CN117670270A - Method, device, equipment and storage medium for associating artificial family space - Google Patents
Method, device, equipment and storage medium for associating artificial family space Download PDFInfo
- Publication number
- CN117670270A CN117670270A CN202311361497.5A CN202311361497A CN117670270A CN 117670270 A CN117670270 A CN 117670270A CN 202311361497 A CN202311361497 A CN 202311361497A CN 117670270 A CN117670270 A CN 117670270A
- Authority
- CN
- China
- Prior art keywords
- individual
- employment
- family
- artificial
- mobile phone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 230000011664 signaling Effects 0.000 claims abstract description 88
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 238000004590 computer program Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000011835 investigation Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 4
- 230000001186 cumulative effect Effects 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a device, equipment and a storage medium for associating artificial family space, which are used for generating basic artificial families through an artificial family generation algorithm based on investigation statistical data; presetting an individual employment selection model, and predicting the individual employment probability of the basic artificial family through the individual employment selection model to obtain the individual employment situation; meanwhile, an individual commuting distance model is preset, and the commuting distance of a basic artificial family is predicted based on the individual employment situation through the individual commuting distance model, so that the probability of each individual commuting distance interval is obtained; and acquiring mobile phone signaling data, and matching the basic artificial family with the mobile phone signaling data according to the probability and the individual attribute of the individual commute distance interval to acquire the spatial position information of the artificial family. According to the invention, the difference of the individual commuting distances under different families is calculated, so that the space association result of the artificial family is more in line with the actual situation, and the method has more usability.
Description
Technical Field
The embodiment of the application relates to the technical field of computer social simulation, in particular to a method, a device, equipment and a storage medium for associating space of an artificial family.
Background
An artificial family (Synthetic Population), i.e. synthetic population, artificial population, refers to a virtual family data set generated by simulating a real family in a computer. In order to solve the problems that the acquisition cost of a real microscopic household sample is high, privacy protection is difficult to coordinate and the like, the artificial household is widely applied to urban population and household analysis, urban population simulation, policy effect analysis and the like. And artificial family spatial association refers to assigning spatial attributes to the synthesized underlying artificial family.
At present, the existing artificial home space association method cannot consider the complexity of real world travel, cannot cope with the complex situation of urban travel, does not consider the mutual influence of family member travel, has large difference with the real travel scene, and has limited availability of constructed artificial home data.
Disclosure of Invention
The invention provides a method, a device, computer equipment and a storage medium for associating space of an artificial household, which enable the space association result of the artificial household to be more consistent with the real situation and have more usability by calculating the difference of individual commuting distances under different household conditions.
In a first aspect, the present invention provides an artificial home space association method, including the steps of:
generating a basic artificial family through an artificial family generation algorithm according to the survey statistical data, wherein the basic artificial family comprises individual attributes and family attributes;
presetting an individual employment selection model, and predicting the individual employment probability of the basic artificial family through the individual employment selection model to obtain the individual employment situation;
presetting an individual commute distance model, and predicting the commute distance of the basic artificial family through the individual commute distance model based on the individual employment situation to obtain the probability of each commute distance interval of an individual;
acquiring mobile phone signaling data, wherein the mobile phone signaling data comprises space position information and personal attribute information;
and matching the basic artificial family with the mobile phone signaling data according to the probability of the individual commute distance interval and the individual attribute to acquire the space position information of the artificial family.
Further, the basic artificial family is matched with the mobile phone signaling data, and the method comprises the following steps:
acquiring employment individuals in the artificial families, determining the commute distance interval of the employment individuals according to the probability on each commute distance interval of the individuals, and acquiring the corresponding relation between the commute distance interval and the individual attribute;
presetting a first family requirement, wherein the first family requirement indicates that the correspondence between a commute distance interval of employment individuals located in the same artificial family and individual attributes is the same, and the personal attribute information of the employment individuals is matched with the individual attributes;
acquiring a grid point set meeting the first family requirement according to the mobile phone signaling data;
determining living grid points of the artificial family according to the grid point set and the quantity of corresponding mobile phone signaling data on each grid point;
and acquiring mobile phone signaling data corresponding to the residential grid points, and distributing the mobile phone signaling data to the employment individuals, wherein the distribution indicates that the personal attribute information of the mobile phone signaling data is consistent with the individual attribute of the employment individuals.
Further, the basic artificial family is matched with the mobile phone signaling data, and the method further comprises the following steps:
acquiring the artificial families which are not allocated with mobile phone signaling data, and presetting a second family requirement, wherein the second family requirement indicates that the personal attribute information of employment individuals is matched with the individual attributes;
acquiring a grid point set meeting the second family requirement according to the mobile phone signaling data;
according to the grid point set and the quantity of the corresponding mobile phone signaling data on each grid point, determining the living grid points of the artificial family not assigned with the mobile phone signaling data;
and acquiring mobile phone signaling data corresponding to the resident grid points, and distributing the mobile phone signaling data to the employment individuals.
Further, the preset individual employment selection model comprises the following steps:
according to the social statistical data, constructing the individual employment selection model through a logic cliff model, wherein the expression of the individual z employment selection model is as follows:
wherein P is z Representing the probability of z employment of an individual, X zk Representing the value of individual z on element k, beta k To influence the force parameter beta 0 Being constant, ε is the error that fits the normal distribution.
Further, the preset individual commute distance model comprises the following steps:
according to the social statistical data, constructing the individual commute distance model by a Gamma regression method, wherein the expression of the individual z commute distance model is as follows:
wherein alpha is a shape parameter, lambda is a scale parameter, y is a commute distance, u z For the mean value of the z commute distance of an individual beta 0 Is constant, X zk For the value of the individual z element k, beta k As a parameter thereof.
Further, the individual employment situation is obtained, which comprises the following steps:
acquiring individual employment probability according to the individual employment selection model;
setting a random number between 0 and 1 for each individual, judging the individual as a employment state if the random number of the individual is less than or equal to the employment probability of the individual, judging the individual as an unoperated state if the random number of the individual is greater than the employment probability of the individual, and acquiring the number of the individual in all employment states;
obtaining the employment population quantity in the mobile phone signaling data, and scaling the random number through an employment individual scaling formula, wherein the employment population scaling formula is as follows:
wherein l m Representing the random number of the mth round, W m-1 The number of employment individuals in the m-1 th round is represented, and N represents the number of mobile phone signaling data;
and when the difference value between the individual number of the employment status and the employment population number tends to be stable, ending the scaling process, and obtaining the current individual employment situation.
Further, the probability on each commute distance interval of the individual is obtained, comprising the following steps:
the method comprises the steps of presetting a distance interval, and calculating the probability of each employment individual in different commute distance intervals through the individual commute distance model, wherein the calculation formula is as follows:
wherein P is z (a, b) represents the probability that the z-th employment individual commute distance is in the distance interval a-b, a represents the lower bound of the distance interval, b represents the upper bound of the distance interval, x represents the commute distance, a represents the shape parameter of the individual commute distance model, u z Representing a mean value of z-th employment individual commute distances predicted from the individual commute distance model.
In a second aspect, the present invention also provides an artificial home space association apparatus, including:
the basic artificial family generation module is used for generating basic artificial families according to the survey statistical data through an artificial family generation algorithm, wherein the basic artificial families comprise individual attributes and family attributes;
the employment probability prediction module is used for presetting an individual employment selection model, and predicting the individual employment probability of the basic artificial family through the individual employment selection model to obtain individual employment conditions;
the commute distance prediction module is used for presetting an individual commute distance model, predicting the commute distance of the basic artificial family through the individual commute distance model based on the individual employment situation, and obtaining the probability of each individual commute distance interval;
the signaling data acquisition module is used for acquiring mobile phone signaling data, wherein the mobile phone signaling data comprises space position information and personal attribute information;
and the artificial family space position acquisition module is used for matching the basic artificial family with the mobile phone signaling data according to the probability on the individual commute distance interval and the individual attribute to acquire the space position information of the artificial family.
In a third aspect, the present invention also provides a computer device comprising:
at least one memory and at least one processor;
the memory is used for storing one or more programs;
the one or more programs, when executed by the at least one processor, cause the at least one processor to implement the steps of a method of artificial home space association as described in the first aspect.
In a fourth aspect, the present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of a method of artificial home space correlation according to the first aspect.
The invention generates basic artificial families through an artificial family generation algorithm based on investigation statistical data; presetting an individual employment selection model, and predicting the individual employment probability of the basic artificial family through the individual employment selection model to obtain the individual employment situation; meanwhile, an individual commuting distance model is preset, and the commuting distance of a basic artificial family is predicted based on the individual employment situation through the individual commuting distance model, so that the probability of each individual commuting distance interval is obtained; acquiring mobile phone signaling data, wherein the mobile phone signaling data comprises space position information and personal attribute information; and matching the basic artificial family with the mobile phone signaling data according to the probability and the individual attribute of the individual commute distance interval to obtain the spatial position information of the artificial family. According to the method and the device for the spatial correlation of the artificial families, the difference of the individual commuting distances under different family conditions is calculated, so that the spatial correlation results of the artificial families are more in line with the actual conditions, and the method and the device for the spatial correlation of the artificial families are more available.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Drawings
FIG. 1 is a flow chart of steps of a method of artificial home space association provided in one exemplary embodiment;
FIG. 2 is a flowchart of the employment individual quantity prediction step of a method for artificial home space correlation provided in one exemplary embodiment;
FIG. 3 is a flow chart of steps of a primary matching process of an artificial home space association method provided in one exemplary embodiment;
FIG. 4 is a flow chart of steps of a secondary matching process of an artificial home space association method provided in one exemplary embodiment;
FIG. 5 is a flow chart of steps of a non-working family matching process of an artificial family space association method provided in one exemplary embodiment;
FIG. 6 is a block diagram of an artificial home space association apparatus provided in one exemplary embodiment;
FIG. 7 is an internal block diagram of a computer device provided in one exemplary embodiment;
fig. 8 is an internal structural diagram of a computer device provided in one exemplary embodiment.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the following detailed description of the embodiments of the present application will be given with reference to the accompanying drawings.
It should be understood that the described embodiments are merely some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the embodiments of the present application, are within the scope of the embodiments of the present application.
The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of the application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims. In the description of this application, it should be understood that the terms "first," "second," "third," and the like are used merely to distinguish between similar objects and are not necessarily used to describe a particular order or sequence, nor should they be construed to indicate or imply relative importance. The specific meaning of the terms in this application will be understood by those of ordinary skill in the art as the case may be.
Furthermore, in the description of the present application, unless otherwise indicated, "a plurality" means two or more.
"and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.
The artificial families are not in one-to-one correspondence with the real families, but integrally accord with the statistical characteristics of the real population and the families, and the artificial families comprise basic attributes and spatial attributes, wherein the basic attributes comprise family types and scales, the sexes, the ages and the like of all the members of the families, and the spatial attributes comprise family residence places, family employment population workplaces and the like. Since 1990 s, artificial households are widely applied to urban population and household analysis, urban population simulation, policy effect analysis and other aspects in order to solve the problems that the acquisition cost of a real microscopic household sample is high, privacy protection is difficult to coordinate and the like.
The artificial family generation comprises two steps, wherein the basic artificial family is spatially associated with the artificial family. The basic artificial family refers to an artificial family only comprising individual and family attributes and not comprising spatial attributes, and common methods can be divided into a synthesis reconstruction method and a combination optimization method. While artificial family space association refers to assigning spatial attributes, such as residence, workplace, etc., to the synthesized underlying artificial family. The main methods for associating the space of the artificial families at present can be divided into the following two types: an association method based on an activity place is to construct the activity place according to auxiliary data such as land utilization, business data and the like, and then allocate living places and working places for artificial families; one is an association method based on activity information, which uses travel survey data, mobile phone data and the like to directly assign the existing residence place work place information to the corresponding artificial families.
However, the related method based on the activity place needs to construct the activity place by itself, which leads to a larger difference between the activity place and the activity place in the real world, and because the basic manual home is generally distributed only according to the capacity limitation and the nearby principle, the complexity of the real world trip cannot be considered comprehensively obviously; the correlation method based on the activity information partially considers the mutual influence of family members, but is limited to endowing the space attribute with real family sample data, the sample size is small and is not representative, and the other part uses city big data, so that the travel characteristic difference caused by different family composition differences is ignored.
Based on the above considerations, the embodiment of the present application provides an artificial home space association method, as shown in fig. 1, including the following method steps:
s201: and generating a basic artificial family through an artificial family generation algorithm according to the survey statistical data, wherein the basic artificial family comprises individual attributes and family attributes.
In particular, the survey statistics include relevant social statistics, which may be official published demographic information statistics, and small amounts of family survey data, the individual attributes including gender, age, etc., and the family attributes including family size, family type, etc. In the embodiment of the application, the marginal constraint of population and family attributes is constructed through social statistical data, investigation statistical data is taken as a sample, and the sample is expanded by combining a simulated annealing algorithm, so that the sample is attached to the marginal constraint, and a basic artificial family with individual and family attributes is obtained, and the overall attribute distribution of the basic artificial family accords with the social statistical data.
In a specific example, the individual attributes and family attributes selected by the artificial family are generated as shown in the following table:
based on the selected individual attribute and family attribute, acquiring relevant social statistical data, and constructing marginal constraint through the statistical data, wherein a cross table of family scale and family type is schematically shown as follows:
| first generation household | Second generation household | Third generation family | Four-generation household | |
| One person | 54370 | 0 | 0 | 0 |
| Two-person household | 64550 | 15487 | 0 | 0 |
| Three-person household | 1654 | 68722 | 2211 | 0 |
| Four-person household | 567 | 10843 | 12230 | 14 |
| Five-person household | 120 | 864 | 8695 | 101 |
| Six-person household | 57 | 258 | 1901 | 220 |
| Seven-person household | 30 | 75 | 508 | 93 |
| Eight-person household | 11 | 26 | 160 | 15 |
| Nine-person household | 10 | 37 | 117 | 13 |
| Ten-person household | 11 | 8 | 49 | 3 |
The cross-table of individual gender versus age is shown below:
| age 0-5 years old | Age 6-18 | 19-29 years old | Age of 30-39 years | Age of 40-49 years | Age 50-59 | Age of 60-69 years | Age 70 and older | |
| Male men | 12665 | 17738 | 42960 | 29036 | 44291 | 62353 | 51775 | 30582 |
| Female woman | 12449 | 15183 | 41089 | 39505 | 49652 | 59906 | 48177 | 41917 |
The generated basic artificial family data is shown in the following table:
| individual numbering | Family numbering | Sex (sex) | Age of | Household scale | Family type |
| 1 | 1 | Man's body | 19-29 | 1 | First generation household |
| 2 | 2 | Female | 0-5 | 2 | Two generations of households |
| 3 | 2 | Man's body | 19-29 | 2 | Two generations of households |
S202: presetting an individual employment selection model, and predicting the individual employment probability of the basic artificial family through the individual employment selection model to obtain the individual employment situation.
In a preferred embodiment, an individual employment selection model is constructed, using a Logistic model to characterize whether employment and relationships between individual and family attributes by taking relevant survey statistics as sample data, and specifically expressed as:
wherein P is z Representing the probability of z employment of an individual, X zk Representing the value of person z on element k, beta k Characterizing the influence of the element as a parameter thereof; beta 0 Being constant, ε is the error that fits the normal distribution.
In a specific example, whether the employment of an individual is taken as a dependent variable, the sex, the age, the family scale, the family type, the number of people with each sex in the family and the number of people with each age in the family are taken as independent variables, and the sample is analyzed through the individual employment selection model, and the results are shown in the following table:
| parameters (parameters) | Estimated value |
| Sex of individual male | 1.50918*** |
| Age of the individual 19-29 years | 4.09326*** |
| The age of the individual is 30-39 years old | 5.12129*** |
| The age of the individual is 40-49 years | 4.59662*** |
| The age of the individual is 50-59 years | 2.33563*** |
| Household scale | 0.42112*** |
| First generation household | 0.52220*** |
| The number of men | -0.18754*** |
| Total number of families 0-5 years old | -0.63066*** |
| Total number of households 19-29 years old | 0.12147* |
| Total number of families 30-39 years old | -0.20144*** |
| Total number of families 40-49 years old | -0.24722*** |
| Total number of families 60-69 years old | -0.28241*** |
| Family 70 years old and above | -0.09844 |
| Constant (constant) | -4.08509*** |
| Number of samples | 18342 |
Wherein, parameter significance: * <0.05, <0.01, <0.001, the insignificant parameter was removed from the model, corresponding to an estimate of 0.
In a preferred embodiment, the predicted employment population is obtained from the individual employment selection model. Specifically, as shown in fig. 2, all basic artificial family population is obtained and predicted to obtain probability of each individual employment. Setting a random number between 0 and 1 for each individual, judging the individual as employment status if the random number of the individual is less than or equal to the employment probability, and judging the individual as non-employment status if the random number of the individual is greater than the employment probability. After one round of calculation is completed, the number of predicted employment individuals often deviates from the number of employment population in the actual mobile phone signaling data, so that the number of predicted employment individuals and the number of employment population in the actual mobile phone signaling data are converged through scaling random numbers, and a specific scaling formula is as follows:
wherein l m Representing the random number of the mth round, W m-1 The number of employment population of the m-1 th round is represented, and N represents the number of mobile phone signaling data. And counting the number of employment population after each round of scaling until the number of finally determined employment individuals approaches to the mobile phone data and remains stable.
In one specific embodiment, the individual employment decisions obtained by scaling the random number are shown in the following table:
s203: the individual commute distance model is preset, and based on the individual employment situation, the commute distance of the basic artificial family is predicted through the individual commute distance model, so that the probability of each commute distance interval of the individual is obtained.
In a preferred embodiment, an individual commute distance model is constructed, relevant social statistics are taken as samples, and the relationship between the commute distance and the individual and family attributes is modeled through Gamma regression, wherein the expression is as follows:
wherein the method comprises the steps ofAlpha is a shape parameter, lambda is a scale parameter, y is a commute distance, u z For the mean value of the z commute distance of an individual beta 0 Is constant, X zk For the value of the individual z element k, beta k Is the parameter of element k.
In a specific example, with resident trip survey data of a certain area as a sample, and with the individual commute distance of the business as a dependent variable, the individual gender, age, family scale, family type, the number of people in each gender in the family, the number of people in each age in the family and the total number of people in the family as independent variables, the sample is analyzed by the individual commute distance model, and the results are shown in the following table:
in a preferred embodiment, the probability of each employment individual being in a different commute distance interval is obtained by means of the individual commute distance model. In the embodiment of the application, 5km is taken as a distance interval, and different number of distance intervals are divided for different administrative areas according to the distance range of the mobile phone signaling data. Calculating the probability of each employment individual on different commute distance intervals through the individual commute distance model, wherein the calculation formula is as follows:
wherein P is z (a, b) represents the probability that the z-th employment individual commute distance is in the distance interval a-b, a represents the lower bound of the distance interval, b represents the upper bound of the distance interval, x represents the commute distance, a represents the shape parameter of the individual commute distance model, u z Representing a mean value of z-th employment individual commute distances predicted from the individual commute distance model.
In a preferred embodiment, after calculating the probability that an individual commute distance is within each distance interval, the cumulative probability for each commute distance interval is calculated, and in a specific embodiment, the cumulative probability for an individual commute distance for a region is calculated as shown below:
wherein the probability of the individual commuting distance is 0.5557 for 0-5km, the cumulative probability of the commuting distance is 0.7536 for 5-10km, i.e., the probability of the commuting distance being 0.1979 for 5-10 km.
S204: and acquiring mobile phone signaling data, wherein the mobile phone signaling data comprises space position information and personal attribute information.
In a preferred embodiment, after the handset signaling data is obtained, the handset signaling data is corrected according to specified characteristics in the handset signaling data. Specifically, the information of the residence place and the age group of the working place in the mobile phone signaling data is extracted, and the mobile phone signaling is calibrated by expanding the mobile phone data according to the corresponding number according to the number of the working population of each age group in each region in the related social statistical data.
In a specific example, the mobile phone signaling data includes the working grid point, the living grid point, and the age group of the individual, and coordinates of each grid point, wherein the format of the mobile phone signaling data is shown in the following table.
| Numbering device | Residential grid | Coordinates of living places | Working grid point | Work area coordinates | Age of |
| 1 | 2 | 342492,3455900 | 3 | 343492,3455900 | 19-29 |
S205: and matching the basic artificial family with the mobile phone signaling data according to the probability of the individual commute distance interval and the individual attribute to acquire the space position information of the artificial family.
In a preferred embodiment, the spatial location information is determined for the artificial home by a two-time basic process of matching the artificial home with the mobile phone signaling data, and each individual in the artificial home is assigned mobile phone signaling data with the best matching characteristics.
Specifically, as shown in fig. 3, in the primary matching stage, a first home requirement is set, where the first home requirement indicates that in a matching process between mobile phone signaling data and a basic artificial home, the following two requirements are satisfied: firstly, residence information in mobile phone signaling data distributed by employment individuals in the same family should be the same; second, the mobile phone signaling data matched by each employment individual should be consistent with the age and predicted commute distance interval in its personal attribute.
Setting random numbers between 0 and 1 for all individuals on the basis of the accumulated probability of the commute distance interval of the employment population, traversing from the distance interval of 0-5km, and when the random numbers are larger than the accumulated probability of the previous commute distance interval and smaller than or equal to the accumulated probability of the current commute distance interval, namely, considering the commute distance corresponding to the employment population to be in the current distance interval, so as to obtain the number of people corresponding to the commute distance interval in each age range of each work family, wherein in a specific example, the following table shows:
| 0-5km | 5-10km | …… | 65-70km | |
| 19-29 years old | 0 | 0 | …… | 0 |
| Age of 30-39 years | 1 | 1 | …… | 0 |
| …… | …… | …… | …… | …… |
| Age of 60-69 years | 0 | 0 | …… | 0 |
Wherein the family has two people working, wherein the age of one person is 30-39 years old, and the commute distance is within the interval of 0-5 km; the other person is 30-39 years old and the commute distance is in the interval of 5-10 km.
The cell phone signaling data at each mesh point is also converted into a corresponding expression format as a margin at the mesh point. And comparing whether the surplus on the grid points is matched with the current household demand one by one, if the surplus is smaller than the current household demand, not taking the grid points into consideration, and if the surplus is larger than or equal to the current household demand, taking the grid points into consideration, and finally obtaining a grid point set meeting the household demand. And randomly extracting one from the grid points meeting the requirements of the family by taking the mobile phone signaling data allowance on each grid point as a weight, and taking the mobile phone signaling data allowance as the residential grid point to which the family to be matched is finally matched. And acquiring all mobile phone signaling data of the individuals to be allocated on the grid points corresponding to the age groups and the distance intervals by a random extraction method, randomly extracting one piece of mobile phone signaling data to be allocated to the individuals, removing the signaling from the allowance, and continuing to allocate the next individuals. After all the individual families are allocated, correcting the mobile phone data allowance on the grid point, and entering the allocation process of the next family. After all families pass the primary distribution program, a final distribution result is output, and the primary distribution is finished.
In a specific example, as shown in fig. 4, the secondary matching process is similar to the primary matching process, except that for the modification of the home requirement condition, a second home requirement is set in the secondary matching process, where the second home requirement indicates that in the matching process of the mobile phone signaling data and the basic manual home, the following two requirements are satisfied: firstly, residence information in mobile phone signaling data distributed by employment individuals in the same family should be the same; second, the mobile phone signaling data matched by each employment individual should be matched with the age in the personal attribute.
In a preferred embodiment, as shown in fig. 5, for the households that still fail the second matching process, the unassigned state is maintained, no more handset data is assigned to them, and they are considered as non-working households, and the residence is uniformly assigned. Specifically, for the working families and the non-working families which fail to be matched, the living places are allocated to the working families and the non-working families through a weighted random allocation algorithm. The distribution of the number of the non-working families based on the practical experience is similar to the distribution of the number of the mobile phone signaling data, so that the proportion of the total mobile phone signaling data of each grid point to the total mobile phone signaling data of all the mobile phone signaling data is used as the weight of each grid point, and the residence is randomly selected for each non-working family on the basis of weighting, thereby completing the space information assignment work of all families.
According to the artificial family space association method provided by the embodiment of the application, basic artificial families are generated through an artificial family generation algorithm based on investigation statistical data; presetting an individual employment selection model, and predicting the individual employment probability of the basic artificial family through the individual employment selection model to obtain the individual employment situation; meanwhile, an individual commuting distance model is preset, and the commuting distance of a basic artificial family is predicted based on the individual employment situation through the individual commuting distance model, so that the probability of each individual commuting distance interval is obtained; acquiring mobile phone signaling data, wherein the mobile phone signaling data comprises space position information and personal attribute information; and matching the basic artificial family with the mobile phone signaling data according to the probability and the individual attribute of the individual commute distance interval to obtain the spatial position information of the artificial family. According to the method and the device for the spatial correlation of the artificial families, the difference of the individual commuting distances under different family conditions is calculated, so that the spatial correlation results of the artificial families are more in line with the actual conditions, and the method and the device for the spatial correlation of the artificial families are more available.
The embodiment of the application further provides an artificial home space association device 300, as shown in fig. 6, including:
a basic artificial family generation module 301, configured to generate a basic artificial family according to the survey statistics through an artificial family generation algorithm, where the basic artificial family includes an individual attribute and a family attribute;
the employment probability prediction module 302 is configured to preset an individual employment selection model, predict an individual employment probability of the basic artificial family through the individual employment selection model, and obtain an individual employment situation;
the commute distance prediction module 303 is configured to preset an individual commute distance model, predict the commute distance of the basic artificial family according to the individual commute distance model based on the individual employment situation, and obtain the probability on each commute distance interval of the individual;
a signaling data acquisition module 304, configured to acquire mobile phone signaling data, where the mobile phone signaling data includes spatial location information and personal attribute information;
and the artificial family space position acquisition module 305 is configured to match the basic artificial family with the mobile phone signaling data according to the probability on the individual commute distance interval and the individual attribute, and acquire space position information of the artificial family.
It should be noted that, both an artificial home space association apparatus and an artificial home space association method are derived from the same inventive concept, and the explanation of the correlation of an artificial home space association apparatus may refer to an embodiment of an artificial home space association method, which is not described herein.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of artificial home space association.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 8. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of artificial home space association. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements an artificial home space association method according to any one of the above embodiments.
The present invention may take the form of a computer program product embodied on one or more storage media (including, but not limited to, magnetic disk storage, CD-ROM, optical storage, etc.) having program code embodied therein. Computer-readable storage media include both non-transitory and non-transitory, removable and non-removable media, and information storage may be implemented by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to: phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, may be used to store information that may be accessed by the computing device.
It is to be understood that the embodiments of the present application are not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be made without departing from the scope thereof. The scope of embodiments of the present application is limited only by the appended claims.
The above examples merely represent a few implementations of the examples of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the embodiments of the present application, which are all within the scope of the embodiments of the present application.
Claims (10)
1. The method for associating the artificial home space is characterized by comprising the following steps of:
generating a basic artificial family through an artificial family generation algorithm according to the survey statistical data, wherein the basic artificial family comprises individual attributes and family attributes;
presetting individual employment selection, and predicting the individual employment probability of the basic artificial family through the individual employment selection model to obtain individual employment conditions;
presetting an individual commute distance model, and predicting the commute distance of the basic artificial family through the individual commute distance model based on the individual employment situation to obtain the probability of each commute distance interval of an individual;
acquiring mobile phone signaling data, wherein the mobile phone signaling data comprises space position information and personal attribute information;
and matching the basic artificial family with the mobile phone signaling data according to the probability of the individual commute distance interval and the individual attribute to acquire the space position information of the artificial family.
2. The method according to claim 1, wherein the matching the basic artificial home with the mobile phone signaling data comprises the steps of:
acquiring employment individuals in the artificial families, determining the commute distance interval of the employment individuals according to the probability on each commute distance interval of the individuals, and acquiring the corresponding relation between the commute distance interval and the individual attribute;
presetting a first family requirement, wherein the first family requirement indicates that the correspondence between a commute distance interval of employment individuals located in the same artificial family and individual attributes is the same, and the personal attribute information of the employment individuals is matched with the individual attributes;
acquiring a grid point set meeting the first family requirement according to the mobile phone signaling data;
determining living grid points of the artificial family according to the grid point set and the quantity of corresponding mobile phone signaling data on each grid point;
and acquiring mobile phone signaling data corresponding to the residential grid points, and distributing the mobile phone signaling data to the employment individuals, wherein the distribution indicates that the personal attribute information of the mobile phone signaling data is consistent with the individual attribute of the employment individuals.
3. The method of spatial association of an artificial home according to claim 2, wherein the matching of the basic artificial home with the mobile phone signaling data further comprises the steps of:
acquiring the artificial families which are not allocated with mobile phone signaling data, and presetting a second family requirement, wherein the second family requirement indicates that the personal attribute information of employment individuals is matched with the individual attributes;
acquiring a grid point set meeting the second family requirement according to the mobile phone signaling data;
according to the grid point set and the quantity of the corresponding mobile phone signaling data on each grid point, determining the living grid points of the artificial family not assigned with the mobile phone signaling data;
and acquiring mobile phone signaling data corresponding to the resident grid points, and distributing the mobile phone signaling data to the employment individuals.
4. The method according to claim 1, wherein the preset individual employment selection model comprises the steps of:
according to the social statistical data, constructing the individual employment selection model through a logic cliff model, wherein the expression of the individual z employment selection model is as follows:
wherein P is z Representing the probability of z employment of an individual, X zk Representing the value of individual z on element k, beta k To influence the force parameter beta 0 Being constant, ε is the error that fits the normal distribution.
5. The method according to claim 1, wherein the preset individual commute distance model comprises the steps of:
according to the social statistical data, constructing the individual commute distance model by a Gamma regression method, wherein the expression of the individual z commute distance model is as follows:
wherein alpha is a shape parameter, lambda is a scale parameter, y is a commute distance, u z For the individual z commute distance mean, beta 0 Is constant, X zk For the value of the individual z element k, beta k Is the parameter of element k.
6. The method of claim 4, wherein the step of obtaining the employment situation of the individual comprises the steps of:
acquiring individual employment probability according to the individual employment selection model;
setting a random number between 0 and 1 for each individual, judging the individual as a employment state if the random number of the individual is less than or equal to the employment probability of the individual, judging the individual as an unoperated state if the random number of the individual is greater than the employment probability of the individual, and acquiring the number of the individual in all employment states;
obtaining the employment population quantity in the mobile phone signaling data, and scaling the random number through an employment individual scaling formula, wherein the employment population scaling formula is as follows:
wherein l m Random number representing mth round，W m-1 The number of employment individuals in the m-1 th round is represented, and N represents the number of mobile phone signaling data;
and when the difference value between the individual number of the employment status and the employment population number tends to be stable, ending the scaling process, and obtaining the current individual employment situation.
7. The method of claim 5, wherein the step of obtaining the probability of each commuting distance interval of the individual comprises the steps of:
the method comprises the steps of presetting a distance interval, and calculating the probability of each employment individual in different commute distance intervals through the individual commute distance model, wherein the calculation formula is as follows:
wherein P is z (a, b) represents the probability that the z-th employment individual commute distance is in the distance interval a-b, a represents the lower bound of the distance interval, b represents the upper bound of the distance interval, x represents the commute distance, a represents the shape parameter of the individual commute distance model, u z Representing a mean value of z-th employment individual commute distances predicted from the individual commute distance model.
8. An artificial home space association apparatus, comprising:
the basic artificial family generation module is used for generating basic artificial families according to the survey statistical data through an artificial family generation algorithm, wherein the basic artificial families comprise individual attributes and family attributes;
the employment probability prediction module is used for presetting individual employment selection, predicting the individual employment probability of the basic artificial family through the individual employment selection model, and obtaining individual employment conditions;
the commute distance prediction module is used for presetting an individual commute distance model, predicting the commute distance of the basic artificial family through the individual commute distance model based on the individual employment situation, and obtaining the probability of each individual commute distance interval;
the signaling data acquisition module is used for acquiring mobile phone signaling data, wherein the mobile phone signaling data comprises space position information and personal attribute information;
and the artificial family space position acquisition module is used for matching the basic artificial family with the mobile phone signaling data according to the probability on the individual commute distance interval and the individual attribute to acquire the space position information of the artificial family.
9. A computer device, comprising:
at least one memory and at least one processor;
the memory is used for storing one or more programs;
when said one or more programs are executed by said at least one processor, the at least one processor is caused to implement the steps of an artificial home space association method as claimed in any one of claims 1 to 7.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of an artificial home space correlation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311361497.5A CN117670270A (en) | 2023-10-19 | 2023-10-19 | Method, device, equipment and storage medium for associating artificial family space |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311361497.5A CN117670270A (en) | 2023-10-19 | 2023-10-19 | Method, device, equipment and storage medium for associating artificial family space |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117670270A true CN117670270A (en) | 2024-03-08 |
Family
ID=90072214
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311361497.5A Pending CN117670270A (en) | 2023-10-19 | 2023-10-19 | Method, device, equipment and storage medium for associating artificial family space |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117670270A (en) |
-
2023
- 2023-10-19 CN CN202311361497.5A patent/CN117670270A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Schmitt et al. | ssdm: An r package to predict distribution of species richness and composition based on stacked species distribution models | |
| CN107563803B (en) | Quotient circle dividing method based on distance consumption grid | |
| CN110019568B (en) | Spatial clustering-based addressing method and device, computer equipment and storage medium | |
| Wu et al. | Modified data-driven framework for housing market segmentation | |
| CN113191023B (en) | Crowd-sourcing-aware task allocation and user recruitment model cross-validation method and system | |
| Montero et al. | Fusing mobile phone data with other data sources to generate input OD matrices for transport models | |
| CN102750411A (en) | Urban dynamic micro-simulation method based on multi-agent discrete choice model | |
| CN112085250B (en) | Population space distribution simulation method, terminal equipment and storage medium | |
| CN110956412A (en) | Flood dynamic assessment method, device, medium and equipment based on real-scene model | |
| KR102297195B1 (en) | Population dispersal prediction device based on population dispersal simulation model and population dispersal prediction method using the same | |
| CN115409671B (en) | Method, device, terminal and storage medium for synthesizing microscopic data of community resident population | |
| WO2020086336A1 (en) | Space utilization measurement and modeling using artificial intelligence | |
| Oloritun et al. | Identifying close friendships in a sensed social network | |
| CN115018119A (en) | Power load prediction method and system | |
| Bruna et al. | Geographically weighted panel regression and development accounting for European Regions | |
| Lagarias | Exploring land use policy scenarios with the use of a cellular automata-based model: urban sprawl containment and sustainable development in Thessaloniki | |
| CN117670270A (en) | Method, device, equipment and storage medium for associating artificial family space | |
| Georgati et al. | Spatially explicit population projections: The case of Copenhagen, Denmark | |
| CN114492905A (en) | Customer appeal rate prediction method and device based on multi-model fusion and computer equipment | |
| White et al. | A model for Antarctic surface mass balance and ice core site selection | |
| Huang et al. | A doubly weighted approach to urban data disaggregation in GIS: A case study of Wuhan, China | |
| CN114388100B (en) | Method and device for establishing muscle mapping model and computer equipment | |
| Peña-Guillen | Simulation of house consolidation process in Lima using an epidemic diffusion mechanism | |
| Murata et al. | Distribution of Synthetic Populations of Japan for Social Scientists and Social Simulation Researchers | |
| JP6965129B2 (en) | Information processing equipment, information processing methods and programs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |