WO2019205306A1 - 一种出行提醒方法及终端设备 - Google Patents

一种出行提醒方法及终端设备 Download PDF

Info

Publication number
WO2019205306A1
WO2019205306A1 PCT/CN2018/096257 CN2018096257W WO2019205306A1 WO 2019205306 A1 WO2019205306 A1 WO 2019205306A1 CN 2018096257 W CN2018096257 W CN 2018096257W WO 2019205306 A1 WO2019205306 A1 WO 2019205306A1
Authority
WO
WIPO (PCT)
Prior art keywords
delay
traffic
shift
information
time
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.)
Ceased
Application number
PCT/CN2018/096257
Other languages
English (en)
French (fr)
Inventor
陈颖聪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2019205306A1 publication Critical patent/WO2019205306A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
    • G06Q10/1093—Calendar-based scheduling for persons or groups
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/52—Network services specially adapted for the location of the user terminal
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/029—Location-based management or tracking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/12—Messaging; Mailboxes; Announcements

Definitions

  • the present application belongs to the field of communications technologies, and in particular, to a travel reminding method and a terminal device.
  • the embodiment of the present application provides a travel reminding method and a terminal device to solve the existing travel reminding method, and only reminds based on the planned departure time of the traffic shift, which is easy to waste user time and cause departure when the delay occurs.
  • a first aspect of the embodiment of the present application provides a travel reminding method, including:
  • the travel information includes a traffic shift and a planned departure time of the traffic shift;
  • the delay reminder information is pushed to the user terminal; the delay reminder information includes a recommended departure time; and the recommended departure time is calculated according to the planned departure time and the delay duration.
  • the embodiment of the present application obtains the travel information of the user, and when detecting the delay pre-judgment start condition, acquires a plurality of feature parameters for calculating the delay duration, respectively, the historical travel record and the current position of the traffic shift traveled by the user. And the current traffic congestion level, based on the above three parameters are imported into the delay time estimation model to determine the delay time of the flight.
  • the delay time is greater than the delay reminding threshold, the user is prompted to do so, without the user waiting in the departure hall for a long time, the user can reasonably arrange the time of going out, and complete other matters in the delay time, and can also avoid the departure hall personnel. Congestion.
  • FIG. 1 is a flowchart of an implementation of a travel reminding method provided by a first embodiment of the present application
  • FIG. 2 is a flowchart of a specific implementation of a travel reminding method S103 according to a second embodiment of the present application;
  • FIG. 3 is a flowchart of a specific implementation of a travel reminding method provided by a third embodiment of the present application.
  • FIG. 4 is a flowchart of a specific implementation of a travel reminding method S102 according to a fourth embodiment of the present application.
  • FIG. 5 is a flowchart of a specific implementation of a travel reminding method according to a fourth embodiment of the present application.
  • FIG. 6 is a structural block diagram of a terminal device according to an embodiment of the present application.
  • FIG. 7 is a schematic diagram of a terminal device according to another embodiment of the present application.
  • the execution body of the process is a terminal device.
  • the terminal device includes but is not limited to: a mobile terminal such as a smart phone, a notebook computer, a computer, a tablet computer, and the like.
  • a mobile terminal such as a smart phone, a notebook computer, a computer, a tablet computer, and the like.
  • the terminal device meets the preset reminder condition, it will send a travel reminder to the user.
  • FIG. 1 is a flowchart of an implementation of a travel reminding method provided by a first embodiment of the present application, which is described in detail as follows:
  • travel information of the user is acquired; the travel information includes a traffic shift and a planned departure time of the traffic shift.
  • the user inputs the travel account of the user to the terminal device, and the terminal device queries whether the user has relevant travel information on the current day based on the travel account, and if the travel information of the user is detected on the current day, the related operation of S101 is performed; On the other hand, if the terminal device determines that the travel information corresponding to the user does not exist on the current day, it waits for the arrival of the next natural day, and then determines whether or not the travel information is present. Specifically, if the terminal device detects that the travel account of the user adds the travel information, it identifies whether the travel date of the travel information is the current date, and if so, performs the related operation of S101.
  • the manner in which the terminal device obtains the travel information through the travel account is specifically: the terminal device generates an appearance information query request according to the user's appearance account and the account password, and sends the travel information query to the server of each transportation agency.
  • the transportation agency includes: a server of a transportation agency such as an airline A, an airline B, a railway customer center, and a passenger service center, and the server of the relevant transportation agency receives the inquiry request of the travel information, and returns according to the account appearance.
  • the account-related travel information appears to the terminal device, and the terminal device identifies, from the travel information returned by each server, whether there is travel information that is effective on the current day.
  • the travel information includes the traffic schedule booked by the user and the planned departure time of the traffic shift.
  • the traffic shift includes, but is not limited to, the flight number of the flight, the train, the train, the train number of the high-speed train, the ferry number of the ferry, and the license plate number of the passenger car, etc., which can determine the number of the vehicle that the user is riding.
  • the presence information also records the planned departure time of the traffic shift. Since the planned departure time is based on the ideal situation, the traffic shift does not delay the corresponding departure time, so the departure time and the actual departure time will be certain. The difference, therefore, in order to avoid the user waiting for a long time, it is necessary to determine the actual departure time of the traffic shift before the trip, to determine whether the user needs to be reminded to delay the travel time.
  • the terminal device after determining the travel information of the user on the current day, extracts the planned departure time of the travel information, and continuously monitors the difference between the current time and the scheduled departure time, and determines whether the difference is less than the pre-determination.
  • the delay is pre-determined to initiate the threshold; if so, the process of determining the delay time of the traffic shift is initiated; otherwise, the monitoring is continued.
  • the delay pre-judging activation threshold can be manually set by the user or a default value set by the system.
  • the terminal device in order to determine the delay time of the traffic shift, the terminal device needs to obtain a historical travel record of the traffic shift.
  • the historical record includes the travel record of the traffic shift on the same day. Since some traffic shifts will travel back and forth between the destination and the departure place on the same day, the same traffic shift may be corresponding to the planned departure time of the user reservation on the same day. Historical departure time, of course, the historical travel record may also include travel records of all dates before the current day, and the historical delay record may determine the average delay time of the traffic shift, and the average delay time is used as the traffic shift for determining the user's travel time. One of the factors of delay time.
  • the current location of the current traffic shift is also obtained, based on the distance difference between the current location and the predicted location, as one of the factors determining the delay time of the traffic shift. Since the delay time of the terminal device is related to the traffic congestion level on the round-trip path in addition to the actual running speed of the vehicle, the terminal device also acquires the traffic congestion level at the current time.
  • the terminal device obtains the historical travel record of the traffic shift, and also obtains the travel record of other traffic shifts in the departure hall of the traffic shift. If there is a traffic jam in other traffic shifts in the departure hall, it will affect the departure time of the traffic scheduled by the user, and the average delay time of other traffic shifts in the departure hall can also be used as the delay time for estimating the traffic shift of the user. One of the factors, therefore, the terminal device will obtain the historical record of the day of the other traffic shifts in the departure hall, and determine the delay time of the traffic shift based on the historical appearance record.
  • the historical travel record, the current location, and the traffic congestion level are introduced into a delay time estimation model to determine a delay time of the traffic shift.
  • the terminal device imports the historical record of the obtained traffic shift, the current location of the traffic shift, and the traffic congestion level corresponding to the current time into the delay time estimation model, and determines the three parameters by using the above three parameters.
  • the delay time of the traffic shift preferably, if the terminal device obtains the historical travel record of other traffic shifts, the historical occurrence record of the other traffic shifts may be imported into the delay time estimation model to determine the delay time of the traffic shift. Improve the accuracy of the delay time estimation model.
  • the terminal device determines a historical average delay factor of the traffic shift according to the historical appearance record, and then obtains a location delay factor according to a difference between the current location and the predicted location, and then queries the traffic congestion.
  • the correspondence table between the level and the delay duration is used to query the congestion delay factor corresponding to the obtained traffic congestion level, and the above three factors are introduced into the preset delay estimation function to calculate the delay time of the traffic shift.
  • the delay estimation function is specifically:
  • h t is the calculated delay time;
  • Add is the position delay factor,
  • Crsh is the congestion delay factor;
  • ⁇ , ⁇ , ⁇ are the delay weights corresponding to each factor.
  • the delay reminder information is pushed to the user terminal; the delay reminder information includes a recommended departure time; the recommended departure time is according to the planned departure time and the delay duration Calculated.
  • the terminal device compares the delay duration with a preset delay reminder threshold. If the delay duration is greater than the delay remind threshold, the delay time is too long. If the departure time is determined according to the estimated departure time, it is necessary to wait for a long time in the departure hall. In order to help the user to use the time reasonably, the terminal device will push the delay reminding information to the user to inform the traffic shift that there is a delay, and the delay reminding information includes The recommended departure time allows the user to re-plan the travel plan based on the recommended departure time.
  • the terminal device calculates the recommended departure time of the user based on the delay duration and the planned departure time of the traffic shift.
  • the specific calculation method is as follows: the terminal device acquires the location information of the user and the location information of the departure hall of the traffic shift, calculates the travel time based on the two location information, and superimposes according to the travel time, the delay duration, and the planned departure time. , get the departure time of the plan.
  • the terminal device if the terminal device detects that the delay duration is less than or equal to the delay reminding threshold, the terminal indicates that the delay time is short, and the user can still determine the exit time according to the estimated departure time.
  • the terminal device returns to perform the operations of S101 to S103 at the preset delay detection period interval, and obtains the delay time of the traffic shift at intervals, and determines whether the delay reminding information needs to be pushed to the user.
  • the delay detection period varies according to the difference between the current time and the planned departure time.
  • the difference is larger, the duration of the delay detection period is longer, and the delay reminder threshold is larger; The smaller the difference is, the shorter the delay detection period is, and the smaller the delay reminder threshold is, so that the purpose of dynamically adjusting the cue frequency can be achieved.
  • the travel reminding method acquires the travel information of the user, and when detecting the delay pre-judgment start condition, obtains a plurality of characteristic parameters for calculating the delay duration, respectively
  • the historical travel record of the traffic shift traveled by the user and the current location, as well as the current traffic congestion level, are imported into the delay time estimation model based on the above three parameters to determine the delay time of the flight.
  • the delay time is greater than the delay reminding threshold
  • the user is prompted to do so, without the user waiting in the departure hall for a long time, the user can reasonably arrange the time of going out, and complete other matters in the delay time, and can also avoid the departure hall personnel. Congestion.
  • FIG. 2 is a flowchart showing a specific implementation of the travel reminding method S103 provided by the second embodiment of the present application.
  • the travel reminding method S103 provided in this embodiment includes S1031 to S1033, and the details are as follows:
  • the historical travel record, the current location, and the traffic congestion level are introduced into a delay time estimation model to determine a delay time of the traffic shift, including:
  • a multi-layer feedback cyclic neural network matching the traffic type is acquired based on the traffic type of the traffic shift.
  • the terminal device before calculating the delay time, the terminal device needs to acquire the traffic type of the traffic shift, and the traffic type includes: the type of the vehicle, the type of the aircraft, the type of the ferry, the type of the train, the type of the high-speed rail, etc., which are divided according to different vehicles.
  • Type of traffic Since the factors affecting the delay of different vehicles are different, in order to improve the accuracy of the delay time, the terminal device first determines the traffic type of the user's traffic shift, and determines the corresponding multi-layer cyclic neural network based on the traffic type. .
  • the delay time estimation model for calculating the delay duration is a combination of a multi-layer cyclic neural network and a delay duration determination function. Since the multi-layer cyclic neural network can use multiple vector with timing relationship as the input of the neural network, the output result is based on the superposition of multiple time series variables on the time axis, and the characteristics of the neural network and the delay time are calculated. The phase contrast is good. Therefore, the embodiment of the present application firstly calculates the delay expectation value by using the multi-layer cyclic neural network, and then determines the delay time of the traffic shift based on the delay expectation value, thereby improving the accuracy of the delay time estimation and providing the user travel plan formulation. The exact standard.
  • the terminal device may determine the traffic type of the traffic shift based on the coding rule of the number of the traffic shift, and then adjust various parameters of the multi-layer neural network by using the traffic type, thereby obtaining the traffic type corresponding to the traffic type.
  • Multi-layer neural network may determine the traffic type of the traffic shift based on the coding rule of the number of the traffic shift, and then adjust various parameters of the multi-layer neural network by using the traffic type, thereby obtaining the traffic type corresponding to the traffic type.
  • each of the historical travel records is sequentially introduced into each level of the multi-layer feedback loop neural network, and the current delay expected value of the traffic shift is determined; the multi-layer feedback
  • the circulating neural network is specifically:
  • h 0 is the initial delay expected value
  • x 1 , x 2 ... x t are the respective historical travel records
  • h 1 , h 2 ... h t-1 are delay iterations of the output of each layer of the multilayer feedback cyclic neural network
  • the terminal device sorts the historical processing records according to the obtained historical record time from the oldest to the newest, determines the time sequence of each historical occurrence record, and uses the time sequence as the multi-layer network.
  • the input level which is the input signal at the Nth cycle. For example, if the time sequence of a historical occurrence record is 5, it indicates an input signal as a layer 5 neural network, that is, an input signal corresponding to when the neural network cycles to the 5th time.
  • the output of each level will be used as the feedback signal of the next level, and the delay time obtained this time is iterated to the next level, that is, the delay time of the previous time will affect the delay of the latter time.
  • This is precisely the logic for delaying the estimation of the duration, which can accurately determine the expected value of the delay.
  • the number of levels of the neural network may be set by the user. If the number of historical travel records obtained is smaller than the level of the neural network, the multi-layer feedback loop neural network level is adjusted. The number, ie the number of cycles, is such that the neural network matches the number of historical travel records. Among them, the feedback information of the next level is the above-mentioned delay iteration intermediate value.
  • the initial delay expectation value and each adjustment coefficient are determined based on the traffic type of the traffic shift, and the initial delay expected value and the adjustment coefficient of the different traffic types are different. For example, for the aircraft type, the initial delay expectation value is larger, and for the vehicle type, the initial delay expectation value is smaller, and the delay probability based on different traffic types is reflected on the initial delay expectation value.
  • a delay duration determining function is input to calculate a delay duration of the traffic shift; the delay duration determining function is specifically:
  • y is the delay duration
  • Lv is the congestion level
  • Pst is the current position
  • V, U', b' are delay adjustment coefficients.
  • each delay adjustment coefficient can also be adjusted correspondingly according to the traffic type of the traffic shift.
  • the delay time of the traffic shift is calculated by the multi-layer cyclic neural network and the delay duration determination function, and the accuracy is high, which can provide an accurate time reference standard for the user to formulate the travel plan.
  • FIG. 3 is a flowchart showing a specific implementation of a travel reminding method provided by a third embodiment of the present application. As shown in FIG. 3, in the travel reminding method provided in this embodiment, if the delay duration is greater than the delay reminding threshold, the delay reminder information is pushed to the user terminal, and the method further includes S301 ⁇ S303, the details are as follows:
  • the delay reminding information is pushed to the user terminal, and the method further includes:
  • the estimated departure time of each candidate traffic shift is determined based on the delay duration.
  • the terminal device also records a change time threshold. It should be noted that the delay reminder threshold is less than the change time threshold. Due to the need to remind the user to change the situation, it is generally the delay of the shift is too long, which has affected the normal travel plan of the user. If the user waits for the traffic shift that has been delayed, it may result in the inability to complete the scheduled task or transfer. In the next traffic shift, in this case, the terminal device can not only remind the user that the shift has been delayed, but also remind the user to perform the change operation, thereby reducing the impact on the user's travel plan. It can be seen that the change time threshold is greater than the delay time threshold.
  • the terminal device can automatically provide an optional travel plan to the user to reduce the impact of the delay on the user, and reduce the user's operation and improve the efficiency of the change.
  • the terminal device acquires the departure place and the destination point of each traffic shift in the travel hall, and selects other traffic shifts that are the same as the departure place and the destination point of the traffic shift that the user has reserved as the offer for the user to change.
  • the candidate traffic shifts are determined based on the planned departure time of each candidate traffic shift and the delay duration calculated in S103, and the estimated departure time of each candidate traffic shift is determined.
  • the candidate traffic shift with the smallest difference between the estimated departure time and the planned departure time is selected as the target shift for the change.
  • the terminal device calculates a difference between the estimated departure time of each candidate shift and the scheduled departure time of the traffic shift subscribed by the user, and selects one candidate traffic shift with the smallest difference as the user needs to perform the change of the change. Sign the target shift. Since the smaller the difference, the smaller the influence on the travel plan of the user is, the candidate traffic shift can be used as the target shift for the user to change.
  • the terminal device queries whether the target shift of the change has a bookable agent. If yes, the related operation of S303 is performed; otherwise, if there is no bookable agent, the second smallest candidate traffic shift is selected as the target shift, and the above operation is performed cyclically until the selected target shift is performed. There is a bookable agent, and then the related operations of S303 are performed.
  • the terminal device will push the change target shift to the user's terminal to prompt the user to perform the change operation.
  • the change confirmation information sent by the user is received, submitting the change request to the server corresponding to the travel information subscribed by the user, performing a change operation, and returning the change result to the terminal of the user.
  • the terminal device when detecting that the delay time is greater than the change time threshold, the terminal device automatically starts the change process, and selects the traffic shift of the appropriate user from the candidate traffic shifts as the target shift to be sent to the user. It reduces the user's re-query and the operation of selecting traffic shifts, which improves the operation efficiency.
  • FIG. 4 is a flowchart showing a specific implementation of the travel reminding method S102 provided by the fourth embodiment of the present application.
  • the travel reminding method provided in this embodiment, if the difference between the current time and the planned departure time is less than the preset delay prediction After the threshold is started, the historical travel record of the traffic shift and the current location are queried, and the current traffic congestion level is obtained, including: S1021 to S1023, as follows:
  • the traffic type of the traffic shift is a road traffic type
  • the road congestion information of the round trip route of the traffic shift is acquired, and the traffic congestion level is determined based on the road congestion information.
  • the terminal device determines the traffic congestion level based on the different traffic types in order to accurately determine the traffic congestion level.
  • the terminal device obtains the round trip of the traffic shift.
  • the congestion information of the road surface on the path is based on the congestion information to obtain the current traffic congestion level.
  • the specific implementation manner is as follows: road congestion information includes: road vehicle density, number of traffic accidents, number of construction projects, and the like. If the road vehicle density is large, the traffic congestion level is higher; if the number of traffic accidents on the round-trip path is larger, the traffic congestion level is higher; if the number of construction works on the round-trip path is larger, the traffic congestion level is higher.
  • the traffic type of the traffic shift is a rail transit type
  • delay information of all the trains on the round trip track of the traffic shift is acquired, and the traffic congestion level is determined based on the delay information.
  • this type of vehicle for the type of rail transit, unlike the type of road traffic, this type of vehicle often needs to share the same track. Therefore, if there is a delay in the traffic shift on a certain track, the track will be affected. The departure time of other traffic shifts. Therefore, the terminal equipment corresponding to this type of traffic shift will obtain the delay of all the trains on the round-trip orbit, and determine whether the track is in a congested state based on the delay of other trains, thereby determining the traffic congestion level.
  • the sailing runway waiting information of the departure airport of the traffic shift is acquired, and the traffic congestion level is determined based on the sailing runway waiting information.
  • the flight orbits are all preset, there is no overlap of the flight orbits, but different flights use the same departure airport's sailing runway when traveling, if The waiting time of each flight on the sailing runway will time out, which will affect the departure time of the flight booked by the user. Therefore, for the type of flight traffic, the traffic congestion situation is related to the waiting time of each flight on the sailing runway, and the terminal device will obtain the waiting information of the sailing runway, the waiting information including the waiting time of other flights on the sailing runway.
  • the accuracy of the delay time estimation is improved by determining the method for determining the traffic congestion level corresponding to different types of traffic shifts.
  • FIG. 5 is a flowchart of a specific implementation of a travel reminding method provided by a fifth embodiment of the present application.
  • the travel reminding method provided by the embodiment further includes: S501 and S502 after the obtaining the travel information of the user, and the details are as follows:
  • the terminal device first determines the location information of the current user before the delay threshold is surely delayed. The farther the user is located from the departure hall of the traffic shift, the user goes to the departure hall. The longer the time is, the earlier it is necessary to remind the user whether there is a delay in the traffic shift, and to avoid the user having to go out; if the location of the user is closer to the trigger hall of the traffic shift, the process of estimating the delay duration can be postponed.
  • the delay reminding threshold is determined based on the location information and the traffic type of the traffic shift.
  • the length of the inbound of different traffic types is also different.
  • the baggage check, security check, gate entry, and even the shuttle bus can complete the pit stop process, so the cost is increased.
  • the station time is longer, so it is necessary to delay the user earlier, and for the car traffic type, the pit stop process is shorter, and the pit stop time is also less, so the user can be delayed to remind the user later.
  • the terminal device determines the delay reminding threshold based on the location information and the traffic type of the user, and determines when the user needs to delay the reminder.
  • the greater the distance between the location information and the departure hall the greater the delay threshold is; if the distance between the location information and the departure hall is smaller, the delay threshold is smaller; The longer the length of time required for the inbound of the traffic type, the greater the threshold for the delay reminder; if the length of time required for the inbound of the traffic type is shorter, the delay threshold for the delay is smaller.
  • the delay reminder threshold is determined by identifying the synchronized traffic type and the user location information, and the dynamic start delay duration judgment process is implemented, and the accuracy of the delay reminder is improved.
  • FIG. 6 is a structural block diagram of a terminal device according to an embodiment of the present application, where each unit included in the terminal device is used to execute each step in the embodiment corresponding to FIG. 1.
  • each unit included in the terminal device is used to execute each step in the embodiment corresponding to FIG. 1.
  • please refer to the related description in the embodiment corresponding to FIG. 1 and FIG. For the convenience of explanation, only the parts related to the present embodiment are shown.
  • the terminal device includes:
  • the travel information obtaining unit 61 is configured to acquire travel information of the user; the travel information includes a traffic shift and a planned departure time of the traffic shift;
  • the delay factor obtaining unit 62 is configured to query the historical travel record of the traffic shift and the current location, and obtain the current traffic congestion, if the difference between the current time and the planned departure time is less than a preset delay pre-determination threshold grade;
  • a delay duration calculating unit 63 configured to import the historical travel record, the current location, and the traffic congestion level into a delay time estimation model, and determine a delay time of the traffic shift;
  • the delay reminding execution unit 64 is configured to: if the delay duration is greater than the delay reminding threshold, push the delay reminding information to the user terminal; the delay reminding information includes a recommended departure time; and the recommended departure time is according to the planned departure time and The delay time is calculated.
  • the delay duration calculation unit 63 includes:
  • a multi-layer feedback cyclic neural network determining unit configured to acquire a multi-layer feedback cyclic neural network matching the traffic type based on a traffic type of the traffic shift;
  • a delay expectation calculation unit configured to sequentially import each of the historical travel records into each level of the multi-layer feedback loop neural network according to a time sequence of the historical travel record, and determine a current delay expected value of the traffic shift;
  • the multilayer feedback loop neural network is specifically:
  • h 0 is the initial delay expected value
  • x 1 , x 2 ... x t are the respective historical travel records
  • h 1 , h 2 ... h t-1 are delay iterations of the output of each layer of the multilayer feedback cyclic neural network The intermediate value
  • h t is the current expected delay value of the traffic shift
  • W, U, b are adjustment coefficients
  • a delay duration determining unit configured to import a delay duration determining function according to the delay expected value, the current location, and the traffic congestion level, and calculate a delay duration of the traffic shift;
  • the delay duration determining function is specifically:
  • y is the delay duration
  • Lv is the congestion level
  • Pst is the current location
  • V, U', b' are delay adjustment coefficients.
  • the terminal device further includes:
  • a change determining unit configured to determine an estimated departure time of each candidate traffic shift based on the delay duration if the delay duration is greater than a change time threshold
  • the target shift selection unit is configured to select a candidate traffic shift with the smallest difference between the estimated departure time and the planned departure time as a target shift for the change;
  • a change information sending unit configured to send the change target shift to the terminal of the user.
  • the delay factor obtaining unit 62 includes:
  • a road traffic determining unit configured to acquire road congestion information of a round trip path of the traffic shift if the traffic type of the traffic shift is a road traffic type, and determine the traffic congestion level based on the road congestion information
  • a rail transit type determining unit configured to obtain, if the traffic type of the traffic shift is a rail transit type, obtain delay information of all the trains on the round trip track of the traffic shift, and determine the traffic congestion level based on the delay information;
  • a flight traffic type determining unit configured to acquire an outbound runway waiting information of the departure airport of the traffic shift if the traffic type of the traffic shift is a flight traffic type, and determine the traffic congestion level based on the sailing runway waiting information.
  • the terminal device further includes:
  • the delay reminder threshold is determined based on the location information and a traffic type of the traffic shift.
  • the terminal device provided by the embodiment of the present application also requires the user to wait for a long time in the departure hall, can reasonably arrange his own departure time, and complete other matters in the delay time, and can also avoid the congestion of the departure hall personnel.
  • FIG. 7 is a schematic diagram of a terminal device according to another embodiment of the present application.
  • the terminal device 7 of this embodiment includes a processor 70, a memory 71, and computer readable instructions 72 stored in the memory 71 and operable on the processor 70, such as a travel reminder program. .
  • the processor 70 executes the computer readable instructions 72, the steps in the embodiments of the above various travel reminding methods are implemented, such as S101 to S104 shown in FIG. 1.
  • the processor 70 when executing the computer readable instructions 72, implements the functions of the various units in the various apparatus embodiments described above, for example, the functions of the modules 61 to 64 as shown in FIG.
  • the computer readable instructions 72 may be partitioned into one or more units, the one or more units being stored in the memory 71 and executed by the processor 70 to complete the application.
  • the one or more units may be a series of computer readable instruction instructions segments capable of performing a particular function for describing the execution of the computer readable instructions 72 in the terminal device 7.
  • the computer readable instructions 72 may be divided into an appearance information acquisition unit, a delay factor acquisition unit, a delay duration calculation unit, and a delay reminder execution unit, each unit having a specific function as described above.
  • the terminal device 7 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
  • the terminal device may include, but is not limited to, a processor 70 and a memory 71. It will be understood by those skilled in the art that FIG. 7 is only an example of the terminal device 7, and does not constitute a limitation of the terminal device 7, and may include more or less components than those illustrated, or combine some components or different components.
  • the terminal device may further include an input/output device, a network access device, a bus, and the like.
  • the processor 70 may be a central processing unit (CPU), or may be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)

Abstract

本申请适用于通信技术领域，提供了一种出行提醒方法及终端设备，包括：获取用户的出行信息；若当前时间与计划出发时间的差值小于预设的延误预判启动阈值，则查询交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级；将历史出行记录、当前位置以及交通拥堵等级导入延误时间估算模型，确定交通班次的延误时长；若延误时长大于延误提醒阈值，则向用户的终端推送延误提醒信息。本申请无需用户在出发大厅长时间等待，可以合理安排自己的出门时间，并在延误时间内完成其他事项，同时也能够避免出发大厅人员拥堵。

Description

一种出行提醒方法及终端设备
本申请申明享有2018年04月24日递交的申请号为201810371576.7、名称为“一种出行提醒方法及终端设备”中国专利申请的优先权，该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请属于通信技术领域，尤其涉及一种出行提醒方法及终端设备。
背景技术
随着各类交通方式技术的不断发展，高铁、飞机等交通方式为用户的出行带来了极大的方便，往来不同城市、国家之间的时间也越来越短。但随着交通工具的不断增加，路面、轨道甚至航道也会出现拥堵的情况，从而导致延误的情况发生。然而延误信息只有用户到达出发大厅才能够获取得到，此时只能在出发大厅等待交通班次到达，浪费了用户的时间，并且当多个班次均发生延误情况时，会导致出发大厅人员拥堵。由此可见，现有的出行提醒方法、容易在发生延误时浪费用户时间以及造成出发大厅人员拥堵。
技术问题
有鉴于此，本申请实施例提供了一种出行提醒方法及终端设备，以解决现有的出行提醒方法，只是基于交通班次的计划出发时间进行提醒，容易在发生延误时浪费用户时间以及造成出发大厅人员拥堵的问题。
技术解决方案
本申请实施例的第一方面提供了一种出行提醒方法，包括：
获取用户的出行信息；所述出行信息包括交通班次以及所述交通班次的计划出发时间；
若当前时间与所述计划出发时间的差值小于预设的延误预判启动阈值，则查询所述交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级；
将所述历史出行记录、所述当前位置以及所述交通拥堵等级导入延误时间估算模型，确定所述交通班次的延误时长；
若所述延误时长大于延误提醒阈值，则向用户的终端推送延误提醒信息；所述延误提醒信息包含推荐出发时间；所述推荐出发时间根据所述计划出发时间以及所述延误时长计算得到。
有益效果
本申请实施例通过获取用户的出行信息，并当检测到满足延误预判启动条件时，则获 取用于计算延误时长的多个特征参数，分别为用户出行的交通班次的历史出行记录以及当前位置，以及当前的交通拥堵等级，基于上述三个参数导入到延误时间估算模型，确定该航班的延误时长。当检测到延误时长大于延误提醒阈值时，则向用户进行提示，无需用户在出发大厅长时间等待，可以合理安排自己的出门时间，并在延误时间内完成其他事项，同时也能够避免出发大厅人员拥堵。
附图说明
图1是本申请第一实施例提供的一种出行提醒方法的实现流程图；
图2是本申请第二实施例提供的一种出行提醒方法S103具体实现流程图；
图3是本申请第三实施例提供的一种出行提醒方法具体实现流程图；
图4是本申请第四实施例提供的一种出行提醒方法S102具体实现流程图；
图5是本申请第四实施例提供的一种出行提醒方法具体实现流程图；
图6是本申请一实施例提供的一种终端设备的结构框图；
图7是本申请另一实施例提供的一种终端设备的示意图。
本发明的实施方式
在本申请实施例中，流程的执行主体为终端设备。该终端设备包括但不限于：智能手机、笔记本电脑、计算机、平板电脑等移动终端。终端设备在满足预设的提醒条件时，则会向用户发出出行提醒。图1示出了本申请第一实施例提供的出行提醒方法的实现流程图，详述如下：
在S101中，获取用户的出行信息；所述出行信息包括交通班次以及所述交通班次的计划出发时间。
在本实施例中，用户将自身的出行账户输入到终端设备，终端设备基于该出行账户查询该用户当日是否存在相关的出行信息，若检测到用户当日存在出行信息，则执行S101的相关操作；反之，若终端设备判定当日并不存在该用户所对应的出行信息，则等待下一个自然日的到达，再进行出行信息有无的判定。特别地，若终端设备检测到用户的出行账户添加了出行信息，则识别该出行信息的出行日期是否为当日，若是，则执行S101的相关操作。
具体地，在本实施例中，终端设备通过出行账户获取出行信息的方式具体为:终端设备根据用户的出现账户以及账户密码生成一个出现信息查询请求，向各个交通机构的服务器发送出行信息的查询请求，该交通机构包括：航空公司A、航空公司B、铁路客户中心、客运服务中心等交通机构的服务器，相关交通机构的服务器接收到该出行信息的查询请求 后，会根据出现账户返回与该出现账户相关的出行信息至终端设备，终端设备将从各个服务器返回的出行信息中识别是否存在当日生效的出行信息。
在本实施例中，出行信息中包含了用户预订的交通班次以及该交通班次的计划出发时间。需要说明的是，该交通班次包括但不限于：飞机航班的航班编号、火车、动车、高铁的列车车次、渡轮的轮渡编号以及客运汽车的车牌号码等能够确定用户所乘坐交通工具的编号。除了交通班次外，出现信息还记录有该交通班次的计划出发时间，由于计划出发时间是基于理想情况下，交通班次不延误所对应的出发时间，因此该出发时间与实际的出发时间会存在一定的差异，因此为了避免用户长时间等待，需要在出行之前对交通班次的实际出发时间进行判定，确定是否需要提醒用户推迟出门时间。
在S102中，若当前时间与所述计划出发时间的差值小于预设的延误预判启动阈值，则查询所述交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级。
在本实施例中，终端设备在确定了用户存在当日的出行信息后，将提取该出行信息的计划出发时间，并持续监测当前时间与计划出发时间之间差值，判断该差值是否小于预设的延误预判启动阈值；若是，则启动交通班次的延误时间的确定流程；反之，则继续进行监测。该延误预判启动阈值可以由用户手动设备，也可以为系统设置的默认值。
在本实施例中，终端设备为了确定该交通班次的延误时长，需要获取该交通班次的历史出行记录。该历史出现记录包括该交通班次当日的出行记录，由于部分交通班次在同一日会在目的地与出发地多次往返，因此同一交通班次可能在当日除了用户预订的计划出发时间外，还对应多个历史出发时间，当然，该历史出行记录还可以包括当日之前所有日期的出行记录，通过历史出现记录可以判定该交通班次的平均延误时长，将该平均延误时长作为判定用户待出行的交通班次的延误时长的因素之一。除了获取用户的历史出行记录外，还会获取当前交通班次的当前位置，基于该当前位置与预计位置的之间距离差，作为判定交通班次的延误时长的因素之一。由于终端设备的延误时长除了交通工具实际的运行速度之外，还与往返路径上的交通拥堵等级相关，因此终端设备还会获取当前时刻的交通拥堵等级。
可选地，在本实施例中，终端设备除了获取该交通班次的历史出行记录外，还会获取交通班次的出发大厅内其他交通班次当日的出行记录。由于出发大厅的其他交通班次若存在出发堵塞的情况，则会影响用户所预定的交通班次的出发时间，并且该出发大厅的其他交通班次的平均延误时长也可以作为估算用户的交通班次的延误时长的因素之一，因此，终端设备会获取该出发大厅其他交通班次当日的历史出现记录，基于该历史出现记录确定交通班次的延误时长。
在S103中，将所述历史出行记录、所述当前位置以及所述交通拥堵等级导入延误时间估算模型，确定所述交通班次的延误时长。
在本实施例中，终端设备将获取得到的交通班次的历史出现记录、该交通班次的当前所在的位置以及当前时刻所对应的交通拥堵等级导入到延误时间估算模型，通过上述三个参数确定该交通班次的延误时长，优选地，若终端设备获取了其他交通班次的历史出行记录，还可以将其他交通班次的历史出现记录导入到该延误时间估算模型内，用于确定该交通班次的延误时长，提高延误时间估算模型的准确率。
可选地，在本实施例中，终端设备根据历史出现记录确定该交通班次的历史平均延误因子，然后在根据当前位置与预计位置之间的距离之差，得到位置延误因子，然后查询交通拥堵等级与延误时长的对应关系表，查询获取得到的交通拥堵等级所对应的拥堵延误因子，将上述三个因子导入到预设的延误估算函数内，计算该交通班次的延误时长。其中该延误估算函数具体为：
Figure PCTCN2018096257-appb-000001
其中，h t为计算得到的延误时长；
Figure PCTCN2018096257-appb-000002
为平均延误因子；Add为位置延误因子，Crsh为拥堵延误因子；α、β、γ为各个因子对应的延误权重。
在S104中，若所述延误时长大于延误提醒阈值，则向用户的终端推送延误提醒信息；所述延误提醒信息包含推荐出发时间；所述推荐出发时间根据所述计划出发时间以及所述延误时长计算得到。
在本实施例中，终端设备在计算了延误时长后，会将该延误时长与预设的延误提醒阈值进行比对，若该延误时长大于该延误提醒阈值，则表示延误时间过长，用户若按预计出发时间确定出门时间的话，需要在出发大厅等待较长时间，为了帮助用户合理利用时间，终端设备会向用户推送延误提醒信息，以告知该交通班次存在延误情况，该延误提醒信息中包括推荐出发时间，用户可根据该推荐出发时间重新规划出行计划。
在本实施例中，终端设备在确定了延误时长后，则基于该延误时长以及交通班次的计划出发时间，计算用户的推荐出发时间。具体的计算方式为：终端设备会获取用户的位置信息以及交通班次的出发大厅的位置信息，基于上述两个位置信息计算路程花费时间，并根据将路程花费时间、延误时长以及计划出发时间进行叠加，得到该计划出发时间。
可选地，在本实施例中，终端设备若检测到延误时长小于或等于延误提醒阈值，则表示延误时间较短，用户依然可以按照预计出发时间确定出门时间。在该情况下，终端设备会以预设的延误检测周期间隔返回执行S101至S103的操作，间隔获取该交通班次的延误 时长，确定是否需要对用户推送延误提醒信息。优选地，该延误检测周期会随着当前时间与计划出发时间的差值的变化而变化，若该差值越大，则延误检测周期的时长越长，且该延误提醒阈值越大；若该差值越小，则延误检测周期的时长越短，且该延误提醒阈值越小，从而能够实现动态调整提示频率的目的。
以上可以看出，本申请实施例提供的一种出行提醒方法通过获取用户的出行信息，并当检测到满足延误预判启动条件时，则获取用于计算延误时长的多个特征参数，分别为用户出行的交通班次的历史出行记录以及当前位置，以及当前的交通拥堵等级，基于上述三个参数导入到延误时间估算模型，确定该航班的延误时长。当检测到延误时长大于延误提醒阈值时，则向用户进行提示，无需用户在出发大厅长时间等待，可以合理安排自己的出门时间，并在延误时间内完成其他事项，同时也能够避免出发大厅人员拥堵。
图2示出了本申请第二实施例提供的一种出行提醒方法S103的具体实现流程图。参见图2所示，相对于图1所述实施例，本实施例提供的一种出行提醒方法S103中包括S1031～S1033，具体详述如下：
进一步地，作为本申请另一实施例，所述将所述历史出行记录、所述当前位置以及所述交通拥堵等级导入延误时间估算模型，确定所述交通班次的延误时长，包括：
在S1031中，基于所述交通班次的交通类型，获取与所述交通类型匹配的多层反馈循环神经网络。
在本实施例中，终端设备在计算延误时间之前，需要获取该交通班次的交通类型，该交通类型包括：汽车类型、飞机类型、渡轮类型、火车类型、高铁类型等基于不同交通工具所划分的交通类型。由于不同的交通工具影响延误的因素各不相同，因此为了提高延误时长的准确率，终端设备会首先确定用户的交通班次的交通类型，并基于该交通类型确定与之对应的多层循环神经网络。
在本实施例中，用于计算延误时长的延误时间估算模型为多层循环神经网络以及延误时长确定函数的组合。由于多层循环神经网络可以将多个具有时序关系的向量作为该神经网路的输入，输出结果时基于多个时序变量在时间轴上叠加后的结果，该神经网络的特性与延误时间计算的相性较好，因此本申请实施例采用多层循环神经网络先计算延误期望值，然后在基于该延误期望值确定该交通班次的延误时长，能够提高延误时长估算的准确性，为用户出行计划的制定提供准确的标准。
在本实施例中，终端设备可以基于该交通班次的编号的编码规则，确定该交通班次的交通类型，继而通过该交通类型调整该多层神经网络的各个参数，从而得到该交通类型所对应的多层神经网络。
在S1032中，依据所述历史出行记录的时间次序，将各个所述历史出行记录依次导入所述多层反馈循环神经网络的各层级，确定所述交通班次当前的延误期望值；所述多层反馈循环神经网络具体为：
Figure PCTCN2018096257-appb-000003
其中，h 0为初始延误期望值；x 1、x 2…x t为各个所述历史出行记录；h 1、h 2…h t-1为所述多层反馈循环神经网络各层级输出的延误迭代中间值；h t为所述交通班次当前的延误期望值；W、U、b为调整系数。
在本实施例中，终端设备会根据获取得到的历史出现记录的时间从旧到新的顺序对各个历史处理记录进行排序，确定各个历史出现记录的时间次序，将该时间次序作为该多层网络输入的层级，即第N次循环时的输入信号。例如，某一历史出现记录的时间次序为5，则表示作为第5层神经网络的输入信号，也就是当神经网络循环到第5次时所对应的输入信号。
在本实施例中，每一个层级的输出将作为下一层级的反馈信号，将本次得到的延误时长迭代到下一层级，即上一时刻的延误时长会对后一时刻的延误产生影响，这恰恰是延误时长估算的逻辑，能够准确确定延误期望值。需要说明的是，该神经网络的层级的个数可以由用户自行设定，若获取得到的历史出行记录的个数小于该神经网络的层级，则会调整该多层反馈循环神经网络层级的个数，即循环的次数，以使该神经网络与历史出行记录的个数相匹配。其中，向下一层级的反馈信息即上述的延误迭代中间值。
在本实施例中，初始延误期望值以及各个调整系数均是基于交通班次的交通类型所决定的，不同的交通类型的初始延误期望值以及调整系数存在差异。举例性地，对于飞机类型而言，其初始延误期望值较大，而对于汽车类型而言，其初始延误期望值则较小，基于不同交通类型的延误概率，则会反映于该初始延误期望值上。
在S1033中，根据所述延误期望值、所述当前位置以及所述交通拥堵等级，导入到延误时长确定函数，计算所述交通班次的延误时长；所述延误时长确定函数具体为：
y＝t(Vh t+U′Lv+b′Pst)
其中，y为所述延误时长；Lv为所述拥堵等级；Pst为所述当前的位置；V、U’、b’为延误调整系数。
在本实施例中，当确定了当前的交通班次所对应的延误期望值后，可以将该延误期望值、交通拥堵等级以及交通班次的当前位置导入到延误时长确定模型内以估算延误时长。如上所述，各个延误调整系数也可以根据交通班次的交通类型进行对应的调整。
在本申请实施例中，通过多层循环神经网络以及延误时长确定函数两者共同计算该交通班次的延误时长，准确率较高，能够为用户制定出行计划提供一个准确的时间参考标准。
图3示出了本申请第三实施例提供的一种出行提醒方法的具体实现流程图。参见图3所示，相对于图1所述实施例，本实施例提供的一种出行提醒方法中在所述若是延误时长大于延误提醒阈值，则向用户的终端推送延误提醒信息之后，还包括S301～S303，具体详述如下：
进一步地，作为本申请另一实施例，在所述若是延误时长大于延误提醒阈值，则向用户的终端推送延误提醒信息之后，还包括：
在S301中，若所述延误时长大于改签时间阈值，则基于所述延误时长确定各个候选交通班次的预估出发时间。
在本实施例中，终端设备还记录了一个改签时间阈值，需要说明的是，该延误提醒阈值小于该改签时间阈值。由于需要提醒用户进行改签的情况，一般是该班次的延误时间过长，已经影响到用户的正常出行计划，若用户等待原有已经延误的交通班次，可能会导致无法完成既定任务或转乘下一交通班次，在该情况下，终端设备不但可以提醒用户该班次已经延误，还可以提醒用户进行改签操作，减少对用户的出行计划造成影响。由此可见，改签时间阈值将大于延误时间阈值，当终端设备向用户推送延误提醒信息之后，若确定该延误时长大于改签时间阈值，则表示延误情况可能会严重影响用户的出行计划，此时终端设备可以自动提供可选的出行方案给到用户，以减少延误情况给用户带来的影响，并且减少了用户的操作，提高了改签效率。
在本实施例中，终端设备会获取出行大厅中各个交通班次的出发地点以及目的地点，并选取与用户已经预订的交通班次的出发地点以及目的地点相同的其他交通班次作为提供给用户改签的候选交通班次，并基于各个候选交通班次的计划出发时间以及在S103中计算得到的延误时长，确定各个候选交通班次的预计出发时间。
在S302中，选取所述预估出发时间与所述计划出发时间之差最小的候选交通班次，作为改签目标班次。
在本实施例中，终端设备计算各个候选班次的预计出发时间与用户预订的交通班次的计划出发时间之间差值，并选取该差值最小的一个候选交通班次作为用户需要进行改签的改签目标班次。由于差值越小，则表示对用户的出行计划的影响越小，因此可以将该候选 交通班次作为用户进行改签的目标班次。
可选地，在本实施例中，终端设备在确定了改签目标班次之后，会查询该改签目标班次是否存在可预订的坐席。若存在，则执行S303的相关操作；反之，若不存在可预订的坐席，则选取差值第二小的候选交通班次作为改签目标班次，循环执行上述操作，直到选定的改签目标班次存在可预订的坐席，再执行S303的相关操作。
在S303中，将所述改签目标班次发送给所述用户的终端。
在本实施例中，终端设备会将该改签目标班次推送给用户的终端，以提示用户需要进行改签操作。可选地，若接收到用户发送的改签确认信息，则提交改签请求到该用户预订的出行信息所对应的服务器进行改签操作，并将改签结果返回给用户的终端。
在本申请实施例中，终端设备在检测到延误时长大于改签时间阈值时，则会自动启动改签流程，并从候选交通班次中选取合适用户的交通班次作为改签目标班次发送给用户，减少了用户重新查询以及选取交通班次的操作，提高了操作效率。
图4示出了本申请第四实施例提供的一种出行提醒方法S102的具体实现流程图。参见图4所示，相对于图1～图3所述实施例，本实施例提供的一种出行提醒方法中所述若当前时间与所述计划出发时间的差值小于预设的延误预判启动阈值，则查询所述交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级，包括：S1021～S1023，具体详述如下：
在S1021中，若所述交通班次的交通类型为路面交通类型，则获取所述交通班次的往返路径的路面拥堵信息，并基于所述路面拥堵信息确定所述交通拥堵等级。
在本实施例中，由于对于不同的交通类型，影响其交通拥堵的因素各不相同，因此终端设备为了准确确定交通拥堵等级，将基于不同交通类型通过与之匹配的方式确定其交通拥堵等级。
在本实施例中，对于路面交通类型的交通工具，影响其行驶速度的主要因素是往返路径上是否通畅，例如路面车辆的密度以及路面交通事故的件数，因此，终端设备会获取交通班次的往返路径上路面的拥堵信息，基于该拥堵信息得到当前的交通拥堵等级。具体实现方式如下：路面拥堵信息包括：路面车辆密度、交通事故的数量、施工工程的数量等。若路面车辆密度较大，则交通拥堵等级越高；若往返路径上交通事故的数量越多，则交通拥堵等级越高；若往返路径上施工工程的数量越大，则交通拥堵等级越高。
在S1022中，若所述交通班次的交通类型为轨道交通类型，则获取所述交通班次的往返轨道上所有车次的延误信息，基于所述延误信息确定所述交通拥堵等级。
在本实施例中，对于轨道交通类型，与路面交通类型不同的是，该类型的交通工具常 常需要公用同一条轨道，因此若某一轨道上的交通班次存在延误情况，则会影响使用该轨道的其他交通班次的出发时间。因此，终端设备对应与该类型的交通班次，将获取往返轨道上所有车次的延误情况，基于其他车次的延误情况，确定该轨道是否处于拥堵状态，从而确定其交通拥堵等级。
在S1023中，若所述交通班次的交通类型为飞行交通类型，则获取所述交通班次的出发机场的出航跑道等待信息，基于所述出航跑道等待信息确定所述交通拥堵等级。
在本实施例中，对于飞行交通类型，虽然飞行轨道均是预先设定的，不存在飞行轨道交叠而拥堵的情况，但不同的航班在出行时均使用同一出发机场的出航跑道，若该出航跑道上各个航班等待时间超时，则会影响用户预订的航班的出发时间。因此，对于飞行交通类型而言，其交通拥堵情况与其出航跑道上各个航班的等待时长相关，终端设备将获取该出航跑道的等待信息，该等待信息包括其他航班在出航跑道上等待的时长。
在本申请实施例中，通过对于不同类型的交通班次，确定与之对应的交通拥堵等级的确定方法，提高了延误时长估算的准确率。
图5示出了本申请第五实施例提供的一种出行提醒方法的具体实现流程图。参见图5所示，相对于图1所述实施例，本实施例提供的一种出行提醒方法在所述获取用户的出行信息之后，还包括：S501以及S502，具体详述如下：
在S501中，获取所述用户的位置信息。
在本实施例中，终端设备会在确地延误提醒阈值之前，会首先确定该当前用户所在的位置信息，由于用户所在位置距离交通班次的出发大厅的距离越远，则用户去往出发大厅的时间则越长，因此需要较早提醒用户是否存在交通班次延误的情况，避免用户已经出门；若用户所在位置距离交通班次的触发大厅的距离越近，则可以推迟启动延误时长估算的流程。
在S502中，基于所述位置信息以及所述交通班次的交通类型，确定所述延误提醒阈值。
在本实施例中，不同交通类型进站时长也各不相同，对于飞行交通类型，由于需要进行行李托运、安全检查、入闸甚至乘坐接驳巴士才能够完成进站流程，因此所耗费的进站时间较长，因此需要较早对用户进行延误提醒，而对于汽车交通类型，进站流程较短，进站耗时也较少，因此可以较迟才对用户进行延误提醒。
在本实施例中，终端设备会基于用户的位置信息与交通类型，确定该延误提醒阈值，确定需要在何时对用户进行延误提醒。如上所述，位置信息与出发大厅之间距离值越大，则该延误提醒阈值越大；反之，若位置信息与出发大厅之间的距离值越小，则该延误提醒阈值越小；若该交通类型的进站所需时长越长，则该延误提醒阈值越大；若该交通类型的 进站所需时长越短，则该延误提醒阈值越小。
在本申请实施例中，通过识别同步的交通类型以及用户位置信息，确定延误提醒阈值，实现动态启动延误时长判断流程，提高了延误提醒的准确性。
应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
图6示出了本申请一实施例提供的一种终端设备的结构框图，该终端设备包括的各单元用于执行图1对应的实施例中的各步骤。具体请参阅图1与图1所对应的实施例中的相关描述。为了便于说明，仅示出了与本实施例相关的部分。
参见图6，所述终端设备包括：
出行信息获取单元61，用于获取用户的出行信息；所述出行信息包括交通班次以及所述交通班次的计划出发时间；
延误因子获取单元62，用于若当前时间与所述计划出发时间的差值小于预设的延误预判启动阈值，则查询所述交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级；
延误时长计算单元63，用于将所述历史出行记录、所述当前位置以及所述交通拥堵等级导入延误时间估算模型，确定所述交通班次的延误时长；
延误提醒执行单元64，用于若所述延误时长大于延误提醒阈值，则向用户的终端推送延误提醒信息；所述延误提醒信息包含推荐出发时间；所述推荐出发时间根据所述计划出发时间以及所述延误时长计算得到。
可选地，延误时长计算单元63包括：
多层反馈循环神经网络确定单元，用于基于所述交通班次的交通类型，获取与所述交通类型匹配的多层反馈循环神经网络；
延误期望计算单元，用于依据所述历史出行记录的时间次序，将各个所述历史出行记录依次导入所述多层反馈循环神经网络的各层级，确定所述交通班次当前的延误期望值；所述多层反馈循环神经网络具体为：
Figure PCTCN2018096257-appb-000004
其中，h 0为初始延误期望值；x 1、x 2…x t为各个所述历史出行记录；h 1、h 2…h t-1为 所述多层反馈循环神经网络各层级输出的延误迭代中间值；h t为所述交通班次当前的延误期望值；W、U、b为调整系数；
延误时长确定单元，用于根据所述延误期望值、所述当前位置以及所述交通拥堵等级，导入到延误时长确定函数，计算所述交通班次的延误时长；所述延误时长确定函数具体为：
y＝t(Vh t+U′Lv+b′Pst)
其中，y为所述延误时长；Lv为所述拥堵等级；Pst为所述当前的位置；V、U′、b′为延误调整系数。
可选地，终端设备还包括：
改签判定单元，用于若所述延误时长大于改签时间阈值，则基于所述延误时长确定各个候选交通班次的预估出发时间；
改签目标班次选取单元，用于选取所述预估出发时间与所述计划出发时间之差最小的候选交通班次，作为改签目标班次；
改签信息发送单元，用于将所述改签目标班次发送给所述用户的终端。
可选地，延误因子获取单元62包括：
路面交通确定单元，用于若所述交通班次的交通类型为路面交通类型，则获取所述交通班次的往返路径的路面拥堵信息，并基于所述路面拥堵信息确定所述交通拥堵等级；
轨道交通类型确定单元，用于若所述交通班次的交通类型为轨道交通类型，则获取所述交通班次的往返轨道上所有车次的延误信息，基于所述延误信息确定所述交通拥堵等级；
飞行交通类型确定单元，用于若所述交通班次的交通类型为飞行交通类型，则获取所述交通班次的出发机场的出航跑道等待信息，基于所述出航跑道等待信息确定所述交通拥堵等级。
可选地，终端设备还包括：
获取所述用户的位置信息；
基于所述位置信息以及所述交通班次的交通类型，确定所述延误提醒阈值。
因此，本申请实施例提供的终端设备同样无需用户在出发大厅长时间等待，可以合理安排自己的出门时间，并在延误时间内完成其他事项，同时也能够避免出发大厅人员拥堵。
图7是本申请另一实施例提供的一种终端设备的示意图。如图7所示，该实施例的终端设备7包括：处理器70、存储器71以及存储在所述存储器71中并可在所述处理器70上运行的计算机可读指令72，例如出行提醒程序。所述处理器70执行所述计算机可读指令72时实现上述各个出行提醒方法实施例中的步骤，例如图1所示的S101至S104。或者，所述处理器70执行所述计算机可读指令72时实现上述各装置实施例中各单元的功能，例 如图6所示模块61至64功能。
示例性的，所述计算机可读指令72可以被分割成一个或多个单元，所述一个或者多个单元被存储在所述存储器71中，并由所述处理器70执行，以完成本申请。所述一个或多个单元可以是能够完成特定功能的一系列计算机可读指令指令段，该指令段用于描述所述计算机可读指令72在所述终端设备7中的执行过程。例如，所述计算机可读指令72可以被分割成出现信息获取单元、延误因子获取单元、延误时长计算单元以及延误提醒执行单元，各单元具体功能如上所述。
所述终端设备7可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。所述终端设备可包括，但不仅限于，处理器70、存储器71。本领域技术人员可以理解，图7仅仅是终端设备7的示例，并不构成对终端设备7的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述终端设备还可以包括输入输出设备、网络接入设备、总线等。
所称处理器70可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (20)

  1. 一种出行提醒方法，其特征在于，包括：
    获取用户的出行信息；所述出行信息包括交通班次以及所述交通班次的计划出发时间；
    若当前时间与所述计划出发时间的差值小于预设的延误预判启动阈值，则查询所述交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级；
    将所述历史出行记录、所述当前位置以及所述交通拥堵等级导入延误时间估算模型，确定所述交通班次的延误时长；
    若所述延误时长大于延误提醒阈值，则向用户终端推送延误提醒信息；所述延误提醒信息包含推荐出发时间；所述推荐出发时间根据所述计划出发时间以及所述延误时长计算得到。
  2. 根据权利要求1所述的出行提醒方法，其特征在于，所述将所述历史出行记录、所述当前位置以及所述交通拥堵等级导入延误时间估算模型，确定所述交通班次的延误时长，包括：
    基于所述交通班次的交通类型，获取与所述交通类型匹配的多层反馈循环神经网络；
    依据所述历史出行记录的时间次序，将各个所述历史出行记录依次导入所述多层反馈循环神经网络的各层级，确定所述交通班次当前的延误期望值；所述多层反馈循环神经网络具体为：
    Figure PCTCN2018096257-appb-100001
    其中，h 0为初始延误期望值；x 1、x 2…x t为各个所述历史出行记录；h 1、h 2…h t-1为所述多层反馈循环神经网络各层级输出的延误迭代中间值；h t为所述交通班次当前的延误期望值；W、U、b为调整系数；
    根据所述延误期望值、所述当前位置以及所述交通拥堵等级，导入到延误时长确定函数，计算所述交通班次的延误时长；所述延误时长确定函数具体为：
    y＝t(Vh t+U′Lv+b′Pst)
    其中，y为所述延误时长；Lv为所述拥堵等级；Pst为所述当前的位置；V、U′、b′为延误调整系数。
  3. 根据权利要求1所述的出行提醒方法，其特征在于，在所述若是延误时长大于延误 提醒阈值，则向用户的终端推送延误提醒信息之后，还包括：
    若所述延误时长大于改签时间阈值，则基于所述延误时长确定各个候选交通班次的预估出发时间；
    选取所述预估出发时间与所述计划出发时间之差最小的候选交通班次，作为改签目标班次；
    将所述改签目标班次发送给所述用户终端。
  4. 根据权利要求1-3任一项所述的出行提醒方法，其特征在于，所述若当前时间与所述计划出发时间的差值小于预设的延误预判启动阈值，则查询所述交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级，包括：
    若所述交通班次的交通类型为路面交通类型，则获取所述交通班次的往返路径的路面拥堵信息，并基于所述路面拥堵信息确定所述交通拥堵等级；
    若所述交通班次的交通类型为轨道交通类型，则获取所述交通班次的往返轨道上所有车次的延误信息，基于所述延误信息确定所述交通拥堵等级；
    若所述交通班次的交通类型为飞行交通类型，则获取所述交通班次的出发机场的出航跑道等待信息，基于所述出航跑道等待信息确定所述交通拥堵等级。
  5. 根据权利要求1所述的出行提醒方法，其特征在于，在所述获取用户的出行信息之后，还包括：
    获取所述用户的位置信息；
    基于所述位置信息以及所述交通班次的交通类型，确定所述延误提醒阈值。
  6. 一种终端设备，其特征在于，包括：
    出行信息获取单元，用于获取用户的出行信息；所述出行信息包括交通班次以及所述交通班次的计划出发时间；
    延误因子获取单元，用于若当前时间与所述计划出发时间的差值小于预设的延误预判启动阈值，则查询所述交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级；
    延误时长计算单元，用于将所述历史出行记录、所述当前位置以及所述交通拥堵等级导入延误时间估算模型，确定所述交通班次的延误时长；
    延误提醒执行单元，用于若所述延误时长大于延误提醒阈值，则向用户的终端推送延误提醒信息；所述延误提醒信息包含推荐出发时间；所述推荐出发时间根据所述计划出发时间以及所述延误时长计算得到。
  7. 根据权利要求6所述的终端设备，其特征在于，所述延误时长计算单元包括：
    多层反馈循环神经网络确定单元，用于基于所述交通班次的交通类型，获取与所述交通类型匹配的多层反馈循环神经网络；
    延误期望计算单元，用于依据所述历史出行记录的时间次序，将各个所述历史出行记录依次导入所述多层反馈循环神经网络的各层级，确定所述交通班次当前的延误期望值；所述多层反馈循环神经网络具体为：
    Figure PCTCN2018096257-appb-100002
    其中，h 0为初始延误期望值；x 1、x 2…x t为各个所述历史出行记录；h 1、h 2…h t-1为所述多层反馈循环神经网络各层级输出的延误迭代中间值；h t为所述交通班次当前的延误期望值；W、U、b为调整系数；
    延误时长确定单元，用于根据所述延误期望值、所述当前位置以及所述交通拥堵等级，导入到延误时长确定函数，计算所述交通班次的延误时长；所述延误时长确定函数具体为：
    y＝t(Vh t+U′Lv+b′Pst)
    其中，y为所述延误时长；Lv为所述拥堵等级；Pst为所述当前的位置；V、U′、b′为延误调整系数。
  8. 根据权利要求6所述的终端设备，其特征在于，所述终端设备还包括：
    改签判定单元，用于若所述延误时长大于改签时间阈值，则基于所述延误时长确定各个候选交通班次的预估出发时间；
    改签目标班次选取单元，用于选取所述预估出发时间与所述计划出发时间之差最小的候选交通班次，作为改签目标班次；
    改签信息发送单元，用于将所述改签目标班次发送给所述用户的终端。
  9. 根据权利要求6-8任一项所述的终端设备，其特征在于，所述延误因子获取单元包括：
    路面交通确定单元，用于若所述交通班次的交通类型为路面交通类型，则获取所述交通班次的往返路径的路面拥堵信息，并基于所述路面拥堵信息确定所述交通拥堵等级；
    轨道交通类型确定单元，用于若所述交通班次的交通类型为轨道交通类型，则获取所述交通班次的往返轨道上所有车次的延误信息，基于所述延误信息确定所述交通拥堵等级；
    飞行交通类型确定单元，用于若所述交通班次的交通类型为飞行交通类型，则获取所 述交通班次的出发机场的出航跑道等待信息，基于所述出航跑道等待信息确定所述交通拥堵等级。
  10. 根据权利要求6所述的终端设备，其特征在于，所述终端设备还包括：
    获取所述用户的位置信息；
    基于所述位置信息以及所述交通班次的交通类型，确定所述延误提醒阈值。
  11. 一种终端设备，其特征在于，所述终端设备包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令，所述处理器执行所述计算机可读指令时实现如下步骤：
    获取用户的出行信息；所述出行信息包括交通班次以及所述交通班次的计划出发时间；
    若当前时间与所述计划出发时间的差值小于预设的延误预判启动阈值，则查询所述交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级；
    将所述历史出行记录、所述当前位置以及所述交通拥堵等级导入延误时间估算模型，确定所述交通班次的延误时长；
    若所述延误时长大于延误提醒阈值，则向用户的终端推送延误提醒信息；所述延误提醒信息包含推荐出发时间；所述推荐出发时间根据所述计划出发时间以及所述延误时长计算得到。
  12. 根据权利要求11所述的终端设备，其特征在于，所述将所述历史出行记录、所述当前位置以及所述交通拥堵等级导入延误时间估算模型，确定所述交通班次的延误时长，包括：
    基于所述交通班次的交通类型，获取与所述交通类型匹配的多层反馈循环神经网络；
    依据所述历史出行记录的时间次序，将各个所述历史出行记录依次导入所述多层反馈循环神经网络的各层级，确定所述交通班次当前的延误期望值；所述多层反馈循环神经网络具体为：
    Figure PCTCN2018096257-appb-100003
    其中，h 0为初始延误期望值；x 1、x 2…x t为各个所述历史出行记录；h 1、h 2…h t-1为所述多层反馈循环神经网络各层级输出的延误迭代中间值；h t为所述交通班次当前的延误期望值；W、U、b为调整系数；
    根据所述延误期望值、所述当前位置以及所述交通拥堵等级，导入到延误时长确定函数，计算所述交通班次的延误时长；所述延误时长确定函数具体为：
    y＝t(Vh t+U′Lv+b′Pst)
    其中，y为所述延误时长；Lv为所述拥堵等级；Pst为所述当前的位置；V、U′、b′为延误调整系数。
  13. 根据权利要求11所述的终端设备，其特征在于，在所述若是延误时长大于延误提醒阈值，则向用户的终端推送延误提醒信息之后，所述处理器执行所述计算机可读指令时还实现如下步骤：
    若所述延误时长大于改签时间阈值，则基于所述延误时长确定各个候选交通班次的预估出发时间；
    选取所述预估出发时间与所述计划出发时间之差最小的候选交通班次，作为改签目标班次；
    将所述改签目标班次发送给所述用户的终端。
  14. 根据权利要求11-13任一项所述的终端设备，其特征在于，所述若当前时间与所述计划出发时间的差值小于预设的延误预判启动阈值，则查询所述交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级，包括：
    若所述交通班次的交通类型为路面交通类型，则获取所述交通班次的往返路径的路面拥堵信息，并基于所述路面拥堵信息确定所述交通拥堵等级；
    若所述交通班次的交通类型为轨道交通类型，则获取所述交通班次的往返轨道上所有车次的延误信息，基于所述延误信息确定所述交通拥堵等级；
    若所述交通班次的交通类型为飞行交通类型，则获取所述交通班次的出发机场的出航跑道等待信息，基于所述出航跑道等待信息确定所述交通拥堵等级。
  15. 根据权利要求11所述的终端设备，其特征在于，在所述获取用户的出行信息之后，所述处理器执行所述计算机可读指令时实现如下步骤：
    获取所述用户的位置信息；
    基于所述位置信息以及所述交通班次的交通类型，确定所述延误提醒阈值。
  16. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机可读指令，其特征在于，所述计算机可读指令被处理器执行时实现如下步骤：
    获取用户的出行信息；所述出行信息包括交通班次以及所述交通班次的计划出发时间；
    若当前时间与所述计划出发时间的差值小于预设的延误预判启动阈值，则查询所述交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级；
    将所述历史出行记录、所述当前位置以及所述交通拥堵等级导入延误时间估算模型，确定所述交通班次的延误时长；
    若所述延误时长大于延误提醒阈值，则向用户的终端推送延误提醒信息；所述延误提醒信息包含推荐出发时间；所述推荐出发时间根据所述计划出发时间以及所述延误时长计算得到。
  17. 根据权利要求16所述的计算机可读存储介质，其特征在于，所述将所述历史出行记录、所述当前位置以及所述交通拥堵等级导入延误时间估算模型，确定所述交通班次的延误时长，包括：
    基于所述交通班次的交通类型，获取与所述交通类型匹配的多层反馈循环神经网络；
    依据所述历史出行记录的时间次序，将各个所述历史出行记录依次导入所述多层反馈循环神经网络的各层级，确定所述交通班次当前的延误期望值；所述多层反馈循环神经网络具体为：
    Figure PCTCN2018096257-appb-100004
    其中，h 0为初始延误期望值；x 1、x 2…x t为各个所述历史出行记录；h 1、h 2…h t-1为所述多层反馈循环神经网络各层级输出的延误迭代中间值；h t为所述交通班次当前的延误期望值；W、U、b为调整系数；
    根据所述延误期望值、所述当前位置以及所述交通拥堵等级，导入到延误时长确定函数，计算所述交通班次的延误时长；所述延误时长确定函数具体为：
    y＝t(Vh t+U′Lv+b′Pst)
    其中，y为所述延误时长；Lv为所述拥堵等级；Pst为所述当前的位置；V、U′、b′为延误调整系数。
  18. 根据权利要求16所述的计算机可读存储介质，其特征在于，在所述若是延误时长大于延误提醒阈值，则向用户的终端推送延误提醒信息之后，所述处理器执行所述计算机可读指令时还实现如下步骤：
    若所述延误时长大于改签时间阈值，则基于所述延误时长确定各个候选交通班次的预估出发时间；
    选取所述预估出发时间与所述计划出发时间之差最小的候选交通班次，作为改签目标 班次；
    将所述改签目标班次发送给所述用户的终端。
  19. 根据权利要求16-18任一项所述的计算机可读存储介质，其特征在于，所述若当前时间与所述计划出发时间的差值小于预设的延误预判启动阈值，则查询所述交通班次的历史出行记录以及当前位置，并获取当前的交通拥堵等级，包括：
    若所述交通班次的交通类型为路面交通类型，则获取所述交通班次的往返路径的路面拥堵信息，并基于所述路面拥堵信息确定所述交通拥堵等级；
    若所述交通班次的交通类型为轨道交通类型，则获取所述交通班次的往返轨道上所有车次的延误信息，基于所述延误信息确定所述交通拥堵等级；
    若所述交通班次的交通类型为飞行交通类型，则获取所述交通班次的出发机场的出航跑道等待信息，基于所述出航跑道等待信息确定所述交通拥堵等级。
  20. 根据权利要求16所述的计算机可读存储介质，其特征在于，在所述获取用户的出行信息之后，所述处理器执行所述计算机可读指令时实现如下步骤：
    获取所述用户的位置信息；
    基于所述位置信息以及所述交通班次的交通类型，确定所述延误提醒阈值。
PCT/CN2018/096257 2018-04-24 2018-07-19 一种出行提醒方法及终端设备 Ceased WO2019205306A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810371576.7A CN108830543B (zh) 2018-04-24 2018-04-24 一种出行提醒方法及终端设备
CN201810371576.7 2018-04-24

Publications (1)

Publication Number Publication Date
WO2019205306A1 true WO2019205306A1 (zh) 2019-10-31

Family

ID=64155131

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/096257 Ceased WO2019205306A1 (zh) 2018-04-24 2018-07-19 一种出行提醒方法及终端设备

Country Status (2)

Country Link
CN (1) CN108830543B (zh)
WO (1) WO2019205306A1 (zh)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111047356A (zh) * 2019-11-29 2020-04-21 阿里巴巴集团控股有限公司 一种交通班次的价值评估方法及装置
CN112418998A (zh) * 2020-12-04 2021-02-26 飞友科技有限公司 一种基于航班历史延误和取消信息的机票购买方法和系统
CN112633713A (zh) * 2020-12-28 2021-04-09 广州羊城通有限公司 基于乘车记录的风险地区提醒方法及装置
CN112966859A (zh) * 2021-02-20 2021-06-15 海南太美航空股份有限公司 一种确定乘客提前出行时间的方法、系统和电子设备
CN113449207A (zh) * 2020-03-24 2021-09-28 华为技术有限公司 电子设备定位的方法、装置、服务器、系统以及存储介质
CN114444163A (zh) * 2021-12-13 2022-05-06 中建五局安装工程有限公司 基于bim技术的机电施工方法及系统
CN115115312A (zh) * 2022-07-11 2022-09-27 智航信息服务(深圳)有限公司 一种航班延误预警方法以及系统
CN116758726A (zh) * 2023-07-13 2023-09-15 西藏金采科技股份有限公司 一种基于车联网的大数据分析方法和系统
CN119728767A (zh) * 2024-12-13 2025-03-28 中国民航信息网络股份有限公司 一种航班行程信息推送方法、装置、设备、介质及产品

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109670649A (zh) * 2018-12-27 2019-04-23 连尚（新昌）网络科技有限公司 一种用于提供用户公交出行提醒信息的方法与设备
CN109741033A (zh) * 2019-01-01 2019-05-10 唐伟 一种高速铁路后台管理的信息通信系统
CN109727098A (zh) * 2019-01-01 2019-05-07 唐伟 一种基于信息通信的高速铁路后台管理方法
CN109558514B (zh) * 2019-01-08 2023-04-11 青岛聚看云科技有限公司 视频推荐方法、其装置、信息处理设备及存储介质
CN110033217A (zh) * 2019-03-22 2019-07-19 深圳市轱辘汽车维修技术有限公司 基于共享后备箱的托运方法、服务器及存储介质
CN109887344A (zh) * 2019-04-19 2019-06-14 鄂尔多斯应用技术学院 一种确定机场航班延误程度的方法
CN109978282A (zh) * 2019-04-23 2019-07-05 深圳市元征科技股份有限公司 一种出行提醒方法及相关装置
CN110377825A (zh) * 2019-07-15 2019-10-25 腾讯科技（深圳）有限公司 内容提供方法、装置、设备及存储介质
CN112541725A (zh) * 2019-09-20 2021-03-23 青岛海信移动通信技术股份有限公司 一种行程提示方法和行程提示的终端
CN111144594B (zh) * 2019-11-25 2023-07-28 大众问问(北京)信息科技有限公司 一种出发时刻确定方法、装置及设备
CN115018436B (zh) * 2021-11-16 2023-12-01 荣耀终端有限公司 出行提醒方法及电子设备
CN115017202B (zh) * 2021-12-17 2023-03-31 荣耀终端有限公司 时长的提醒方法及装置
CN116468134A (zh) * 2022-01-10 2023-07-21 荣耀终端有限公司 行程提示方法和装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102855777A (zh) * 2012-08-27 2013-01-02 合肥飞友网络科技有限公司 航班延误可能性判断方法
CN103400053A (zh) * 2013-08-26 2013-11-20 合肥飞友网络科技有限公司 航班准点起飞的预估方法
US20150226569A1 (en) * 2008-10-22 2015-08-13 Tomtom International B.V. Navigation system and method for providing departure times
CN106600224A (zh) * 2016-12-12 2017-04-26 北京小米移动软件有限公司 行程规划方法及装置
CN107526796A (zh) * 2017-08-17 2017-12-29 上海擎感智能科技有限公司 旅程信息推送方法及装置、计算机可读存储介质、终端
CN107766987A (zh) * 2017-10-27 2018-03-06 携程旅游网络技术（上海）有限公司 航班动态延误信息推送方法、系统、存储介质和电子设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090105940A1 (en) * 2007-10-23 2009-04-23 Destinator Technologies, Inc. Route calculation based on traffic events
US9140570B1 (en) * 2011-09-08 2015-09-22 Amazon Technologies, Inc. Time-inclusive route and trip planning
CN107491517B (zh) * 2017-08-14 2019-10-29 携程旅游网络技术（上海）有限公司 基于事件驱动的改签方法、系统、设备及存储介质
CN107886301A (zh) * 2017-11-08 2018-04-06 维沃移动通信有限公司 一种交通信息的提醒方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150226569A1 (en) * 2008-10-22 2015-08-13 Tomtom International B.V. Navigation system and method for providing departure times
CN102855777A (zh) * 2012-08-27 2013-01-02 合肥飞友网络科技有限公司 航班延误可能性判断方法
CN103400053A (zh) * 2013-08-26 2013-11-20 合肥飞友网络科技有限公司 航班准点起飞的预估方法
CN106600224A (zh) * 2016-12-12 2017-04-26 北京小米移动软件有限公司 行程规划方法及装置
CN107526796A (zh) * 2017-08-17 2017-12-29 上海擎感智能科技有限公司 旅程信息推送方法及装置、计算机可读存储介质、终端
CN107766987A (zh) * 2017-10-27 2018-03-06 携程旅游网络技术（上海）有限公司 航班动态延误信息推送方法、系统、存储介质和电子设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
WU, RENBIAO ET AL.: "Flight Delay Prediction Model based on Dual-Channel Convolutional Neural Network", JOURNAL OF COMPUTER APPLICATIONS, vol. 38, no. 7, 3 April 2018 (2018-04-03), XP055649408 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111047356A (zh) * 2019-11-29 2020-04-21 阿里巴巴集团控股有限公司 一种交通班次的价值评估方法及装置
CN111047356B (zh) * 2019-11-29 2023-04-28 阿里巴巴集团控股有限公司 一种交通班次的价值评估方法及装置
CN113449207A (zh) * 2020-03-24 2021-09-28 华为技术有限公司 电子设备定位的方法、装置、服务器、系统以及存储介质
CN112418998A (zh) * 2020-12-04 2021-02-26 飞友科技有限公司 一种基于航班历史延误和取消信息的机票购买方法和系统
CN112633713A (zh) * 2020-12-28 2021-04-09 广州羊城通有限公司 基于乘车记录的风险地区提醒方法及装置
CN112966859A (zh) * 2021-02-20 2021-06-15 海南太美航空股份有限公司 一种确定乘客提前出行时间的方法、系统和电子设备
CN114444163A (zh) * 2021-12-13 2022-05-06 中建五局安装工程有限公司 基于bim技术的机电施工方法及系统
CN115115312A (zh) * 2022-07-11 2022-09-27 智航信息服务(深圳)有限公司 一种航班延误预警方法以及系统
CN116758726A (zh) * 2023-07-13 2023-09-15 西藏金采科技股份有限公司 一种基于车联网的大数据分析方法和系统
CN116758726B (zh) * 2023-07-13 2024-03-22 西藏金采科技股份有限公司 一种基于车联网的大数据分析方法和系统
CN119728767A (zh) * 2024-12-13 2025-03-28 中国民航信息网络股份有限公司 一种航班行程信息推送方法、装置、设备、介质及产品

Also Published As

Publication number Publication date
CN108830543B (zh) 2023-04-28
CN108830543A (zh) 2018-11-16

Similar Documents

Publication Publication Date Title
WO2019205306A1 (zh) 一种出行提醒方法及终端设备
Tan et al. Cycle-based queue length estimation for signalized intersections using sparse vehicle trajectory data
CN108151756A (zh) 一种城市公共交通系统的行程时间计算方法和装置
KR101974109B1 (ko) 출발지 위치로부터 목적지 위치로의 여정에 대한 루트 또는 루트 소요 시간을 제공하기 위한 방법 및 컴퓨터 시스템
CN108010378B (zh) 停车场泊位占用率预测方法、装置、设备及存储介质
CN107230091B (zh) 拼车请求订单匹配方法及装置
CN106781511B (zh) 一种基于gps数据和交通事故类型的拥堵时间预测方法
CN105118312A (zh) 信号交叉口多线路多公交车辆优先控制方法
Semchugova et al. Models of estimation of application of passenger service quality parameters
US20140172294A1 (en) Method and system for predicting expected time of arrival of objects
Bie et al. Prediction model of bus arrival time at signalized intersection using GPS data
Wang et al. Providing real-time bus crowding information for passengers: A novel policy to promote high-frequency transit performance
CN105303245A (zh) 交通分析系统以及交通分析方法
Xianmin et al. Optimization method for transit signal priority considering multirequest under connected vehicle environment
Dou et al. Time control point strategy coupled with transfer coordination in bus schedule design
Liang et al. An optimization model for vehicle routing of automated taxi trips with dynamic travel times
Hofleitner et al. Probability distributions of travel times on arterial networks: A traffic flow and horizontal queuing theory approach
CN116013059B (zh) 一种营运车辆的调度方法、装置、电子设备及存储介质
CN115985093B (zh) 基于可变周期策略考虑到达随机性的公交信号优先方法
Zhang et al. EasyComeEasyGo: Predicting bus arrival time with smart phone
Wang et al. Optimization Algorithm Design for the Taxi‐Sharing Problem and Application
Gentile et al. The theory of transit assignment: demand and supply phenomena
CN107563537B (zh) 一种候车时间的确定方法及装置
Lam Route and scheduling choice under travel time uncertainty
WO2019119319A1 (zh) 停车场泊位占用率预测方法、装置、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18916124

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 02/02/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18916124

Country of ref document: EP

Kind code of ref document: A1