CN110288125B - Commuting model establishing method based on mobile phone signaling data and application - Google Patents
Commuting model establishing method based on mobile phone signaling data and application Download PDFInfo
- Publication number
- CN110288125B CN110288125B CN201910449958.1A CN201910449958A CN110288125B CN 110288125 B CN110288125 B CN 110288125B CN 201910449958 A CN201910449958 A CN 201910449958A CN 110288125 B CN110288125 B CN 110288125B
- Authority
- CN
- China
- Prior art keywords
- base station
- unit
- mobile phone
- commute
- commuting
- 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.)
- Active
Links
- 230000011664 signaling Effects 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000013139 quantization Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 31
- 230000002093 peripheral effect Effects 0.000 claims description 22
- 238000007405 data analysis Methods 0.000 claims description 20
- 238000004891 communication Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 15
- 230000005484 gravity Effects 0.000 description 15
- 230000007547 defect Effects 0.000 description 8
- 238000005457 optimization Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 241000729176 Fagopyrum dibotrys Species 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 230000001413 cellular effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 241001269524 Dura Species 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W8/00—Network data management
- H04W8/18—Processing of user or subscriber data, e.g. subscribed services, user preferences or user profiles; Transfer of user or subscriber data
- H04W8/183—Processing at user equipment or user record carrier
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention provides a commuting model establishing method based on mobile phone signaling data, which is used for establishing a commuting model of a city according to mobile phone signaling data acquired by mobile phone base stations in the city, and is characterized by comprising the following steps: step S1, acquiring mobile phone signaling data and analyzing the mobile phone signaling data to obtain user commuting data; s2, calculating the distribution weight of the mobile phone base station and the urban space unit around the mobile phone base station according to the base station position information of the mobile phone base station, and S3, distributing user commuting data according to the distribution weight to obtain unit commuting data; s4, constructing a unit commuting model; s5, calculating to obtain a residual error of the unit commuting model according to the commuting amount calculated by the unit commuting model and the actual commuting amount; s6, clustering the residual errors in a spatial clustering mode and carrying out variable quantization processing to generate a residual error virtual variable; and S7, substituting the residual virtual variable into the unit commuting model to obtain a residual commuting model.
Description
Technical Field
The invention belongs to the field of urban planning, and particularly relates to a commuting model establishing method based on mobile phone signaling data and application thereof.
Background
The concept of the commute model is derived from urban traffic planning, and in fact, in the traffic model system, the concept of the commute model is equivalent to home-based work trip (HBW), i.e. going out from home to work. At present, traditional gravity models (gravitymodels) are mainly used for modeling such trips in the fields of urban planning and urban traffic. Specifically, a commuting and traveling model of the whole city is constructed based on large-scale traffic survey data, and the influence of different residential land and employment post layouts on the commuting behavior of the whole city is simulated by means of the model.
The current commuting model mainly has the following three defects:
the first is a data plane defect. The traditional commute model data sources are mainly large-scale census data, such as census and traffic census. Compared with general questionnaire survey data, the large-scale census data has the characteristics of large sample amount and high coverage rate, but has the defects of high survey cost, large consumption of manpower and material resources and capability of being carried out once every 10 years. And the population distribution, traffic conditions and the like of cities change greatly within ten years, and the utility of census data is expected to gradually decrease with the lapse of time.
The second is a method level deficiency. Taking the above sea city as an example, the current traffic model system in Shanghai is mainly based on traffic survey data and a traditional gravity model (refer to the works of Chenbizhuang, luxinming, dongguan, etc.). The defects of traffic survey data already show that the traditional gravity model has the defects of poor expansibility, which directly results in poor prediction effect of the model on commuting behaviors. In fact, in addition to the fields of urban planning and urban traffic, other fields will also study commuting models, typically the field of space-metering economics. The expansibility of a spatial regression model in the field of spatial metering is better than that of a traditional gravity model, which means that more factors or variables can be considered in the model, but the defect of the spatial regression model is that the theory is relatively complex and cannot be easily mastered by planning practitioners.
Finally, the application level is defective. The defects of data and methods directly cause poor fitting effect of the model and indirectly cause defects in the aspect of model application, namely, the deviation of results is generated by guiding planning practice by using the model with poor prediction effect, and unreasonable results are generated.
Disclosure of Invention
In order to solve the problems, the invention provides a commuting model establishing method for optimizing a commuting model through mobile phone signaling big data, which adopts the following technical scheme:
the invention provides a commuting model establishing method based on mobile phone signaling data, which is used for establishing a commuting model of a city according to mobile phone signaling data acquired by each mobile phone base station in the city, and is characterized by comprising the following steps: step S1, acquiring mobile phone signaling data and analyzing the mobile phone signaling data to obtain user commuting data including a departure place base station and a employment place base station of a user; s2, calculating distribution weights of the mobile phone base station and a preset number of city space units around the mobile phone base station according to the base station position information of the mobile phone base station, and S3, distributing user commuting data to the city space units according to the distribution weights so as to obtain unit commuting data comprising a departure place unit and a employment place unit of a user; s4, constructing a unit commute model, wherein the unit commute model is in the following form:
ln T ij ＝κ i +α i ln N j +β i ln d ij +ε ij
in the formula, T ij For commute volume between city space units, N j Number of employment posts for jth employment unit, d ij For the commute cost between the ith departure location unit and the jth employment location unit, α i 、β i The population number influence coefficient and employment position influence coefficient, kappa, of the ith departure place unit i Is a constant term of the ith origin unit, epsilon ij The residual error between the ith departure place unit and the jth employment place unit is obtained; step S5, calculating a residual error { R ] of the unit commuting model according to the commuting amount calculated by the unit commuting model and the actual commuting amount n ，X n ，Y n In which R is n Absolute number, X, representing the residual error for the nth city space unit n And Y n A plane coordinate representing an nth city space unit; step S6, to residual error { R n ，X n ，Y n Clustering in a spatial clustering mode, classifying according to a preset classification mode to obtain 4 clustering types, and further performing variable quantization processing on the 4 clustering types to generate a residual virtual variable; and S7, substituting the residual virtual variable into the unit commuting model to obtain a residual commuting model, wherein the residual commuting model is in the following form:
ln T ij ＝κ i +α i ln N j +β i ln d ij +∑ k α k D_SE k +ε ij
in the formula, D _ SE k Is the residual error of the cluster type corresponding to the kth class, k is taken to be [0,1,2,3]，D_SE k Is taken as value of [0,1]，α k Are the corresponding residual coefficients.
The commuting model optimization method based on the mobile phone signaling data provided by the invention can also have the technical characteristics that the mobile phone signaling data comprises base station information and time information generated during mobile phone communication, and the step S1 comprises the following substeps: s1-1, acquiring mobile phone signaling data; s1-2, identifying a departure base station and a employment base station of a user according to the base station information and the time information; and S1-3, generating user commuting data according to the mobile phone signaling data, the departure base station and the employment foundation station.
The commuting model optimization method based on the mobile phone signaling data provided by the invention can also have the technical characteristics that the step S2 comprises the following substeps: s2-1, acquiring base station position information of a mobile phone base station and unit position information of a city space unit; s2-2, acquiring city space units with the periphery quantity being a preset quantity and the nearest distance for each mobile phone base station as the peripheral space units of each mobile phone base station; s2-3, respectively calculating the adjacent distance between each mobile phone base station and each corresponding peripheral space unit according to the base station position information and the unit position information; s2-4, sequentially judging the largest value of all adjacent distances corresponding to each mobile phone base station as the maximum adjacent distance for each mobile phone base station, and further calculating and acquiring the bandwidth distance of the corresponding mobile phone base station according to the maximum adjacent distance; and S2-5, calculating the distribution weight of the mobile phone base station and the peripheral space unit according to the bandwidth distance and the adjacent distance.
The commuting model optimization method based on the mobile phone signaling data provided by the invention can also have the technical characteristics that the preset classification mode is to classify according to a first residual error and a second residual error, wherein the first residual error is the residual error of the urban space unit, and the second residual error is the residual error of the urban space unit surrounding the urban space unit corresponding to the first residual error.
The commuting model optimization method based on the mobile phone signaling data provided by the invention can also have the technical characteristics that the city space unit is a living committee unit.
The method for optimizing the commuting model based on the mobile phone signaling data provided by the invention can also have the technical characteristics that the commuting cost is the commuting time or the commuting distance.
The method for optimizing the commuting model based on the mobile phone signaling data provided by the invention can also have the technical characteristics that the preset number is 30.
The invention also provides an application of the residual commute model established according to the commute model establishing method, which is characterized in that the city commute data analysis system with the residual commute model is used for analyzing the mobile phone signaling data of the city based on the employment post number in the city preset by an analyst so as to obtain the resident commute data of the city, and the city commute data analysis system comprises: a commuting model storage unit for storing a residual commuting model; a signaling data acquisition part for acquiring the mobile phone signaling data collected by each mobile phone base station in the city; a signaling data analysis and acquisition part for analyzing the mobile phone signaling data to acquire user commuting data including a departure place base station and a employment place base station of the user; the distribution weight calculation part is used for calculating the distribution weights of the mobile phone base station and a preset number of city space units around the mobile phone base station according to the base station position information of the mobile phone base station; a commute data allocation unit which allocates user commute data to the city space units according to the allocation weight to obtain unit commute data including a departure place unit and a employment place unit of the user; thereby the portion of acquireing is calculated to commute data, thereby calculates unit commute data and employment post quantity through the residual error model and acquires resident's commute data.
The urban commute data calculation system provided by the invention can also have the technical characteristics that the resident commute data is the average commute distance or the average commute time of the city.
Action and Effect of the invention
According to the commuting model establishing method based on the mobile phone signaling data, the user commuting data corresponding to each mobile phone base station is obtained through calculation according to the mobile phone signaling data, the distribution weights of the mobile phone base stations and each urban space unit are obtained through calculation, the user commuting data are uniformly distributed to each urban space unit to obtain the unit commuting data corresponding to each urban space unit, the problem that each unit cannot be uniformly covered by urban traffic data adopted in urban planning is solved, and therefore a data source adopted in model establishing is optimized; and moreover, the mobile phone signaling data can be updated quickly, so that the real-time performance of the commuting model can be better optimized. Meanwhile, a unit commuting model is established on the basis of the traditional gravity model, and the problem that the traditional gravity model cannot analyze the direction of commuting is solved; furthermore, the method also obtains the residual commuting model by calculating the residual optimization, so that the fitting goodness of the model is further improved, the prediction effect of the model is greatly improved, and the land use layout of the city is better guided.
Drawings
FIG. 1 is a flow chart of a commute model establishment method in an embodiment of the present invention;
FIG. 2 is a schematic illustration of unit commute data in an embodiment of the present invention;
FIG. 3 is a schematic illustration of the difference in employment attraction in an embodiment of the present invention;
FIG. 4 is a comparison of goodness-of-fit of various models in an embodiment of the invention;
FIG. 5 is a block diagram of a system for analyzing urban commute data in an embodiment of the present invention;
FIG. 6 is a schematic illustration of commuting distances for the entire Shanghai city in an embodiment of the present invention; and
fig. 7 is a flowchart of a communication data analysis process in the embodiment of the present invention.
Detailed Description
In recent years, city commute research based on mobile positioning big data is started to rise, and a more accurate commute model can be constructed through the big data. However, at present, research aiming at big data mostly stays at a qualitative description level of the current situation of the urban commuting space, and deeper research on urban models and the like is less, so that planning practice cannot be well guided. Colloquially, existing big data research is to answer the question of "what" rather than the question of "why" and what in the future. The invention aims to excavate the commuting rule of the city and construct a commuting model of the city through the big data of the mobile phone signaling, thereby carrying out quantitative analysis and deeply discussing the factors behind the commuting amount and answering the question of the reason; secondly, after the construction of the commute model is completed, the question of 'what' can be answered in the future can be combined with the planning of actual requirements.
In order to make the technical means, creation features, achievement purposes and effects of the invention easy to understand, the commuting model establishing method based on the mobile phone signaling data is specifically described below with reference to the embodiments and the accompanying drawings.
< example >
Fig. 1 is a flowchart of a commute model building method in an embodiment of the present invention.
As shown in fig. 1, the commuting model establishing method based on the mobile phone signaling data mainly includes the following steps:
step S1, acquiring mobile phone signaling data, and analyzing the mobile phone signaling data to obtain user commuting data including a departure place base station and a employment place base station of a user, wherein the specific steps are shown in step S1-1 to step S1-3.
And S1-1, acquiring the mobile phone signaling data. The mobile phone signaling data is mobile phone signaling generated when each mobile phone base station in a city communicates with mobile phones of users (namely mobile phone holders). When a mobile phone of a user is turned on or off, receives and sends short messages and receives and calls, the mobile phone and a base station perform 'information exchange', namely the mobile phone is recorded with a point by a peripheral specific base station (space position) at a specific time (action occurrence time) to obtain space-time information. If the user does not have any behavior, the location of the mobile phone is also updated periodically, that is, the location of the mobile phone is updated periodically every 2 hours, that is, even if the mobile phone of the user is not used, a point is recorded every 2 hours.
In this embodiment, the mobile phone signaling data includes mobile phone information (for example, a mobile phone number) of the mobile phone, time information (that is, time when communication occurs), and base station information (for example, a base station number) during communication.
And S1-2, identifying the departure base station and the employment base station of the user according to the base station information and the time information in the mobile phone signaling data.
In step S1-2 of this embodiment, two consecutive weeks of mobile phone signaling data are obtained, and the mobile phone signaling data is counted according to the mobile phone information, so as to obtain the mobile phone signaling data of each user in two weeks. Furthermore, for the mobile phone signaling data of each user, the living track of the user is analyzed sequentially according to the time information in the mobile phone signaling data, so that the living place (namely, the departure place base station) and the working place (namely, the employment place base station) of the user are identified.
Specifically, if the point at which the user is recorded at night (8 pm to 6 pm) is relatively fixed (referred to as "night high-frequency recording point"), it may be considered that this point (i.e., the location information corresponding to the cell phone base station) is the residence of the user. Similarly, if the point at which the user is recorded during the day (9 am to 6 pm) is relatively fixed (referred to as "daytime high frequency recording point"), then this point is likely to be the user's work place. Namely: the night high-frequency recording point represents a residence, and the day high-frequency recording point represents a work place.
And S1-3, generating user commuting data according to the mobile phone signaling data, the departure base station and the employment base station.
In this embodiment, the user commute data includes departure base station information corresponding to a departure place, a corresponding departure time, employment base station information corresponding to a employment place, a corresponding employment time, and mobile phone information.
In step S1 of this embodiment, mobile 2G mobile phone signaling data of two consecutive weeks in the first half of 2014 in shanghai city is used, and about 1370 ten thousands of users having relatively stable residence and employment places are recognized in total, and account for about 60% of 2400 ten thousands of permanent population in shanghai city.
And S2, calculating the distribution weights of the mobile phone base station and a preset number of city space units around the mobile phone base station according to the base station position information of the mobile phone base station, wherein the specific steps are shown in the step S2-1 to the step S2-5.
And S2-1, acquiring the base station position information of the mobile phone base station and the unit position information of the urban space unit. The base station location information and the unit location information are obtained from public city planning information.
In this embodiment, the city planning information is city information published by the sixth national census or city information and geographic information from other sources, and the city planning information divides city space units (for example, street space units or living committee space units) and records base station location information of locations of mobile phone base stations.
And S2-2, acquiring the city space units with the peripheral quantity being a preset quantity and the nearest distance for each mobile phone base station as the peripheral space units of each mobile phone base station.
In step S2-2 of this embodiment, the predetermined number is 30, that is, the nearest city space units whose number is 30 around each cell phone base station are used as the surrounding space units. Meanwhile, since the city space units used in this embodiment are commission space units and the spatial distribution thereof is irregular, the locations of the centroids of the commission space units are used for corresponding calculation (similarly, the unit location information of the commission space unit is also based on the location of the centroid).
And S2-3, respectively calculating the adjacent distance between each mobile phone base station and each corresponding peripheral space unit according to the base station position information and the unit position information.
In this embodiment, the adjacent distance is the distance between the mobile phone base station and the centroid of the peripheral space unit, and each mobile phone base station corresponds to 30 peripheral space units, so that each mobile phone base station has 30 adjacent distances corresponding to each peripheral space unit.
And S2-4, sequentially judging the largest value of all adjacent distances corresponding to each mobile phone base station as the maximum adjacent distance for each mobile phone base station, and further calculating and acquiring the bandwidth distance of the corresponding mobile phone base station according to the maximum adjacent distance.
In this embodiment, the bandwidth distance is the maximum range of data allocation of the base station, that is, when the straight-line distance between a city space unit and a certain base station exceeds the bandwidth distance, the base station does not allocate data to the city space unit.
In step S2-4 of this embodiment, the maximum adjacent distance is the adjacent distance between the urban space unit with the centroid farthest from the mobile phone base station and the mobile phone base station among the 30 urban space units (i.e., the peripheral space units) corresponding to the mobile phone base station. In this embodiment, the data of the bandwidth distance is that the maximum adjacent distance has the same numerical value, and meanwhile, the bandwidth distance of this embodiment is not more than 4km at most, that is, when the maximum adjacent distance is greater than 4km, the bandwidth distance of the mobile phone base station is calculated by 4 km.
And S2-5, calculating the distribution weight of the mobile phone base station and the peripheral space unit according to the bandwidth distance and the adjacent distance.
In step S2-5 of this embodiment, the basic calculation method for assigning weights is as follows:
simultaneously, the following requirements are met:
in the formula (I), the compound is shown in the specification,
is the assigned weight of the cell phone base station numbered i obtained by the residence committee space unit numbered k, d (i)k Is the adjacent distance between the base station i and the centroid of the living committee unit k, and θ is the bandwidth distance. Equation (2) ensures that the sum of the assigned weights calculated by equation (1) is 1.
By the formulas (1) and (2), the distribution weight of each base station of the mobile phone and the corresponding 30 peripheral space units can be obtained.
And S3, distributing the user commute data to the city space unit according to the distribution weight so as to obtain unit commute data comprising the departure place unit and the employment place unit of the user.
In step S3 of this embodiment, the commute data is a connection between two points, including both the residential area and the employment area, i.e., including two base stations of the residential area and the employment area. Therefore, when the commuting data is distributed in step S3, the residential base station data and the employment base station data need to be distributed at the same time, and a specific formula algorithm is as follows:
and:
equations (3), (4), (5) and (6) are based on equations (1) and (2), and are explained in turn as follows:
for equation (3), λ ij Is the commute amount from base station i to base station j, base station i and base station j are base stations in the vicinity of residence commission o and residence commission d, respectively,
is the weight of base station i obtained by unit o at the origin (which can be understood as the commuter's residence),
is the weight, T, of the base station j obtained by the destination (understood as the place of work of the commuter) unit d od The amount of commute from the departure place commission unit o to the destination commission unit d calculated from the weight.
The expressions (4) and (5) are the same as the expression (1), and the assignment weight of the departure base station and the destination base station to the neighboring cell is obtained by calculating the distance between the base station and the neighboring cell, and d in the expressions (i)o Is the distance between the base station i and the residence committee unit o, d (j)d Is the distance, θ, between the base station j and the residence committee unit d i And theta j The base station and the weight of the base station allocate bandwidth, respectively.
In equation 6, the meaning is the same as equation 2, and the sum of the calculated weights is guaranteed to be 1, so that the total amount of data when the base station assigns data to the commission cell is not changed.
And distributing the commuting stream data of the user into the commuting stream between the living committee and the living committee through formulas (3), (4), (5) and (6), namely, uniformly distributing the user commuting data corresponding to each mobile phone base station to each peripheral space unit according to the distribution weight, and enabling each urban space unit to obtain the user commuting data distributed by the peripheral base station so as to form unit commuting data.
In this embodiment, the unit commuting data includes information such as a resident population, employment posts, and commuting time between the committees, and the specific form of the data is shown in fig. 2, where pcq _ O represents a commuting departure place number (i.e., a place of residence), pcq _ D represents a commuting destination number (place of employment), and num _ home _ O represents a total resident population of the departure place (hereinafter abbreviated as P) i ) Num _ work _ D represents a total employment position of a destination (hereinafter abbreviated as N) j ) And num represents the amount of commuting between a residential site and a workplace (hereinafter abbreviated as T) ij ) And dist represents a commuting distance (hereinafter abbreviated as d) ij ) Dura _ car represents the commuting time of the car (the mode is car), dura _ bus represents the commuting time of the bus (the mode is bus, such as ground bus and subway). In the actual modeling process, one of commute distance, automobile commute time and bus commute time can be taken, and the embodiment adopts the commute distance to model.
S4, constructing a unit commute model, wherein the unit commute model is in the following form:
ln T ij ＝κ i +α i ln N j +β i ln d ij +ε ij (7)
in the formula, T ij For the commute amount between city space units, i represents the ith departure place unit, j represents the jth employment place unit, N j Number of employment posts for jth employment unit, d ij For the commute cost (including commute time or commute distance) between the ith departure place unit and the jth employment place unit, the implementation adopts the commute distanceIon), α) i 、β i Respectively is the population number influence coefficient and employment position influence coefficient of the ith departure place unit, the coefficient is positive under normal condition, kappa i Is a constant term of the ith origin unit, epsilon ij Is the residual between the ith departure location unit and the jth employment location unit. (wherein ln represents taking logarithm of corresponding variable, which is equivalent to making a numerical transformation of original variable, and making a transformation of commute amount, resident population, employment post and commute distance in the formula.)
The traditional commuting model employs a global commuting model (i.e., global model) of the form:
ln T ij ＝κ+αln P i +βln N j +γln d ij +ε (8)
in which the meanings of the corresponding variables are in accordance with the Unit Commuting model, P i The number of the population of the ith departure place unit is alpha and beta respectively are a population number influence coefficient and a employment position influence coefficient, gamma is a distance attenuation coefficient, the coefficient is negative under normal conditions, kappa is a constant term, and epsilon is a residual error.
The average goodness of fit (which is the most important index for evaluating the model effect and is between 0 and 1, the higher the value is, the better the model effect) of the global model is 0.65, and the fitting effect can be accepted. However, in this global model, there is an important drawback that the difference in appeal to the practitioner between the two units, or the "directionality" of the commute, cannot be taken into account, as will be explained by way of example.
As shown in fig. 3, two units a and B are located on both sides of the same subway line, the unit a is located in a suburban area, and the unit B is located within the central urban ring. Because they are located on both sides of the same subway line, the commute time and distance from A to B and from B to A should be the same, then according to the global model, the people from A unit to B unit employment and from B unit to A unit employment should be about the same, but in practice, the people from A unit to B unit employment should be much higher than the people from B unit to A unit employment. Since the B unit is located in a central city and the a unit is located in a suburban area, B has a greater attraction to a than a to B, which is the case in the practice of shanghai, many people in the suburban area work inside the central city, but few people in the opposite. While the global model does not reflect this "appeal" difference. To reflect this discrepancy, a unit-by-unit model (i.e., a unit commute model) must be employed.
The split-unit model is equivalent to "splitting" the global gravity model, and the total split is divided into 4991 (corresponding to the number of the living committee space units) split-unit models (hereinafter referred to as base models) which are constructed. The base model form is similar to the global model, the only difference being: because the data is split into 4991 subsets, each subset separately constructs a model, and the population of living in each subset is a constant (constant is a constant number, and different from variable, variable is variable between different units), the model has one less variable of the population of living in the unit of departure, namely P i . As shown in the above-described unit commute model, the basic model has a large number of models, but the amount of computation is not large, and the computation time is almost the same as that of the global model.
The average goodness of fit of the basic model is 0.76, and the effect is greatly improved compared with 0.65 of the global model. In the past, the modeling of the cells is not carried out, and mainly, data (traffic survey data) is not enough to cover each city space cell, and the problem can be perfectly solved by mobile phone signaling data. In the following, the basic model is further optimized through the residual error, the goodness of fit of the model is improved, the prediction precision is further improved, and planning practice is guided better.
Step S5, calculating a residual error { R ] of the unit commuting model according to the commuting amount calculated by the unit commuting model and the actual commuting amount n ，X n ，Y n In which R is n Absolute number, X, representing the residual error for the nth city space unit n And Y n Representing the plane coordinates of the nth city space unit.
In this embodiment, the residual is the difference between the actual value and the predicted value, and is determined by using any two pointsTaking A as the starting place and B as the destination, there is an actual commute amount between the two places, abbreviated as T 1 Secondly, for A, there is a coefficient of the unit-divided model, and the commuting amount predicted by the model can be calculated by substituting the coefficient into the model, which is abbreviated as T 2 Residual namely (T) 1 -T 2 ) Abbreviated as R, for the same departure point a to a different destination point B (B) 1 、B 2 、B 3 ……B n ) Are different in residual error and are respectively marked as R 1 、R 2 、R 3 ……R n And because the spatial position of each destination is different, each residual has a spatial position attribute, and the value and the spatial position attribute of the residual are marked as { { R 1 ，X 1 ，Y 1 }、{R 2 ，X 2 ，Y 2 }……{R n ，X n ，Y n }}. Where R represents the absolute value of the residual and X and Y represent the planar coordinates (i.e., latitude and longitude) of the location of the residual.
Step S6, for residual errors { R } n ，X n ，Y n And clustering in a spatial clustering mode, classifying according to a preset classification mode to obtain 4 clustering types, and further performing variable quantization processing on the 4 clustering types to generate residual virtual variables.
In this embodiment, the residual error { R }is used n ，X n ，Y n And fourthly, carrying out clustering calculation on the ArcGIS software platform so as to obtain a spatial clustering mode of the residual errors. Specifically, a local spatial autocorrelation calculation tool built in the ArcGIS is adopted, and a python writing cyclic algorithm is adopted to sequentially calculate all urban spatial units. The residuals are thus finally divided into 4 typical types, and the connotation of these types is the "special relation" between the units, namely, besides employment posts and commuting time, many factors influence the commuting amount between two places. In this embodiment, clustering is performed according to residual errors from residents starting from one unit to employment in a certain area and residual errors of units around the area, and 4 types of clustering results, namely high-high cluster (HH cluster) and low-low cluster (LL cluster), are further obtained according to the heights of the two residual errorscluster), high oligomeric class (HL cluster), and low high cluster (LH cluster). For example, a space unit is located along a subway, so that most of the employment of residents in the space unit is likely to be located along the subway, and the residual error along the subway may be high, and the subway is a high-level cluster.
Further, these 4 types are taken as 4 virtual variables, that is, a variable quantization process is performed, thereby obtaining residual virtual variables. In the present embodiment, a "virtual variable" can be simply understood as abstracting the form of a variable into two values, 1 and 0. See table 1 for details:
table: residual virtual variable setting specification table
Taking "high-high cluster (HH)" as an example, the high-high cluster corresponds to the virtual variable D _ SE _0, the value is 1, the other three values, D _ SE _1, D_SE _2, D _SE _3are all 0, and so on, each cluster type corresponds to one of the virtual variables, only one is 1, the other three are all 0, and for the cells without significant cluster features, the 4 virtual variables are all 0.
And S7, substituting the residual virtual variable into a unit commuting model to obtain a residual commuting model, wherein the residual commuting model is in the following form:
ln T ij ＝κ i +α i ln N j +β j ln d ij +∑ k α k D_SE k +ε ij (9)
in the formula, D _ SE k Is the residual error of the cluster type corresponding to the kth class, k is taken to be [0,1,2,3]，D_SE k Is taken to be [0,1 ]]，α k Are the corresponding residual coefficients, and the meaning of the remaining parameters is similar to that in the unit commute model.
As shown in fig. 4, the average goodness of fit of the residual commuting model reaches 0.92, which is far higher than 0.76 of the basic model and 0.65 of the global model (i.e. the conventional gravity model in the figure), and the improvement of the goodness of fit means that the prediction effect is greatly improved.
Table 1: traditional gravity model, base model, and residual model comparison
In table 1, the global model has 3 variables, the base model has 2 variables, and the residual model has 3 variables. The three variables of the global model are the resident population of the place of residence, the number of employment posts of the place of employment, and the commute time between the place of residence and the place of employment. Two variables of the base model are the employment position number of the employment location and the commute time from the residential location to the employment location. Two conventional variables of the residual error model, namely the employment post number and the commuting time, are consistent with the basic model, residual error variables are newly added on the basis, one residual error variable actually comprises four virtual variables, the four virtual variables are obtained through the spatial clustering analysis of the residual errors, 4 spatial types of the clustered residual errors are used as 4 virtual variables, in the embodiment, the 4 virtual variables are collectively referred to as one residual error virtual variable, and the basic model is further optimized after the residual error virtual variable is added into the basic model.
For a model, poor expandability means that fewer variables (variables) can be considered. For example, the basic assumption of the conventional gravity model is that the commuting amount between two places is directly proportional to the residential population of the departure place and the employment post number of the destination, and inversely proportional to the traffic time or distance between the two places, i.e., the higher the total population of the two places, the greater the employment post number, the shorter the traffic time or the closer the distance is, the greater the commuting amount between the two places, which conforms to the general rule. The "resident population", "employment post number" and "traffic time" are three variables, and the traditional gravity model can only consider the three variables. However, there are many factors affecting the commute amount, such as scale effect existing in a large employment center, deep-level reasons such as historical culture and the like, and the traditional gravity model cannot take the factors into consideration.
The commuting model establishing method based on the mobile phone signaling data is explained above. In addition, the residual commuting model established by the method can be applied to planning systems such as city planning and employment planning which need to calculate the commuting cost of residents, and the urban commuting data analysis system for analyzing the commuting data of the residents in the city based on the residual commuting model and the preset employment post number is described below by combining the attached drawings.
Fig. 5 is a block diagram of a city commute data analysis system in an embodiment of the present invention.
As shown in fig. 5, the urban commute data analysis system 100 includes a commute model storage unit 11, a signaling data storage unit 12, a signaling data analysis acquisition unit 13, an assignment weight calculation unit 14, a commute data assignment unit 15, a commute data calculation acquisition unit 16, an input display unit 17, a communication unit 18, and a control unit 19.
The communication unit 17 is used for performing communication interaction between the components of the urban commute data analysis system 100, and the control unit 18 is used for controlling the operation of the components of the urban commute data analysis system 100.
The commute model storage unit 11 stores the residual commute model created by the commute model creation method based on the mobile phone signaling data.
The signaling data storage unit 12 stores mobile phone signaling data acquired in advance from each mobile phone base station in a city.
The signaling data analysis and acquisition unit 13 is configured to analyze the mobile phone signaling data to acquire user commuting data including a departure base station and a employment base station of the user.
The distribution weight calculation unit 14 is configured to calculate distribution weights of the cellular phone base station and a predetermined number of city space units around the cellular phone base station according to the base station location information of the cellular phone base station.
The commute data assigning section 15 assigns the user commute data to the city space units in accordance with the assignment weights to obtain city commute data including the departure place unit and employment place unit of the user.
In the present embodiment, the processing methods of the signaling data analysis acquiring unit 13, the assignment weight calculating unit 14, and the commuting data assigning unit 15 are respectively identical to the processing methods of step S1, step S2, and step S3 of the commuting model building method described above.
The commute data calculation acquisition section 16 calculates the city commute data and the employment post number through the residual commute model stored in the commute model storage section 11, thereby acquiring the resident commute data.
In the present embodiment, the number of employment posts is the number of employment input by the analyst through the input display portion 17 according to the specific analysis situation. The resident commute data is the average commute distance of the city, and the average commute distance corresponds to the commute distance in the unit commute data adopted when the residual commute model is established. In other embodiments, the resident commute data may also be an average commute time, and the average commute time is divided into an average bus commute time and an average car commute time.
Theoretically, if a certain number of employment posts are added to any one unit, the commute amount of all units will change, and if the distribution in some units can maximally shorten the average commute time of the whole city, the units will perform best. The goal of the calculation is therefore to maximize the magnitude of the reduction in average commuting distance (or time) across the city after the number of employment opportunities for certain units has increased.
In the above sea city example, assuming that 1 ten thousand employment sites need to be added (i.e., the number of employment sites is 10000), the commute data calculation and acquisition unit 16 calculates the changes in the average commute distance of the entire city after the addition of the employment sites for 4991 units of the living and committee space, respectively, and the distribution of the changes in the units is as shown in fig. 6.
In fig. 6, jiangwan-pentagon field, jin qiao, zhangjiang-chun sand and shen zhuang-qi bao all belong to the level of city depocenter, and for this part of area, the requirements of overall planning are to accelerate the transformation and space adjustment of industry, increase employment opportunities appropriately, and promote the integration of producing city. In addition, the Luoshan-Gucun, jinqiao, nanting-Jing, cao Lu, cokang-Daling, gao Qing Lu-Yu Qiao and the like all belong to the central level of the region, and the requirement for the overall planning is to realize the balanced layout of public service and employment posts according to the population scale and development requirements of the region and mainly serve the surrounding regions. Other areas basically belong to the current major employment centers, including areas such as Minjing-Kongxin and outer Gao bridge, and other areas, and the employment posts in areas such as Pujiang and Zhopu can improve the commuting status of the whole city.
Meanwhile, the current employment posts are very centralized in the inner-ring core bands including the band of the mouth of the Lujia, the band of the Toyowa of Nanjing and the band of the West Lane of Nanjing, and the inner-ring core bands are the highest-level employment centers of the whole city. However, the results of the model calculations show that these regions do not have the need to further increase employment opportunities, as too many employment opportunities will attract residents in more distant regions to come into employment, resulting in a further increase in the average commuting distance across the city.
Further, based on the calculation results of the model, policy suggestions for employment position layout in Shanghai city can be made, as shown in Table 2. Among them, the areas Zhang Jiang-Chuan Sha and jin Qiao are areas that should be developed in the Shanghai in the future because they belong to the city depocenter, have more comprehensive functions and have large need for employment position increment from the calculation result. Secondly, the employment post increment requirements of south station-Jingjing and Luo shop-Gumural areas are large, the average commuting distance of residents nearby the areas is long, and therefore the commuting condition of residents in peripheral areas by employment posts is greatly improved.
Table 2: shanghai city employment post layout optimization suggestion
Therefore, the unit with the most shortened city-wide average distance is the best unit through calculation of the residual commuting model. In the traditional gravity model (i.e. global model) environment, it cannot be calculated which unit is shortened the most after the post is added.
The input display portion 17 is used to display a employment amount input screen at the time of system startup to let the analyst input the number of employment posts, and to display a result display screen and display resident commute data in the screen to let the analyst view when the commute data calculation acquisition portion 16 calculates the resident commute data.
In this embodiment, the employment quantity input screen may be an input box, and the result display screen may display a data distribution diagram as shown in fig. 6.
Fig. 7 is a flowchart of a communication data analysis process in the embodiment of the present invention.
As shown in fig. 7, when the analyst inputs the employment number and confirms the calculation in the employment number input screen displayed on the input display unit 17, the following procedure is started:
step T1, the signaling data analysis and acquisition part 13 analyzes the mobile phone signaling data to acquire user commuting data, and then step T2 is carried out;
step T2, the distribution weight calculation part 14 calculates the distribution weights of the mobile phone base station and the preset number of city space units around the mobile phone base station according to the base station position information of the mobile phone base station, and then the step T3 is carried out;
step T3, the commute data allocation section 15 allocates the user commute data obtained in step T1 to the city space unit according to the allocation weight obtained in step T2 to obtain unit commute data, and then proceeds to step T4;
step T4, the commuting data calculation and acquisition part 16 calculates the unit commuting data and the employment post number input by the analyst through a residual commuting model so as to acquire resident commuting data, and then the step T5 is carried out;
in step T5, the input display unit 17 displays the result display screen, displays the resident commute data calculated in step T4 on the screen for the analyst to view, and enters the end state.
In the communication data analysis process according to the present embodiment, the signaling data analysis acquisition unit 13, the assignment weight calculation unit 14, and the commute data assignment unit 15 sequentially perform calculation processing to obtain unit commute data. In another embodiment, the signaling data analyzing and acquiring unit 13, the assignment weight calculating unit 14, and the commuting data assigning unit 15 can also complete the calculation of the unit commuting data in advance, so that the resident commuting data can be calculated by the commuting data calculating and acquiring unit 16 directly after the analyst inputs the number of employment posts, thereby speeding up the calculation.
The urban commute data analysis system 100 is only one application layer of the model, and the set target is single (and commuting distance is shortened), and the simulation method is single (and employment posts are added). In practical planning applications, the faced scenario is more complex, and a specific simulation needs to be performed for a specific situation, so that the simulation result can better guide the planning practice.
Effects and effects of the embodiments
According to the method for establishing the commute model based on the mobile phone signaling data, the user commute data corresponding to each mobile phone base station is obtained through calculation according to the mobile phone signaling data, the distribution weight of each mobile phone base station and each urban space unit is obtained through calculation, the user commute data are uniformly distributed to each urban space unit to obtain the unit commute data corresponding to each urban space unit, the problem that each unit cannot be uniformly covered by urban traffic data adopted in urban planning is solved, and therefore a data source adopted in model establishment is optimized; and the mobile phone signaling data can be updated quickly, so that the real-time performance of the commuting model can be better optimized. Meanwhile, a unit commuting model is established on the basis of the traditional gravity model, and the problem that the traditional gravity model cannot analyze the direction of commuting is solved; furthermore, the residual error commuting model is obtained through calculation of residual error optimization, so that the fitting goodness of the model is further improved, and a plurality of factors which influence commuting but cannot be accurately obtained are brought into the model in a residual error variable mode, so that the model is higher in applicability, the prediction effect of the model is greatly improved, and the urban land layout is better guided.
In the embodiment, because the adjacent distance between each mobile phone base station and each corresponding peripheral space unit is calculated according to the base station position information and the unit position information, the maximum adjacent distance of each mobile phone base station is calculated as the bandwidth distance of the mobile phone base station, and the distribution weight between the mobile phone base station and the peripheral space unit is further calculated according to the bandwidth distance and the adjacent distance, the bandwidth distance can be dynamically calculated according to the number of units in the range of each base station, so that the problem that the coverage of the base station in a central city is too many and the coverage of the base station in a suburban area is too little can be effectively avoided, and the mobile phone base station data can be more accurately distributed to each urban space unit.
The above-described embodiments are merely illustrative of specific embodiments of the present invention, and the present invention is not limited to the description of the above-described embodiments.
Claims (7)
1. A commuting model establishing method based on mobile phone signaling data is used for establishing a commuting model of a city according to mobile phone signaling data collected by mobile phone base stations in the city, and is characterized by comprising the following steps:
step S1, acquiring the mobile phone signaling data and analyzing the mobile phone signaling data to obtain user commuting data including a departure place base station and a employment place base station of a user;
step S2, calculating the distribution weight of the mobile phone base station and a preset number of city space units around the mobile phone base station according to the base station position information of the mobile phone base station, wherein the city space units are street space units or living committee space units;
step S3, distributing the user commuting data to the urban space unit according to the distribution weight so as to obtain unit commuting data comprising a departure place unit and a employment place unit of the user, wherein the user commuting data are residence place base station data and employment place base station data;
s4, constructing a unit commute model, wherein the unit commute model is in the following form:
ln T ij ＝κ i +α i ln N j +β i ln d ij +ε ij (1)
in the formula, T ij For commuting amounts between city space units, N j The number of employment posts of the jth employment location unit, d ij For the commute cost, α, between the ith said origin unit and the jth said employment unit i 、β i The population number influence coefficient and employment position influence coefficient, kappa, of the ith departure place unit i Is a constant term of the ith said origin unit, epsilon ij The residual error between the ith departure place unit and the jth employment place unit is obtained;
step S5, calculating and obtaining a residual error { Rn, xn, yn } of the unit commuting model according to the commuting amount calculated by the unit commuting model and the actual commuting amount, wherein Rn represents an absolute value of the residual error corresponding to the nth city space unit, and Xn and Yn represent plane coordinates of the nth city space unit;
s6, clustering the residual errors { Rn, xn, yn } in a spatial clustering mode, classifying the residual errors according to a preset classification mode to obtain 4 clustering types, and further performing variable quantization processing on the 4 clustering types to generate residual error virtual variables;
and S7, substituting the residual virtual variable into the unit commuting model to obtain a residual commuting model, wherein the residual commuting model is in the following form:
ln T ij ＝κ i +α i ln N j +β i ln d ij +∑ k α k D_SE k +ε ij (2)
in the formula, D _ SE k Is the residual virtual variable corresponding to the cluster type of the kth class, k being taken to be [0,1,2,3]，D_SE k Is taken as value of [0,1]，α k Are the corresponding residual coefficients;
wherein, the step S2 comprises the following substeps:
s2-1, acquiring base station position information of the mobile phone base station and unit position information of the urban space unit, wherein the user commuting data are residential area base station data and employment area base station data;
s2-2, acquiring the city space units with the peripheral quantity being the preset quantity and the nearest distance for each mobile phone base station as the peripheral space units of each mobile phone base station;
s2-3, respectively calculating the adjacent distance between each mobile phone base station and each peripheral space unit corresponding to the mobile phone base station according to the base station position information and the unit position information;
s2-4, sequentially judging the largest value of all adjacent distances corresponding to each mobile phone base station as the maximum adjacent distance for each mobile phone base station, and further calculating and acquiring the bandwidth distance corresponding to the mobile phone base station according to the maximum adjacent distance;
s2-5, calculating the distribution weight of the mobile phone base station and the peripheral space unit according to the bandwidth distance and the adjacent distance, wherein the basic calculation method of the distribution weight comprises the following steps:
simultaneously, the following requirements are met:
in the formula (I), the compound is shown in the specification,
is the assigned weight of the cell phone base station with number i obtained by the committee space unit with number k, d (i)k Is the neighboring distance of the centroid of the base station i and the living committee unit k, theta is the bandwidth distance, the formula (4) ensures that the sum of the assigned weights calculated by the formula (3) is 1,
when the user commute data is distributed in the step S3, a specific formula algorithm is as follows:
and:
in the formula of lambda ij Is the commute amount from base station i to base station j, base station i and base station j are base stations in the vicinity of residence commission o and residence commission d, respectively,
is the origin, i.e., the weight of base station i obtained by the commuter's residence unit o,
is the weight, T, of the base station j obtained by the destination, i.e. the commuter's work location unit d od The amount of the commute from the departure place committee unit o to the destination committee unit d calculated from the weight, d (i)o Is the distance between base station i and the residence committee unit o, d (j)d Is the distance, θ, between the base station j and the residence committee unit d i And theta j The base station and the weight distribution bandwidth of the base station are respectively, and the formula (8) ensures that the sum of the calculated weights is 1.
2. The commute model building method based on handset signaling data according to claim 1, wherein:
wherein, the mobile phone signaling data comprises base station information and time information generated during mobile phone communication,
the step S1 includes the following substeps:
s1-1, acquiring the mobile phone signaling data;
s1-2, identifying a departure place base station and a employment place base station of the user according to the base station information and the time information;
and S1-3, generating the user commuting data according to the mobile phone signaling data, the departure place base station and the employment foundation station.
3. The commute model building method based on handset signaling data according to claim 1, wherein:
wherein the preset classification mode is to classify according to the first residual error and the second residual error,
the first residual is the residual of the city space unit, and the second residual is the residual of the city space unit around the city space unit corresponding to the first residual.
4. The commute model building method based on handset signaling data according to claim 1, wherein:
wherein the commute cost is a commute time or a commute distance.
5. The commute model building method based on handset signaling data according to claim 1, wherein:
wherein the predetermined number is 30.
6. The application of the residual commute model established by the commute model establishing method according to any one of claims 1 to 5 in a city commute data analysis system, for analyzing the mobile phone signaling data of a city based on the number of employment sites in the city preset by an analyst to obtain the resident commute data of the city, includes:
a commute model storage unit for storing the residual commute model;
a signaling data storage unit for storing the mobile phone signaling data acquired from each mobile phone base station in the city in advance;
the signaling data analysis and acquisition part is used for analyzing the mobile phone signaling data so as to acquire user commuting data comprising a departure place base station and a employment place base station of a user;
the distribution weight calculation part is used for calculating the distribution weights of the mobile phone base station and a preset number of city space units around the mobile phone base station according to the base station position information of the mobile phone base station;
a commute data allocation unit that allocates the user commute data to the city space unit according to the allocation weight to obtain unit commute data including a departure place unit and a employment place unit of the user;
a commute data calculation acquisition unit, through the residual commute model is right the unit commute data and the employment post quantity is calculated thereby to acquire the resident commute data.
7. The use of the residual commute model established by the commute model establishing method according to claim 6 in an urban commute data analysis system, wherein:
wherein the resident commute data is an average commute distance or an average commute time of the city.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910449958.1A CN110288125B (en) | 2019-05-28 | 2019-05-28 | Commuting model establishing method based on mobile phone signaling data and application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910449958.1A CN110288125B (en) | 2019-05-28 | 2019-05-28 | Commuting model establishing method based on mobile phone signaling data and application |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110288125A CN110288125A (en) | 2019-09-27 |
| CN110288125B true CN110288125B (en) | 2023-02-28 |
Family
ID=68002828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910449958.1A Active CN110288125B (en) | 2019-05-28 | 2019-05-28 | Commuting model establishing method based on mobile phone signaling data and application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288125B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111105130A (en) * | 2019-11-07 | 2020-05-05 | 同济大学 | Optimal employment post layout site selection decision-making system based on commuting model |
| CN114021800A (en) * | 2021-10-29 | 2022-02-08 | 南京大学 | Cumulative model employment reachability analysis method based on multi-source big data |
| CN114153899A (en) * | 2021-11-30 | 2022-03-08 | 南京大学 | Method and electronic equipment for acquiring employment posts of unit building area of different land types |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6584401B2 (en) * | 2001-11-27 | 2003-06-24 | Hewlett-Packard Development Company, Lp. | Automatic gathering and analysis of data on commute paths |
| CN102333274A (en) * | 2010-07-12 | 2012-01-25 | 同济大学 | Cell phone signal data based-method for processing commuting information and apparatus thereof |
| CN106897417B (en) * | 2017-02-22 | 2019-04-09 | 东南大学 | A kind of construction method of the city space holographic map based on the fusion of multi-source big data |
| CN107194525A (en) * | 2017-03-23 | 2017-09-22 | 同济大学 | A kind of down town appraisal procedure based on mobile phone signaling |
| CN107305590B (en) * | 2017-06-14 | 2020-11-10 | 北京市交通信息中心 | Urban traffic trip characteristic determination method based on mobile phone signaling data |
| CN109743723B (en) * | 2019-01-28 | 2021-07-06 | 同济大学 | Method for distributing mobile phone base station data to peripheral space units |
-
2019
- 2019-05-28 CN CN201910449958.1A patent/CN110288125B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110288125A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288125B (en) | Commuting model establishing method based on mobile phone signaling data and application | |
| CN110309952B (en) | City employment spatial layout optimization auxiliary system based on commuting model | |
| CN109978224B (en) | Method for analyzing and acquiring traffic trip rates of buildings with different properties | |
| CN106503843A (en) | A kind of regular public traffic line network optimization and method of adjustment based on mobile phone signaling data | |
| CN111784830B (en) | Rule-based three-dimensional geographic information model space analysis method and system | |
| Li et al. | Explore the recreational service of large urban parks and its influential factors in city clusters–Experiments from 11 cities in the Beijing-Tianjin-Hebei region | |
| CN108495254B (en) | Traffic cell population characteristic estimation method based on signaling data | |
| CN113657688B (en) | Simulation measurement method for community life circle | |
| CN109509351B (en) | Method for calculating bus sharing rate in areas around bus stop | |
| CN113642928B (en) | Planning simulation measurement and evaluation method applied to city updating community life circle | |
| Dong et al. | Spatial autocorrelation and spatial heterogeneity of underground parking space development in Chinese megacities based on multisource open data | |
| Jin et al. | Urban travel demand analysis for Austin TX USA using location-based social networking data | |
| CN114662774A (en) | City block vitality prediction method, storage medium and terminal | |
| CN114037239A (en) | Potential model employment reachability analysis method based on multi-source big data | |
| CN112949997A (en) | System and method for community portrayal in urban planning design | |
| CN113344370A (en) | Emergency unit division method and device based on urban road network and regional function | |
| CN116796904A (en) | Method, system, electronic equipment and medium for predicting new line passenger flow of rail transit | |
| JP2023155476A (en) | Information processing system, information processing apparatus, information processing method, and information processing program | |
| CN115600855A (en) | GIS-based urban planning land intensity partitioning method, system and storage medium | |
| CN109743723B (en) | Method for distributing mobile phone base station data to peripheral space units | |
| Song et al. | Effects of planning variables on urban traffic noise at different scales | |
| Lin et al. | Passenger flow scale prediction of urban rail transit stations based on multilayer perceptron (mlp) | |
| Dogaroglu et al. | Investigation of car park preference by intelligent system guidance | |
| CN116957280A (en) | Mountain village and town community life circle public service facility configuration method based on supply and demand balance | |
| CN116307927A (en) | Life circle planning rationality evaluation method and system based on people stream prediction |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |