CN114090704B

CN114090704B - Passenger identification method and device, electronic device and readable storage medium

Info

Publication number: CN114090704B
Application number: CN202010772726.2A
Authority: CN
Inventors: 赵娟娟; 张刘涛; 须成忠; 叶可江
Original assignee: Shenzhen Institute of Advanced Technology of CAS
Current assignee: Shenzhen Institute of Advanced Technology of CAS
Priority date: 2020-08-04
Filing date: 2020-08-04
Publication date: 2024-06-07
Anticipated expiration: 2040-08-04
Also published as: CN114090704A; WO2022027748A1

Abstract

There is provided a method of identifying public transportation passengers, comprising: respectively acquiring a first travel track comprising a plurality of first logic travel and a second travel track comprising a plurality of second logic travel based on a first passenger travel data source and a second passenger travel data source; classifying the first logical travel matched with the second logical travel into a matched logical travel set; acquiring a travel time period of overlapping a travel time period of a first logic travel and a travel time period of a second logic travel in a matched logic travel set, and corresponding overlapping time periods; performing attenuation treatment on the overlapped duration to obtain the overlapped duration after the attenuation treatment; calculating the track similarity of the first travel track and the second travel track according to the overlapping time length after the attenuation treatment; and identifying the first passenger and the second passenger according to the track similarity. An identification device for public transportation passengers is also provided. The invention improves the identification accuracy of the same passenger under different data sources.

Description

Passenger identification method and device, electronic device and readable storage medium

Technical Field

The invention belongs to the technical field of space-time data processing and public transportation, and particularly relates to a public transportation passenger identification method, a public transportation passenger identification device, electronic equipment and a machine-readable storage medium.

Background

With the development of the perception technology and the network transmission technology, more and more data of the passengers traveling in public transportation (such as subways and buses) can be obtained, for example, AFC data (such as ticket data) collected through an automatic charging system (Auto Fare Collection, AFC), and AP data (such as location data) of the passengers carrying the mobile terminal collected through an Access Point (AP) device installed in a public transportation station. The acquisition of the data provides new analysis thought for analyzing the travel of the passengers, particularly the individual passengers, for example, the AFC data records the arrival and arrival data of the passengers, the AP data records partial position data of the passengers in the travel, and if the two data are associated, the complete travel information of the passengers can be acquired. However, in practice, the data sources from which the different data are acquired are isolated from each other, and the identification information possessed by the same passenger in the different data sources is also different, so how to associate the same passenger in the different data sources is a precondition for constructing detailed travel information of the passenger.

The correlation matching of space-time trajectories (namely, the traveling trajectories of passengers) among different data sources can be reduced to the problem of similarity of two space-time trajectories, and the existing method is mainly used for comparing the similarity of the space-time trajectories of road traffic with uncertain paths, namely, the comparison among stations, but can not realize the identification matching of the same passenger under different data sources under the condition that a large amount of space-time trajectories overlap exists among different passengers. FIG. 1 is a schematic diagram of a prior art method of comparing spatio-temporal trajectory similarity.

Referring to fig. 1, the following information of passenger a and passenger B may be collected:

Based on the AFC system, it is obtained that the passenger a often goes from the station s ₁ to the station s ₅ during a fixed travel period of one day, and the passenger a passes the station s ₂～s₄ on the way of traveling, we call such travel a regular travel, as shown in (a) of fig. 1. However, in one occasional trip of passenger a, passenger a goes from station s ₅ to station s ₈, we call this type of trip random. In fig. 1 (B), another passenger B also often goes from station s ₁ to station s ₅ during the same fixed travel period of the day.

Based on the AP system, the travel track of the passenger a and the passenger B is obtained as shown in (c) and (d) of fig. 1, and the travel of the passenger a includes: regular trips (site s ₂～s₅, site s ₁～s₃) and random trips (site s ₅～s₆); the travel of passenger B includes: regular travel (site s ₂～s₅, site s ₁～s₃, site s ₂～s₄).

If the existing space-time trajectory matching method is based on the matching between stations, the wrong matching is obtained, and the obtained matching result is that the space-time trajectories in the (a) diagram and the space-time trajectories in the (d) diagram are matched, so that the matching between the passenger A and the passenger B is obtained, which is caused by overlapping space-time trajectories (meaning that the stations are also overlapped) between different passengers.

Disclosure of Invention

In order to solve the problems in the prior art, the invention provides a public transportation passenger identification method and a public transportation passenger identification device capable of improving the identification matching accuracy of the same passenger under different data sources.

According to an aspect of an embodiment of the present invention, there is provided a method of identifying public transportation passengers, comprising: acquiring a first travel track comprising a plurality of first logic trips based on a first passenger trip data source, and acquiring a second travel track comprising a plurality of second logic trips based on a second passenger trip data source, wherein the first logic trips and the second logic trips respectively comprise trip time periods for forming one logic trip; matching the first logic travel with the second logic travel to classify the first logic travel matched with the second logic travel into a matched logic travel set; acquiring a travel time period of the first logic travel in the matched logic travel set and a travel time period of the second logic travel matched with the travel time period of the first logic travel in the matched logic travel set, so as to obtain an overlapping duration corresponding to the overlapped travel time period; performing attenuation treatment on the overlapping duration to obtain the overlapping duration after the attenuation treatment; calculating the track similarity of the first travel track and the second travel track according to the overlapping time length after the attenuation treatment; and identifying the first passenger and the second passenger according to the track similarity.

Optionally, in an example of the foregoing aspect, the attenuating the overlapping duration to obtain an overlapping duration after the attenuating includes: attenuating the overlapping duration corresponding to the first logic travel, which meets the preset condition, in the matched logic travel set to obtain attenuation overlapping duration; determining the attenuation overlapping time length and the overlapping time length corresponding to the first logic travel which does not meet the preset condition in the matched logic travel set as the attenuation processed overlapping time length; wherein, the preset conditions include: and in one travel time period in the matched logic travel set, the sum of travel duration of all the first logic travel corresponding to the travel time period is larger than a preset duration.

Optionally, in an example of the foregoing aspect, the attenuating the overlapping duration corresponding to the first logic trip in the matching logic trip set, where the first logic trip meets a preset condition, so as to obtain an attenuation overlapping duration specifically includes: the attenuation overlap period is calculated based on the following equation,

Wherein i represents an ith travel time period in the matching logic travel set, c _i represents the total number of the first logic travel in the ith travel time period, j represents a jth first logic travel in the ith travel time period, gamma represents a decay contribution rate,Representing the overlapping time length corresponding to the j-th first logic trip,/>And representing the attenuation overlapping time length corresponding to the j-th first logic trip.

Optionally, in one example of the above aspect, the first logical trip and the second logical trip each further include a trip shortest duration that constitutes one logical trip; the calculating the track similarity of the first travel track and the second travel track according to the overlapping time after the attenuation processing specifically includes: and calculating the similarity of the first travel track and the second travel track according to the overlapped time length after the attenuation processing, the travel shortest time length of the plurality of first logic travel and the travel shortest time length of the second logic travel which is not matched with the plurality of first logic travel.

Optionally, in one example of the above aspect, the first logical trip and the second logical trip each further include a trip shortest duration that constitutes one logical trip; the calculating the track similarity of the first travel track and the second travel track according to the overlapping time after the attenuation processing specifically includes: respectively giving different weight coefficients to the shortest travel duration of the first logic travel in the matched logic travel set, the shortest travel duration of the first logic travel which is not matched with the plurality of second logic travel, and the shortest travel duration of the second logic travel which is not matched with the plurality of first logic travel; and calculating the similarity of the first travel track and the second travel track according to the overlapped time length after the attenuation processing, the travel shortest time length of the first logic travel, the travel shortest time length of the second logic travel, and the travel shortest time length of the second logic travel.

Optionally, in one example of the above aspect, the first logical trip and the second logical trip each further include an inbound site, an outbound site, an inbound time, and an outbound time that constitute a single logical trip; the matching the first logic travel and the second logic travel to classify the first logic travel matched with the second logic travel into a matched logic travel set specifically includes: subtracting the inbound time of the second logic trip from the inbound time of the first logic trip to obtain an inbound time, and subtracting the outbound time of the first logic trip from the outbound time of the second logic trip to obtain an outbound time; acquiring the shortest inbound time from an inbound site of the first logic trip to an inbound site of the second logic trip, and acquiring the shortest outbound time from an outbound site of the second logic trip to an outbound site of the first logic trip; if the absolute value of the sum of the inbound time length and the shortest inbound time length is smaller than a preset time length threshold value, and the absolute value of the sum of the outbound time length and the shortest outbound time length is smaller than the preset time length threshold value, determining that the first logic travel and the second logic travel are matched, and classifying the first logic travel matched with the second logic travel into a matched logic travel set.

According to another aspect of an embodiment of the present invention, there is provided an apparatus for identifying public transportation passengers, comprising: the travel track acquisition module is configured to acquire a first travel track comprising a plurality of first logic travel based on a first passenger travel data source and acquire a second travel track comprising a plurality of second logic travel based on a second passenger travel data source; the first logic travel and the second logic travel respectively comprise travel time periods forming one logic travel; the logic travel matching module is configured to match the first logic travel with the second logic travel so as to classify the first logic travel matched with the second logic travel into a matched logic travel set; the overlapping duration obtaining module is configured to obtain a travel time period of overlapping the travel time period of the first logic travel in the matched logic travel set and the travel time period of the second logic travel matched by the travel time period of the first logic travel set, so as to obtain an overlapping duration corresponding to the overlapped travel time period; the overlapping time length attenuation module is configured to attenuate the overlapping time length to obtain the attenuated overlapping time length; the track similarity calculation module is configured to calculate the track similarity of the first travel track and the second travel track according to the overlapping duration after the attenuation processing; and the passenger identification module is configured to identify the first passenger and the second passenger according to the track similarity.

Optionally, in one example of the above another aspect, the overlapping duration attenuation module includes: the time length attenuation unit is configured to attenuate the overlapping time length corresponding to the first logic travel meeting the preset condition in the matched logic travel set so as to obtain attenuation overlapping time length; a time length determining unit, configured to determine the attenuation overlapping time length and the overlapping time length corresponding to the first logic travel which does not meet the preset condition in the matched logic travel set as the attenuation processed overlapping time length; wherein, the preset conditions include: and in one travel time period in the matched logic travel set, the sum of travel duration of all the first logic travel corresponding to the travel time period is larger than a preset duration.

Optionally, in one example of the above another aspect, the duration decay unit is further configured to calculate the decay overlap duration using the following equation,

Optionally, in one example of the above another aspect, the first logical trip and the second logical trip each further include a trip shortest duration that constitutes one logical trip; the trajectory similarity calculation module is further configured to: and calculating the similarity of the first travel track and the second travel track according to the overlapped time length after the attenuation processing, the travel shortest time length of the plurality of first logic travel and the travel shortest time length of the second logic travel which is not matched with the plurality of first logic travel.

Optionally, in one example of the above another aspect, the first logical trip and the second logical trip each further include a trip shortest duration that constitutes one logical trip; the track similarity calculation module comprises: a weight coefficient giving unit configured to give different weight coefficients to a travel shortest time length of the first logical travel in the matched logical travel set, a travel shortest time length of the first logical travel that is not matched with the plurality of second logical travel, and a travel shortest time length of the second logical travel that is not matched with the plurality of first logical travel, respectively; and a similarity calculating unit configured to calculate a track similarity of the first travel track and the second travel track according to the overlapping time length after the attenuation processing and the travel shortest time length of the first logic travel in the matching logic travel set respectively given with different weight coefficients, the travel shortest time length of the first logic travel which is not matched with the plurality of second logic travel, and the travel shortest time length of the second logic travel which is not matched with the plurality of first logic travel.

Optionally, in one example of the above another aspect, the first logical trip and the second logical trip each further include an inbound site, an outbound site, an inbound time, and an outbound time that constitute one logical trip; the logic trip matching module comprises: the outbound time length determining unit is configured to subtract the inbound time of the second logic travel from the inbound time of the first logic travel to obtain an inbound time length, and subtract the outbound time of the first logic travel from the outbound time of the second logic travel to obtain an outbound time length; a shortest arrival time length determining unit configured to obtain a shortest arrival time length from an arrival site of the first logical trip to an arrival site of the second logical trip, and obtain a shortest arrival time length from an arrival site of the second logical trip to an arrival site of the first logical trip; the matching determining unit is configured to determine that the first logic travel is matched with the second logic travel and classify the first logic travel matched with the second logic travel into a matched logic travel set if the absolute value of the sum of the inbound time and the shortest inbound time is smaller than a preset time threshold and the absolute value of the sum of the outbound time and the shortest outbound time is smaller than the preset time threshold.

According to still another aspect of embodiments of the present invention, there is provided an electronic device including: at least one processor, and a memory coupled to the at least one processor, the memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the method of identifying public transportation passengers as described above.

A machine-readable storage medium according to still another aspect of embodiments of the present invention is provided that stores executable instructions that, when executed, cause the machine to perform the method of identifying public transportation passengers as described above.

The beneficial effects are that: the overlapping time length of the first logic travel and the second logic travel which are matched with each other is acquired, and the acquired overlapping time length is attenuated, so that the weight of the overlapping time length is reduced in the process of calculating the track similarity, and the identification matching accuracy of the same passenger under different data sources is improved.

Drawings

The above and other aspects, features and advantages of embodiments of the present invention will become more apparent from the following description when taken in conjunction with the accompanying drawings in which:

FIG. 1 is a schematic diagram of a prior art method of comparing spatio-temporal trajectory similarity;

FIG. 2 is a flow chart of a method of identifying public transportation passengers according to an embodiment of the invention;

FIG. 3A is a block diagram of a mass transit passenger identification device according to an embodiment of the invention;

FIG. 3B is a block diagram of one example of a logical trip matching module of the identification device of FIG. 3A;

FIG. 3C is a block diagram of one example of an overlap duration decay module of the identification device of FIG. 3A;

FIG. 3D is a block diagram of one example of a trajectory similarity calculation module of the identification device of FIG. 3A;

fig. 4 is a block diagram illustrating an electronic device implementing a method of identifying public transportation passengers according to an embodiment of the present invention.

Detailed Description

Hereinafter, specific embodiments of the present invention will be described in detail with reference to the accompanying drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the specific embodiments set forth herein. Rather, these embodiments are provided to explain the principles of the invention and its practical application so that others skilled in the art will be able to understand the invention for various embodiments and with various modifications as are suited to the particular use contemplated.

As used herein, the term "comprising" and variations thereof mean open-ended terms, meaning "including, but not limited to. The terms "based on", "in accordance with" and the like mean "based at least in part on", "in part in accordance with". The terms "one embodiment" and "an embodiment" mean "at least one embodiment. The term "another embodiment" means "at least one other embodiment". The terms "first," "second," and the like, may refer to different or the same object. Other definitions, whether explicit or implicit, may be included below. Unless the context clearly indicates otherwise, the definition of a term is consistent throughout this specification.

As described in the background art, in a public transportation trip, a large number of overlapped space-time tracks exist between different passengers, and the overlapped space-time tracks in the space-time track recognition process can influence the recognition matching accuracy of the same passenger under different data sources. Therefore, if the weight of the overlapped space-time tracks (namely regular travel) can be reduced in the matching process of the space-time tracks, the accuracy of identifying and matching the same passenger under different data sources can be improved.

In order to achieve the above object, there is provided a public transportation passenger identification method according to an embodiment of the present invention. The identification method comprises the following steps: acquiring a first travel track comprising a plurality of first logic travel based on a first passenger travel data source, and acquiring a second travel track comprising a plurality of second logic travel based on a second passenger travel data source, wherein the first logic travel and the second logic travel respectively comprise travel time periods for forming one logic travel; matching the first logic travel with the second logic travel to classify the first logic travel matched with the second logic travel into a matched logic travel set; acquiring a travel time period of overlapping a travel time period of a first logic travel in a matched logic travel set and a travel time period of a second logic travel matched with the travel time period of the first logic travel set so as to obtain an overlapping time length corresponding to the overlapped travel time period; performing attenuation treatment on the overlapped duration to obtain the overlapped duration after the attenuation treatment; calculating the track similarity of the first travel track and the second travel track according to the overlapping time length after the attenuation treatment; the first passenger and the second passenger are identified based on the trajectory similarity. Of course, the identification herein refers to identifying whether the primary passenger and the secondary passenger are the same passenger.

In the identification method, the overlapping time length of the matched first logic travel and the second logic travel is acquired, and the acquired overlapping time length is attenuated, so that the weight of the overlapping time length is reduced in the process of calculating the track similarity, and the identification matching accuracy of the same passenger under different data sources is improved.

In the following, before describing in detail the method and apparatus for identifying public transportation passengers according to embodiments of the present invention, some term concepts for the embodiments of the present invention will be described.

Travel data source: which can acquire and store passenger travel data of passenger identification, station data, time data, etc. of passengers when the passengers travel.

Logic trip: refers to a logical ride of passengers, i.e., the overall process of passengers entering from an entry station and exiting from an exit station. In one example, a logical trip may include: an inbound site, an inbound time, an outbound site, an outbound time, etc. Here, the inbound time and the outbound time constitute a travel time period, and thus, one logical travel may further include: travel time period. In addition, a time length corresponding to the travel time period is set as a travel time length. In one example, a passenger enters from an entry station a in morning 8 of the day and exits from an exit station b in morning 9 of the day, such a logical ride constitutes a logical trip; when the arrival time is 8 in the morning and the arrival time is 9 in the morning, the travel time period is 8 in the morning to 9 in the morning, and the travel time corresponding to the travel time period is 1 hour.

Travel shortest time length: given the duration of the shortest path (also called the active path) that any two physical stations take from one physical station to the other. In one example, given two physical sites, site a and site b, respectively, from site a to site b, there are two paths (generally known by public transportation routes), where one path is from site a, route to site a1, site a2, and the other path is from site a, route to site b1, then the shortest travel time from site a to site b is the time taken from site a, route to site b1, to reach site b, and of course, the assumption here is that the route distance between any two physical sites is substantially equal, which also conforms to the setting of actual public transportation. Thus, in one example, a logical trip may also include a trip minimum duration.

Travel track: refers to a sequence of spatiotemporal points consisting of a plurality of spatiotemporal points (or detection points) in chronological order acquired by a sensing device (e.g., AFC system, AP system) of a passenger over a period of time. In one example, each spatiotemporal point includes a site where the sensing device is installed and a corresponding time (i.e., the time of sensing detection).

The above is a description of some term concepts used for the embodiments of the present invention, and next, a method of identifying a public transportation passenger and an apparatus for identifying a public transportation passenger according to the embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Fig. 2 is a flowchart of a method of identifying public transportation passengers according to an embodiment of the present invention.

Referring to fig. 2, in block S202, a first travel track including a plurality of first logical trips is acquired based on a first passenger trip data source, and a second travel track including a plurality of second logical trips is acquired based on a second passenger trip data source.

In an embodiment according to the present invention, the first passenger travel data source is capable of acquiring and storing all inbound stops, inbound times, outbound stops, outbound times, passenger identifications (i.e., identities), etc. of the first passenger when the first passenger travels. In one example, the primary passenger travel data source may be, for example, an AFC data source (i.e., an AFC system).

The first travel track comprises a plurality of inbound stations acquired from a first passenger travel data source, inbound times corresponding to the inbound stations, a plurality of outbound stations and outbound times corresponding to the outbound stations. Thus, each first logical trip includes a corresponding one of the inbound sites, one of the inbound times, one of the outbound sites, one of the outbound times. As described above, the travel time period and the corresponding travel duration thereof can be obtained according to the arrival time and the departure time, so that each first logic travel can further include a corresponding travel time period and travel duration. As also described above, the shortest travel time may be obtained from the inbound and outbound sites, and thus each first logical trip may also include a corresponding one of the shortest travel time.

In an embodiment according to the present invention, the second passenger travel data source is capable of acquiring and storing all of the route stops of the second passenger at the time of the second passenger's departure, route times corresponding to each route stop, passenger identification (i.e., identity), etc. In one example, the second passenger trip data source may be, for example, an AP data source. It should be noted that the approach station is a public transportation station that the second passenger gets on going out, and of course, may be a station that the second passenger gets on being perceived and detected when getting on or getting off.

The second travel track comprises a plurality of route stations acquired from a second passenger travel data source and route time corresponding to each route station. In one example, the plurality of pathway sites are arranged in chronological order, if the current pathway site p _i and the previous pathway site p _i-1 satisfy the dividing conditionThe previous pathway site p _i-1 (and its corresponding pathway time) and all pathway sites preceding the pathway site p _i-1 (and their respective corresponding pathway times) are included in a second logical trip, where p _i. T represents the pathway time corresponding to pathway site p _i, and p _i-1. T represents the pathway time corresponding to pathway site p _i-1,/>Representing the shortest travel time from pathway site p _i to the previous pathway site p _i-1, δ is an additional time that can be tolerated. It should be noted that the route site preceding the previous route site p _i-1 refers to a route site preceding the previous route site p _i-1 that does not satisfy the dividing condition and is not included in the other second logical trip. In addition, if the current route site and the previous route site satisfy the dividing condition and the next route site also satisfy the dividing condition, the current route site is deleted. That is, the isolated path site divided by the dividing condition is deleted. In this case, each second logical trip includes at least two pathway sites.

In one example, a first one of the at least two pathway sites chronologically ordered in each second logical trip (corresponding pathway time earliest) is set as belonging to an inbound site in the second logical trip, and a last one of the pathway sites (corresponding pathway time latest) is set as belonging to an outbound site in the second logical trip. In this case, the route time corresponding to the first route site is the arrival time, and the route time corresponding to the last route site is the departure time. As described above, the travel time period and the corresponding travel time period thereof can be obtained according to the arrival time and the arrival time, and thus each second logical travel can further include a corresponding one of the travel time period and one of the travel time period. As also described above, the shortest travel time may be obtained from the inbound and outbound sites, and thus each second logical trip may also include a corresponding one of the shortest travel time.

In block S204, each first logical trip and each second logical trip are matched to categorize the first logical trip that matches the second logical trip into a set of matched logical trips.

In one example, if the ith first logical trip and the jth second logical trip satisfy the following conditions, the ith first logical trip and the jth second logical trip are deemed to match each other.

The conditions that need to be met may be specified. In one example, the conditions that need to be met may include the following:

first, the arrival time of the ith first logic trip is utilized Subtract the arrival time/>, of the j-th second logic tripTo obtain the inbound time length and outbound time/>, using the j-th second logic tripSubtract the outbound time/>, of the ith first logical tripTo obtain the outbound duration.

Secondly, acquiring an inbound site from the ith first logic tripInbound site/>, to jth second logical tripShortest inbound duration between/>And obtain outbound site/>, from the j-th second logical tripOutbound site/>, to the ith first logical tripShortest outbound duration between/>

Finally, if the inbound time period and the shortest inbound time periodThe absolute value of the sum is smaller than a preset time threshold epsilon' and the outbound time and the shortest outbound time/>And if the absolute value of the sum is smaller than the preset duration threshold epsilon', the ith first logic trip and the jth second logic trip are considered to be matched with each other, and the ith first logic trip matched with the jth second logic trip is classified into a matched logic trip set PG.

In other words, in this example, the condition to be satisfied can be expressed by the following expression 1.

[1]And/>

In another example, the conditions to be satisfied may include the following conditions in addition to the above conditions: inbound site of ith first logic tripAnd outbound site/>The effective path between the two logic travel station arrival stations/>, through the j-th second logic travel station arrival station/>And outbound site/>

In addition, in the embodiment according to the present invention, after the matching is performed on each first logical travel and each second logical travel, the first logical travel that is not matched with each second logical travel of the second travel track is classified into the first unmatched logical travel set NPG1, and the second logical travel that is not matched with each first logical travel of the first travel track is classified into the second unmatched logical travel set NPG2. Here, the mismatch means that the above condition is not satisfied. In one example, if equation 1 above is not satisfied, the ith first logical trip and the jth second logical trip do not match. In another example, if "inbound site for ith first logical trip" is not satisfiedAnd outbound site/>The effective path between the two logic travel station arrival stations/>, through the j-th second logic travel station arrival station/>And the condition of the outbound site ", the ith first logic trip and the jth second logic trip are not matched. In yet another example, if equation 1 above is not satisfied and "inbound site of the ith first logical trip/>And outbound site/>The effective path between the two logic travel station arrival stations/>, through the j-th second logic travel station arrival station/>And outbound site ", the ith first logical trip and the jth second logical trip are not matched.

In block S206, a travel time period of each first logic travel in the matched logic travel set and a travel time period of each matched second logic travel are obtained, so as to obtain an overlapping duration corresponding to each overlapping travel time period.

In one example, taking the example that the ith first logical trip and the jth second logical trip match each other. For example, the ith first logical trip is set to include 30 minutes from the inbound site S1 through the site S2, the site S3, the site S4 to the outbound site S5 from the morning 8 to the morning 9, and the jth second logical trip includes from the inbound site S2 through the site S3 to the outbound site S4 from the morning 8 to the morning 9. The travel time period of the ith first logic travel (from 8 in the morning to 9 in the morning for 30 minutes) and the travel time period of the jth second logic travel (from 8 in the morning to 9 in the morning) overlap, and the corresponding overlap period is one hour, from 8 in the morning to 9 in the morning.

In this case, one overlapping duration corresponding to each of all the first logical trips in the matching logical trip set PG may be obtained.

In block S208, the respective overlapping time periods are subjected to attenuation processing to obtain respective attenuation-processed overlapping time periods.

The "attenuation processing" may include attenuation processing for attenuating the overlapping period of time, or attenuation processing for not attenuating the overlapping period of time.

In addition, in one example, the overlapping duration corresponding to each first logic trip meeting the preset condition in the matching logic trip set PG is attenuated, so as to obtain the attenuation overlapping duration corresponding to each first logic trip meeting the preset condition. To put it differently, the overlapping duration corresponding to each first logic trip in the matching logic trip set PG, which does not meet the preset condition, is not attenuated.

Of course, in an example, the setting of the preset condition may make the overlapping duration corresponding to all the first logic trips in the matching logic trip set PG attenuated. However, in another example, the setting of the preset condition may cause the overlapping period corresponding to the first logical trip of the part of the matching logical trip set PG to be attenuated, while the overlapping period corresponding to the first logical trip of the rest of the matching logical trip set PG is not attenuated.

In one example, the preset condition may include: in one travel time period in the matching logic travel set PG, the sum of travel duration of all the first travel tracks corresponding to the travel time period is larger than a preset duration. Taking the first passenger traveling for 30 days as an example, a traveling time period, for example, a traveling time period from 8 in the morning to 9 in the morning, is selected in the first logical travel of the first passenger, which reaches the outbound site D2 from the inbound site D1. In this travel period, if the first passenger arrives at the outbound station D2 from the inbound station D1 from 8 in the morning to 9 in the morning on a daily basis for 8 in the morning on 30 days, the travel duration of all the first logical trips (i.e., 30 first logical trips) corresponding to the travel period is 30 hours; if the first passenger arrives at the outbound station D2 from the inbound station D1 from the daily morning 8 to the morning 9 of 20 out of the 30 days, the travel duration of all the first logical trips (i.e., 20 first logical trips) corresponding to the travel period is 20 hours. Therefore, a preset time period (such as 20 hours) is set, all first logic trips in a certain trip time period in the corresponding matching logic trip set PG are obtained, and if the sum of the trip time periods of the first logic trips is greater than the preset time period, the first logic trips corresponding to the trip time period conform to the preset condition, so that the overlapping time periods corresponding to the first logic trips are all attenuated.

It should be noted that a plurality of different travel time periods (or travel patterns) may be included in the matching logic travel set PG, which is caused by the difference in regular travel time periods of the passengers.

Further, in the above example, the preset condition may also be set by days. For example, the first passenger arrives at the outbound station D2 from the inbound station D1 from the morning 8 to the morning 9, and if the travel days of the first passenger from the morning 8 to the morning 9 reach a preset number of days (for example, 20 days), the first logical travel corresponding to the morning 8 to the morning 9 is considered to meet the preset condition.

In one example, the overlapping duration corresponding to each first logic trip meeting the preset condition in the matching logic trip set PG may be attenuated by using the following equation 2.

[2]

Wherein a represents an a-th travel time period meeting the preset condition in the matching logic travel set PG, c _a represents the total number of first logic travel in the a-th travel time period, b represents a b-th first logic travel in the a-th travel time period, gamma represents the attenuation contribution rate,Indicating the overlapping time length corresponding to the b-th first logic trip,And representing the attenuation overlapping time length corresponding to the b-th first logic trip. In this case, by attenuating the overlapping duration meeting the preset condition in the matching logic travel set PG, the weight of the overlapping duration meeting the preset condition in the track similarity calculation process is reduced, that is, the weight of the overlapping travel time period is reduced (the specific gravity of the non-overlapping travel time period is relatively improved), so that the recognition and matching accuracy of the same passenger under different data sources is improved.

In an example, the obtained attenuation overlapping duration corresponding to each first logic trip and the overlapping duration corresponding to each first logic trip which does not meet the preset condition in the matching logic trip set PG are determined as the overlapping duration after each attenuation processing. That is, all the attenuation-processed overlap periods include the attenuation overlap periods after the attenuation of the respective overlap periods and the respective unattenuated overlap periods.

In block S210, the track similarity of the first travel track and the second travel track is calculated according to the overlapping time period after the attenuation processing.

In an example of the specific implementation block S210, track similarity of the first travel track and the second travel track is calculated according to the overlapping duration after each attenuation process, the travel shortest duration of all the first logic travel of the first travel track, and the travel shortest duration of the second logic travel (i.e., all the second logic travel in the second unmatched logic travel set NPG 2) that is unmatched with all the first logic travel of the first travel track.

In one example, the trajectory similarity of the first travel trajectory and the second travel trajectory may be calculated based on the following equation 3.

[3]

TS _afc represents a first travel track, TS _ap represents a second travel track, sim (TS _afc,TS_ap) represents track similarity of the first travel track and the second travel track, M represents the number of different travel time periods meeting preset conditions in the matched logic travel set PG, alpha _p represents the corresponding overlapping duration of the P-th first logic travel which does not meet preset conditions in the matched logic travel set PG, P represents the total number of first logic travel which does not meet preset conditions in the matched logic travel set PG,Representing the nth first logical trip in the first trip track,/>Represents the travel shortest time length of the nth first logic travel, N represents the total number of the first logic travel in the first travel track, and is/areRepresenting the q-th second logical trip in the second unmatched logical trip set NPG2,/>And the shortest travel duration of the Q-th second logic travel is represented, and Q represents the total number of second logic travel in the second unmatched logic travel set NPG 2.

From the above, it can be seen that the first travel track includes N first logic travel, where M and P are both smaller than N, and Q is also smaller than the total number of second logic travel in the second travel track.

In one example, taking the first passenger trip data source as an AFC data source and the second passenger trip data source as an AP data source as an example, three types of trip situations can be respectively corresponding to the matched logic trip set PG, the first unmatched logic trip set NPG1, and the second unmatched logic trip set NPG 2.

Specifically, the first class of travel corresponding to the matching logic travel set PG means that the passenger is sensed by the AFC device when entering and exiting the station, and the mobile terminal carried by the passenger is detected by the AP device during the travel; the second class of travel corresponding to the first unmatched logic travel set NPG1 means that the passenger is sensed by the AFC device when entering and exiting the station, but the mobile terminal carried by the passenger is not detected by the AP device during the travel; the third class of travel corresponding to the second unmatched logical travel set NPG2 refers to that the passenger does not use a sensed object (such as a bus card) which can be sensed by the AFC device when entering and exiting the station, or that the passenger is only moving near the public transportation station, or that the passenger passes through the public transportation station and is detected by the AP device.

In the actual process, the three travel conditions are considered to be different, so that different punishment coefficients (also can be weight coefficients if the punishment coefficients are large and the corresponding weight coefficients are small) are respectively given when the track similarity is calculated. For example, the first and second types of travel are more likely to occur, so the corresponding penalty factor is smaller (i.e., the weight factor is larger), and the third type of travel is less likely to occur, so the corresponding penalty factor is larger (i.e., the weight factor is smaller). Through the design, the interference of irrelevant travel tracks can be effectively reduced.

Therefore, based on the above analysis, in another example of the concrete implementation block S210, different penalty coefficients are respectively given to the travel shortest duration of the first logical travel in the matched logical travel set PG, the travel shortest duration of the first logical travel in the first unmatched logical travel set NPG1, and the travel shortest duration of the second logical travel in the second unmatched logical travel set NPG 2.

Further, according to the overlapping time length after each attenuation treatment and according to the shortest time length of travel of the first logic travel in the matched logic travel set PG, the shortest time length of travel of the first logic travel in the first unmatched logic travel set NPG1 and the shortest time length of travel of the second logic travel in the second unmatched logic travel set NPG2, which are respectively endowed with different penalty coefficients, the similarity of the first travel track and the second travel track is calculated. Specifically, the similarity of the first travel track and the second travel track may be calculated based on the following equation 4.

[4]

Wherein TS _afc represents a first travel track, TS _ap represents a second travel track, sim (TS _afc,TS_ap) represents track similarity of the first travel track and the second travel track, M represents the total number of different travel time periods meeting preset conditions in the matched logic travel set PG, alpha _p represents the corresponding overlapping time length of the P first logic travel which does not meet preset conditions in the matched logic travel set PG, P represents the total number of first logic travel which does not meet preset conditions in the matched logic travel set PG,Representing the s first logical trip in the matching logical trip set PG,/>Representing the shortest travel duration of the S-th first logic travel, and S represents the total number of first logic travel in the matched logic travel set PG,/>Represents the r first logical trip in the first unmatched logical trip set NPG1,/>Representing the shortest travel duration of the R first logic travel, wherein R represents the total number of the first logic travel in the first unmatched logic travel set NPG1,/>Representing the q-th second logical trip in the second unmatched logical trip set NPG2,/>And (3) representing the travel shortest time length of the Q-th second logic travel, wherein Q represents the total number of the second logic travel in the second unmatched logic travel set NPG2, and theta ₁、θ₂ and theta ₃ respectively represent different penalty coefficients.

As can be seen from the above, the first travel track includes s+r (the sum of the two is equal to N in equation 3) first logic trips, while M and P are both smaller than s+r, and Q is also smaller than the total number of second logic trips in the second travel track.

In block S212, the first and second passengers are identified according to the trajectory similarity. Of course, the identification herein refers to identifying whether the primary passenger and the secondary passenger are the same passenger.

In one example, a trajectory similarity threshold may be set, and the trajectory similarity threshold may be specified. In this case, when the calculated trajectory similarity is greater than or equal to the trajectory similarity threshold, it is recognized that the first passenger and the second passenger are the same passenger; and when the calculated trajectory similarity is less than the trajectory similarity threshold, identifying that the first passenger and the second passenger are not the same passenger.

Fig. 3A is a flowchart of an identification device of a public transportation passenger according to an embodiment of the present invention.

Referring to fig. 3A, an apparatus 300 for identifying public transportation passengers according to an embodiment of the present invention includes: a travel track acquisition module 310, a logic travel matching module 320, an overlap duration acquisition module 330, an overlap duration decay module 340, a track similarity calculation module 350, and a passenger identification module 360.

The travel track acquisition module 310 is configured to acquire a first travel track including a plurality of first logical trips based on a first passenger travel data source and a second travel track including a plurality of second logical trips based on a second passenger travel data source. In one example, each first logical trip includes a corresponding one of an inbound site, an inbound time, an outbound site, an outbound time, a trip period, a trip duration, and a shortest trip duration. Each second logical trip comprises a corresponding inbound site (a first route site arranged according to time sequence), an inbound time (a route time corresponding to the first route site), an outbound site (a last route site arranged according to time sequence), an outbound time (a route time corresponding to the last route site), a trip time period, a trip duration and a shortest trip duration.

The logic travel matching module 320 is configured to match each first logic travel with each second logic travel to categorize the first logic travel that matches the second logic travel into a set of matching logic travel.

In one example, referring to fig. 3B, the logical trip matching module 320 may include: an outbound time length determining unit 321, a shortest outbound time length determining unit 322, and a matching determining unit 323. The outbound time determining unit 321 is configured to utilize the inbound time of the ith first logic tripSubtract the arrival time/>, of the j-th second logic tripTo obtain the inbound time length and outbound time/>, using the j-th second logic tripSubtract the outbound time/>, of the ith first logical tripTo obtain the outbound duration. The shortest arrival/arrival time determining unit 322 is configured to obtain the arrival site/>, which is going out from the ith first logic tripInbound site/>, to jth second logical tripThe shortest inbound time betweenAnd obtain outbound site/>, from the j-th second logical tripOutbound site to ith first logical tripShortest outbound duration between/>The match determination unit 323 is configured to determine if the inbound time period and the shortest inbound time period/>The absolute value of the sum is smaller than a preset time threshold epsilon' and the outbound time and the shortest outbound time/>And if the absolute value of the sum is smaller than the preset duration threshold epsilon', the ith first logic trip and the jth second logic trip are considered to be matched with each other, and the ith first logic trip matched with the jth second logic trip is classified into a matched logic trip set PG. Thus, in this example, the matching determination unit 323 may determine that the ith first logical trip and the jth second logical trip match each other according to the above equation 1.

In addition, in another example, the matching determination unit 323 may also determine the inbound site of the ith first logical trip according to the conditionAnd outbound site/>The effective path between the two stops going through the j second logic travelAnd outbound site/>"To determine that the ith first logical trip and the jth second logical trip match each other.

In addition, in one example, after each first logical trip and each second logical trip are matched, the first logical trip that is not matched with each second logical trip of the second trip track is categorized into a first unmatched logical trip set NPG1, and the second logical trip that is not matched with each first logical trip of the first trip track is categorized into a second unmatched logical trip set NPG2. Here, the mismatch means that the above condition is not satisfied. In one example, if equation 1 above is not satisfied, the ith first logical trip and the jth second logical trip do not match. In another example, if "inbound site for ith first logical trip" is not satisfiedAnd outbound site/>The effective path between the two logic travel station arrival stations/>, through the j-th second logic travel station arrival station/>And the condition of the outbound site ", the ith first logic trip and the jth second logic trip are not matched. In yet another example, if equation 1 above is not satisfied and "inbound site of the ith first logical trip/>And outbound site/>The effective path between the two stops going through the j second logic travelAnd outbound site ", the ith first logical trip and the jth second logical trip are not matched.

The overlapping duration obtaining module 330 is configured to obtain an overlapping duration corresponding to each overlapping travel time period by matching the travel time period of each first logic travel in the logic travel set with the travel time period of each matched second logic travel.

The overlap period attenuation module 340 is configured to attenuate each overlap period to obtain an overlap period after each attenuation process.

The "attenuation processing" may include attenuation processing for attenuating the overlapping time period, or attenuation processing for not attenuating the overlapping time period.

In one example, referring to fig. 3C, the overlap duration decay module 340 includes a duration decay unit 341 and a duration determination unit 342. The duration attenuation unit 341 is configured to attenuate the overlapping duration corresponding to each first logic trip meeting the preset condition in the matching logic trip set PG, so as to obtain the attenuation overlapping duration corresponding to each first logic trip meeting the preset condition. To put it differently, the overlapping duration corresponding to each first logic trip in the matching logic trip set PG, which does not meet the preset condition, is not attenuated. The duration determining unit 342 is configured to determine the obtained attenuation overlapping duration corresponding to each first logic trip and the overlapping duration corresponding to each first logic trip in the matching logic trip set PG, which do not meet the preset condition, as the overlapping duration after each attenuation processing. That is, all the attenuation-processed overlap periods include the attenuation overlap periods after the attenuation of the respective overlap periods and the respective unattenuated overlap periods.

In an example, the duration attenuation unit 341 may attenuate, using the above equation 2, the overlapping duration corresponding to each first logic trip in the matching logic trip set PG that meets the preset condition.

The track similarity calculation module 350 is configured to calculate the track similarity of the first travel track and the second travel track according to the overlapping time length after the attenuation processing.

In one example, the track similarity calculation module 350 is further configured to calculate the track similarity of the first travel track and the second travel track according to the overlapping time periods after the attenuation processing, the travel shortest time periods of all the first logic travel of the first travel track, and the travel shortest time periods of the second logic travel (i.e., all the second logic travel in the second unmatched logic travel set NPG 2) that are unmatched with all the first logic travel of the first travel track. In this case, the trajectory similarity calculation module 350 may calculate the trajectory similarity of the first travel trajectory and the second travel trajectory based on equation 3 above.

In another example, referring to fig. 3D, the trajectory similarity calculation module 350 may include a weight coefficient imparting unit 351, a similarity calculation unit 352. The weight coefficient giving unit 351 is configured to give different penalty coefficients to the travel shortest time length of the first logical travel in the matched logical travel set PG, the travel shortest time length of the first logical travel in the first unmatched logical travel set NPG1, and the travel shortest time length of the second logical travel in the second unmatched logical travel set NPG2, respectively. The similarity calculating unit 352 calculates the similarity between the first travel track and the second travel track according to the overlapping time periods after the attenuation processing, and according to the travel shortest time period of the first logic travel in the matching logic travel set PG to which different penalty coefficients are respectively assigned, the travel shortest time period of the first logic travel in the first unmatched logic travel set NPG1, and the travel shortest time period of the second logic travel in the second unmatched logic travel set NPG 2. In this case, the similarity calculation unit 352 may calculate the similarity of the first travel track and the second travel track based on the above equation 4.

The passenger identification module 360 is configured to identify the primary passenger and the secondary passenger based on the trajectory similarity. Of course, the identification herein refers to identifying whether the primary passenger and the secondary passenger are the same passenger.

Referring to fig. 4, an electronic device 400 may include at least one processor 410, a memory (e.g., a non-volatile memory) 420, a memory 430, and a communication interface 440, and the at least one processor 410, the memory 420, the memory 430, and the communication interface 440 are connected together via a bus 450. At least one processor 410 executes at least one machine readable instruction (i.e., the elements described above as being implemented in software) stored or encoded in memory.

In one example, computer-executable instructions are stored in memory that, when executed, cause the at least one processor 410 to perform the following: acquiring a first travel track comprising a plurality of first logic travel based on a first passenger travel data source, and acquiring a second travel track comprising a plurality of second logic travel based on a second passenger travel data source, wherein the first logic travel and the second logic travel respectively comprise travel time periods for forming one logic travel; matching the first logic travel with the second logic travel to classify the first logic travel matched with the second logic travel into a matched logic travel set; acquiring a travel time period of overlapping a travel time period of a first logic travel in a matched logic travel set and a travel time period of a second logic travel matched with the travel time period of the first logic travel set so as to obtain an overlapping time length corresponding to the overlapped travel time period; performing attenuation treatment on the overlapped duration to obtain the overlapped duration after the attenuation treatment; calculating the track similarity of the first travel track and the second travel track according to the overlapping time length after the attenuation treatment; the first passenger and the second passenger are identified based on the trajectory similarity. Of course, the identification herein refers to identifying whether the primary passenger and the secondary passenger are the same passenger.

It should be appreciated that the computer-executable instructions stored in the memory, when executed, cause the at least one processor 410 to perform the various operations and functions described above in connection with fig. 2 in accordance with embodiments of the present invention.

According to one embodiment, a program product, such as a machine-readable medium, is provided. The machine-readable medium may have instructions (i.e., elements described above implemented in software) that, when executed by a machine, cause the machine to perform various operations and functions described above in connection with fig. 2 in embodiments of the invention.

In particular, a system or apparatus provided with a readable storage medium having stored thereon software program code implementing the functions of any of the above embodiments may be provided, and a computer or processor of the system or apparatus may be caused to read out and execute instructions stored in the readable storage medium.

In this case, the program code itself read from the readable medium may implement the functions of any of the above-described embodiments, and thus the machine-readable code and the readable storage medium storing the machine-readable code form part of the embodiments of the present invention.

Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RAMs, DVD-RWs), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or cloud by a communications network.

The foregoing describes specific embodiments of the present invention. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Not all steps or units in the above-mentioned flowcharts and system configuration diagrams are necessary, and some steps or units may be omitted according to actual needs. The order of execution of the steps is not fixed and may be determined as desired. The apparatus structures described in the above embodiments may be physical structures or logical structures, that is, some units may be implemented by the same physical entity, or some units may be implemented by multiple physical entities, or may be implemented jointly by some components in multiple independent devices.

The terms "exemplary," "example," and the like, as used throughout this specification, mean "serving as an example, instance, or illustration," and do not mean "preferred" or "advantageous" over other embodiments. The detailed description includes specific details for the purpose of providing an understanding of the described technology. However, the techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described embodiments.

The alternative implementation of the embodiment of the present invention has been described in detail above with reference to the accompanying drawings, but the embodiment of the present invention is not limited to the specific details of the foregoing implementation, and various simple modifications may be made to the technical solutions of the embodiment of the present invention within the scope of the technical concept of the embodiment of the present invention, and these simple modifications all fall within the protection scope of the embodiment of the present invention.

The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of identifying a passenger, the method comprising:

acquiring a first travel track comprising a plurality of first logic trips based on a first passenger trip data source, and acquiring a second travel track comprising a plurality of second logic trips based on a second passenger trip data source, wherein the first logic trips and the second logic trips respectively comprise trip time periods for forming one logic trip;

matching the first logic travel with the second logic travel to classify the first logic travel matched with the second logic travel into a matched logic travel set;

acquiring a travel time period of the first logic travel in the matched logic travel set and a travel time period of the second logic travel matched with the travel time period of the first logic travel in the matched logic travel set, so as to obtain an overlapping duration corresponding to the overlapped travel time period;

performing attenuation treatment on the overlapping duration to obtain the overlapping duration after the attenuation treatment;

calculating the track similarity of the first travel track and the second travel track according to the overlapping time length after the attenuation treatment;

Identifying a first passenger and a second passenger according to the track similarity;

the attenuating processing is performed on the overlapping duration to obtain the overlapping duration after the attenuating processing, which specifically includes:

attenuating the overlapping duration corresponding to the first logic travel, which meets the preset condition, in the matched logic travel set to obtain attenuation overlapping duration;

determining the attenuation overlapping time length and the overlapping time length corresponding to the first logic travel which does not meet the preset condition in the matched logic travel set as the attenuation processed overlapping time length;

Wherein, the preset conditions include: in one travel time period in the matched logic travel set, the sum of travel duration of all the first logic travel corresponding to the travel time period is larger than a preset duration;

The step of attenuating the overlapping duration corresponding to the first logic travel, which meets a preset condition, in the matching logic travel set to obtain an attenuation overlapping duration specifically includes: the attenuation overlap period is calculated based on the following equation 1, Wherein i represents an ith travel time period in the matching logic travel set, c _i represents the total number of the first logic travel in the ith travel time period, j represents a jth first logic travel in the ith travel time period, and γ represents a decay contribution rate,/>Representing the overlapping time length corresponding to the j-th first logic trip,/>And representing the attenuation overlapping time length corresponding to the j-th first logic trip.

2. The identification method of claim 1, wherein the first logical trip and the second logical trip each further comprise a trip shortest duration that constitutes one logical trip;

the calculating the track similarity of the first travel track and the second travel track according to the overlapping time after the attenuation processing specifically includes:

And calculating the similarity of the first travel track and the second travel track according to the overlapped time length after the attenuation processing, the travel shortest time length of the plurality of first logic travel and the travel shortest time length of the second logic travel which is not matched with the plurality of first logic travel.

3. The identification method of claim 1, wherein the first logical trip and the second logical trip each further comprise a trip shortest duration that constitutes one logical trip;

Respectively giving different weight coefficients to the shortest travel duration of the first logic travel in the matched logic travel set, the shortest travel duration of the first logic travel which is not matched with the plurality of second logic travel, and the shortest travel duration of the second logic travel which is not matched with the plurality of first logic travel;

And calculating the similarity of the first travel track and the second travel track according to the overlapped time length after the attenuation processing, the travel shortest time length of the first logic travel, the travel shortest time length of the second logic travel, and the travel shortest time length of the second logic travel.

4. The identification method of claim 1, wherein the first logical trip and the second logical trip each further comprise an inbound site, an outbound site, an inbound time, and an outbound time that make up a single logical trip;

the matching the first logic travel and the second logic travel to classify the first logic travel matched with the second logic travel into a matched logic travel set specifically includes:

Subtracting the inbound time of the second logic trip from the inbound time of the first logic trip to obtain an inbound time, and subtracting the outbound time of the first logic trip from the outbound time of the second logic trip to obtain an outbound time;

acquiring the shortest inbound time from an inbound site of the first logic trip to an inbound site of the second logic trip, and acquiring the shortest outbound time from an outbound site of the second logic trip to an outbound site of the first logic trip;

If the absolute value of the sum of the inbound time length and the shortest inbound time length is smaller than a preset time length threshold value, and the absolute value of the sum of the outbound time length and the shortest outbound time length is smaller than the preset time length threshold value, determining that the first logic travel and the second logic travel are matched, and classifying the first logic travel matched with the second logic travel into a matched logic travel set.

5. A passenger identification device, the device comprising:

The travel track acquisition module is configured to acquire a first travel track comprising a plurality of first logic travel based on a first passenger travel data source and acquire a second travel track comprising a plurality of second logic travel based on a second passenger travel data source; the first logic travel and the second logic travel respectively comprise travel time periods forming one logic travel;

the logic travel matching module is configured to match the first logic travel with the second logic travel so as to classify the first logic travel matched with the second logic travel into a matched logic travel set;

the overlapping duration obtaining module is configured to obtain a travel time period of overlapping the travel time period of the first logic travel in the matched logic travel set and the travel time period of the second logic travel matched by the travel time period of the first logic travel set, so as to obtain an overlapping duration corresponding to the overlapped travel time period;

The overlapping time length attenuation module is configured to attenuate the overlapping time length to obtain the attenuated overlapping time length;

The track similarity calculation module is configured to calculate the track similarity of the first travel track and the second travel track according to the overlapping duration after the attenuation processing;

a passenger identification module configured to identify a first passenger and a second passenger according to the trajectory similarity;

Wherein, the overlapping duration attenuation module includes:

The time length attenuation unit is configured to attenuate the overlapping time length corresponding to the first logic travel meeting the preset condition in the matched logic travel set so as to obtain attenuation overlapping time length;

A time length determining unit, configured to determine the attenuation overlapping time length and the overlapping time length corresponding to the first logic travel which does not meet the preset condition in the matched logic travel set as the attenuation processed overlapping time length;

Wherein the duration decay unit is further configured to calculate the decay overlap duration using equation 1 below, Wherein i represents an ith travel time period in the matching logic travel set, c _i represents the total number of the first logic travel in the ith travel time period, j represents a jth first logic travel in the ith travel time period, and γ represents a decay contribution rate,/>Representing the overlapping time length corresponding to the j-th first logic trip,/>And representing the attenuation overlapping time length corresponding to the j-th first logic trip.

6. The identification device of claim 5, wherein the first logical trip and the second logical trip each further comprise a trip shortest duration that constitutes one logical trip;

The trajectory similarity calculation module is further configured to: and calculating the similarity of the first travel track and the second travel track according to the overlapped time length after the attenuation processing, the travel shortest time length of the plurality of first logic travel and the travel shortest time length of the second logic travel which is not matched with the plurality of first logic travel.

7. The identification device of claim 5, wherein the first logical trip and the second logical trip each further comprise a trip shortest duration that constitutes one logical trip;

The track similarity calculation module comprises:

A weight coefficient giving unit configured to give different weight coefficients to a travel shortest time length of the first logical travel in the matched logical travel set, a travel shortest time length of the first logical travel that is not matched with the plurality of second logical travel, and a travel shortest time length of the second logical travel that is not matched with the plurality of first logical travel, respectively;

And a similarity calculating unit configured to calculate a track similarity of the first travel track and the second travel track according to the overlapping time length after the attenuation processing and the travel shortest time length of the first logic travel in the matching logic travel set respectively given with different weight coefficients, the travel shortest time length of the first logic travel which is not matched with the plurality of second logic travel, and the travel shortest time length of the second logic travel which is not matched with the plurality of first logic travel.

8. The identification device of claim 5, wherein the first logical trip and the second logical trip each further comprise an inbound site, an outbound site, an inbound time, and an outbound time that make up a single logical trip;

The logic trip matching module comprises:

The outbound time length determining unit is configured to subtract the inbound time of the second logic travel from the inbound time of the first logic travel to obtain an inbound time length, and subtract the outbound time of the first logic travel from the outbound time of the second logic travel to obtain an outbound time length;

A shortest arrival time length determining unit configured to obtain a shortest arrival time length from an arrival site of the first logical trip to an arrival site of the second logical trip, and obtain a shortest arrival time length from an arrival site of the second logical trip to an arrival site of the first logical trip;

The matching determining unit is configured to determine that the first logic travel is matched with the second logic travel and classify the first logic travel matched with the second logic travel into a matched logic travel set if the absolute value of the sum of the inbound time and the shortest inbound time is smaller than a preset time threshold and the absolute value of the sum of the outbound time and the shortest outbound time is smaller than the preset time threshold.

9. An electronic device, comprising:

At least one processor, and

A memory coupled to the at least one processor, the memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the method of identifying a passenger as claimed in any one of claims 1 to 4.

10. A readable storage medium storing executable instructions which, when executed, cause a machine to perform the method of identifying a passenger as claimed in any one of claims 1 to 4.