain the outflow population weight curves corresponding to each age of the target area.

[0119] For the implementation principles and related technical details of steps S011 to S014, reference can be made to the relevant records of steps S001 to S004 above, and no further elaboration will be provided here.

[0120] After calculating the total predicted inflow population of the target area in the next year and the total predicted outflow population of the target area in the next year through any embodiment of step S400, step S500 will be executed to further calculate the total predicted population of the target area in the next year according to the total predicted inflow population in the next year, the total predicted outflow population in the next year, the surviving population number of the target area in the current year, and the total predicted number of newborns in the next year. Among them, the total predicted population of the target area in the next year = the total predicted inflow population in the next year - the total predicted outflow population in the next year + the surviving population number of the current year + the total predicted number of newborns in the next year, where the surviving population number of the current year and the total predicted number of newborns in the next year can be obtained through related technologies and will not be elaborated here.

[0121] Thus, after obtaining the total predicted population of the target area in the next year through any of the above embodiments, the total predicted population of the target area in the next year can be output and displayed for subsequent applications.

[0122] In addition, the population prediction results obtained by the population prediction method provided by the embodiments of the present invention have a difference of less than 1% from the actual published data, with relatively high prediction accuracy. For relevant verification data, reference can be made to Table 1 below.

[0123] Table 1 Schematic table of the error between the prediction results obtained by the population prediction method based on the embodiments of the present invention and the actual published data

[0124]

[0125] It should be noted that the technical features or technical solutions in any of the above embodiments of the present invention can be combined with each other as long as there is no combination conflict.

[0126] To execute the corresponding steps in the above embodiments and various possible ways, an implementation manner of a population prediction device is given below. Optionally, the population prediction device may adopt the device structure of the electronic device shown above. Further, please refer to Figure 1 Figure Figure 3 , Figure 3 which is a functional module diagram of a population prediction device provided by an embodiment of the present invention. It should be noted that for the population prediction device provided in this embodiment, its basic principle and the generated technical effects are the same as those in the above embodiments. For the sake of brief description, for the parts not mentioned in this embodiment, reference can be made to the corresponding content in the above embodiments. The population prediction device 300 includes:

[0127] A household registration location determination module 310, configured to: determine the household registration location of each user according to the identity card information associated with the mobile devices of each user in the target group in the target area and the location information of specified holidays in multiple years;

[0128] A usual residence location determination module 320, configured to: determine the current-year usual residence location and the previous-year usual residence location of each user according to the household registration location of each user and the location information of the mobile devices of each user;

[0129] A floating population determination module 330, configured to: determine the number of inflowing population of each age and the number of outflowing population of each age in the target area according to the current-year usual residence location and the previous-year usual residence location of each user; the number of inflowing population of each age represents the total population corresponding to different-age users who flow out of the target area in the target group, and the number of outflowing population of each age represents the total population corresponding to different-age users who flow into the target area in the target group;

[0130] A floating population prediction module 340, configured to: obtain the total predicted inflowing population in the next year of the target area according to the number of inflowing population of each age and its corresponding weight coefficient, and obtain the total predicted outflowing population in the next year of the target area according to the number of outflowing population of each age and its corresponding weight coefficient; wherein, any weight coefficient is determined based on the policy factor value, environmental factor value, economic factor value, and education level value in the next year of the target area;

[0131] A total population prediction module 350, configured to: determine the total predicted population in the next year of the target area according to the total predicted inflowing population in the next year, the total predicted outflowing population in the next year, the number of surviving population in the current year of the target area, and the total predicted number of newborns in the next year.

[0132] In some embodiments, the process by which the household registration location determination module 310 determines the household registration locations of each user is configured as follows:

[0133] Obtain the ID card registration locations of each user according to the ID card information associated with the mobile devices carried by each user in the target group;

[0134] Determine the hometown locations of each user according to the location information of the mobile devices carried by each user during designated holidays over the years;

[0135] For each user, if the ID card registration location and the hometown location match, determine that the household registration location is the ID card registration location; if the ID card registration location and the hometown location do not match, determine that the household registration location is the hometown location.

[0136] In some embodiments, the process by which the household registration location determination module 310 determines the hometown locations of each user is configured as follows:

[0137] Determine the stay location where each user stays for the longest time during the designated holiday each year according to the location information of the mobile devices carried by each user during the designated holidays over the years;

[0138] Determine the number of times each user stays at the same location over the years, and use the location with the most stays as the hometown location.

[0139] In some embodiments, the process by which the usual residence determination module 320 determines the current year's usual residence of each user is configured as follows:

[0140] Determine whether each user lives in the household registration location in the current month according to the location information of the mobile device of each user in the month where the current time is located;

[0141] When the current user does not live in the household registration location in the current month, determine whether the current user has left his / her household registration location for more than a preset duration according to the location information of the current user's mobile device during the statistical period of the current year;

[0142] When the current user has left his / her household registration location for more than a preset duration, determine the place where the current user stays for the longest time other than the household registration location as the current year's usual residence according to the location information of the current user's mobile device during the statistical period of the current year;

[0143] When the current user has not left his / her household registration location for more than a preset duration, or when the current user lives in the household registration location in the current month, determine the current year's usual residence of the current user as the household registration location.

[0144] In some embodiments, the process by which the usual residence determination module 320 determines the previous year's usual residence of each user is configured as follows:

[0145] Based on the location information of each user's mobile device in the last month of the last year's statistical period, determine whether each user lived in their place of household registration in the last month;

[0146] When the current user did not live in their place of household registration in the last month, based on the location information of the current user's mobile device in the last year's statistical period, determine whether the current user has been away from their place of household registration for more than a preset duration;

[0147] When the current user has been away from their place of household registration for more than a preset duration, based on the location information of the current user's mobile device in the last year's statistical period, determine that the place where the current user stayed the longest in addition to their place of household registration is their usual residence last year;

[0148] When the current user has not been away from their place of household registration for more than a preset duration, or when the current user lived in their place of household registration in the last month, determine that the current user's usual residence last year is their place of household registration.

[0149] In some embodiments, the process by which the floating population determination module 330 determines the number of inflowing population and the number of outflowing population of each age in the target area is configured as follows:

[0150] For each user, determine whether the distance between their usual residence this year and their usual residence last year exceeds a set distance threshold;

[0151] When the distance between the current user's usual residence this year and their usual residence last year exceeds the set distance threshold, determine that the current user is a floating user;

[0152] When the distance between the current user's usual residence this year and their usual residence last year does not exceed the set distance threshold, determine that the current user is a non-floating user;

[0153] Based on the usual residence this year and the usual residence last year of all floating users, determine the number of inflowing population and the number of outflowing population of each age in the target area.

[0154] In some embodiments, the process by which the floating population determination module 330 determines the number of inflowing population and the number of outflowing population of each age in the target area based on the usual residence this year and the usual residence last year of all floating users is configured as follows:

[0155] For each floating user, if the current usual residence of the floating user is the target area and the usual residence last year is not the target area, then determine that the floating user is an inflowing user in the target area; if the usual residence last year of the floating user is the target area and the current usual residence is not the target area, then determine that the floating user is an outflowing user in the target area;

[0156] Determine the number of inflowing population of each age and the number of outflowing population of each age in the target area according to the inflowing users and the outflowing users.

[0157] In some embodiments, the population prediction device 300 further includes a weight acquisition module, and the weight acquisition module is configured to:

[0158] According to the policies, environment, economy and education level of the target area in the next year, obtain the policy factor value, environment factor value, economic factor value and education level value of the target area in the next year from a pre-constructed factor value table;

[0159] Process the policy factor value, environment factor value, economic factor value and education level value of the target area in the next year to obtain an influence integration value;

[0160] For each age, input the influence integration value into the inflowing population weight curve corresponding to that age to obtain the weight coefficient corresponding to the number of inflowing population of each age.

[0161] In some embodiments, the weight acquisition module is further configured to:

[0162] According to the policies, environment, economy and education level of the target area in the next year, obtain the policy factor value, environment factor value, economic factor value and education level value of the target area from a pre-constructed factor value table;

[0163] Process the policy factor value, environment factor value, economic factor value and education level value of the target area to obtain an influence integration value;

[0164] For each age, input the influence integration value into the outflowing population weight curve corresponding to that age to obtain the weight coefficient corresponding to the number of outflowing population of each age.

[0165] In some embodiments, the population prediction device 300 further includes a curve construction module, and the curve construction module is configured to:

[0166] For each year in the historical years of the target area, process the obtained influence integration value according to the policy factor value, environment factor value, economic factor value and education level value corresponding to that year;

[0167] For each year in the historical years of the target area, calculate the weight coefficient corresponding to the predicted inflowing population number of each age according to the actual inflowing population number of each age and the predicted inflowing population number of each age corresponding to that year;

[0168] For each historical year in the target area, the impact fusion value corresponding to that year is used as the independent variable, and the weight coefficient corresponding to the predicted inflow population of each age group in that year is used as the dependent variable, thereby forming a first data subset corresponding to each age group in that year;

[0169] For each age in the historical years of the target area, a weight curve of the inflow population corresponding to the age is constructed based on all the first data subsets corresponding to the age number in the historical years, so as to obtain the weight curve of the inflow population corresponding to each age in the target area.

[0170] In some embodiments, the curve construction module is further configured to:

[0171] For each of the target regions in the past years, the impact fusion value is obtained based on the policy factor value, environmental factor value, economic factor value and education level value corresponding to that year;

[0172] For each of the target areas in each of the historical years, the weight coefficients corresponding to the predicted outflow population of each age group are calculated based on the actual outflow population of each age group and the predicted outflow population of each age group corresponding to that year;

[0173] For each historical year in the target area, the impact fusion value corresponding to that year is used as the independent variable, and the weight coefficient corresponding to the predicted outflow population of each age group in that year is used as the dependent variable, to form a second data subset corresponding to different ages in that year;

[0174] For each age in the historical years of the target area, a weight curve of the outflow population corresponding to the age is constructed based on all the second data subsets corresponding to the age in the historical years, so as to obtain the weight curve of the outflow population corresponding to each age in the target area.

[0175] Optionally, the above modules can be stored in the form of software or firmware. Figure 1 The memory shown in the figure or solidified in the operating system (OS) of the electronic device, and can be Figure 1 Meanwhile, the data and program codes required to execute the above modules may be stored in the memory.

[0176] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0177] In addition, each functional module in various embodiments of the present invention can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0178] If the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0179] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A population prediction method, characterized in that, Including: Determine the household registration locations of each user according to the identity card information associated with the mobile devices of each user in the target group in the target area and the location information of specified holidays over the years; Determine the current-year permanent residence and last-year permanent residence of each user according to the household registration location of each user and the location information of the mobile device of each user; Determine the number of inflowing population of each age and the number of outflowing population of each age in the target area according to the current-year permanent residence and last-year permanent residence of each user; The number of inflowing population of each age represents the total population corresponding to each user of different ages who flow out of the target area in the target group, and the number of outflowing population of each age represents the total population corresponding to each user of different ages who flow into the target area in the target group; Obtain the total predicted inflowing population of the target area in the next year according to the number of inflowing population of each age and its corresponding weight coefficient, and obtain the total predicted outflowing population of the target area in the next year according to the number of outflowing population of each age and its corresponding weight coefficient; wherein, the weight coefficient corresponding to the number of inflowing population of each age is calculated based on the influence fusion value by the corresponding inflowing population weight curve, and the influence fusion value is obtained by processing the policy factor value, environmental factor value, economic factor value and education level value of the target area in the next year; Determine the total predicted population of the target area in the next year according to the total predicted inflowing population in the next year, the total predicted outflowing population in the next year, the number of surviving population in the current year of the target area and the total predicted number of newborns in the next year; Wherein, the construction process of the inflowing population weight curve includes: For each year in the historical years of the target area, obtain the influence fusion value by processing the policy factor value, environmental factor value, economic factor value and education level value corresponding to that year; For each year in the historical years of the target area, calculate the weight coefficient corresponding to the predicted number of inflowing population of each age according to the actual number of inflowing population of each age and the predicted number of inflowing population of each age corresponding to that year; For each year in the historical years of the target area, form the first data subset corresponding to each age in that year with the influence fusion value corresponding to that year as the independent variable and the weight coefficient corresponding to the predicted number of inflowing population of each age in that year as the dependent variable; For each age in the historical years of the target area, construct the inflowing population weight curve corresponding to that age according to all the first data subsets corresponding to that age number in the historical years, so as to obtain the inflowing population weight curves corresponding to each age in the target area.

2. The method according to claim 1, wherein The step of determining the household registration location of each user according to the identity card information associated with the mobile devices of each user in the target group in the target area and the location information of specified holidays over the years includes: Obtain the identity card registration location of each user according to the identity card information associated with the mobile devices carried by each user in the target group; Determine the hometown location of each user according to the location information of the mobile devices carried by each user during specified holidays over the years; For each user, if the place of registration of their ID card matches the place of their hometown, determine their place of household registration as the place of ID card registration; if the place of registration of their ID card does not match the place of their hometown, determine their place of household registration as the place of their hometown.

3. The method according to claim 2, characterized in that, The step of determining the place of each user's hometown according to the positioning information of the mobile devices carried by each user on designated holidays over the years includes: According to the positioning information of the mobile devices carried by each user on designated holidays over the years, determine the place where each user stays for the longest time during the designated holidays each year; Determine the number of times each user stays in the same place over the years, and take the place with the most stays as the place of their hometown.

4. The method according to claim 1, wherein The step of determining the place where each user usually resides this year according to the place of each user's household registration and the positioning information of each user's mobile device includes: According to the positioning information of each user's mobile device in the month when the current time is located, determine whether each user lives in the place of household registration in that month; When the current user does not live in the place of household registration in that month, according to the positioning information of the current user's mobile device during the statistical period this year, determine whether the current user has left their place of household registration for more than a preset duration; When the current user has left their place of household registration for more than a preset duration, according to the positioning information of the current user's mobile device during the statistical period this year, determine the place where the current user stays for the longest time other than the place of household registration as the place where the user usually resides this year; When the current user has not left their place of household registration for more than a preset duration, or when the current user lives in the place of household registration in that month, determine the place where the current user usually resides this year as the place of household registration.

5. The method according to claim 4, wherein The step of determining the place where each user usually resided last year according to the place of each user's household registration and the positioning information of each user's mobile device includes: According to the positioning information of each user's mobile device in the last month of the statistical period last year, determine whether each user lived in the place of household registration in that last month; When the current user did not live in the place of household registration in that last month, according to the positioning information of the current user's mobile device during the statistical period last year, determine whether the current user has left their place of household registration for more than a preset duration; When the current user has left their place of household registration for more than a preset duration, according to the positioning information of the current user's mobile device during the statistical period last year, determine the place where the current user stays for the longest time other than the place of household registration as the place where the user usually resided last year; When the current user has not left their place of household registration for more than a preset duration, or when the current user lived in the place of household registration in that last month, determine the place where the current user usually resided last year as the place of household registration.

6. The method according to claim 1, wherein The step of determining the number of inflowing population and the number of outflowing population of each age in the target area according to the place where each user usually resides this year and the place where each user usually resided last year includes: For each user, determine whether the distance between the place where they usually reside this year and the place where they usually resided last year exceeds a set distance threshold; When the distance between the place where the current user usually resides this year and the place where the current user usually resided last year exceeds the set distance threshold, determine that the current user is a mobile user; When the distance between the place where the current user usually resides this year and the place where the current user usually resided last year does not exceed the set distance threshold, determine that the current user is a non-mobile user; Determine the number of inflowing population and the number of outflowing population of each age in the target area according to the current-year usual residence and the last-year usual residence of all mobile users.

7. The method according to claim 6, characterized in that, The step of determining the number of inflowing population and the number of outflowing population of each age in the target area according to the current-year usual residence and the last-year usual residence of all mobile users includes: For each mobile user, if the current-year usual residence of the mobile user is the target area and the last-year usual residence is not the target area, determine that the mobile user is an inflowing user of the target area; if the last-year usual residence of the mobile user is the target area and the current-year usual residence is not the target area, determine that the mobile user is an outflowing user of the target area; Determine the number of inflowing population and the number of outflowing population of each age in the target area according to the inflowing users and the outflowing users.

8. The method according to claim 1, characterized in that, The process of obtaining the weight coefficient corresponding to the number of inflowing population of each age includes: According to the policies, environment, economy and education level of the target area in the next year, obtain the policy factor value, environment factor value, economic factor value and education level value of the target area in the next year from a pre-constructed factor value table; Process the policy factor value, environment factor value, economic factor value and education level value of the target area in the next year to obtain an influence integration value; For each age, input the influence integration value into the inflowing population weight curve corresponding to this age to obtain the weight coefficient corresponding to the number of inflowing population of each age.

9. The method according to any one of claims 1 to 8, characterized in that, The process of obtaining the weight coefficient corresponding to the number of outflowing population of each age includes: According to the policies, environment, economy and education level of the target area in the next year, obtain the policy factor value, environment factor value, economic factor value and education level value of the target area from a pre-constructed factor value table; Process the policy factor value, environment factor value, economic factor value and education level value of the target area to obtain an influence integration value; For each age, input the influence integration value into the outflowing population weight curve corresponding to this age to obtain the weight coefficient corresponding to the number of outflowing population of each age.

10. The method according to claim 9, wherein The process of constructing the outflowing population weight curve includes: For each year in the historical years of the target area, process the policy factor value, environment factor value, economic factor value and education level value corresponding to this year to obtain an influence integration value; For each year in the historical years of the target area, calculate the weight coefficient corresponding to the predicted number of outflowing population of each age according to the actual number of outflowing population of each age and the predicted number of outflowing population of each age corresponding to this year; For each year in the historical years of the target area, use the influence integration value corresponding to this year as the independent variable and the weight coefficient corresponding to the predicted number of outflowing population of each age in this year as the dependent variable to form a second data subset corresponding to different ages in this year; For each age in the historical years of the target area, construct the outflowing population weight curve corresponding to this age according to all the second data subsets corresponding to this age in the historical years to obtain the outflowing population weight curve corresponding to each age of the target area.

11. A population prediction device, characterized in that, Include: A household registration location determination module, configured to: determine the household registration location of each user according to the identity card information associated with the mobile devices of each user in the target group in the target area and the location information of specified holidays over the years; A usual residence location determination module, configured to: determine the current-year usual residence location and the last-year usual residence location of each user according to the household registration location of each user and the location information of the mobile devices of each user; A floating population determination module, configured to: determine the number of inflowing population of each age and the number of outflowing population of each age in the target area according to the current-year usual residence location and the last-year usual residence location of each user; The number of inflowing population of each age represents the total population corresponding to each user of different ages who flow out of the target area in the target group, and the number of outflowing population of each age represents the total population corresponding to each user of different ages who flow into the target area in the target group; A floating population prediction module, configured to: obtain the total predicted inflowing population of the target area in the next year according to the number of inflowing population of each age and their respective corresponding weight coefficients, and obtain the total predicted outflowing population of the target area in the next year according to the number of outflowing population of each age and their respective corresponding weight coefficients; wherein, the weight coefficient of each age's inflowing population is calculated based on the influence fusion value by the corresponding inflowing population weight curve, and the influence fusion value is obtained by processing the policy factor value, environmental factor value, economic factor value and education level value of the target area in the next year; A total population prediction module, configured to: determine the total predicted population of the target area in the next year according to the total predicted inflowing population in the next year, the total predicted outflowing population in the next year, the number of surviving population in the current year of the target area and the total predicted number of newborns in the next year; Wherein, the construction process of the inflowing population weight curve includes: For each year in the historical years of the target area, obtain the influence fusion value by processing the policy factor value, environmental factor value, economic factor value and education level value corresponding to that year; For each year in the historical years of the target area, calculate the weight coefficient corresponding to each age's predicted inflowing population according to the actual inflowing population of each age and the predicted inflowing population of each age corresponding to that year; For each year in the historical years of the target area, use the influence fusion value corresponding to that year as the independent variable and the weight coefficient corresponding to the predicted inflowing population of each age in that year as the dependent variable to form the first data subset corresponding to each age in that year; For each age in the historical years of the target area, construct the inflowing population weight curve corresponding to that age according to all the first data subsets corresponding to that age number in the historical years, so as to obtain the inflowing population weight curves corresponding to each age in the target area.

12. An electronic device, characterized in that, It includes a processor and a memory, the memory stores machine-executable instructions that can be executed by the processor, and the processor can execute the machine-executable instructions to implement the method described in any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method described in any one of claims 1 to 10.

Images