CN111584091A - Method and device for identifying cross infection risk of urban rail line level close contact person - Google Patents
Method and device for identifying cross infection risk of urban rail line level close contact person Download PDFInfo
- Publication number
- CN111584091A CN111584091A CN202010357460.5A CN202010357460A CN111584091A CN 111584091 A CN111584091 A CN 111584091A CN 202010357460 A CN202010357460 A CN 202010357460A CN 111584091 A CN111584091 A CN 111584091A
- Authority
- CN
- China
- Prior art keywords
- time
- train
- probability
- station
- risk
- 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.)
- Granted
Links
- 206010011409 Cross infection Diseases 0.000 title claims abstract description 178
- 206010029803 Nosocomial infection Diseases 0.000 title claims abstract description 178
- 238000000034 method Methods 0.000 title claims abstract description 88
- 238000009826 distribution Methods 0.000 claims abstract description 105
- 230000006399 behavior Effects 0.000 claims description 89
- 238000012545 processing Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 13
- 239000000203 mixture Substances 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 238000004904 shortening Methods 0.000 claims description 4
- 239000013589 supplement Substances 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 7
- 238000012216 screening Methods 0.000 abstract description 5
- 230000008451 emotion Effects 0.000 abstract description 4
- 238000013210 evaluation model Methods 0.000 abstract description 3
- 230000003542 behavioural effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 6
- 238000012546 transfer Methods 0.000 description 4
- 241000287107 Passer Species 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000002955 isolation Methods 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000005180 public health Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Public Health (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for identifying cross infection risks of urban rail line level close contacts. The method is based on behavioral science and data science, starts with microscopic travel behavior analysis, and constructs a probability distribution model of the traveling time of the risk exposure line site; from the perspective of iterative risk period, the range of close contacts with cross infection possibility is continuously reduced; performing model solution by using an EM algorithm, estimating the risk probability of cross-infection risk exposure trains and the cross-infection risk probability of the close contact persons, and establishing a risk grade evaluation model of the close contact persons; and forming an urban rail risk level decision support and information query device. The method is an important means for improving the suspected case screening precision and efficiency, provides a convenient and efficient query tool for the public to judge whether the suspected case screening is a close contact person, fills the blank of risk identification of the close contact person in the field of public transportation, and has great decision support significance for public emotion guidance and emergency resource deployment in emergencies.
Description
Technical Field
The invention relates to the technical field of rail transit passenger health management, in particular to a method and a device for identifying cross infection risks of urban rail line level close contacts.
Background
Urban rail transit (hereinafter referred to as urban rail) is an indispensable tool for public trips as the backbone force for public transportation operation in urban circles. The major public health emergencies have the characteristics of close contact and high transmission, and once the major public health emergencies occur under the urban rail network formation operation condition, the risk transmission speed is high, the transmission range is wide, and uncontrollable risks are easy to generate. However, urban rails, public transportation such as airplanes, railways, and buses have an accurate identification function of "one-ticket vehicle/machine", and if a confirmed or suspected case (hereinafter, referred to as a case) travels on the urban rails, since a plurality of trains can be logged in during the time of entering and leaving the station, it is impossible to quickly screen a close contact person (hereinafter, referred to as a passer) of the case only when the logged-in train is unknown on the basis of a physical route. Therefore, before case isolation and in a period with limited prevention and control measures, if a close receiver can be quickly identified and the cross infection risk level can be confirmed, the method has great decision support significance for providing accurate study and judgment, joint prevention and control, public emotion guidance and emergency resource deployment for relevant departments.
At present, in the prior art, methods related to epidemic situation isolation management and control and track tracking of a close contact are only related to track tracking and risk type division of the close contact in public transportation means such as airplanes, railways and buses, and for public transportation means such as urban rails, only basic information collection and release stages are involved, and no method or tool for automatically identifying cross infection risks of the close contact at the urban rail line level based on data driving is found. In addition, the method in the prior art is only suitable for cases to travel on one route of an urban rail road network, does not involve transfer and multiple routes, does not involve risk identification conditions of transfer passenger flow in the routes, and cannot screen close-splicers within the range of urban rail road network level.
Disclosure of Invention
The embodiment of the invention provides a method and a device for acquiring the cross infection risk level of rail transit close contacts, which overcome the problems in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme.
According to one aspect of the invention, a method for identifying the risk of cross infection of urban rail line-level close contacts is provided, which comprises the following steps:
step S1, acquiring a risk exposure line REL, a risk exposure physical path RER and travel duration of a case;
step S2, analyzing the microscopic trip behavior and trip time of the case according to the REL and the RER of the case and the trip time, and acquiring the physical trip path, the microscopic trip behavior and the trip process of the close receiver;
step S3, determining a cross infection risk exposure site RESFC set, a cross infection risk exposure train RETFC set and a cross infection risk exposure period REPFC according to the microscopic trip behavior and trip process constitution of the case and the physical trip path, microscopic trip behavior and trip process of the close receiver; the close contact is an urban rail line level close contact;
step S4, constructing a cross infection risk exposure physical path RERFC set and an effective train ET set of the close-contact person, giving a unique identification code to one piece of data, and constructing an initial data set Dataset (0) of the close-contact person containing the unique identification code of a case;
s5, constructing a passenger traveling time probability distribution model of each station in the risk exposure line REL containing hidden variables based on the initial data set Dataset (0) of the close contact;
step S6, solving a passenger traveling time probability distribution model based on an expectation maximization EM algorithm, and calculating the probability of the boarding trains of a passenger group and the distribution parameters of the passenger outbound traveling time;
step S7, calculating the distribution parameters of the passenger in-and-out station traveling time of each station according to the probability of the train on the journey of the passenger group and the distribution parameters of the passenger out-station traveling time, and calculating the cross infection risk probability of the train in the RETFC set and the train on the journey probability of a close receiver;
step S8, updating the cross infection risk exposure period REPFC in the step 3 based on the cross infection risk probability of the train in the RETFC set and the train landing probability of the close-coupled device, updating the Dataset (0) to be a cross-infected device risk data set Dataset (new) based on the updated REPFC, and keeping the unique identification code unchanged;
step S9, calculating the cross infection risk probability POC of the close-coupled person based on the cross-infected person risk data set (new);
and step S10, determining the cross infection risk level of the close contact according to the close contact cross infection risk probability POC and the set cross infection risk level division strategy.
Preferably, the acquiring of the risk exposure route REL, the risk exposure physical route RER, and the travel duration of the case in step S1 specifically includes:
step S011, determining intelligent traffic card number, trip time interval and trip origin-destination OD (origin-destination) information of a case;
step S012, inquiring basic information of line stations in a database, and determining the travel OD pair code of the case as follows:
the risk exposure physical path RER for a case is:
step S013, intelligent traffic card number and trip OD pair of case are used as indexes to inquire passenger AFC data in databaseDetermining the case record and the corresponding travel time wherein ,determining the trip duration of a case according to the trip time
Preferably, the analyzing the microscopic trip behavior and the trip time of the case according to the REL, RER and the trip duration of the case in the step S2 specifically includes:
step S021, analyzing microscopic travel behaviors contained in a travel link of a case, wherein the microscopic travel behaviors comprise: the travel OD comprises an inbound OD pair selection behavior, an inbound card swiping behavior, an inbound traveling behavior, an inbound waiting behavior, a boarding train selection behavior, an outbound traveling behavior and an outbound card swiping behavior;
step S022, obtaining travel time T corresponding to microscopic travel behaviors of the case, wherein the travel time T comprises the following steps: the station-entering traveling time AT, the station-entering waiting time WT, the riding time BT and the station-exiting traveling time ET, namely T is AT + WT + BT + ET;
preferably, the determining, in the step S3, the ESFC set, the RETFC set, and the REPFC according to the microscopic travel behavior and the travel process composition of the case, and the physical travel path, the microscopic travel behavior, and the travel process of the close contact specifically include:
step S031, according to the line site basic information, inquiring the same direction site on REL after the trip starting point of the case, and constructing the RESFC set
wherein ,indicating the origin of the case on the risk exposure line, liRepresents the ith station on the line l;
step S032, encoding the patient according to ODTime of trip wherein ,train in combination with automatic train positioning dataAnd constructing the RETFC set at the arrival time and the departure time:
wherein ,tiIs the ith train exposed to the risk of cross infection, and all trains in the RETFC set meet the following constraint conditions:
(1) the minimum entering and traveling time constraint of the starting station is that the departure time of the train at the starting station is greater than the entering card swiping time
wherein ,indicating a train tiAt case p origin station opThe time of departure of the vehicle is,indicating case p at origin station opAt the time of the card swiping at the arrival,represents opThe minimum entering and traveling time of the station, and t represents the maximum number of exposed trains with cross infection risk;
(2) a terminal minimum outbound travel time constraint. The arrival time of the train at the terminal station is less than the card swiping time of the train at the terminal station:
wherein ,indicating case p is at terminal dpAt the time of the outbound card swiping,indicating a train tiAt case p terminal dpThe time of arrival of the (c) signal,denotes dpThe minimum outbound running time of the station, and t represents the maximum number of exposed trains with cross infection risks;
step S033, determining REPFC, T according to AVL data of each train in RETFC setrepfc=[Tstart,Tend]The following conditions are satisfied:
wherein ,indicating a train t1The origination station l on the REL in the same direction as case p1At the time of arrival of the station,indicating the originating station l1The maximum inbound travel time of;indicating a train ttTerminal l on REL co-directional with case pnAt the time of departure from the station,indicating a terminalnThe maximum inbound travel time.
Preferably, the step S4 constructs a cross-infection risk exposure physical path RERFC set and an effective train ET set of the close receiver, specifically including:
S042, inquiring AFC data of an automatic fare collection system of urban rail transit in a database, determining an initial data set Dataset (0) of a close-coupled person, wherein the initial data set includes AFC data of a case, each record corresponds to a unique identification code, and each record contains an identity identification code, an ID card number, an arrival card swiping time, an exit card swiping time, an arrival station number and an exit station number;
and S043, constructing the secret contact ET set by combining the arrival time and the departure time of the train at the O and D stations in the automatic train positioning data according to the encoding and the trip time of the passenger OD and the automatic train positioning data by imitating the method for constructing the RETFC set in the step S032.
Preferably, the step S5 of constructing a passenger travel time probability distribution model of each station in the risk exposure line REL containing hidden variables based on the initial data set Dataset (0) of the close receiver specifically includes:
s051, assuming station traveling time distribution, and setting a passenger group comprising cases and close receivers, wherein the station traveling time of passengers on all stations on the REL is independent probability density distribution;
step S052, classifying passengers coming into station according to Trepfc=[Tstart,Tend]Total time period and REFRC setAnd in the middle OD pair, dividing the initial data set Dataset (0) of the close splicer into N types according to the time granularity delta t, wherein the N types comprise:
(1) converting the arrival card swiping time of the same OD to the observation data of the jth individual in the kth passenger groupAnd the time of outbound card swipingTime format, expressed in seconds
(2) Dividing initial data set Dataset (0) of the splicer into N types,
N=Tend-Tstart/Δt (9)
step S053, according to unknown definition of hidden variables of the train on which passengers board the platform, the hidden variables comprise:
(1)UDiunobserved data representing a k-th class passenger population
(2) By UDj kUnobserved data representing jth individual in kth passenger group
wherein ,
(3)πkrepresenting the probability of a class k passenger group boarding train,indicating the probability of class k passenger groups boarding the t-th train
(4) The supplement of the initial data set of the close receiver is satisfied by the complete data setWhich comprises the following steps:
step S054, representing the parameters to be estimated according to the probability density distribution parameters in the step S051 and the passenger boarding train probability variables in the step S053, wherein the method comprises the following steps:
(1) constructing parameters to be estimated for a k-th passenger group
wherein ,representing the probability of the class k passenger group boarding the ith train,representing site lsInternal outbound running time parameters;
(2) constructing a model parameter θ ═ θ1,…,θk,…,θN)(step);
Step S055, constructing likelihood function of passenger traveling time probability distribution model containing hidden variables
Step S056, converting the likelihood function into a log likelihood function
Step S057, maximization log-likelihood function
L(θ)=maxLc(θ)=max(logP(tin,tout,UD|θ)) (20)
Preferably, the solving of the probability distribution model of the passenger travel time based on the expectation-maximization EM algorithm in the step S6 is performed to calculate the distribution parameters of the probability of the boarding trains of the passenger population and the passenger outbound travel time, and specifically includes:
step S061 of determining an initial parameter value θ ═ θ(0);
Step S062, E-step calculation is carried out, and observation data (t) is combinedin,tout) At θ ═ θ(step)Lower computation Q function Q (θ)
Q(θ)=E(Lc(θ)|(tin,tout),θ(step)) (21)
wherein ,θ(step)Is the estimated value of the step theta of the algorithm;
step S063, M-step calculation, maximization Q function Q(step)(theta) to update the parameter estimate theta(step+1)=argmaxQ(step)(θ)
Wherein, the probability of the train of the kth class passenger group in the step +1 isMethod for calculating distribution parameters of passenger outbound travel time by using L-BFGS-B optimization method
Step S064, step S062, and step S063 are alternately performed until the algorithm converges.
Preferably, the step S7 of calculating the distribution parameters of the passenger arrival/departure travel time of each station, the cross infection risk probability of the train in the tfc set, and the train departure probability of the close receiver according to the distribution parameters of the passenger arrival/departure travel time and the boarding probability of the passenger group specifically includes:
step S071 of obtaining the final parameter estimation resultAnd distribution parameters of outbound traveling time of each site of risk line REL
wherein ,representing the probability of a class k passenger group for a train on the way;representing site lsThe passenger outbound traveling time distribution parameter;
step S072, according to AFC data between OD pairs, calculating each station l of the risk exposure linesDistribution parameter of passenger outbound traveling time
Step S073, fitting a station arrival traveling time distribution curve according to the station arrival traveling time distribution of passengers, and determining each station l of the risk exposure linesPassenger station-entering running time parameterNumber of
And distinguishing a case and a passerby according to the unique identification codes, and identifying the cross infection risk probability and the train boarding probability of the passerby in the RETFC set.
Preferably, the updating of the cross infection risk exposure period REPFC in step S8, the updating Dataset (0) being a cross infector risk Dataset (new), the unique identification code being unchanged, specifically includes:
exposing each station l of the line according to said risksDistribution parameter of passenger in-and-out-of-station traveling time and calculation formula T of REPFCrepfc=[Tstart,Tend]And updating the REPFC, shortening the minimum on-station card swiping time and the maximum off-station card swiping time of the Dataset (0) based on the time length of the updated REPFC, and updating the cross infector risk data set Dataset (new), wherein the total time length of the Dataset (new) is less than that of the Dataset (0).
Preferably, the calculating of the close-coupled device cross-infection risk probability POC based on the cross-infected device risk data set (new) in step S9 specifically includes:
step S091, extracting case data according to the unique identification code, and confirming the risk probability of each train in the RETFC set
wherein ,shows that case p belongs to the kth passenger group and trains in the journey RETFC setA risk probability value of (a);
step S092, according to the RETFC set train numberAll trains logged in index dataset (new)Close contact of the train, pick up the train on the wayProbability of risk
wherein ,shows that the subscriber j belongs to the kth passenger group and the train in the journey RETFC setA probability value of (d);
step S093, calculating POC (Point of sale) of cross infection risk probability of close receiver
According to another aspect of the present invention, there is provided an urban rail line level close contact person cross infection risk identification device, comprising:
the information acquisition module is used for acquiring a risk exposure line REL, a risk exposure physical path RER and travel time of a case, analyzing microscopic travel behaviors and travel time of the case according to the REL, the RER and the travel time of the case, and acquiring the travel physical path, the microscopic travel behaviors and the travel process of the close-coupled person;
the data analysis and processing module is used for determining a cross infection risk exposure site RESFC set, a cross infection risk exposure train RETFC set and a cross infection risk exposure period REPFC according to the microcosmic travel behavior and travel process composition of the case and the physical travel path, microcosmic travel behavior and travel process of the close receiver; constructing a remote cross infection exposure physical path (REFRC) set and an effective train ET set of a close receiver, giving a unique identification code to one piece of data, and constructing a close receiver initial data set (0) containing the unique identification code of a case;
the model building and calculating module is used for building a passenger traveling time probability distribution model of each station in the risk exposure line REL containing hidden variables based on the initial data set Dataset (0) of the close-connected person; solving a passenger traveling time probability distribution model based on an expectation maximization EM algorithm, and calculating the probability of the trains on the journey of the passenger group and the distribution parameters of the passenger outbound traveling time; calculating passenger in-out station traveling time distribution parameters of each station according to the boarding train probability of the passenger group and the distribution parameters of the passenger out-station traveling time, and calculating the cross infection risk probability of the trains in the RETFC set and the boarding probability of the close-receiver trains;
updating the cross infection risk exposure period REPFC in the step 3 based on the cross infection risk probability of the train in the RETFC set and the train landing probability of the close-coupled device, updating the Dataset (0) to be a cross-infected device risk data set Dataset (new) based on the updated REPFC, and keeping the unique identification code unchanged; calculating the cross-infection risk probability POC of the close-coupled person based on the cross-infected person risk data set (new).
The decision support module is used for setting the cross infection risk level and issuing information;
and the risk grade query module is used for determining the cross infection risk grade of the close-coupled person according to the close-coupled person cross infection risk probability POC and the set cross infection risk grade division strategy and providing a public query function.
According to the technical scheme provided by the embodiment of the invention, the method for acquiring the cross infection risk level of the rail transit line-level close contact person is based on statistics, behavior science and data science, starts with microscopic trip behavior analysis, provides a risk train set generation method and a boarding train matching generation method, and constructs a probability distribution model of the traveling time of each station of the risk exposure line containing hidden variables; continuously reducing the screening range of the close contacts with the possibility of cross infection from the angle of the iterative risk time interval window; and (3) carrying out model solution by using an expectation maximization EM algorithm, estimating the risk probability of the cross-infection risk exposure train and the cross-infection risk probability of the close contact person, and establishing a close contact person risk level evaluation model on the basis.
The method provided by the embodiment of the invention can be suitable for a scene that a case travels on a plurality of lines and is transferred on different lines, and can screen passers by taking the urban rail network level as a range and acquire the cross infection risk level of the transfer passenger flow in different lines.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a processing flow chart of a method for acquiring a cross infection risk level of a rail transit person in close contact according to an embodiment of the present invention.
Fig. 2 is a circuit diagram of the risk of cross infection of a case provided by the embodiment of the invention.
Fig. 3 is a schematic view of a microscopic behavior analysis of a subway-boarding train scheme provided by an embodiment of the present invention.
Fig. 4 is a graph showing a time distribution of outbound site travel of confirmed or suspected cases according to an embodiment of the present invention.
FIG. 5 is a probability of risk ranking plot for an embodiment of the present invention;
fig. 6 is a specific structural diagram of an urban rail line-level close-contact person cross-infection risk identification device according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
For the convenience of understanding the embodiments of the present invention, the following description will be further explained by taking several specific embodiments as examples in conjunction with the drawings, and the embodiments are not to be construed as limiting the embodiments of the present invention.
Example one
The embodiment of the invention provides a risk identification method of an urban rail transit line level close contact person (hereinafter referred to as a close contact person) based on data driving, and an implementation principle schematic diagram of the method is shown in figure 1 and comprises the following processing steps:
step S1, acquiring a Risk Exposure Line (REL), a Risk exposure physical route (RER) and a trip duration of the case;
the risk exposure line REL is a case riding line, the risk exposure physical path RER is an interval through which an OD pair of a case trip passes, for example, the case trips on a fourth line, the OD pair is a west door-safety lining, the risk exposure line REL is a 4 th line, and the risk exposure physical path RER is an interval of the west door-safety lining.
Step S2, analyzing the microscopic travel behavior and travel time of the case, relating to the same case of the analysis method of the physical travel path, the microscopic travel behavior and the travel process of the close contact;
step S3, determining a set of Risk Exposure Sites (RESFC), a set of Risk exposure trains (tfc), and a REPFC);
step S4, constructing a task exposure route (RERFC) set and an Effective Train (ET) set of the splicer, wherein the Effective train ET set is constructed in the same manner as the RETFC set in step 3, and a splicer initial data set Dataset (0) containing a unique identification code of a case is constructed;
and S5, constructing a passenger traveling time probability distribution model of each station in the risk exposure line REL containing hidden variables based on the initial data set Dataset (0) of the close contact.
And step S6, solving the passenger traveling time probability distribution model based on an Expectation-maximization (EM) algorithm, and calculating the boarding train probability of the passenger group and the distribution parameters of the passenger outbound traveling time.
Step S7, calculating the distribution parameters of the passenger in-and-out station traveling time of each station according to the probability of the train on the journey of the passenger group and the distribution parameters of the passenger out-station traveling time, and calculating the cross infection risk probability of the train in the RETFC set and the train on the journey probability of a close receiver;
step S8, updating the cross infection risk exposure period REPFC in the step 3 based on the cross infection risk probability of the train in the RETFC set and the train landing probability of the close-coupled device, updating the Dataset (0) to be a cross-infected device risk data set Dataset (new) based on the updated REPFC, and keeping the unique identification code unchanged;
step S9, calculating the Probability of cross infection risk (POC) of the close contact based on the cross infection risk data set (new);
and step S10, determining the cross infection risk level of the close contact according to the close contact cross infection risk probability POC and the set cross infection risk level division strategy.
In a specific embodiment of the present invention, the step 1 of obtaining a risk exposure route REL, a risk exposure physical route RER, and a trip duration of a case specifically includes:
step S011, determining intelligent transportation card number, trip time period and trip Origin-Destination (OD) peer information of a case according to forms of case reporting, network collection, publication newspaper consulting and telephone confirmation;
step S012, inquiring basic information of line stations in a basic information database of the rail transit line, and determining the travel OD pair code of the case as follows:
the risk exposure physical path RER for a case is:
wherein ,the starting station of the patient p on the line l is shown asThe arrival station isThe travel route of (2); lmRepresenting the set of all stations on the line l; lo、ldIndicating a certain station on line i.
Step S013, using the intelligent transportation card number and the travel OD pair of the case as indexes, inquiring the passenger card swiping transaction record (AFC) data in the database, and determining the case record and the corresponding travel time( wherein ,) Determining the trip duration of the case according to the trip time
In a specific embodiment of the present invention, the analyzing step 2 includes analyzing microscopic trip behavior and trip time of the case, and specifically includes:
step S021, analyzing microscopic travel behaviors contained in a travel link of the case, wherein the microscopic travel behaviors comprise: the travel OD comprises an inbound OD pair selection behavior, an inbound card swiping behavior, an inbound traveling behavior, an inbound waiting behavior, a boarding train selection behavior, an outbound traveling behavior and an outbound card swiping behavior;
step S022, the OD inter-pair microscopic trip behavior of the case in step 021 corresponds to four travel times, which include: an Access Time (AT), a Waiting Time (WT), a Boarding Time (BT), and an outbound Time (ET), that is, T is AT + WT + BT + ET;
in the embodiment of the present invention, the step 3 of confirming the cross infection risk exposure site RESFC set, the cross infection risk exposure train reffc set, and the cross infection risk exposure period REPFC specifically includes:
step S031, according to the line site basic information, inquiring the same direction site on REL after the trip starting point of the case, and constructing the RESFC set
wherein ,indicating the origin of the case on the risk exposure line, liRepresents the ith station on the line l;
step S032, encoding the patient according to ODTime of trip( wherein ,) Combining the train in the Automatic Vehicle Location (AVL) dataAnd (2) a Train Arrival Time (TAT) and a Departure Time (TDT), constructing the RETFC set
wherein ,tiIs the ith train exposed to the risk of cross infection, and all trains in the RETFC set meet the following constraint conditions:
(1) the minimum entering and traveling time constraint of the starting station is that the departure time of the train at the starting station is greater than the entering card swiping time
wherein ,indicating a train tiAt case p origin station opThe time of departure of the vehicle is,indicating case p at origin station opAt the time of the card swiping at the arrival,represents opThe minimum entering and traveling time of the station, and t represents the maximum number of exposed trains with cross infection risk;
(2) a terminal minimum outbound travel time constraint. The arrival time of the train at the terminal station is less than the card swiping time of the train at the terminal station:
wherein ,indicating case p is at terminal dpAt the time of the outbound card swiping,indicating a train tiAt case p terminal dpThe time of arrival of the (c) signal,denotes dpThe minimum outbound running time of the station, and t represents the maximum number of exposed trains with cross infection risks;
step S033, determining REPFC, T according to the automatic positioning data of each train in the RETFC setrepfc=[Tstart,Tend]The following conditions are satisfied:
wherein ,indicating a train t1The origination station l on the REL in the same direction as case p1At the time of arrival of the station,indicating the originating station l1The maximum inbound travel time of;indicating a train ttTerminal l on REL co-directional with case pnAt the time of departure from the station,indicating a terminalnThe maximum inbound travel time of;
in the specific embodiment of the present invention, step 4 constructs a cross-infection risk exposure physical path RERFC set and an effective train ET set of a close receiver, which specifically include:
Step S042, inquiring AFC (Automatic Fare Collection System) data in a database, determining an initial data set Dataset (0) of a close receiver, including AFC data of a case, and giving each record corresponding to a unique identification code, wherein the unique identification code comprises an identity identification code, an ID card number, an arrival card swiping time, an departure card swiping time, an arrival station number and an departure station number;
step S043, constructing the secret contact ET set according to the encoding and the trip time of the passenger OD pair and the arrival time and the departure time of the train at the O and D stations in the automatic train positioning data by imitating the RETFC set constructing method in the step S032;
in a specific embodiment of the present invention, the constructing a passenger travel time probability distribution model of each station in the risk exposure line REL containing hidden variables based on the initial data set Dataset (0) of the close-contact recipient in step 5 specifically includes:
step S051, assuming station traveling time distribution, and assuming that a case and a close receiver are both passengers, the following passengers are uniformly represented, wherein the station traveling time of all the station passengers on the REL is independent and uniformly distributed, and the station traveling time distribution can be assumed to be a certain probability density distribution such as normal distribution, gamma distribution and the like according to experience or actual data verification;
step S052, classifying passengers coming into station according to Trepfc=[Tstart,Tend]Total time period and REFRC setAnd (3) dividing Dataset (0) into N types according to the time granularity delta t, wherein the N types comprise:
(1) converting the arrival card swiping time of the same OD to the observation data of the jth individual in the kth passenger groupAnd the time of outbound card swipingTime format, expressed in seconds
(2) Dividing initial data set Dataset (0) of the splicer into N types,
N=Tend-Tstart/Δt (9)
step S053, defining a hidden variable according to the unknown getting-on event of the passenger in the platform, wherein the hidden variable comprises:
(1)UDiis shown asUnobserved data for class k passenger groups
wherein ,
(3)πkrepresenting the probability of a class k passenger population stepping on,indicating the probability of class k passenger groups boarding the t-th train
(4) The supplement of the initial data set of the close receiver is satisfied by the complete data setWhich comprises the following steps:
step S054, representing the parameters to be estimated according to the probability density distribution parameters in the step S051 and the passenger boarding train probability variables in the step S053, wherein the method comprises the following steps:
(1) constructing parameters to be estimated for a k-th passenger group
wherein ,representing the probability of the class k passenger group boarding the ith train,representing site lsInternal outbound running time parameters;
(2) constructing a model parameter θ ═ θ1,…,θk,…,θN)(step);
Step S055, constructing likelihood function of passenger traveling time probability distribution model containing hidden variables
Step S056, converting the likelihood function into a log likelihood function
Step S057, maximization log-likelihood function
L(θ)=maxLc(θ)=max(logP(tin,tout,UD|θ)) (20)
In a specific embodiment of the present invention, step 6 is to solve the passenger travel time probability distribution model based on the expectation-maximization EM algorithm, and calculate distribution parameters of the boarding train probability and the passenger outbound travel time of the passenger population, and specifically includes:
step S061 of determining an initial parameter value θ ═ θ(0);
Step S062, E-step calculation is carried out, and observation data (t) is combinedin,tout) At θ ═ θ(step)Lower computation Q function Q (θ)
Q(θ)=E(Lc(θ)|(tin,tout),θ(step)) (21)
wherein ,θ(step)Is the estimated value of the step theta of the algorithm;
step S063, M-step calculation, maximization Q function Q(step)(theta) to update the parameter estimate theta(step+1)=argmaxQ(step)(θ)
Wherein, the probability of the train of the kth class passenger group in the step +1 isMethod for calculating distribution parameters of passenger outbound travel time by using L-BFGS-B optimization method
Step S064, step S062 and step S063 are alternately carried out until the algorithm is converged;
in the specific embodiment of the present invention, the step 7 of calculating the passenger in-out station travel time distribution parameters of each station, the cross infection risk probability of trains in the tfc set, and the close receiver train trip probability according to the passenger group in-trip train probability and the passenger out-station travel time distribution parameters specifically includes:
step S071 of obtaining the final parameter estimation resultAnd distribution parameters of outbound traveling time of each site of risk line REL
wherein ,representing the probability of a class k passenger group for a train on the way;representing site lsThe passenger outbound traveling time distribution parameter;
step S072, according to AFC data between OD pairs, calculating each station l of the risk exposure linesDistribution parameter of passenger outbound traveling time
Step S073, fitting a station entering traveling time distribution curve according to the passenger 'S exiting traveling time distribution, and determining the passenger' S entering traveling time parameter
In an embodiment of the present invention, the updating of the period of time of exposure to cross-infection Risk (REPFC) in step 8 updates Dataset (0) to the cross-infectors risk Dataset (new), and the unique identification code is not changed, and specifically includes:
updating the REPFC according to the parameters obtained in the step 7 in S072 and S073 and the REPFC calculation formula in the step 3 in S033, shortening the minimum inbound card swiping time and the maximum outbound card swiping time of the Dataset (0) based on the time length of the updated REPFC, and updating the cross infector risk data set Dataset (new), wherein the total time length of the obtained Dataset (new) is less than the Dataset (0);
in a specific embodiment of the present invention, the calculating the close-coupled person cross-infection risk probability POC in step 9 based on the cross-infected person risk data set (new) specifically includes:
step S091, extracting case data according to the unique identification code, and confirming the risk probability of each train in the RETFC set
wherein ,shows that case p belongs to the kth passenger group and trains in the journey RETFC setA risk probability value of (a);
step S092, according to the RETFC set train numberAll trains logged in index dataset (new)Close contact of the train, pick up the train on the wayProbability of risk
wherein ,shows that the subscriber j belongs to the kth passenger group and the train in the journey RETFC setA probability value of (d);
step S093, calculating cross infection risk probability of close-coupled person
In an embodiment of the present invention, the determining the cross infection risk level of the close-coupled device according to the close-coupled device cross infection risk probability POC in step 10 specifically includes:
dividing four risk levels of low cross infection risk, general cross infection risk, high cross infection risk and extremely high cross infection risk, wherein the risk probability value ranges respectively corresponding to the low cross infection risk, the general cross infection risk, the high cross infection risk and the extremely high cross infection risk are as follows: { (0,0.25], (0.25,0.5], (0.5,0.75], (0.75,1] };
determining the cross infection risk level of the close receiver as follows according to the risk probability value range corresponding to the value of the close receiver cross infection risk probability POC: low risk of cross-infection, general risk of cross-infection, high risk of cross-infection, or very high risk of cross-infection.
Example two
The risk level of a person in close contact (hereinafter, referred to as a close contact) is automatically identified by taking a subway-found behavior case of confirmed or suspected cases (hereinafter, referred to as cases) in Beijing City, and the process of the invention is as follows:
1. according to the case card number 5 XXXXXXX 9, acquiring a case risk exposure line REL as a certain line l69,l61]The risk exposure physical path RER isThe arrival time is 08:17:00, the conversion second is 29820, the departure time is 08:31:03, the conversion second is 30663, the trip time length is 14min, and the cross infection risk circuit diagram RER is shown in figure 2;
2. analyzing the microscopic trip behavior and trip process constitution of a case, wherein the starting station is a first-sending station l69The direction is downlink, RER is a line-level transfer-free path, and the total number of the stations is 10 { l }69,l65,l63,l61,l59,l57,l55,l53,l51,l49}; the microscopic travel behaviors comprise: the travel OD comprises an inbound OD pair selection behavior, an inbound card swiping behavior, an inbound traveling behavior, an inbound waiting behavior, a boarding train selection behavior, an outbound traveling behavior and an outbound card swiping behavior; the corresponding travel time includes: entering station and running time AT, entering station and waitingThe time WT, the taking time BT and the outbound running time ET, and the microscopic travel behavior and travel time composition are also suitable for travel analysis of a passerby, the travel time composition is described by taking a first vehicle with case ability to step on a journey, and a schematic diagram of the microscopic behavior analysis of a subway journey train scheme is shown in FIG. 3;
3. determining a set of cross-infection risk exposed sites RESFCSince the case starting station is the starting station, stations after the starting station are all listed as RESFC aggregate elements as destinations;
determining a RETFC set of the cross-infection risk exposure train according to the AFC data and the AVL dataNamely, the case has two trains which can possibly ascend during the subway trip;
setting initial maximum in-and-out-of-station traveling time, and determining the REPFC (cross infection risk exposure period) as Trepfc(0)=[07:48:00,9:20:50]I.e., [28080s,33650s];
4. Determining a remote access control (RERFC) set of subway cross-infection risk exposure physical paths of close-splicers, wherein the starting station of the case is the originating station, so that OD pairs in the downlink direction formed by all stations on the line are included, and 10 × 9/2-45 pairs in total;
5. constructing a splicer initial data set Dataset (0) containing a unique identification code of a case, wherein the splicer initial data set Dataset contains AFC data of the case, and 7744 AFC data are calculated in total;
6. constructing a probability distribution model of passenger traveling time of each station of a risk exposure line containing hidden variables, and assuming that the passenger traveling time distribution obeys gamma distribution; the precision of the time when a passenger arrives at the station and swipes the card is 1min, and the 1min is assumed as a window to divide the same OD pairs of passengers, namely delta t is equal to 1min and equal to 60 s;
7. solving the model based on the EM algorithm, wherein the parameter estimation result of the case isOutbound site travel time minutesFIG. 4 shows the result values of parameter estimation of other individualsNot listed here;
8. probability of risk for each train in the retc setAccording to the contact person ET groupThe number of any one train can determine that the total number of close receivers on the same line is 788;
9. updating REPFC to T according to distribution probability density function of incoming and outgoing traveling time of line start station and line stop station and REPFC calculation formularepfc(new)=[07:56:00,08:56:50]I.e., [28560s,32210 s)]Updating Dataset (0) into a cross-infected person risk Dataset (new), wherein 5069 AFC data are counted, and the total number of individuals with the risk of cross infection is reduced to 767;
10. estimating a risk probability value according to a cross infection risk probability formula of the close-coupled person, and determining that 635 persons exist in the close-coupled person on the same line according to the risk probability value;
11. the cross infection risk level of the close contact is determined according to the close contact cross infection risk probability POC and the set cross infection risk level division strategy, and the risk probability level distribution situation of the close contact provided by the embodiment of the invention is shown in FIG. 5.
EXAMPLE III
The embodiment provides a cross infection risk identification device for urban rail line-level close contact persons, the specific structure of which is shown in fig. 6 and comprises:
the information acquisition module 61 is attached to the back-end processing module and is used for acquiring a risk exposure line REL, a risk exposure physical path RER and travel time of a case, analyzing microscopic travel behaviors and travel time of the case according to the REL, the RER and the travel time of the case, and acquiring a physical travel path, the microscopic travel behaviors and a travel process of a close receiver;
a data analysis and processing module 62, which is subordinate to the back-end processing module, and is used for inquiring the REL number of the case risk exposure line, the RER number of the risk exposure physical path, the RESFC number of the cross-infection risk exposure station, the RETFC train number of the cross-infection risk exposure train, and the RERFC set OD pair number of the cross-infection risk exposure physical path of the splicer; for preprocessing AFC data of the splicer data set. Determining a cross infection risk exposure site RESFC set, a cross infection risk exposure train RETFC set and a cross infection risk exposure period REPFC according to the microcosmic travel behavior and travel process composition of the case, and the physical travel path, microcosmic travel behavior and travel process of the close-connected person; constructing a remote cross infection exposure physical path (REFRC) set and an effective train ET set of a close receiver, giving a unique identification code to one piece of data, and constructing a close receiver initial data set (0) containing the unique identification code of a case;
the model building and calculating module 63 is subordinate to the back-end processing module and is used for building a passenger walking time probability distribution model of each station in the risk exposure line REL containing hidden variables based on the initial data set Dataset (0) of the close receiver; solving a passenger traveling time probability distribution model based on an expectation maximization EM algorithm, and calculating the probability of the trains on the journey of the passenger group and the distribution parameters of the passenger outbound traveling time; calculating passenger in-out station traveling time distribution parameters of each station according to the boarding train probability of the passenger group and the distribution parameters of the passenger out-station traveling time, and calculating the cross infection risk probability of the trains in the RETFC set and the boarding probability of the close-receiver trains;
updating the cross infection risk exposure period REPFC in the step 3 based on the cross infection risk probability of the train in the RETFC set and the train landing probability of the close-coupled device, updating the Dataset (0) to be a cross-infected device risk data set Dataset (new) based on the updated REPFC, and keeping the unique identification code unchanged; calculating the cross-infection risk probability POC of the close-coupled person based on the cross-infected person risk data set (new).
A decision support module 64 which is subordinate to the back-end processing module and is used for setting the cross infection risk level and carrying out decision support such as information release, emergency command, public emotion dispersion and the like;
and the risk level inquiry module 65 is subordinate to the front-end information issuing module and is used for assisting the public to inquire whether the person is a close receiver. And determining the cross infection risk level of the close-coupled person according to the close-coupled person cross infection risk probability POC and the set cross infection risk level classification strategy.
Preferably, the specific processing procedure of the information obtaining module 61 for obtaining the risk exposure route REL, the risk exposure physical route RER, and the trip duration of the case includes:
step S011, determining intelligent traffic card number, trip time interval and trip origin-destination OD (origin-destination) information of a case;
step S012, inquiring basic information of line stations in a database, and determining the travel OD pair code of the case as follows:
step S013, using intelligent traffic card number and trip OD pair of the case as indexes, inquiring AFC data of passengers in the database, and determining case records and corresponding trip time wherein ,determining the trip duration of a case according to the trip time
Preferably, the information obtaining module 61 analyzes the microscopic trip behavior and trip time of the case according to the REL, RER and trip duration of the case, and the specific processing procedure includes:
step S021, analyzing microscopic travel behaviors contained in a travel link of a case, wherein the microscopic travel behaviors comprise: the travel OD comprises an inbound OD pair selection behavior, an inbound card swiping behavior, an inbound traveling behavior, an inbound waiting behavior, a boarding train selection behavior, an outbound traveling behavior and an outbound card swiping behavior;
step S022, obtaining travel time T corresponding to microscopic travel behaviors of the case, wherein the travel time T comprises the following steps: the station-entering traveling time AT, the station-entering waiting time WT, the riding time BT and the station-exiting traveling time ET, namely T is AT + WT + BT + ET;
preferably, the data analysis and processing module 62 determines the ESFC set, the RETFC set, and the REPFC according to the microscopic trip behavior and trip process composition of the case, and the physical trip path, the microscopic trip behavior, and the trip process of the close receiver, and the specific processing process includes:
step S031, according to the line site basic information, inquiring the same direction site on REL after the trip starting point of the case, and constructing the RESFC set
wherein ,indicating the origin of the case on the risk exposure line, liIndicates the first on the line liEach site;
step S032, encoding the patient according to ODTime of trip wherein ,train in combination with automatic train positioning dataAnd constructing the RETFC set at the arrival time and the departure time:
wherein ,tiIs the ith train exposed to the risk of cross infection, and all trains in the RETFC set meet the following constraint conditions:
(1) the minimum entering and traveling time constraint of the starting station is that the departure time of the train at the starting station is greater than the entering card swiping time
wherein ,indicating a train tiAt case p origin station opThe time of departure of the vehicle is,indicating case p at origin station opAt the time of the card swiping at the arrival,represents opThe minimum entering and traveling time of the station, and t represents the maximum number of exposed trains with cross infection risk;
(2) a terminal minimum outbound travel time constraint. The arrival time of the train at the terminal station is less than the card swiping time of the train at the terminal station:
wherein ,indicating case p is at terminal dpAt the time of the outbound card swiping,indicating a train tiAt case p terminal dpThe time of arrival of the (c) signal,denotes dpThe minimum outbound running time of the station, and t represents the maximum number of exposed trains with cross infection risks;
step S033, determining REPFC, T according to AVL data of each train in RETFC setrepfc=[Tstart,Tend]The following conditions are satisfied:
wherein ,indicating a train t1The origination station l on the REL in the same direction as case p1At the time of arrival of the station,indicating the originating station l1The maximum inbound travel time of;indicating a train ttTerminal l on REL co-directional with case pnAt the time of departure from the station,indicating a terminalnThe maximum inbound travel time.
Preferably, the data analysis and processing module 62 constructs a cross infection risk exposure physical path RERFC set and an effective train ET set of the close receiver, and the specific processing procedure includes:
S042, inquiring AFC data of an automatic fare collection system of urban rail transit in a database, determining an initial data set Dataset (0) of a close-coupled person, wherein the initial data set includes AFC data of a case, each record corresponds to a unique identification code, and each record contains an identity identification code, an ID card number, an arrival card swiping time, an exit card swiping time, an arrival station number and an exit station number;
and S043, constructing the secret contact ET set by combining the arrival time and the departure time of the train at the O and D stations in the automatic train positioning data according to the encoding and the trip time of the passenger OD and the automatic train positioning data by imitating the method for constructing the RETFC set in the step S032.
Preferably, the model building and calculating module 63 includes a model building module and a model calculating module.
The model building module is used for building a passenger traveling time probability distribution model of each station in the risk exposure line REL containing hidden variables based on the initial data set Dataset (0) of the close receiver, and the specific processing process comprises the following steps:
s051, assuming station traveling time distribution, and setting a passenger group comprising cases and close receivers, wherein the station traveling time of passengers on all stations on the REL is independent probability density distribution;
step S052, classifying passengers coming into station according to Trepfc=[Tstart,Tend]Total time period and REFRC setAnd in the middle OD pair, dividing the initial data set Dataset (0) of the close splicer into N types according to the time granularity delta t, wherein the N types comprise:
(1) converting the arrival card swiping time of the same OD to the observation data of the jth individual in the kth passenger groupAnd the time of outbound card swipingTime format, expressed in seconds
(2) Dividing initial data set Dataset (0) of the splicer into N types,
N=Tend-Tstart/Δt (8)
step S053, according to unknown definition of hidden variables of the train on which passengers board the platform, the hidden variables comprise:
(1)UDiunobserved data representing a k-th class passenger population
wherein ,
(3)πkrepresenting the probability of a class k passenger group boarding train,indicating the probability of class k passenger groups boarding the t-th train
(4) The supplement of the initial data set of the close receiver is satisfied by the complete data setWhich comprises the following steps:
UD=(UD1,…,UDk,…,UDN) (15)
step S054, representing the parameters to be estimated according to the probability density distribution parameters in the step S051 and the passenger boarding train probability variables in the step S053, wherein the method comprises the following steps:
wherein ,representing the probability of the class k passenger group boarding the ith train,representing site lsInternal outbound running time parameters;
(2) constructing a model parameter θ ═ θ1,…,θk,…,θN)(step);
Step S055, constructing likelihood function of passenger traveling time probability distribution model containing hidden variables
Step S056, converting the likelihood function into a log likelihood function
Step S057, maximization log-likelihood function
L(θ)=maxLc(θ)=max(logP(tin,tout,UD|θ)) (19)
Preferably, the model operation module solves the probability distribution model of the passenger travel time based on the expectation maximization EM algorithm, and calculates the probability of the trains entering the passenger population and the distribution parameters of the passenger outbound travel time, and the specific processing procedure includes:
step S061 of determining an initial parameter value θ ═ θ(0);
Step S062, E-step calculation is carried out, and observation data (t) is combinedin,tout) At θ ═ θ(step)Lower computation Q function Q (θ)
Q(θ)=E(Lc(θ)|(tin,tout),θ(step)) (20)
wherein ,θ(step)Is the estimated value of the step theta of the algorithm;
step S063, M-step calculation, maximization Q function Q(step)(theta) to update the parameter estimate theta(step+1)=argmaxQ(step)(θ)
Wherein, the probability of the train of the kth class passenger group in the step +1 isMethod for calculating distribution parameters of passenger outbound travel time by using L-BFGS-B optimization method
Step S064, step S062, and step S063 are alternately performed until the algorithm converges.
Preferably, the model operation module calculates the distribution parameters of the passenger in-and-out station traveling time of each station, the cross infection risk probability of the train in the RETFC set, and the train boarding probability of the close receiver according to the distribution parameters of the boarding train probability and the passenger out-of-station traveling time of the passenger group, and the specific processing procedure includes:
step S071 of obtaining the final parameter estimation resultAnd distribution parameters of outbound traveling time of each site of risk line REL
wherein ,representing the probability of a class k passenger group for a train on the way;representing site lsThe passenger outbound traveling time distribution parameter;
step S072, according to AFC data between OD pairs, calculating each station l of the risk exposure linesDistribution parameter of passenger outbound traveling time
Step S073, fitting a station arrival traveling time distribution curve according to the station arrival traveling time distribution of passengers, and determining each station l of the risk exposure linesTime parameter of passenger entering station
And distinguishing a case and a passerby according to the unique identification codes, and identifying the cross infection risk probability and the train boarding probability of the passerby in the RETFC set.
Preferably, the model operation module updates the cross infection risk exposure period REPFC, updates Dataset (0) to be a cross infector risk data set Dataset (new), and the unique identification code is not changed, and the specific processing procedure includes:
exposing each station l of the line according to said risksDistribution parameter of passenger in-and-out-of-station traveling time and calculation formula T of REPFCrepfc=[Tstart,Tend]And updating the REPFC, shortening the minimum on-station card swiping time and the maximum off-station card swiping time of the Dataset (0) based on the time length of the updated REPFC, and updating the cross infector risk data set Dataset (new), wherein the total time length of the Dataset (new) is less than that of the Dataset (0).
Preferably, the model operation module calculates the close-coupled device cross-infection risk probability POC based on a cross-infected device risk data set (new), and the specific processing procedure includes:
step S091, extracting case data according to the unique identification code, and confirming the risk probability of each train in the RETFC set
wherein ,shows that case p belongs to the kth passenger group and trains in the journey RETFC setA risk probability value of (a);
step S092, according to the RETFC set train numberAll trains logged in index dataset (new)Close contact of the train, pick up the train on the wayProbability of risk
wherein ,shows that the subscriber j belongs to the kth passenger group and the train in the journey RETFC setA probability value of (d);
step S093, calculating POC (Point of sale) of cross infection risk probability of close receiver
Preferably, the risk level query module 65 determines the cross infection risk level of the close-coupled device according to the close-coupled device cross infection risk probability POC, and specifically includes:
dividing four risk levels of low cross infection risk, general cross infection risk, high cross infection risk and extremely high cross infection risk, wherein the risk probability value ranges respectively corresponding to the low cross infection risk, the general cross infection risk, the high cross infection risk and the extremely high cross infection risk are as follows: { (0,0.25], (0.25,0.5], (0.5,0.75], (0.75,1] };
determining the cross infection risk level of the close receiver as follows according to the risk probability value range corresponding to the value of the close receiver cross infection risk probability POC: low risk of cross-infection, general risk of cross-infection, high risk of cross-infection, or very high risk of cross-infection.
The specific process of using the device of the embodiment of the invention to carry out the cross infection risk grade of the rail transit close contact person is similar to the method embodiment, and the detailed description is omitted here.
In summary, the method for acquiring the cross-infection risk level of the rail transit line-level close contact person in the embodiment of the invention starts with the analysis of microscopic travel behaviors based on statistics, behavior science and data science, provides a risk train set generation method and a boarding train matching generation method, and constructs a probability distribution model of the traveling time of each station of the risk exposure line containing hidden variables; continuously reducing the screening range of the close contacts with the possibility of cross infection from the angle of the iterative risk time interval window; and (3) carrying out model solution by using an expectation maximization EM algorithm, estimating the risk probability of the cross-infection risk exposure train and the cross-infection risk probability of the close contact person, and establishing a close contact person risk level evaluation model on the basis.
The method provided by the embodiment of the invention can be suitable for a scene that a case travels on a plurality of lines and is transferred on different lines, and can screen passers by taking the urban rail network level as a range and acquire the cross infection risk level of the transfer passenger flow in different lines.
The method provided by the embodiment of the invention is an important means for improving the suspected case screening precision and efficiency, can provide isolation measures for the close contacts with different risk levels, can also provide a convenient and efficient query tool for the public to judge whether the close contacts are the close contacts, fills the blank of risk probability estimation of the close contacts in the public transportation field, and has great decision support significance for providing accurate research and judgment, joint prevention and control, public emotion guidance and emergency resource deployment for related departments.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (11)
1. A method for identifying the risk of cross infection of urban rail line-level close contacts is characterized by comprising the following steps:
step S1, acquiring a risk exposure line REL, a risk exposure physical path RER and travel duration of a case;
step S2, analyzing the microscopic trip behavior and trip time of the case according to the REL and the RER of the case and the trip time, and acquiring the physical trip path, the microscopic trip behavior and the trip process of the close receiver;
step S3, determining a cross infection risk exposure site RESFC set, a cross infection risk exposure train RETFC set and a cross infection risk exposure period REPFC according to the microscopic trip behavior and trip process constitution of the case and the trip physical path, microscopic trip behavior and trip process of the close contact person, wherein the close contact person is an urban rail line level close contact person;
step S4, constructing a cross infection risk exposure physical path RERFC set and an effective train ET set of the close-coupled person, giving a unique identification code to one piece of data, and constructing an initial data set Dataset (0) of the close-coupled person containing the unique identification code of a case;
s5, constructing a passenger traveling time probability distribution model of each station in the risk exposure line REL containing hidden variables based on the initial data set Dataset (0) of the close contact;
step S6, solving a passenger traveling time probability distribution model based on an expectation maximization EM algorithm, and calculating the probability of the boarding trains of a passenger group and the distribution parameters of the passenger outbound traveling time;
step S7, calculating the distribution parameters of the passenger in-and-out station traveling time of each station according to the probability of the train on the journey of the passenger group and the distribution parameters of the passenger out-station traveling time, and calculating the cross infection risk probability of the train in the RETFC set and the train on the journey probability of a close receiver;
step S8, updating the cross infection risk exposure period REPFC in the step 3 based on the cross infection risk probability of the train in the RETFC set and the train landing probability of the close-coupled device, updating the Dataset (0) to be a cross-infected device risk data set Dataset (new) based on the updated REPFC, and keeping the unique identification code unchanged;
step S9, calculating the cross infection risk probability POC of the close-coupled person based on the cross-infected person risk data set (new);
and step S10, determining the cross infection risk level of the close contact according to the close contact cross infection risk probability POC and the set cross infection risk level division strategy.
2. The method according to claim 1, wherein the acquiring of the risk exposure line REL, the risk exposure physical path RER and the travel duration of the case in step S1 specifically includes:
step S011, determining intelligent traffic card number, trip time interval and trip origin-destination OD (origin-destination) information of a case;
step S012, inquiring basic information of line stations in a database, and determining the travel OD pair code of the case as follows:
the risk exposure physical path RER for a case is:
3. The method according to claim 1, wherein the step S2 of analyzing the microscopic trip behavior and trip time of the case according to the REL, RER and trip duration of the case comprises:
step S021, analyzing microscopic travel behaviors contained in a travel link of a case, wherein the microscopic travel behaviors comprise: the travel OD comprises an inbound OD pair selection behavior, an inbound card swiping behavior, an inbound traveling behavior, an inbound waiting behavior, a boarding train selection behavior, an outbound traveling behavior and an outbound card swiping behavior;
step S022, obtaining travel time T corresponding to microscopic travel behaviors of the case, wherein the travel time T comprises the following steps: the station-entering running time AT, the station-entering waiting time WT, the riding time BT and the station-exiting running time ET, namely T is AT + WT + BT + ET.
4. The method according to claim 1, wherein the determining the ESFC set, the RETFC set, and the REPFC according to the microscopic travel behavior and the travel process composition of the case and the travel physical path, the microscopic travel behavior, and the travel process of the close contact in step S3 specifically includes:
step S031, according to the line site basic information, inquiring the same direction site on REL after the trip starting point of the case, and constructing the RESFC set
wherein ,indicating the origin of the case on the risk exposure line, liRepresents the ith station on the line l;
step S032, encoding the patient according to ODTime of trip wherein ,train in combination with automatic train positioning dataAnd constructing the RETFC set at the arrival time and the departure time:
wherein ,tiIs the ith train exposed to the risk of cross infection, and all trains in the RETFC set meet the following constraint conditions:
(1) the minimum entering and traveling time constraint of the starting station is that the departure time of the train at the starting station is greater than the entering card swiping time
wherein ,indicating a train tiAt case p origin station opThe time of departure of the vehicle is,indicating case p at origin station opAt the time of the card swiping at the arrival,represents opThe minimum entering and traveling time of the station, and t represents the maximum number of exposed trains with cross infection risk;
(2) a terminal minimum outbound travel time constraint. The arrival time of the train at the terminal station is less than the card swiping time of the train at the terminal station:
wherein ,indicating case p is at terminal dpAt the time of the outbound card swiping,indicating a train tiAt case p terminal dpThe time of arrival of the (c) signal,denotes dpThe minimum outbound running time of the station, and t represents the maximum number of exposed trains with cross infection risks;
step S033, determining REPFC, T according to AVL data of each train in RETFC setrepfc=[Tstart,Tend]The following conditions are satisfied:
wherein ,indicating a train t1The origination station l on the REL in the same direction as case p1At the time of arrival of the station,indicating the originating station l1The maximum inbound travel time of;indicating a train ttTerminal l on REL co-directional with case pnAt the time of departure from the station,indicating a terminalnThe maximum inbound travel time.
5. The method according to claim 4, wherein the step S4 constructs a cross infection risk exposure physical path (RERFC) set and a valid train ET set of the close receiver, and specifically includes:
S042, inquiring AFC data of an automatic fare collection system of urban rail transit in a database, determining an initial data set Dataset (0) of a close-coupled person, wherein the initial data set includes AFC data of a case, each record corresponds to a unique identification code, and each record contains an identity identification code, an ID card number, an arrival card swiping time, an exit card swiping time, an arrival station number and an exit station number;
and S043, constructing the secret contact ET set by combining the arrival time and the departure time of the train at the O and D stations in the automatic train positioning data according to the encoding and the trip time of the passenger OD and the automatic train positioning data by imitating the method for constructing the RETFC set in the step S032.
6. The method according to claim 1, wherein the step S5 of constructing a passenger travel time probability distribution model of each station in the risk exposure line REL with hidden variables based on the initial data set Dataset (0) of the splicer specifically includes:
s051, assuming station traveling time distribution, and setting a passenger group comprising cases and close receivers, wherein the station traveling time of passengers on all stations on the REL is independent probability density distribution;
step S052, classifying passengers coming into station according to Trepfc=[Tstart,Tend]Total time period and REFRC setAnd in the middle OD pair, dividing the initial data set Dataset (0) of the close splicer into N types according to the time granularity delta t, wherein the N types comprise:
(1) converting the arrival card swiping time of the same OD to the observation data of the jth individual in the kth passenger groupAnd the time of outbound card swipingTime format, expressed in seconds
(2) Dividing initial data set Dataset (0) of the splicer into N types,
N=Tend-Tstart/Δt (9)
step S053, according to unknown definition of hidden variables of the train on which passengers board the platform, the hidden variables comprise:
(1)UDiunobserved data representing a k-th class passenger population
wherein ,
(3)πkrepresenting the probability of a class k passenger group boarding train,indicating the probability of class k passenger groups boarding the t-th train
(4) The supplement of the initial data set of the close receiver is satisfied by the complete data setWhich comprises the following steps:
UD=(UD1,…,UDk,…,UDN) (16)
step S054, representing the parameters to be estimated according to the probability density distribution parameters in the step S051 and the passenger boarding train probability variables in the step S053, wherein the method comprises the following steps:
(1) constructing parameters to be estimated for a k-th passenger group
wherein ,representing the probability of the class k passenger group boarding the ith train,representing site lsInternal outbound running time parameters;
(2) constructing a model parameter θ ═ θ1,…,θk,…,θN)(step);
Step S055, constructing likelihood function of passenger traveling time probability distribution model containing hidden variables
Step S056, converting the likelihood function into a log likelihood function
Step S057, maximization log-likelihood function
L(θ)=max Lc(θ)=max(logP(tin,tout,UD|θ)) (20)。
7. The method according to claim 1, wherein the step S6 of solving the probability distribution model of passenger travel time based on expectation-maximization EM algorithm to calculate the distribution parameters of the probability of the boarding trains and the passenger outbound travel time of the passenger population comprises:
step S061 of determining an initial parameter value θ ═ θ(0);
Step S062, E-step calculation is carried out, and observation data (t) is combinedin,tout) At θ ═ θ(step)Lower computation Q function Q (θ)
Q(θ)=E(Lc(θ)|(tin,tout),θ(step)) (21)
wherein ,θ(step)Is the estimated value of the step theta of the algorithm;
step S063, M-step calculation, maximization Q function Q(step)(theta) to update the parameter estimate theta(step+1)=arg maxQ(step)(θ)
Wherein, the probability of the train of the kth class passenger group in the step +1 isMethod for calculating distribution parameters of passenger outbound travel time by using L-BFGS-B optimization method
Step S064, step S062, and step S063 are alternately performed until the algorithm converges.
8. The method according to claim 7, wherein the step S7 of calculating the distribution parameters of the passenger in-and-out station traveling time of each station, the probability of cross infection risk of trains in the RETFC set, and the probability of train boarding of the close receiver according to the distribution parameters of the boarding train probability and the passenger out-station traveling time of the passenger population specifically comprises:
step S071 of obtaining the final parameter estimation resultAnd distribution parameters of outbound traveling time of each site of risk line REL
wherein ,representing the probability of a class k passenger group for a train on the way;representing site lsThe passenger outbound traveling time distribution parameter;
step S072, according to AFC data between OD pairs, calculating each station l of the risk exposure linesDistribution parameter of passenger outbound traveling time
Step S073, fitting a station arrival traveling time distribution curve according to the station arrival traveling time distribution of passengers, and determining each station l of the risk exposure linesTime parameter of passenger entering station
And distinguishing a case and a passerby according to the unique identification codes, and identifying the cross infection risk probability and the train boarding probability of the passerby in the RETFC set.
9. The method according to claim 8, wherein the step S8 of updating the cross infection risk exposure period REPFC includes updating Dataset (0) as cross infectors risk data set Dataset (new) without changing the unique identification code, and includes:
exposing each station l of the line according to said risksDistribution parameter of passenger in-and-out-of-station traveling time and calculation formula T of REPFCrepfc=[Tstart,Tend]And updating the REPFC, shortening the minimum on-station card swiping time and the maximum off-station card swiping time of the Dataset (0) based on the time length of the updated REPFC, and updating the cross infector risk data set Dataset (new), wherein the total time length of the Dataset (new) is less than that of the Dataset (0).
10. The method according to claim 9, wherein the calculating of the close recipient cross infection risk probability POC based on the cross-infected person risk data set (new) in step S9 specifically comprises:
step S091, extracting case data according to the unique identification code, and confirming the risk probability of each train in the RETFC set
wherein ,shows that case p belongs to the kth passenger group and trains in the journey RETFC setA risk probability value of (a);
step S092, according to the RETFC set train numberAll trains logged in index dataset (new)Close contact of the train, pick up the train on the wayProbability of risk
wherein ,shows that the subscriber j belongs to the kth passenger group and the train in the journey RETFC setA probability value of (d);
step S093, calculating POC (Point of sale) of cross infection risk probability of close receiver
11. An urban rail line level close contact person cross infection risk identification device, characterized by, includes:
the information acquisition module is used for acquiring a risk exposure line REL, a risk exposure physical path RER and travel time of a case, analyzing microscopic travel behaviors and travel time of the case according to the REL, the RER and the travel time of the case, and acquiring the travel physical path, the microscopic travel behaviors and the travel process of the close-coupled person;
the data analysis and processing module is used for determining a cross infection risk exposure site RESFC set, a cross infection risk exposure train RETFC set and a cross infection risk exposure period REPFC according to the microcosmic travel behavior and travel process composition of the case and the physical travel path, microcosmic travel behavior and travel process of the close receiver; constructing a remote cross infection exposure physical path (REFRC) set and an effective train ET set of a close receiver, giving a unique identification code to one piece of data, and constructing a close receiver initial data set (0) containing the unique identification code of a case;
the model building and calculating module is used for building a passenger traveling time probability distribution model of each station in the risk exposure line REL containing hidden variables based on the initial data set Dataset (0) of the close-connected person; solving a passenger traveling time probability distribution model based on an expectation maximization EM algorithm, and calculating the probability of the trains on the journey of the passenger group and the distribution parameters of the passenger outbound traveling time; calculating passenger in-out station traveling time distribution parameters of each station according to the boarding train probability of the passenger group and the distribution parameters of the passenger out-station traveling time, and calculating the cross infection risk probability of the trains in the RETFC set and the boarding probability of the close-receiver trains;
updating the cross infection risk exposure period REPFC in the step 3 based on the cross infection risk probability of the train in the RETFC set and the train landing probability of the close-coupled device, updating the Dataset (0) to be a cross-infected device risk data set Dataset (new) based on the updated REPFC, and keeping the unique identification code unchanged; calculating the cross-infection risk probability POC of the close-coupled person based on the cross-infected person risk data set (new).
The decision support module is used for setting the cross infection risk level and issuing information;
and the risk grade query module is used for determining the cross infection risk grade of the close-coupled person according to the close-coupled person cross infection risk probability POC and the set cross infection risk grade division strategy and providing a public query function.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010357460.5A CN111584091B (en) | 2020-04-29 | 2020-04-29 | Cross infection risk identification method and device for urban rail line-level close contact person |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010357460.5A CN111584091B (en) | 2020-04-29 | 2020-04-29 | Cross infection risk identification method and device for urban rail line-level close contact person |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111584091A true CN111584091A (en) | 2020-08-25 |
CN111584091B CN111584091B (en) | 2023-10-24 |
Family
ID=72125003
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010357460.5A Active CN111584091B (en) | 2020-04-29 | 2020-04-29 | Cross infection risk identification method and device for urban rail line-level close contact person |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111584091B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114694850A (en) * | 2022-04-12 | 2022-07-01 | 北京交通大学 | Epidemic situation tight-seal crowd tracing method for subway network |
CN116564551A (en) * | 2023-05-17 | 2023-08-08 | 北京交通大学 | Data-knowledge driven urban rail transit risk identification method |
CN117290618A (en) * | 2023-11-27 | 2023-12-26 | 江西鹭鹭行科技有限公司 | Space-time accompanying crowd searching method and system for urban rail transit |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015167169A1 (en) * | 2014-05-02 | 2015-11-05 | 서울대학교 산학협력단 | Method for estimating passenger moving path in subway network |
CN106529815A (en) * | 2016-11-15 | 2017-03-22 | 同济大学 | Estimation method of passenger trip spatial-temporal trajectory of urban rail transit network and application thereof |
CN106779429A (en) * | 2016-12-25 | 2017-05-31 | 北京工业大学 | Track transfer website passenger flow congestion risk evaluating method based on AFC brushing card datas |
CN106875314A (en) * | 2017-01-31 | 2017-06-20 | 东南大学 | A kind of Urban Rail Transit passenger flow OD method for dynamic estimation |
CN110400065A (en) * | 2019-07-12 | 2019-11-01 | 北京交通大学 | Rail Transit System risk chain group construction method based on Epidemic Model |
-
2020
- 2020-04-29 CN CN202010357460.5A patent/CN111584091B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015167169A1 (en) * | 2014-05-02 | 2015-11-05 | 서울대학교 산학협력단 | Method for estimating passenger moving path in subway network |
CN106529815A (en) * | 2016-11-15 | 2017-03-22 | 同济大学 | Estimation method of passenger trip spatial-temporal trajectory of urban rail transit network and application thereof |
CN106779429A (en) * | 2016-12-25 | 2017-05-31 | 北京工业大学 | Track transfer website passenger flow congestion risk evaluating method based on AFC brushing card datas |
CN106875314A (en) * | 2017-01-31 | 2017-06-20 | 东南大学 | A kind of Urban Rail Transit passenger flow OD method for dynamic estimation |
CN110400065A (en) * | 2019-07-12 | 2019-11-01 | 北京交通大学 | Rail Transit System risk chain group construction method based on Epidemic Model |
Non-Patent Citations (1)
Title |
---|
曾璐 等: "基于AFC数据的突发事件下城市轨道交通乘客路径决策研究", 铁道学报 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114694850A (en) * | 2022-04-12 | 2022-07-01 | 北京交通大学 | Epidemic situation tight-seal crowd tracing method for subway network |
CN116564551A (en) * | 2023-05-17 | 2023-08-08 | 北京交通大学 | Data-knowledge driven urban rail transit risk identification method |
CN116564551B (en) * | 2023-05-17 | 2024-01-26 | 北京交通大学 | Data-knowledge driven urban rail transit risk identification method |
CN117290618A (en) * | 2023-11-27 | 2023-12-26 | 江西鹭鹭行科技有限公司 | Space-time accompanying crowd searching method and system for urban rail transit |
CN117290618B (en) * | 2023-11-27 | 2024-03-01 | 江西鹭鹭行科技有限公司 | Space-time accompanying crowd searching method and system for urban rail transit |
Also Published As
Publication number | Publication date |
---|---|
CN111584091B (en) | 2023-10-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111584091A (en) | Method and device for identifying cross infection risk of urban rail line level close contact person | |
US20210354731A1 (en) | Method and system for identifying traveling backward passengers and boarding trains in rail transit | |
CN110704993B (en) | Customized bus route design method for relieving subway passenger flow pressure | |
CN111510496B (en) | Traffic guidance system and method based on block chain information sharing | |
CN105279955B (en) | A kind of share-car method and apparatus | |
CN104517040B (en) | One kind is based on IC-card data public transit vehicle in-car degree of crowding computational methods | |
CN112990648B (en) | Rail transit network operation stability assessment method | |
CN110084397B (en) | Subway through line planning method | |
CN110019569B (en) | Method for acquiring urban rail transit operation state information | |
CN111932925A (en) | Method, device and system for determining travel passenger flow of public transport station | |
CN108364464B (en) | Probability model-based public transport vehicle travel time modeling method | |
CN108388542B (en) | Method and system for calculating rail traffic congestion degree | |
CN111027929B (en) | Subway ticket sorting method and device | |
CN113299106B (en) | Bus arrival time prediction system based on Internet of things | |
CN113393137A (en) | Scheduling sharing system based on Internet of vehicles | |
CN114358808A (en) | Public transport OD estimation and distribution method based on multi-source data fusion | |
CN112784689A (en) | Integrated AI camera structure of subway side window and subway ticket business clearing method | |
CN111757270A (en) | Method and device for identifying overmaning vehicle | |
CN116564551B (en) | Data-knowledge driven urban rail transit risk identification method | |
CN116654058A (en) | Rail transit network operation adjustment method, device, equipment and storage medium | |
Xie et al. | Comparison of passenger walking speed distribution models in mass transit stations | |
CN113160603B (en) | Intelligent bus management based on Internet of vehicles | |
CN114386737B (en) | Method for monitoring safety of passengers on internet about car in mobile interconnection era | |
CN111931968B (en) | Method for optimizing public bicycle station layout by using mobile phone GPS data | |
CN115817587A (en) | Real-time rescheduling method and device for solving train operation delay |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |