CN113408833A - Public traffic key area identification method and device and electronic equipment - Google Patents
Public traffic key area identification method and device and electronic equipment Download PDFInfo
- Publication number
- CN113408833A CN113408833A CN202110955708.2A CN202110955708A CN113408833A CN 113408833 A CN113408833 A CN 113408833A CN 202110955708 A CN202110955708 A CN 202110955708A CN 113408833 A CN113408833 A CN 113408833A
- Authority
- CN
- China
- Prior art keywords
- travel
- index
- information
- area
- indexes
- 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 28
- 238000012546 transfer Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 claims description 5
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 4
- 238000012417 linear regression Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000002790 cross-validation Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000011664 signaling Effects 0.000 description 3
- 230000029305 taxis Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000002035 prolonged effect Effects 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"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G06Q50/40—
Abstract
The invention relates to the technical field of traffic analysis, in particular to a public traffic key area identification method and device and electronic equipment. The identification method comprises the steps of acquiring travel chain information collected in a passenger flow gathering area; classifying and extracting travel information in the travel chain information according to different travel modes to obtain travel indexes of the travel modes; acquiring weighted values of all the travel indexes, and carrying out weighted summation on the travel indexes of all the travel modes based on the weighted values to obtain a comprehensive travel index; and when the comprehensive travel index is larger than a set value, the passenger flow gathering area is regarded as a key area. Therefore, the convenient degree of public transportation in the passenger flow gathering area can be reflected at a plurality of angles through the comprehensive travel index, the identification of the public transportation state in the area with high travel demand is realized, and compared with the mode that the convenient condition of public transportation is reflected only through the congestion degree of the public transportation line in the prior art, the convenient condition of public transportation in the area is reflected more accurately.
Description
Technical Field
The invention relates to the technical field of traffic analysis, in particular to a public traffic key area identification method and device and electronic equipment.
Background
With the increasing development scale of cities, urban bus routes need to be reasonably planned to increase the convenience of people going out. Therefore, the traffic running state of the city needs to be evaluated so as to plan and adjust the bus route. However, in the prior art, the evaluation of the bus lines is often only directed at the running state of a certain bus line, and it is difficult to reflect the bus state of the area with high traffic demand.
Disclosure of Invention
The problem solved by the invention is how to identify the traffic state of the high-traffic demand area.
In order to solve the above problems, the present invention provides a method for identifying a key area of public transportation, comprising: acquiring travel chain information acquired in a passenger flow gathering area, wherein the travel chain information comprises travel information of multiple travel modes; classifying and extracting the travel information in the travel chain information according to different travel modes to obtain travel indexes of the travel modes; acquiring weighted values of all the travel indexes, and carrying out weighted summation on the travel indexes of all the travel modes based on the weighted values to obtain a comprehensive travel index; and when the comprehensive travel index meets a preset condition, the passenger flow gathering area is determined as a key area.
Optionally, the acquiring the travel chain information collected in the passenger flow gathering area includes: acquiring total travel demand information and building position information in a set area; obtaining the demand of a single building according to the total travel demand information and the building position information; obtaining a building group with passenger flow aggregation through a hierarchical clustering algorithm by taking a single building as a sample and building longitude and latitude as clustering characteristics; and taking the building group with the passenger flow gathering as the passenger flow gathering area.
Optionally, the acquiring the travel chain information collected in the passenger flow gathering area further includes: acquiring demand information in demand information of a building in the passenger flow aggregated building group, wherein the demand information comprises travel track data and a travel mode; obtaining a travel destination according to the distribution situation of the locus points in the travel locus data; obtaining an OD position by taking the position of the building as a starting position and the travel destination as an end position; and collecting the OD position and the travel mode to obtain the travel chain information.
Optionally, the classifying and extracting the travel information in the travel chain information according to different travel modes, and obtaining the travel indexes of each travel mode includes: obtaining the OD position of the trip chain information; carrying out bus net navigation on the OD position to obtain transfer times, walking distance and bus travel time; and taking the transfer times, the walking distance and the bus travel time as the travel indexes.
Optionally, the travel information in the travel chain information is classified and extracted according to different travel modes, and obtaining the travel indexes of each travel mode further includes: driving and navigating the OD position to obtain driving travel time, and obtaining a bus/driving time consumption ratio according to the driving travel time and the bus time; and taking the bus/driving time consumption ratio as the travel index.
Optionally, the obtaining the weight values of all the travel indicators includes: obtaining a self-adaptive updating model, an initial index weight value and a corrected comprehensive travel index; inputting the initial index weight value into the self-adaptive updating model, and training the initial index weight value by taking the corrected comprehensive travel index as an output variable of the self-adaptive updating model; and taking the trained initial index weight value as the weight value.
Optionally, the adaptively updated model is a linear regression model.
Optionally, the obtaining the weight values of all the trip indexes, and performing weighted summation on the trip indexes of each trip mode based on the weight values to obtain a comprehensive trip index includes: determining the comprehensive travel index based on the weight values and the travel indexes of the travel modes according to the following formula:
wherein, zone score The comprehensive trip index is shown, i is a trip index category; wiThe weight value of the ith travel index; valueiIs the ith travel index.
Compared with the prior art, the method for identifying the key areas of the public transport has the beneficial effects that:
according to the method, the travel chain information collected in the passenger flow gathering area is obtained, so that all the travel chain information in the area is prevented from being obtained, and the difficulty in extracting the travel chain information in the area is reduced; the public transportation convenience degree of the passenger flow gathering area can be comprehensively reflected in multiple angles through the comprehensive travel index, the identification of the public transportation state of the area with high travel demand is realized, and compared with the mode that the traffic convenience condition is reflected only through the congestion degree of the public transportation line in the prior art, the reflection of the public transportation convenience condition in the area is more accurate; and when the comprehensive travel index is larger than a set value, the passenger flow gathering area is identified as a key area, so that the passenger flow gathering area with low traffic convenience can be identified, and an accurate place is provided for bus network optimization.
The invention also provides a device for identifying the key areas of public transportation, which comprises: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring travel chain information acquired in a passenger flow gathering area and weight values of all travel indexes, and the travel chain information comprises travel information of various travel modes; the analysis module is used for classifying and extracting the travel information in the travel chain information according to different travel modes to obtain travel indexes of the travel modes; the determining module is used for carrying out weighted summation on the travel indexes of the travel modes based on the weight values to obtain a comprehensive travel index; and the judging module is used for determining the set area as a key area when the comprehensive travel index meets the preset condition. The identification device of the key public transport areas has the beneficial effects of the identification method of the key public transport areas, and the details are not repeated herein.
The invention also provides an electronic device comprising a computer-readable storage medium storing a computer program and a processor, wherein when the computer program is solely fetched and run by the processor, the method for identifying the key areas of public transportation is realized. The electronic equipment has the beneficial effects of the identification of the key public traffic areas, and the details are not repeated herein.
Drawings
Fig. 1 is a flow chart of a public transportation key area identification method in the embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
In the description herein, references to the terms "an embodiment," "one embodiment," and "one implementation," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or implementation is included in at least one embodiment or example implementation of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or implementation. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or implementations.
An embodiment of the present invention provides a method for identifying a public transportation key area, as shown in fig. 1, including the following steps:
s1, acquiring travel chain information collected in the passenger flow gathering area, wherein the travel chain information comprises travel information of various travel modes;
s2, classifying and extracting the travel information in the travel chain information according to different travel modes to obtain travel indexes of the travel modes;
s3, obtaining the weight values of all the trip indexes, and carrying out weighted summation on the trip indexes of each trip mode based on the weight values to obtain a comprehensive trip index;
and S4, when the comprehensive travel index meets a preset condition, identifying the passenger flow gathering area as a key area.
Specifically, in S1, the passenger flow gathering area refers to an area with high occurrence or absorption of passenger flow, and the travel chain information refers to a user completing a travel process from a starting point to a destination within a certain time range by using one or more travel modes, where the travel modes include at least one of bus travel, subway travel, taxi travel, shared bicycle travel, or net appointment travel. In this embodiment, the acquisition source of the travel chain information may be different according to the travel mode, for example, in some embodiments, the resident may choose to drive to travel, and in this case, the travel chain information may be derived from a vehicle data recorder or a GPS navigator or the like installed on the vehicle.
In this embodiment, a city may be divided into a plurality of parcel areas, each parcel area is taken as a unit, trip chain information in each parcel area is collected, the trip chain information may be obtained through mobile phone signaling data, bus card swiping data, trip navigation data, shared bicycle trip data or taxi taking data and the like, a total trip demand of each parcel area may be obtained by calculating the mobile phone signaling data, the bus card swiping data, the trip navigation data, the shared bicycle trip data or the taxi taking data, and an area with a higher total trip demand is taken as the passenger flow gathering area. In other embodiments, the passenger flow gathering area may be obtained by a traffic database or by identifying satellite images. Therefore, the difficulty in extracting the travel chain information in the block can be reduced by acquiring the travel chain information in the passenger flow gathering area.
Optionally, the acquiring the collected travel chain information in the passenger flow gathering area includes: acquiring total travel demand and building position information in a set area; obtaining the demand of a single building according to the travel demand and the building position information; obtaining a building group with passenger flow aggregation through a hierarchical clustering algorithm by taking a single building as a sample and building longitude and latitude as clustering characteristics; and taking the building group with the passenger flow gathering as the passenger flow gathering area.
Specifically, in the step of acquiring the total travel demand and the building location information within the set area, the set area refers to a section in which the city is divided into any one of a plurality of sections. The total travel demand includes an area travel occurrence amount and an area travel attraction amount. The region trip occurrence amount refers to the sum of the demands for trip from the region to other regions. The area travel attraction amount refers to the sum of the demand amounts of traveling to the area from other areas. The sum of the demand amounts can be obtained by calculating mobile phone signaling data, bus card swiping data, travel navigation data, shared bicycle travel data or taxi taking data. The building position information can be obtained by identifying the satellite images or by obtaining the building position information through a preset database. The building location information includes location, type and development amount information of the building.
And in the step of obtaining the demand of a single building according to the total travel demand and the building position information, respectively distributing the total travel demand to the single building according to the type information of the building. Taking the occurrence amount of regional trips as an example, in the same type of buildings, the distribution of the number of passengers in the occurrence amount of regional trips in each building is in a positive correlation with the building development amount. Here, the regional trip occurrence amount is the caliber, and can be distributed to each building according to the equal ratio of the building development amount. Specifically, the demand of the single building can be obtained by equation (1).
In the formula (I), the compound is shown in the specification,
for a single buildingThe required amount of (c);
for the total demand in a sector,
in order to be developed for a single building,
the total development amount of the building in the plot area.
In other embodiments, the regional travel attraction amount can be used as the caliber, and the regional travel attraction amount can be distributed to each building according to the equal ratio of the building development amount to obtain the demand of each building. Thus, the accuracy of identifying the district travel demand can be improved by dividing the total demand into the district travel occurrence amount and the district travel attraction amount.
In the step of obtaining the building group with the aggregated passenger flow by using the demand of a single building as a sample and the longitude and latitude of the building as clustering characteristics through a hierarchical clustering algorithm, the demand of the single building as the sample can include the total travel demand of the single building, the travel occurrence of the single building or the regional travel attraction of the single building. The building longitude and latitude can be identified and obtained through satellite images or obtained through obtaining preset database information. And taking the demand of a single building as a sample, taking the demands of all buildings as a sample set, and taking the sample set and the cluster number as input into the hierarchical clustering algorithm to obtain a building group with aggregated passenger flows. For example, all samples in the sample set are classified into a cluster c, the distance between every two samples is calculated in the same cluster c, and a distance discriminant is set to discriminate the distance between the samples to find an inter-cluster average distance sample a and an inter-cluster closest distance sample b; respectively distributing the samples a and b to two different clusters (c 1, c 2), calculating the distance between the other sample points and the samples a and b in the original cluster c, setting a distance threshold, and if the distance between the other sample points and the samples a and b meets the set distance threshold, classifying the sample points into a new cluster to realize the clustering of the samples. The distance threshold is between 300m and 600m, and specifically, the distance threshold may be: 300m, 400m, 500m or 600 m.
Therefore, by taking a single building as a sample and building longitude and latitude as clustering characteristics and obtaining a building group with passenger flow aggregation through a hierarchical clustering algorithm, the precision of analysis of the demand can reach the building level, so that the precision of identification of a traffic key area is improved, the follow-up optimization of buses in the area is more targeted, and the efficiency is improved.
Optionally, the obtaining of the building group with aggregated passenger flows through a hierarchical clustering algorithm further includes setting an evaluation equation as a clustering evaluation index, where the evaluation equation is:
metrics=
；(2)
in the formula, i is one of all clustered clusters;
is the total demand of the ith cluster;
: is the total development amount of the ith cluster.
Therefore, the sample clusters output by the hierarchical clustering algorithm are evaluated by setting the evaluation equation, and each clustered cluster can meet a certain travel demand.
Optionally, the obtaining of the building group with passenger flow aggregation through the hierarchical clustering algorithm further includes iteratively solving an optimal clustering hierarchical algorithm parameter by using a grid cross validation algorithm. The grid cross validation algorithm means that in all candidate parameter selections, each possibility is tried through loop traversal, and the best-performing parameter is the final result. For example, in the hierarchical clustering algorithm, if there are 4 kinds of parameters for the clustering threshold and 3 kinds of parameters for the distance discrimination parameter, all the clustering thresholds and the distance discrimination parameters are listed, and can be represented as a 3 × 4 table, and each grid in the table is traversed and searched to obtain the optimal parameter. Therefore, the hierarchical clustering algorithm can be optimized through the setting of the network cross validation algorithm, and the adaptability of the hierarchical clustering algorithm is improved.
Optionally, the acquiring the travel chain information collected in the passenger flow gathering area further includes:
the method comprises the steps of obtaining demand information in demand information of a building in a building group with passenger flow gathering, wherein the demand information is obtained from a resident mobile terminal (such as a mobile phone), the demand information comprises travel track data and a travel mode, the track data can be obtained from GPS data of the mobile terminal, the travel mode can be obtained according to nfc card swiping information or APP information of the mobile terminal, and for example, in the traveling of the resident, when the travel mode needs to be changed into a shared bicycle, the travel information can be obtained by obtaining travel data of the shared bicycle APP. And obtaining the activity place where the residents stay for a long time according to the distribution condition of the locus points in the travel locus data, obtaining the OD position by taking the position of the building as a starting point and the activity place where the residents stay for a long time as a terminal point, and collecting the OD position and the travel mode to obtain the travel chain information. In some other embodiments, the trip chain information may be a set of information about the trip behavior of the resident, for example, the trip chain information may further include a trip time and a trip distance.
Specifically, in S2, the travel information in the travel chain information is classified and extracted according to different travel modes, so as to obtain travel indexes of the travel modes. The trip characteristic of the trip chain information can be captured and extracted by adopting a preset trip characteristic selection model to obtain the travel information of different trip modes. For example, in a travel chain, residents walk from a residence to a bus stop, transfer from the bus stop to a subway station, and ride a shared bicycle to a destination after coming out of the subway station. The travel chain information is subjected to feature extraction through a travel feature extraction model, so that travel indexes such as OD positions (namely starting point positions and end point positions) of resident travel, bus travel time of a bus travel mode, walking time and walking distance of a whole trip, subway travel time of a subway travel mode, shared bicycle riding time of a shared bicycle travel mode, and shared bicycle riding distance can be obtained. The travel information in the travel chain information is classified and extracted according to different travel modes, the travel indexes of various travel modes can be effectively obtained, and the traffic operation condition of the area can be known by analyzing the travel indexes. For example, in an implementation mode, the travel time and the travel distance of the bus can be acquired, and the bus travel convenience degree of residents in the area can be reflected by taking the ratio of the travel distance to the travel time as a travel index.
Optionally, the travel index includes: at least one of walking distance, bus trip time, bus/driving time consumption ratio, detour times, transfer times, shared single-car running amount larger than 1km, taxi running amount smaller than 5km or citizen complaint amount.
Specifically, the transfer times refer to the times of transfer from a trip to a destination, and the transfer includes the times of transferring buses to buses or transferring buses to subways. The walking distance refers to a walking distance required from a trip to a destination. The bus/driving time consumption ratio refers to the ratio of the time required for traveling by a bus or a subway to the time required for driving a trolley from a starting point to a destination. The number of times of the detour refers to an actual travel distance of the OD position and a straight line distance of the OD position in one trip, where the OD position refers to a start position and a target position. The travel amount of the shared bicycle more than 1km means that the travel amount of the shared bicycle is more than 1km when the shared bicycle is ridden from a trip to a destination. The taxi running amount less than 5km means that the taxi running amount is more than 1km from the trip to the destination. The complaint volume refers to a given poor rating in each mode of travel. For example, the complaint amount can be obtained by obtaining travel evaluation information on the mobile phone APP. Therefore, the travel indexes of different travel modes are obtained, the travel indexes of different travel modes integrally reflect the travel convenience degree of the passenger flow gathering area, and compared with the mode of reflecting the traffic convenience condition only through the congestion degree of the bus route, the method is more accurate.
Optionally, the travel index further includes a total travel volume and a poor-service travel volume in the passenger flow gathering area. The total trip amount is the sum of all the trip chains, and the out-of-service trip amount is the sum of the number of the trip chains with transfer times exceeding 1, detour times exceeding 1.6 and walking distance exceeding 1 km.
Optionally, the classifying and extracting the travel information in the travel chain information according to different travel modes, and obtaining the travel indexes of each travel mode includes: obtaining an OD position in a trip chain; and carrying out bus net navigation on the OD position to obtain transfer times, walking distance and bus travel time, and taking the transfer times, the walking distance and the bus travel time as the travel indexes.
Specifically, the OD position refers to a starting point position and a destination point position of a trip, the OD position is input to the public traffic network navigation system for navigation, and information of a public traffic navigation route is extracted to obtain: the number of transfers from the origin to the destination, the walking distance and the bus travel time. For example, in a piece of travel chain information, a user starts from a residence place to sit on a bus, but sits at a station on the bus due to the fact that the user is too tired, and then returns to a destination through sitting on the bus, so that travel distance and travel time are prolonged.
Therefore, by extracting the OD position from the travel chain information and inputting the OD position into the bus net navigation system for navigation, the actual travel track of the bus net can be obtained, the increase of transfer times or the extension of travel time caused by factors such as taking wrong cars, sitting at a station and the like is prevented, the fault-tolerant rate is improved, and the identification accuracy of the convenient degree of the local buses is improved.
Optionally, after the taking the transfer times, the walking distance and the bus travel time as the travel indexes, the method further includes: and driving and navigating the OD position to obtain driving travel time, and obtaining the bus/driving time consumption ratio according to the driving travel time and the bus travel time. In this embodiment, the OD position is input to the car driving navigation system for navigation, and the travel distance and the car travel time for driving travel can be obtained by extracting information of the car driving navigation route, and then the ratio of the bus travel time to the car travel time is taken as the travel index. For example, in a piece of travel chain information, the travel time of bus travel can be obtained by navigating the OD position through a bus navigation system for 30min, the travel time of bus travel can be obtained by navigating the OD position through a car driving navigation system for 20min, and the bus/driving time consumption ratio is 1.5 at this time.
Therefore, by driving and navigating the OD position, the travel time of the car can be obtained, the bus/driving time consumption ratio can be obtained according to the driving travel time and the bus travel time, the actual detour distance of the bus route can be accurately reflected through the bus/driving time consumption ratio, and the identification accuracy of the convenient degree of the regional bus is improved.
Optionally, the travel information in the travel chain information is classified and extracted according to different travel modes, and obtaining the travel indexes of each travel mode further includes: extracting travel information of the obtained taxi and/or the shared bicycle in the trip chain information; and analyzing the travel information of the taxi and/or the shared bicycle to obtain the travel amount of the shared bicycle greater than the travel distance of 1km and/or the travel amount of the taxi less than the travel distance of 5 km. Specifically, shared bicycle travel information in travel chain information is acquired, real-time GPS data of a shared bicycle is acquired, travel information of the shared bicycle is restored, travel information of the shared bicycle is analyzed, shared bicycle travel amount in a passenger flow gathering area can be obtained, shared bicycle travel amount with shared bicycle travel range larger than 1Km is extracted, and shared bicycle travel amount travel index larger than 1Km can be obtained. The method comprises the steps of acquiring taxi journey information in trip chain information, acquiring real-time GPS data of taxis, restoring trip information of the taxis, analyzing the trip information of the taxis to obtain taxi journey amount in a passenger flow gathering area, extracting taxi journey amount with taxi journey distance larger than 5Km to obtain taxi journey amount journey indexes with taxi journey distance larger than 5 Km.
Therefore, the shared single-vehicle travel amount larger than the travel distance of 1km and/or the travel amount of the taxi smaller than the travel distance of 5km are/is used as travel indexes, the travel demand of the part can be used as the competition demand of the public transport or the subway, on one hand, the identification accuracy of the convenient degree of the public transport in the passenger flow gathering area can be improved, on the other hand, a public transport network can be developed to replace the shared single-vehicle travel amount larger than the travel distance of 1km and/or the travel demand of the taxi smaller than the travel distance of 5km, and the direction can be provided for optimizing the public transport network in the passenger flow gathering area.
Specifically, in S3, weight values of all the travel indexes are obtained, and the travel indexes of the respective travel modes are weighted and summed based on the weight values to obtain a comprehensive travel index. Specifically, the travel indexes include total travel volume in the passenger flow gathering area, travel volume with poor service in a parcel, travel time consumption ratio, transfer times, detour coefficients, walking distance, travel volume of bicycles larger than 1km, travel volume of taxies smaller than 5km and complaint number. The weighted value is obtained according to the influence degree of different indexes on the traffic convenience of the passenger flow gathering area. For example, in one embodiment, the weight value of the total trip amount is 1.35, the weight value of the area under-service trip amount is 1.87, the weight value of the travel time consumption ratio is 1.01, the weight value of the transfer times is 1.20, the weight value of the detour coefficient is 0.84, the weight value of the walking distance is 0.99, the weight value of the greater-than-1 km bicycle trip amount is 0.81, the weight value of the less-than-5 km taxi trip amount is 0.66, and the weight value of the complaint number is 0.59. And according to the weight values of the different travel indexes, carrying out weighted summation on the different travel indexes to obtain the comprehensive travel index. Therefore, through the setting of the weight value, the comprehensive travel index can be determined according to the weight value and different travel indexes.
Optionally, the obtaining of the weight value of the travel index of each travel mode, and performing weighted summation processing on the travel index of each travel mode based on the weight value to obtain a comprehensive travel index includes: determining the comprehensive travel index according to the formula (3) based on the travel indexes of the travel modes of the weight values:
wherein, zone score The comprehensive trip index is shown, i is a trip index category; wiThe weight value of the ith travel index; valueiIs the ith travel index.
Optionally, obtaining the weight values of all the trip indexes, and performing weighted summation on the trip indexes of each trip mode based on the weight values to obtain a comprehensive trip index includes: obtaining a self-adaptive updating model; inputting the initial index weight value into the self-adaptive updating model, and training the initial index weight value by taking the corrected comprehensive travel index as an output variable of the self-adaptive updating model; and taking the trained initial index weight value as the weight value. Specifically, the comprehensive correction index is determined by the coincidence degree of the comprehensive travel indexes of different passenger flow gathering areas in the same city and the actual public transportation convenience degree. Or the corrected comprehensive travel index can be determined by means of expert correction. In the present embodiment, all the travel indexes are subjected to equal weighting processing before summation, that is, the initial weighting values of all the travel indexes are equal. In this embodiment, the weight values are trained periodically, and the travel index is summed up with the trained weight values to update the comprehensive travel index periodically.
Optionally, the adaptive update model is:
in the formula, i is the index type, value is the index value,
in order to correct the comprehensive travel index,
is an index weight value. In other embodiments, the adaptively updated model may also be a linear regression model.
Therefore, the weight value is adaptively updated through the adaptive updating model, so that the weight value can be optimized, and the comprehensive travel index is more in line with the actual bus travel convenience degree.
Specifically, in S4, the passenger flow gathering area is determined as a key area when the comprehensive travel index satisfies a preset condition. For example, the preset condition may be a set value, and the passenger flow gathering area is determined as a key area when the comprehensive travel index is greater than the set value, and the set value may be determined by a total required travel amount of the passenger flow gathering area. For example, in one embodiment, when the total demand in the passenger flow gathering area is 2 ten thousand, the set value is between 18 ten thousand and 30 ten thousand, and specifically, the set value may be 18 ten thousand, 20 ten thousand, 23 ten thousand, 25 ten thousand, or 30 ten thousand.
The method has the advantages that the trip chain information in the passenger flow gathering area is obtained, so that the condition that all trip chain information in the area is obtained is avoided, and the difficulty in extracting the trip chain information in the area is reduced; through the comprehensive travel index can be from a plurality of angles comprehensive reflection the convenient degree of public transport in passenger flow gathering area has realized the discernment to the public transit state in high-out demand region, compares with the mode that the convenient condition of public transport was reflected only through the degree of blocking up of bus route among the prior art, and is more accurate to the reflection of the convenient condition of public transport in the region, through when the comprehensive travel index is greater than the setting value with the regional discernment of passenger flow gathering is key region, can realize discerning the passenger flow gathering area that the convenient degree of traffic is low, provides accurate place for public transport network optimization.
Another embodiment of the present invention provides a public transportation key area recognition apparatus, including:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring trip chain information of various trip modes and weight values of all trip indexes, which are acquired in a passenger flow gathering area, wherein the trip chain information comprises travel information of various trip modes;
the analysis module is used for classifying and extracting the travel information in the travel chain information according to different travel modes to obtain travel indexes of the travel modes;
the determining module is used for carrying out weighted summation on the travel indexes of the travel modes based on the weight values to obtain a comprehensive travel index;
and the judging module is used for determining the set area as a key area when the comprehensive travel index meets the preset condition.
Another embodiment of the present invention provides an electronic device including a computer-readable storage medium storing a computer program and a processor, which when the computer program is exclusively fetched by the processor and executed, implements the public transportation key area identification method as described above.
Although the present disclosure has been described above, the scope of the present disclosure is not limited thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present disclosure, and these changes and modifications are intended to be within the scope of the present disclosure.
Claims (10)
1. A public transportation key area identification method is characterized by comprising the following steps:
acquiring travel chain information acquired in a passenger flow gathering area, wherein the travel chain information comprises travel information of multiple travel modes;
classifying and extracting the travel information in the travel chain information according to different travel modes to obtain travel indexes of the travel modes;
acquiring weighted values of all the travel indexes, and carrying out weighted summation on the travel indexes of all the travel modes based on the weighted values to obtain a comprehensive travel index;
and when the comprehensive travel index meets a preset condition, the passenger flow gathering area is determined as a public transport key area.
2. The method for identifying key areas of public transportation according to claim 1, wherein the acquiring of the travel chain information collected in the passenger flow gathering area comprises:
acquiring total travel demand information and building position information in a set area;
obtaining the demand of a single building according to the total travel demand information and the building position information;
obtaining a building group with passenger flow aggregation through a hierarchical clustering algorithm by taking a single building as a sample and building longitude and latitude as clustering characteristics;
and taking the building group with the passenger flow gathering as the passenger flow gathering area.
3. The method for identifying key areas of public transportation according to claim 2, wherein the acquiring the travel chain information collected in the passenger flow gathering area further comprises:
acquiring demand information in demand information of a building in the passenger flow aggregated building group, wherein the demand information comprises travel track data and a travel mode;
obtaining a travel destination according to the distribution situation of the locus points in the travel locus data;
obtaining an OD position by taking the position of the building as a starting position and the travel destination as an end position;
and collecting the OD position and the travel mode to obtain the travel chain information.
4. The method for identifying key areas of public transportation according to claim 3, wherein the step of classifying and extracting the travel information in the travel chain information according to different travel modes to obtain travel indexes of each travel mode comprises:
obtaining the OD position of the trip chain information;
carrying out bus net navigation on the OD position to obtain transfer times, walking distance and bus travel time;
and taking the transfer times, the walking distance and the bus travel time as the travel indexes.
5. The method for identifying key areas of public transportation according to claim 4, wherein the step of classifying and extracting the travel information in the travel chain information according to different travel modes to obtain travel indexes of each travel mode further comprises:
driving and navigating the OD position to obtain driving travel time;
obtaining a bus/driving time consumption ratio according to the driving travel time and the bus time;
and taking the bus/driving time consumption ratio as the travel index.
6. The method for identifying key areas of public transportation according to claim 1, wherein the obtaining of the weight values of all the travel indicators comprises:
obtaining a self-adaptive updating model, an initial index weight value and a corrected comprehensive travel index;
inputting the initial index weight value into the self-adaptive updating model, and training the initial index weight value by taking the corrected comprehensive travel index as an output variable of the self-adaptive updating model;
and taking the trained initial index weight value as the weight value.
7. The mass transit key region identification method of claim 6, wherein the adaptively updated model is a linear regression model.
8. The method for identifying key areas of public transportation according to claim 1, wherein the obtaining of the comprehensive travel index by performing weighted summation on the travel indexes of the travel modes based on the weight values comprises:
determining the comprehensive travel index according to the following formula:
wherein, zone score The comprehensive trip index is shown, i is a trip index category; wiThe weight value of the ith travel index; valueiIs the ith travel index.
9. A public transportation key area recognition device, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring travel chain information and weight values of all travel indexes collected in a passenger flow gathering area, and the travel chain information comprises travel information of various travel modes;
the analysis module is used for classifying and extracting the travel information in the travel chain information according to different travel modes to obtain travel indexes of the travel modes;
the determining module is used for carrying out weighted summation on the travel indexes of the travel modes based on the weight values to obtain a comprehensive travel index;
and the judging module is used for determining the set area as a public transport key area when the comprehensive travel index meets the preset condition.
10. An electronic device, comprising a computer-readable storage medium storing a computer program and a processor, wherein the computer program, when executed by the processor, implements the mass transit focal area identifying method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110955708.2A CN113408833A (en) | 2021-08-19 | 2021-08-19 | Public traffic key area identification method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110955708.2A CN113408833A (en) | 2021-08-19 | 2021-08-19 | Public traffic key area identification method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113408833A true CN113408833A (en) | 2021-09-17 |
Family
ID=77688930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110955708.2A Pending CN113408833A (en) | 2021-08-19 | 2021-08-19 | Public traffic key area identification method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408833A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115100858A (en) * | 2022-06-20 | 2022-09-23 | 上海海事大学 | Method and system for identifying travel modes of shared bicycle and private bicycle |
| CN115810271A (en) * | 2023-02-07 | 2023-03-17 | 安徽交欣科技股份有限公司 | Method for judging passenger flow corridor position based on card swiping data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130262222A1 (en) * | 2012-03-30 | 2013-10-03 | Xerox Corporation | Customer metrics driven traveler information system for multimodal public transporation systems |
| CN107133743A (en) * | 2017-05-19 | 2017-09-05 | 重庆文理学院 | A kind of appraisal procedure of small micro- enterprise operation project |
| CN112116124A (en) * | 2020-08-07 | 2020-12-22 | 北京工业大学 | Auditing method of bus network optimization scheme based on traveler visual angle |
| CN112132236A (en) * | 2020-11-20 | 2020-12-25 | 深圳市城市交通规划设计研究中心股份有限公司 | Demand subarea dividing and line planning method and device based on clustering algorithm |
| CN112183891A (en) * | 2020-10-28 | 2021-01-05 | 福州大学 | Bus stop point recommendation method for bus stop based on complex network |
| CN112579915A (en) * | 2021-02-26 | 2021-03-30 | 深圳市城市交通规划设计研究中心股份有限公司 | Analysis method and device for trip chain |
| CN113255979A (en) * | 2021-05-17 | 2021-08-13 | 上海旷途科技有限公司 | Method and device for identifying vulnerability of urban public transport network, computer equipment and storage medium |
-
2021
- 2021-08-19 CN CN202110955708.2A patent/CN113408833A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130262222A1 (en) * | 2012-03-30 | 2013-10-03 | Xerox Corporation | Customer metrics driven traveler information system for multimodal public transporation systems |
| CN107133743A (en) * | 2017-05-19 | 2017-09-05 | 重庆文理学院 | A kind of appraisal procedure of small micro- enterprise operation project |
| CN112116124A (en) * | 2020-08-07 | 2020-12-22 | 北京工业大学 | Auditing method of bus network optimization scheme based on traveler visual angle |
| CN112183891A (en) * | 2020-10-28 | 2021-01-05 | 福州大学 | Bus stop point recommendation method for bus stop based on complex network |
| CN112132236A (en) * | 2020-11-20 | 2020-12-25 | 深圳市城市交通规划设计研究中心股份有限公司 | Demand subarea dividing and line planning method and device based on clustering algorithm |
| CN112579915A (en) * | 2021-02-26 | 2021-03-30 | 深圳市城市交通规划设计研究中心股份有限公司 | Analysis method and device for trip chain |
| CN113255979A (en) * | 2021-05-17 | 2021-08-13 | 上海旷途科技有限公司 | Method and device for identifying vulnerability of urban public transport network, computer equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115100858A (en) * | 2022-06-20 | 2022-09-23 | 上海海事大学 | Method and system for identifying travel modes of shared bicycle and private bicycle |
| CN115810271A (en) * | 2023-02-07 | 2023-03-17 | 安徽交欣科技股份有限公司 | Method for judging passenger flow corridor position based on card swiping data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Perrine et al. | Anticipating long-distance travel shifts due to self-driving vehicles | |
| CN112700072B (en) | Traffic condition prediction method, electronic device, and storage medium | |
| CN111653097A (en) | Urban trip mode comprehensive identification method based on mobile phone signaling data and containing personal attribute correction | |
| Owczarzak et al. | Design of passenger public transportation solutions based on autonomous vehicles and their multiple criteria comparison with traditional forms of passenger transportation | |
| Liu et al. | Exploiting heterogeneous human mobility patterns for intelligent bus routing | |
| Miwa et al. | Route identification and travel time prediction using probe-car data | |
| CN109903553B (en) | Multi-source data mining bus station identification and inspection method | |
| CN112542043B (en) | Method and system for identifying bus net coverage blind area based on mobile phone signaling and big data analysis | |
| Zahabi et al. | Spatio-temporal analysis of car distance, greenhouse gases and the effect of built environment: A latent class regression analysis | |
| CN109102114B (en) | Bus trip getting-off station estimation method based on data fusion | |
| CN110398254B (en) | Method and system for relieving traffic congestion | |
| CN112381472B (en) | Subway connection bus route optimization method and device and storage medium | |
| CN113408833A (en) | Public traffic key area identification method and device and electronic equipment | |
| KR20080029505A (en) | A traffic estimating system and the method considered road type | |
| CN112784000A (en) | Passenger searching method based on taxi track data | |
| CN104282142B (en) | Bus station arrangement method based on taxi GPS data | |
| CN114358808A (en) | Public transport OD estimation and distribution method based on multi-source data fusion | |
| Li et al. | Using smart card data trimmed by train schedule to analyze metro passenger route choice with synchronous clustering | |
| CN111341135B (en) | Mobile phone signaling data travel mode identification method based on interest points and navigation data | |
| CN116720997A (en) | Bus route evaluation system and optimization method based on big data analysis | |
| CN111723871B (en) | Estimation method for real-time carriage full load rate of bus | |
| CN111833153B (en) | Method for recommending flights during purchasing high-speed rail tickets | |
| CN109754606B (en) | Method for predicting road congestion condition based on taxi positioning | |
| CN116663811A (en) | Scheduling matching method and device for reciprocating dynamic carpooling of inter-city passenger transport | |
| CN115713206A (en) | Bus individual trip decision model |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210917 |
|
| RJ01 | Rejection of invention patent application after publication |