CN115409671B - Composition method, device, terminal and storage medium of community resident population micro data - Google Patents

Abstract

The invention discloses a method, a device, a terminal and a storage medium for synthesizing community resident population microscopic data. The prediction of urban community scale population socioeconomic performance information is realized, data information support is provided for application scenes such as public facilities site selection, traffic simulation, disaster prevention resource allocation and the like, and the promotion of urban fine treatment is promoted.

Description

Composition method, device, terminal and storage medium of community resident population micro data

technical field

The present invention relates to the technical field of social simulation, in particular to a method, device, terminal and storage medium for synthesizing microscopic data of community resident population.

Background technique

With the continuous advancement of urban digitalization and refined governance, many fields, including demand forecasting for public service facilities, layout and location selection for elderly care and education facilities, accurate simulation of disaster prevention and evacuation, and traffic network design, are critical to the population with spatial information and resident attributes. There is a growing demand for micro data.

The existing population information prediction methods of residential areas mostly use geographic information data or spatial remote sensing information to generate population spatial distribution information without resident attributes, or use population synthesis technology to generate population micro data with resident attributes but no spatial information.

Therefore, the existing technology has no way to obtain population micro data with spatial information and resident attributes.

Contents of the invention

The main purpose of the present invention is to provide a microcosmic data synthesis method, device, intelligent terminal and storage medium of community resident population, capable of generating microcosmic data of community resident population with spatial information and resident attributes.

In order to achieve the above object, the first aspect of the present invention provides a method for synthesizing microcosmic data of community resident population, said method comprising:

Based on the macro-demographic data of the administrative area and the micro-population sampling data of the community, the micro-data set of the community population is obtained according to the iterative proportional update algorithm, and the micro-data set of the community population includes housing information and family information;

Input the microcosmic data set of the community population into the neural network model to obtain a prediction model for predicting the relationship between the family and the building;

Based on the constraints formed by the prediction model and the real capacity of various residential buildings, with the goal of minimizing the utility loss, each family sample in the microscopic data set of the community population is allocated to various residential buildings, and the spatial information and resident attributes are obtained. The population micro-data of community residents.

Optionally, the input layer of the neural network model extracts family features and housing features, and the family features include: family population, maximum education level, maximum age, and intergenerational structure; the housing features include: housing Building type, building rent, property right attribute.

Optionally, based on the macro-demographic data of the administrative region and the micro-population sampling data of the community, the community population micro-data set is obtained according to an iterative proportional update algorithm, including:

According to the relationship between family classification and population characteristics in the micro-population sampling data, a frequency matrix is obtained;

Based on the frequency matrix, a joint distribution value corresponding to each population characteristic is obtained according to an iterative proportional update algorithm;

Iterating in a loop and calculating the fitting degree of each iteration according to the frequency matrix and the joint distribution value, until the fitting degree is less than a set threshold, and obtaining the probability distribution of each family classification;

Based on the probability distribution, a Monte Carlo method is used to randomly select household samples to the microcosmic data set of the community population.

Optionally, the expression for calculating the degree of fit is:

Among them, σ is the degree of fit, D _ij is the frequency matrix, C _j is the joint distribution value, m is the number of population characteristics, and W is the weight vector.

Optionally, the error function model of the neural network model is:

Among them, t _n is the expected output, u _n is the actual output, and N is the number of family samples.

Optionally, based on the constraint conditions formed by the prediction model and the real capacity of various types of residential buildings, with the goal of minimizing the utility loss, each family sample in the community population micro-data set is allocated to various types of residential buildings, and the belt Community resident population microdata with spatial information and resident attributes, including:

Based on the constraint conditions of the real capacity of various residential buildings, with the utility loss minimization as the goal, the objective function of the dynamic optimization model is constructed, and the dynamic optimization model is used to optimize the distribution of residents in each residential building;

Obtain the characteristics of various types of residential buildings and input the characteristics and the prediction results of the prediction model into the dynamic optimization model to obtain the microscopic data of the population of residents in the community.

Optionally, the expression of the objective function is:

Among them, A _ik is the predicted probability that the i-th family chooses the k-type residential building, i=1,2,3...M, M is the number of family categories; B _ik is the four attributes corresponding to the i-th family , k=1,2,3,4; D _ij is the number of households of type i allocated to type j housing, i=1,2,3...M,j=1,2,3.. .N, N is the number of residential building types; P _i =0 or 1 indicates whether the residential building is selected during the allocation process, i=1, 2,...N; W _k is the property of the kth residential building Weights, is the mean value of _Pi .

The second aspect of the present invention provides a microcosmic data synthesis device for community residents, wherein the above-mentioned device includes:

The community population micro-data set acquisition module is used to obtain the community population micro-data set based on the macro-demographic data of the administrative area and the micro-population sampling data of the community according to the iterative proportional update algorithm. The community population micro-data set includes housing information and family information. information;

Prediction module, for inputting the microcosmic data set of the community population into the neural network model to obtain a prediction model for predicting the relationship between the family and the building;

The allocation module is used to allocate the family samples in the community population micro-data set to various types of residential buildings based on the constraints formed by the prediction model and the real capacity of various residential buildings with the goal of minimizing utility loss, and obtain Community resident population micro data of spatial information and resident attributes.

The third aspect of the present invention provides an intelligent terminal. The above-mentioned intelligent terminal includes a memory, a processor, and a community resident population micro-data synthesis program that is stored on the above-mentioned memory and can run on the above-mentioned processor. The above-mentioned community resident population micro-data synthesis program When executed by the above-mentioned processor, the steps of realizing any one of the above-mentioned methods for synthesizing microscopic data of community resident population.

The fourth aspect of the present invention provides a computer-readable storage medium. The above-mentioned computer-readable storage medium stores a community resident population micro-data synthesis program. When the above-mentioned community resident population micro-data synthesis program is executed by a processor, any one of the above-mentioned community The steps of the synthetic method of resident population micro data.

It can be seen from the above that the present invention first obtains the microscopic data set of community population through an iterative proportional update algorithm based on the macroscopic demographic data of the administrative region and the microscopic population sampling data of the community, and then learns the relationship between the family and the building according to the neural network model. , and then optimize the allocation of each household sample to each residential building with the goal of minimizing the utility loss, so as to obtain the microscopic data of the community resident population with spatial information and resident attributes.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings that need to be used in the descriptions of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only of the present invention. For some embodiments, those skilled in the art can also obtain other drawings according to these drawings without paying creative efforts.

Fig. 1 is a schematic flow chart of a microcosmic data synthesis method for community resident population provided by an embodiment of the present invention;

FIG. 2 is a schematic diagram of the specific flow of step S300 in the embodiment of FIG. 1;

FIG. 3 is a schematic diagram of the specific flow of step S100 in the embodiment of FIG. 1;

Fig. 4 is a schematic structural diagram of a community resident population micro data synthesis device provided by an embodiment of the present invention;

Fig. 5 is a functional block diagram of an internal structure of a smart terminal provided by an embodiment of the present invention.

Detailed ways

In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the invention may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and/or components, but does not exclude one or more other features. , whole, step, operation, element, component and/or the presence or addition of a collection thereof.

It should also be understood that the terminology used in the description of the present invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the present invention. As used in this specification and the appended claims, the singular forms "a", "an" and "the" are intended to include plural referents unless the context clearly dictates otherwise.

It should also be further understood that the term "and/or" used in the description of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations .

As used in this specification and the appended claims, the term "if" may be construed as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrases "if determined" or "if detected [the described condition or event]" may be construed, depending on the context, to mean "once determined" or "in response to the determination" or "once detected [the described condition or event]" event]" or "in response to detection of [described condition or event]".

The technical solutions in the embodiments of the present invention are clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Apparently, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

In the following description, a lot of specific details are set forth in order to fully understand the present invention, but the present invention can also be implemented in other ways different from those described here, and those skilled in the art can do it without departing from the meaning of the present invention. By analogy, the present invention is therefore not limited to the specific examples disclosed below.

Usually, the acquisition of population micro-information is time-consuming and labor-intensive and involves the privacy protection of residents. Most of the relevant research and practice can only use the summary of census data based on administrative regions, and its spatial resolution and temporal resolution are difficult to meet. Actual demand.

The existing population information prediction methods of residential areas mostly use geographic information data or spatial remote sensing information to generate population spatial distribution information without resident attribute information, or use population synthesis technology to generate population micro data with resident attributes but no spatial information. Therefore, there is currently no method for generating population microdata with spatial information and resident attributes.

The present invention combines microscopic data synthesis of community resident population with spatial information, integrates neural network model and dynamic programming algorithm, and considers the limitation of housing capacity, matches microscopic family samples with living space information, and generates spatial information and resident The population micro-data of attributes to adapt to urban digitalization and refined governance.

exemplary method

As shown in FIG. 1 , the embodiment of the present invention provides a microcosmic data synthesis method of community resident population, which can be run on various terminals, such as computer terminals, tablet computers, smart phones, and the like. Specifically, the above method includes the following steps:

Step S100: Based on the macro-demographic data of the administrative area and the micro-population sampling data of the community, obtain the community population micro-data set according to the iterative proportional update algorithm, and the community population micro-data set includes housing information and family information;

Specifically, the construction of an artificial population generally refers to the reconstruction of individual social characteristics, and automatically generates the real population according to the demographic characteristics of the real society, such as the individual's age, gender, family, education level, occupation, and other socioeconomic relationships. A dataset of artificial populations with consistent characteristics. The population synthesis method is based on the joint probability distribution of population characteristics, and uses methods such as Monte Carlo simulation for population synthesis. The generated data set contains information such as the overall population size and all possible attribute combinations.

The specific process is as follows: the iterative proportional update algorithm is used to iterate the macro-demographic data and micro-population sampling data of the administrative area, and the micro-data set of the community population is obtained after the iteration is completed. The iterative proportional update algorithm takes the characteristic variables of the family and the population as a whole, uses the macroscopic overall data of the two levels as constraints, optimizes the generation of the family entity set, and then generates its members according to the characteristics of each family to obtain the population individual.

Among them, the macro-demographic data of administrative regions can be obtained from the census data and economic census data published by the National Bureau of Statistics and the statistics bureaus of various provinces and cities. The micro-population sampling data of the community can provide multi-dimensional demographic characteristics attributes, which can be used to restore the family composition in the society based on small-scale high-precision individuals and family structure data.

The macro-demographic data of the administrative area include: age, gender, education level, family population, household registration type, etc.; the micro-population sampling data include: age, gender, education level, family population, household registration type, and the name of the residential area, etc.; Building information includes: house type, year of completion, listing price, property right type, etc.; family information includes: family population, number of family generations, etc.

After obtaining the above data, it is first necessary to quantify factors such as age, gender, education level, family size, type of household registration, and type of house, listing price, and type of property right. For example: gender quantification results are: male is 1, female is 2; age quantification results are: 0-15 years old is 1, 15-30 years old is 2, 30-45 years old is 3, 45-60 years old is 4, 60- 5 for those aged 75 and 6 for those over 75; other element indicators are also quantified and will not be repeated here.

It should be noted that the specific items and quantities of the above-mentioned element indicators are not limited, and can be changed according to specific calculation requirements.

Step S200: input the community population micro-data set into the neural network model to obtain a prediction model for predicting the relationship between the family and the building;

Specifically, the neural network model predicts the housing selection probability of the microscopic family samples under each category based on the microscopic data set of the community population, and obtains the weight corresponding to each category. A neural network model is used to establish a more accurate connection between microscopic family samples and living space information.

In this embodiment, after inputting the community population microscopic data set into the neural network model, the input layer of the neural network model extracts family characteristics and housing characteristics, and the family characteristics include: family population size, highest education level, maximum age, intergenerational structure The characteristics of the residential building include: residential building type, residential building rent, property right attribute. The neural network model quantifies the family characteristics, such as: the number of family members: 1-3 people is 1, 4-6 people is 2, and more than 7 people is 3; intergenerational structure: 1-generation household is 1, 2-generation household is 2 , 3 generations and above are 3; and so on, similar quantitative processing is carried out for other characteristics of family characteristics and residential building characteristics.

The neural network model model in this embodiment is: the number S of neurons in the input layer is 4, namely: the number of family members, the maximum age, the highest level of education, and the intergenerational structure, and the weights are set to W _1s W _2s W _3s W _4s The output layer neuron quantity O is 3, that is: the listing price of the house, the house type, and the property right type of the house; the hidden layer neuron number is 4, which is calculated by the empirical get. The error function of the neural network model is /> Among them, t _n is the expected output, u _n is the actual output, and N is the number of family samples. Perform feedback processing according to the output, adjust the neuron weights of the input layer, output layer, and hidden layer, and repeat the training until the prediction accuracy is greater than the set accuracy.

Step S300: Based on the constraints formed by the prediction model and the real capacity of various residential buildings, with the goal of minimizing the utility loss, assign each family sample in the community population micro-data set to various residential buildings, and obtain information with spatial information and residents. The micro-data of community residents population of attributes;

Specifically, a dynamic programming algorithm is used to consider the real capacity of various residential buildings, and the household samples are allocated to the buildings with the goal of minimizing utility loss, so as to generate microscopic data of community residents with spatial information and resident attributes.

In one embodiment, as shown in FIG. 2 , it specifically includes the following steps:

Step S310: Based on the constraint conditions of the real capacity of various residential buildings, with the goal of minimizing the utility loss, construct the objective function of the dynamic optimization model, and the dynamic optimization model is used to optimize the allocation of residents in each residential building;

Step S320: Obtain the characteristics of various residential buildings and input the characteristics and the prediction results of the prediction model into the dynamic optimization model to obtain the microscopic data of the population of residents in the community.

Specifically, firstly, the objective function is established. Based on the housing selection probability of each classified family sample in the prediction model, with the goal of minimizing the utility loss in the distribution process, the objective function of population micro data allocation is constructed, and the characteristics of each housing building, population micro data The sample and the housing selection probability of the prediction model are input into the optimization model composed of the objective function and constraints, and the model is run.

Among them, the constraints are That is, the sum of the number of families of a certain type contained in all residential areas ≤ the total number of families of this type;/> That is, the sum of the number of households allocated to each residential area ≤ the total capacity of the residential area. The expression of the objective function is:

In the above formula, C _i represents the number of families of type i, i=1, 2, 3,...M, and _M represents a total of M types of families; Probability, i=1,2,3...M, M is the number of household types; T _j represents the number of households in the jth type of residential building, j=1,2,3,...N, a total of N types housing; B _ik is the four attributes corresponding to the i-type family, k=1,2,3,4; D _ij is the number of the i-th family assigned to the j-th type of housing, i=1,2, 3...M, j=1,2,3...N, N is the number of building types; P _i =0 or 1 indicates whether the building is selected during the allocation process, i=1, 2, ...N; W _k is the weight of the kth residential property, is the mean value of _Pi .

From the above, the present invention combines the community resident population micro-data synthesis technology with neural network models and dynamic programming algorithms to realize the generation of residential population micro-data and predict the attributes of residents at all levels, and obtain spatial information and resident attributes. The micro-data of the population of community residents realizes the prediction of population attribute information in urban community areas, provides data information support for application scenarios such as public facility location selection, traffic simulation simulation, and disaster prevention resource allocation, and promotes the advancement of refined urban governance.

In one embodiment, as shown in FIG. 3, the community population micro-data set obtained in the above step S100 specifically includes the following steps:

Step S110: Obtain a frequency matrix according to the relationship between family classification and population characteristics in the micro-population sampling data;

Specifically, the proportion of various types of households is calculated based on the micro-population sampling data, which is defined as λ as a marginal constraint for iterative fitting of family information, where λ represents the proportion of the number of households with the i-th characteristic to the total. Generate a frequency matrix D with a dimension of N×m, where N is the number of samples of all families, and m is the constraint of population characteristics (including family characteristics and population characteristics).

D _ij is the contribution value of the i-th family sample to the j-th population characteristic.

Step S120: Based on the frequency matrix, the joint distribution value corresponding to each population characteristic is obtained according to the iterative proportional update algorithm;

Step S130: Iterate in a loop and calculate the fitting degree of each iteration according to the frequency matrix and the joint distribution value, until the fitting degree is less than the set threshold, and obtain the probability distribution of each family classification;

Specifically, an iterative proportional update algorithm is firstly used to calculate the joint distribution value of each population characteristic. hypothetical target table where, /> represents the joint distribution value of household sample i, /> represents the joint distribution value of individual j. The initial setting tolerance threshold is 0.0001, /> and /> initialization /> j=1,2,...m; initialize the weight column vector W _i =1, i=1,2,...N, initialize the fitness scalar σ _min =σ, and initialize the scalar k=1 as the constraint counter.

Compute the temporary error in each loop:

Continue looping while the temporary error is greater than the tolerance threshold:

Yes />

A joint distribution value C _j corresponding to each population characteristic is obtained, where c _i = _bi , i=1, 2, 3, . . . m.

Compute the fit for each iteration from the frequency matrix and joint distribution values: Among them, σ is the degree of fit, D _ij is the frequency matrix, C _j is the joint distribution value, m is the number of population characteristics, and W is the weight vector.

Generate m column vectors S _j =index(D _ij ≠0) for recording indexes, i=1,2,...N, j=1,2,...m, S _j represents the non- The index column vector of zero elements, S _qj represents the index of the qth non-zero element of the jth column in the frequency matrix.

Calculate the fitness value: Update the weight vector W according to the fitness value, where and recalculate the fit />

According to the fitting value of the current iteration and the fitting value of the last iteration, calculate the improvement of the fitting degree Δ=|σ-σ _prev |, if σ<σ _min , σ _min =σ, SW _i =W _i , i=1,2,3...N.

If Δ>ε, that is, the improvement of the fitting degree is too large, the temporary error is recalculated for loop iteration; when the final σ is all less than the threshold, the operation is stopped, and the weight of each family with the attribute of the housing type is obtained, and the weight value is transformed into Probability distributions for each family category.

Step S140: Based on the probability distribution, a Monte Carlo method is used to randomly select family samples to the community population micro-data set.

Specifically, according to the obtained probability distribution, the Monte Carlo method is used to randomly select household samples to select the final data set, and a community population micro data set with no significant difference from the edited distribution and with residential information is obtained.

In this embodiment, according to the probability distribution of individual attributes such as age, gender, and occupation type in the population micro-data, Monte Carlo simulation is used to assign corresponding individual attributes to individuals of each synthetic community population. Then, a synthetic family is constructed according to the probability of family attributes such as family category, family size, and family age component in the census data, and the individuals of the synthetic community population are filled into the synthetic family.

The advantage of artificial population is that it simulates human travel and other social behaviors at a relatively low cost, and tests the feasibility and effectiveness of policies such as traffic control and social management. At the same time, the calculation model of individual behavior can be simulated to obtain quantitative evaluation results, which can provide reference for the quantitative decision-making of management departments. When the artificial population can accurately reflect the attributes, structure, and distribution characteristics of the real population, the simulation results of travel simulation, economic activities, and urban evolution can have high credibility.

As mentioned above, based on population micro-sampling data and census data, an iterative proportional update algorithm is used to generate community population micro-data sets. This method has short calculation time and high fitting accuracy. An effective method for in-depth development, construction of high-precision micro-population datasets, and removal of population privacy information.

It should be noted that although the present embodiment uses community population data as an example for illustration, the present invention can also construct microscopic databases of households and individuals in megacities.

exemplary device

As shown in Fig. 4, corresponding to the synthesis method of microscopic data of community resident population, an embodiment of the present invention also provides a microscopic data synthesis device of community resident population. The above microscopic data synthesis device of community resident population includes:

The community population micro data set acquisition module 600 is used to obtain the community population micro data set according to the iterative proportional update algorithm based on the macro demographic data of the administrative area and the community micro population sampling data. The community population micro data set includes housing information and family information;

Prediction module 610, for inputting the microcosmic data set of the community population into the neural network model to obtain a prediction model for predicting the relationship between the family and the building;

The allocation module 620 is used to allocate the family samples in the community population micro-data set to various types of residential buildings based on the constraints formed by the prediction model and the real capacity of various residential buildings with the goal of minimizing the utility loss, and obtain Community resident population micro data with spatial information and resident attributes.

Specifically, in this embodiment, the specific functions of each module of the microscopic data synthesis device for community resident population can refer to the corresponding description in the microscopic data synthesis method for community resident population, and will not be repeated here.

Based on the above embodiments, the present invention also provides an intelligent terminal, the functional block diagram of which may be shown in FIG. 5 . The above intelligent terminal includes a processor, a memory, a network interface and a display screen connected through a system bus. Wherein, the processor of the smart terminal is used to provide calculation and control capabilities. The memory of the smart terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a microscopic data synthesis program of community resident population. The internal memory provides an environment for the operation of the operating system in the non-volatile storage medium and the microcosmic data synthesis program of community resident population. The network interface of the smart terminal is used to communicate with external terminals through a network connection. When the microscopic data synthesis program of community resident population is executed by the processor, the steps of any one of the methods for synthesizing microscopic data of community resident population are realized. The display screen of the smart terminal may be a liquid crystal display screen or an electronic ink display screen.

Those skilled in the art can understand that the functional block diagram shown in Figure 5 is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the smart terminal to which the solution of the present invention is applied. The specific smart terminal More or fewer components than shown in the figures may be included, or certain components may be combined, or have a different arrangement of components.

In one embodiment, an intelligent terminal is provided. The above-mentioned intelligent terminal includes a memory, a processor, and a community resident population micro-data synthesis program stored on the above-mentioned memory and operable on the above-mentioned processor. The above-mentioned community resident population micro-data When the synthesis program is executed by the above-mentioned processor, the following operation instructions are performed:

Based on the macro-demographic data of the administrative area and the micro-population sampling data of the community, the micro-data set of the community population is obtained according to the iterative proportional update algorithm, and the micro-data set of the community population includes housing information and family information;

Input the microcosmic data set of the community population into the neural network model to obtain a prediction model for predicting the relationship between the family and the building;

Based on the constraints formed by the prediction model and the real capacity of various residential buildings, with the goal of minimizing the utility loss, each family sample in the microscopic data set of the community population is allocated to various residential buildings, and the spatial information and resident attributes are obtained. The population micro-data of community residents.

Optionally, the input layer of the neural network model extracts family features and housing features, and the family features include: family population, maximum education level, maximum age, and intergenerational structure; the housing features include: housing Building type, building rent, property right attribute.

Optionally, based on the macro-demographic data of the administrative region and the micro-population sampling data of the community, the community population micro-data set is obtained according to an iterative proportional update algorithm, including:

According to the relationship between family classification and population characteristics in the micro-population sampling data, a frequency matrix is obtained;

Based on the frequency matrix, a joint distribution value corresponding to each population characteristic is obtained according to an iterative proportional update algorithm;

Iterating in a loop and calculating the fitting degree of each iteration according to the frequency matrix and the joint distribution value, until the fitting degree is less than a set threshold, and obtaining the probability distribution of each family classification;

Based on the probability distribution, a Monte Carlo method is used to randomly select household samples to the microcosmic data set of the community population.

Optionally, the expression for calculating the degree of fit is:

Among them, σ is the degree of fit, D _ij is the frequency matrix, C _j is the joint distribution value, m is the number of population characteristics, and W is the weight vector.

Optionally, the error function model of the neural network model is:

Among them, t _n is the expected output, u _n is the actual output, and N is the number of family samples.

Optionally, based on the constraint conditions formed by the prediction model and the real capacity of various types of residential buildings, with the goal of minimizing the utility loss, each family sample in the community population micro-data set is allocated to various types of residential buildings, and the belt Community resident population microdata with spatial information and resident attributes, including:

Based on the constraint conditions of the real capacity of various residential buildings, with the utility loss minimization as the goal, the objective function of the dynamic optimization model is constructed, and the dynamic optimization model is used to optimize the distribution of residents in each residential building;

Obtain the characteristics of various types of residential buildings and input the characteristics and the prediction results of the prediction model into the dynamic optimization model to obtain the microscopic data of the population of residents in the community.

Optionally, the expression of the objective function is:

Among them, A _ik is the predicted probability that the i-th family chooses the k-type residential building, i=1,2,3...M, M is the number of family categories; B _ik is the four attributes corresponding to the i-th family , k=1,2,3,4; D _ij is the number of households of type i allocated to type j housing, i=1,2,3...M,j=1,2,3.. .N, N is the number of residential building types; P _i =0 or 1 indicates whether the residential building is selected during the allocation process, i=1, 2,...N; W _k is the property of the kth residential building Weights, is the mean value of _Pi .

The embodiment of the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a community resident population micro-data synthesis program. When the community resident population micro-data synthesis program is executed by a processor, the embodiment of the present invention provides The steps of any method for synthesizing microscopic data of community resident population.

It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution, and the execution order of each process should be determined by its functions and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present invention.

Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used for illustration. In practical applications, the above-mentioned functions can be assigned to different functional units, Module completion means that the internal structure of the above-mentioned device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit, and the above-mentioned integrated units may adopt hardware It can also be implemented in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present invention. For the specific working processes of the units and modules in the above system, reference may be made to the corresponding processes in the aforementioned method embodiments, and details will not be repeated here.

In the above-mentioned embodiments, the descriptions of each embodiment have their own emphases, and for parts that are not detailed or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functions in different ways for each particular application, but such implementation should not be considered as exceeding the scope of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal equipment and method may be implemented in other ways. For example, the device/terminal device embodiments described above are only illustrative. For example, the division of the above-mentioned modules or units is only a logical function division. In actual implementation, other division methods may be used, such as multiple units or Components may be combined or integrated into another system, or some features may be omitted, or not implemented.

If the above-mentioned integrated modules/units are realized in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention realizes all or part of the processes in the methods of the above embodiments, and can also be completed by instructing related hardware through computer programs. The above computer programs can be stored in a computer-readable storage medium. When executed by the processor, the steps in the above-mentioned various method embodiments can be realized. Wherein, the above-mentioned computer program includes computer program code, and the above-mentioned computer program code may be in the form of source code, object code, executable file or some intermediate form. The above-mentioned computer-readable medium may include: any entity or device capable of carrying the above-mentioned computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random Access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the above computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand; The technical solutions recorded in the examples are modified, or some of the technical features are equivalently replaced; and these modifications or replacements do not mean that the essence of the corresponding technical solutions deviates from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should be included in this document. within the scope of protection of the invention.

Claims (8)

1. The community resident population micro-data synthesis method is characterized in that the method comprises: Based on the macro-demographic data of the administrative area and the micro-population sampling data of the community, the micro-data set of the community population is obtained according to the iterative proportional update algorithm, and the micro-data set of the community population includes housing information and family information; The microcosmic data set of the community population is input into the neural network model to obtain a prediction model for predicting the relationship between the family and the building, and the prediction result of the prediction model is the selection probability of the building for each classified family sample; Based on the constraints formed by the prediction model and the real capacity of various residential buildings, with the goal of minimizing the utility loss, each family sample in the microscopic data set of the community population is allocated to various residential buildings, and the spatial information and resident attributes are obtained. The micro-data of the population of community residents; Based on the constraints formed by the prediction model and the real capacity of various types of residential buildings, with the goal of minimizing the utility loss, each family sample in the community population micro-data set is assigned to various types of residential buildings, and the spatial information and Community resident population microdata of resident attributes, including: Based on the constraint conditions of the real capacity of various residential buildings, with the utility loss minimization as the goal, the objective function of the dynamic optimization model is constructed, and the dynamic optimization model is used to optimize the distribution of residents in each residential building; Obtain the characteristics of various types of residential buildings and input the characteristics and the prediction results of the prediction model into the dynamic optimization model to obtain the microscopic data of the population of residents in the community; The expression of the objective function is: Among them, A _ik is the predicted probability that the i-th family chooses the k-type residential building, i=1,2,3...M, M is the number of family categories; B _ik is the four attributes corresponding to the i-th family , k=1,2,3,4; D _ij is the number of households of type i allocated to type j housing, i=1,2,3...M,j=1,2,3.. .N, N is the number of residential building types; P _i =0 or 1 indicates whether the residential building is selected during the allocation process, i=1, 2,...N; W _k is the property of the kth kind of residential building Weights, is the mean value of _Pi . 2. the method for synthesizing microcosmic data of community resident population as claimed in claim 1, is characterized in that, the input layer of described neural network model extracts family feature and residential building feature, and described family feature comprises: family population size, highest education degree, maximum age, and intergenerational structure; the housing features include: housing type, housing rent, and property rights. 3. the microcosmic data synthetic method of community resident population as claimed in claim 1, is characterized in that, described based on the microcosmic population sampling data of administrative area macroscopic demographic data and community, obtains community population microcosmic data set according to iterative ratio update algorithm, include: According to the relationship between family classification and population characteristics in the micro-population sampling data, a frequency matrix is obtained; Based on the frequency matrix, a joint distribution value corresponding to each population characteristic is obtained according to an iterative proportional update algorithm; Iterating in a loop and calculating the fitting degree of each iteration according to the frequency matrix and the joint distribution value, until the fitting degree is less than a set threshold, and obtaining the probability distribution of each family classification; Based on the probability distribution, a Monte Carlo method is used to randomly select household samples to the microcosmic data set of the community population. 4. community resident population microcosmic data synthesis method as claimed in claim 3, is characterized in that, the expression of calculating degree of fit is: Among them, σ is the degree of fit, D _ij is the frequency matrix, C _j is the joint distribution value, m is the number of population characteristics, and W is the weight vector. 5. community resident population microcosmic data synthesis method as claimed in claim 1, is characterized in that, the error function model of described neural network model is: Among them, t _n is the expected output, u _n is the actual output, and N is the number of family samples. 6. A device for synthesizing microscopic data of community resident population, characterized in that the device includes: The community population micro-data set acquisition module is used to obtain the community population micro-data set based on the macro-demographic data of the administrative area and the micro-population sampling data of the community according to the iterative proportional update algorithm. The community population micro-data set includes housing information and family information. information; Prediction module, for inputting the microcosmic data set of the community population into the neural network model, to obtain a prediction model for predicting the relationship between the family and the building; The allocation module is used to allocate the family samples in the community population micro-data set to various types of residential buildings based on the constraints formed by the prediction model and the real capacity of various residential buildings with the goal of minimizing the utility loss, and obtain Community resident population micro-data of spatial information and resident attributes; Based on the constraints formed by the prediction model and the real capacity of various types of residential buildings, the family samples in the community population micro-data set are allocated to various types of residential buildings with the goal of minimizing the utility loss, and the data with spatial information and Community resident population microdata of resident attributes, including: Based on the constraint conditions of the real capacity of various residential buildings, with the utility loss minimization as the goal, the objective function of the dynamic optimization model is constructed, and the dynamic optimization model is used to optimize the distribution of residents in each residential building; Obtain the characteristics of various types of residential buildings and input the characteristics and the prediction results of the prediction model into the dynamic optimization model to obtain the microscopic data of the population of residents in the community; The expression of the objective function is: Among them, A _ik is the predicted probability that the i-th family chooses the k-type residential building, i=1,2,3...M, M is the number of family categories; D _ik is the four attributes corresponding to the i-th family , k=1,2,3,4; D _ij is the number of households of type i allocated to type j housing, i=1,2,3...M,j=1,2,3.. .N, N is the number of residential building types; P _i =0 or 1 indicates whether the residential building is selected during the allocation process, i=1, 2,...N; W _k is the property of the kth residential building Weights, is the mean value of _Pi . 7. An intelligent terminal, characterized in that the intelligent terminal includes a memory, a processor, and a community resident population micro-data synthesis program that is stored on the memory and can run on the processor, and the community resident population micro-data When the synthesis program is executed by the processor, the steps of the method for synthesizing microscopic data of community resident population according to any one of claims 1-5 are realized. 8. Computer-readable storage medium, characterized in that, the computer-readable storage medium is stored with community resident population micro-data synthesis program, and when the community resident population micro-data synthesis program is executed by a processor, it realizes as claimed in claim 1- 5. Steps of any one of the methods for synthesizing microscopic data of community resident population.