Methods, devices, and applications for generating bus stop announcements based on passenger profiles and ETA data.
By combining passenger profiles and ETA data, and using the Viterbi algorithm to calculate the probability of bus stops occurring, the problem of inaccurate stop announcements when GPS signals are poor is solved, and the accuracy and fault tolerance of simulated bus stop announcements are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HANGZHOU SHUZHIMENG TECH CO LTD
- Filing Date
- 2023-03-02
- Publication Date
- 2026-06-30
AI Technical Summary
Existing bus stop announcement systems cannot provide accurate stop information in areas with poor GPS signals or when equipment malfunctions, causing passengers to miss their next stop and affecting passenger flow data mining and scheduling.
By using passenger profiles and ETA data, the probability of bus stops occurring is calculated using the Viterbi algorithm, supplementing the missing GPS location information and generating accurate stop announcement times.
In the absence of GPS positioning, the accuracy of simulated bus stop announcements has been improved, ensuring passengers disembark on time, and the fault tolerance mechanism has been improved to avoid data loss.
Smart Images
Figure CN116205460B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of public transport cloud, and in particular to a method, device and application for generating bus stop announcements based on passenger profiles and ETA data. Background Technology
[0002] The bus stop announcement system employs a series of technologies, including positioning, voice decoding, and wireless transmission, to detect bus stops and automatically announce arrival and departure times. This system allows passengers to easily know the bus's current location and prepare to disembark; it also enables the bus dispatch center to stay informed about the operational status of each bus route and make timely and effective dispatching decisions.
[0003] Currently, bus stop announcements are primarily generated through GPS trajectory simulation. Specifically, the onboard terminal receives navigation messages from satellites, analyzes them to obtain the vehicle's current location, speed, and time, and compares the vehicle's current location with the station locations stored in the terminal. When the vehicle arrives at a station, the voice announcement module is automatically activated to announce the stop. However, in actual operation, due to terrain conditions in certain areas (such as mountainous areas or tunnels where GPS signals are weak) and limitations of the onboard equipment itself (damaged onboard unit or lost GPS signal transmission), bus stop announcement systems relying on GPS positioning may fail to provide accurate announcements. This can lead to passengers missing their stop and the inability to generate corresponding announcements for passenger transactions. Consequently, missing passenger data can occur when statistically analyzing bus route passenger flow, impacting subsequent data mining work on bus schedules, announcements, and passenger flow. Summary of the Invention
[0004] This application provides a method, apparatus, and application for generating bus stop announcements based on passenger profiles and ETA data. It can accurately supplement missing bus stop announcements when some GPS positioning data is missing, thereby improving the accuracy of simulated bus stop announcements.
[0005] In a first aspect, embodiments of this application provide a method for generating bus stop announcements based on passenger profiles and ETA data, including:
[0006] Obtain at least one bus route data, which includes bus number, bus stop, and bus time period;
[0007] The system statistically analyzes the transaction clusters of bus routes in the historical time period of the bus route data. Based on the passenger profile in the transaction cluster, it obtains the first probability that the transaction cluster occurs at the station to be announced. Based on the ETA data corresponding to the transaction cluster, it obtains the second probability that the transaction cluster occurs at the station to be announced. The passenger profile records the boarding frequency of users taking bus routes in the historical time period and the station to be announced. The ETA data records the travel time between station pairs of bus routes in the historical time period.
[0008] Based on the first probability and the second probability, the Viterbi algorithm is used to calculate the third probability of the transaction cluster occurring at the station to be reported. The earliest transaction time of the transaction cluster corresponding to the maximum value of the third probability at the station to be reported is taken as the reporting time of the station to be reported.
[0009] Secondly, embodiments of this application provide a bus stop announcement generation device based on passenger profiles and ETA data, comprising:
[0010] The route record acquisition unit is used to acquire at least one bus route record data, which includes bus number, bus stop, and bus time period.
[0011] The probability prediction unit is used to statistically analyze the transaction clusters of bus routes in the bus route data within a historical time period. Based on the passenger profile in the transaction cluster, it obtains a first probability that the transaction cluster will occur at the station to be announced. Based on the ETA data corresponding to the transaction cluster, it obtains a second probability that the transaction cluster will occur at the station to be announced. The passenger profile records the passenger's bus ride transactions in the historical time period and the boarding frequency at the station to be announced. The ETA data records the travel time between station pairs of bus routes in the historical time period.
[0012] The station announcement generation unit is used to calculate the third probability of the transaction cluster occurring at the station to be announced using the Viterbi algorithm based on the first probability and the second probability, and take the earliest transaction time of the transaction cluster corresponding to the maximum value of the third probability value of the station to be announced as the station announcement time of the station to be announced.
[0013] Thirdly, embodiments of this application provide an electronic device, including a memory and a processor, characterized in that the memory stores a computer program, and the processor is configured to run the computer program to execute a bus stop announcement generation method based on passenger profiles and ETA data.
[0014] Fourthly, embodiments of this application provide a readable storage medium storing a computer program, the computer program including program code for controlling a process to execute the process, the process including a method for generating bus announcements based on passenger profiles and ETA data.
[0015] The main contributions and innovations of this invention are as follows:
[0016] This solution utilizes historical passenger profiles and ETA data to supplement the station announcement times in bus route data. In the absence of some GPS location information, it uses bus route data to supplement bus schedules and makes full use of existing data to simulate station announcements. It has a sound fault tolerance mechanism and only supplements the original station announcement times.
[0017] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description
[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0019] Figure 1 This is a flowchart of a bus stop announcement generation method based on passenger profiles and ETA data according to an embodiment of this application;
[0020] Figure 2 This is a logical framework diagram of a bus stop announcement generation method based on passenger profiles and ETA data according to an embodiment of this application;
[0021] Figure 3 This is a structural block diagram of a bus stop announcement generation device based on passenger profiles and ETA data according to an embodiment of this application;
[0022] Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation
[0023] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.
[0024] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the methods may include more or fewer steps than described in this specification. Furthermore, a single step described in this specification may be broken down into multiple steps in other embodiments; and multiple steps described in this specification may be combined into a single step in other embodiments.
[0025] Example 1
[0026] This solution provides a method for generating bus stop announcements based on passenger profiles and ETA data. To facilitate the explanation of the implementation details, the following provides an explanation of the technical terms involved in this solution:
[0027] Passenger profile: Passenger transactions for bus routes within a historical period, including bus route, boarding station, boarding frequency at each station, passenger information, and transaction time.
[0028] Transaction cluster: A set of bus passenger transactions within a historical period, clustered according to the time of the transaction. Each transaction cluster contains at least one bus transaction that meets the clustering time requirement.
[0029] ETA: Travel time between various stops on a bus route during different time periods, including the statistical time period, bus number, starting station, ending station, start time of the bus at the starting station, and travel time between stations.
[0030] Bus route data: Bus routes dispatched by the on-duty dispatcher based on driving demand, including bus number, bus number stops, planned departure time, planned arrival time, actual departure time, actual arrival time, originating station and destination station, and time period of the bus.
[0031] It should be noted that each bus trip mentioned in this scheme corresponds to a unique bus route. The same bus trip is operated by multiple buses. Therefore, the bus trip records in this scheme include both vehicle identification and route identification. For example, if both vehicle A and vehicle B operate bus trip 101, and bus trip 101 runs from the train station to the railway station, then bus trip 101 will be recorded with either vehicle identification: vehicle A or vehicle B, and the bus route will be represented as 101.
[0032] like Figure 1 and Figure 2 As shown, the bus stop announcement generation method based on passenger profiles and ETA data provided in this solution includes the following steps:
[0033] Obtain at least one bus route data, which includes bus number, bus stop, and bus time period;
[0034] The system statistically analyzes the transaction clusters of bus routes in the historical time period of the bus route data. Based on the passenger profile in the transaction cluster, it obtains the first probability that the transaction cluster occurs at the station to be announced. Based on the ETA data corresponding to the transaction cluster, it obtains the second probability that the transaction cluster occurs at the station to be announced. The passenger profile records the boarding frequency of users taking bus routes in the historical time period and the station to be announced. The ETA data records the travel time between station pairs of bus routes in the historical time period.
[0035] Based on the first probability and the second probability, the Viterbi algorithm is used to calculate the third probability of the transaction cluster occurring at the station to be reported. The earliest transaction time of the transaction cluster corresponding to the maximum value of the third probability at the station to be reported is taken as the reporting time of the station to be reported.
[0036] This solution provides a bus stop announcement generation method based on passenger profiles and ETA data. It utilizes existing passenger profiles and ETA data to supplement simulated bus stop announcements for bus route data that does not rely on GPS positioning, improving the accuracy of simulated bus stop announcements without affecting the original simulated bus stop announcement system. This solution supplements simulated bus stop announcements for bus route data that does not rely on GPS positioning; that is, at least one bus route data obtained by this solution is bus route data that does not rely on GPS positioning. In some embodiments, in the "obtain at least one bus route data" step, the preset announcement time of the bus route's stops generated by the simulated bus stop announcement system is obtained. The bus route data is matched according to the preset announcement time, and unmatched bus route data is filtered out. This solution uses the unmatched bus route data to generate simulated bus stop announcements. It should be noted that this solution generates simulated bus stop announcements for bus route data that cannot be simulated by the simulated bus stop announcement system for an entire bus route.
[0037] In some embodiments, after verifying the correctness of the unmatched bus route data obtained through filtering, the origin station, destination station, actual departure time of the origin station, and actual arrival time of the destination station for the bus route are obtained. The time slot for the current bus route is then calculated based on the actual departure and arrival times. It should be noted that this solution processes historical bus route data, which is manually updated by dispatchers or drivers with actual departure and arrival times. Therefore, the actual departure and arrival times of the bus route data are still known.
[0038] Specifically, the bus route data refers to the bus schedule arranged in advance by the on-duty dispatcher based on the dispatch plan. The bus route data includes bus number, bus route number and stops, planned departure time, planned arrival time, actual departure time, actual arrival time, origin station and destination station, and time period of the bus.
[0039] For example, the information of a bus route list is as follows: Originating station: Railway Station; Destination station: Railway Station; Bus stops: First stop, Second stop, Third stop; Vehicle identifier: Hangzhou AXXXX; Route identifier: 101; Actual departure time: 8:00; Actual arrival time: 10:00.
[0040] Since the bus route data and stops for this type of bus route cannot rely on GPS location information, this solution simulates the announcement of stops based on existing passenger profiles and ETA data after obtaining the bus route data.
[0041] In the step of "statistically analyzing the transaction clusters of bus routes in the historical time period", the transaction clusters are obtained by clustering passenger ride transactions in the historical time period according to the transaction time. The ride transactions include bus routes, boarding stations, passenger information and transaction time.
[0042] Each passenger's bus ride generates a transaction. Multiple transactions for the same passenger constitute a passenger profile; in other words, a passenger profile contains at least one transaction for the same passenger. Since the same passenger may board at the same stop multiple times, the passenger profile includes historical bus ride transactions and the boarding frequency at each stop. The boarding frequency at each stop is calculated based on multiple transactions. Specifically, the number of times a passenger boards at a stop and the total number of transactions for that passenger on that bus route are obtained. The quotient of the number of boardings to the total number of transactions is taken as the passenger's boarding frequency at that stop. This process is repeated for each stop to obtain the passenger's boarding frequency at each stop. Multiple transactions within a set time period for the same bus route are clustered into transaction clusters, and each cluster contains at least one transaction that fits the set time period.
[0043] Generally, when a bus stops at a station, passengers board in order of their queue, and these transactions form a cluster based on the time of boarding. Since no new transactions usually occur during the normal operation of a bus, for the same bus route, the occurrence of a cluster of transactions indicates that the bus is currently stopped at a specific boarding station, and each cluster contains transactions from different passengers.
[0044] In other words, this scheme statistically analyzes passengers' historical bus transactions to form passenger profiles. These profiles include the frequency at which each passenger boarded the bus at various stops on their historical bus routes. The data is then clustered according to the transaction time of each passenger's transactions to obtain transaction clusters for different time periods.
[0045] In some embodiments, a passenger's card number can be used to identify the passenger's passenger information. For example, passenger Li XX's ride transaction is as follows: Bus number: 101; Boarding station: Railway station; Transaction time: 8:30; Ride information: 1101101. Passenger profile of passenger Li XX is as follows: Passenger Li XX's ride transaction is as follows: Bus number: 101; Boarding station: Railway station; Transaction time: 8:30, 8:40, 8:30; Ride information: 1101101; Boarding frequency at station: 3 times.
[0046] In the step of "obtaining the first probability of the transaction cluster occurring at the station to be announced based on the passenger profile in the transaction cluster", passenger profiles of passengers whose number of ride transactions is greater than a set threshold are selected from the transaction cluster, and the first probability of the transaction cluster occurring at the station to be announced is obtained based on the passenger profile.
[0047] In some embodiments, passenger profiles are selected from the transaction clusters of passengers who have made more than 15 ride transactions within 150 days. Of course, the specific selection criteria can be adjusted according to actual needs. This solution uses this method to select passenger profiles of passengers who frequently take the same bus route for calculation, thereby avoiding errors caused by random ride transactions.
[0048] In the step of "obtaining the first probability of a transaction cluster occurring at a station to be announced based on the passenger profile in the transaction cluster," the boarding frequency of each passenger at the station to be announced is obtained based on the passenger profile, and the occurrence probability of each passenger at the station to be announced is obtained. The first probability of the station to be announced is obtained by taking the product of the boarding frequency and the occurrence probability of each passenger and the occurrence probability of all passengers together. This scheme uses the boarding frequency of passengers at the current station as the occurrence probability of each passenger at the station to be announced. Since there is no connection between passengers, they satisfy the concept of independent distribution. Therefore, the probability of all passengers boarding at this station is equal to the product of the probabilities of each passenger boarding at this station, that is, the product of the boarding frequencies of each passenger at this station.
[0049] In other words, the first probability of the transaction cluster occurring at the station to be announced is equal to the product of the boarding frequencies of each passenger at the station to be announced.
[0050] Specifically, the formula for calculating the first probability of the transaction cluster occurring at the station to be announced, based on the passenger profile, is as follows:
[0051]
[0052] Where P(station|personN) represents the frequency at which a passenger N chooses to board the train at the station to be announced, P(personN) represents the probability of a passenger N appearing, N is the number of passengers, and the denominator is the probability of all passengers appearing together. Since there is no connection between the passengers, they satisfy the concept of independent distribution, that is, P(person1,person2,…,personN) and P(person1).
[0053] Since *P(person2)...*P(personN) are equal, the numerator and denominator can be simplified during calculation.
[0054] This solution iterates through and calculates the first probability of each bus stop in the pending announcement data to obtain the first probability of a transaction cluster occurring at that stop. It should be noted that this first probability is obtained based on historical passenger profiles; that is, it is acquired from actual bus transaction data. This method of obtaining the first probability better reflects the actual operational patterns of public transportation.
[0055] In the step of “obtaining the second probability of the transaction cluster occurring at the station of the bus to be reported based on the ETA data corresponding to the transaction cluster”, the ETA data is the travel time between station pairs formed by various stations of the bus route in different time periods. The ETA data includes the statistical time period, bus number, starting station, ending station, the start time of the bus at the starting station, and the travel time between stations.
[0056] Specifically, in the step of "obtaining the second probability of a transaction cluster occurring at a station to be announced based on the ETA data corresponding to the transaction cluster," the difference between the average transaction time of each transaction cluster and the start time of the train is obtained; the travel time from the start time of the train to the station to be announced and the variance of the travel time are obtained; and the second probability of the station to be announced is calculated based on the difference, the travel time, and the variance. The average transaction time of each transaction cluster is obtained by averaging the transaction times of multiple travel transactions for each transaction cluster. In some embodiments, the travel time between stations is calculated based on historical data, the mean of the travel time between stations is obtained, and the difference between the travel time at the same station and the mean is calculated, thereby calculating the variance of the travel time.
[0057] The formula for calculating the second probability for each station is as follows:
[0058]
[0059] Where x is the difference between the average transaction time of ride transactions within the transaction cluster and the start time of the ride, μ is the start time of the ride plus the travel time to the station to be announced, σ is the variance of the travel time used, and P(station) is the second probability of the station to be announced.
[0060] It should be noted that the first probability in this scheme is derived from passenger profiles, and the station to which the transaction cluster belongs can be obtained based on the maximum value of the first probability; the second probability is derived from ET data, and the station to which the transaction cluster belongs can also be obtained based on the maximum value of the second probability. In this scheme, a selection probability model is established based on the second probability as the prediction probability and the first probability as the transition probability. The Viterbi algorithm is used to obtain the station to which the transaction cluster has the highest probability, and the earliest transaction time of the transaction cluster at that station is used as the station's announcement time.
[0061] In the step of "calculating the third probability of the transaction cluster occurring at the station to be announced using the Viterbi algorithm based on the first and second probabilities, and taking the earliest transaction time of the transaction cluster corresponding to the maximum value of the third probability at the station to be announced as the station's announcement time," this scheme uses the Viterbi algorithm to calculate the maximum probability combination of each transaction cluster occurring at the station to be announced based on the first and second probabilities. Due to the limitations of clustering algorithms, different travel transactions at the same station may be mistakenly divided into multiple transaction clusters. In this case, multiple transaction clusters correspond to the same station. Therefore, this scheme takes the earliest transaction time in the transaction cluster of each station as the station's announcement time.
[0062] Specifically, the formula for calculating the third probability is as follows:
[0063] dp[i][j]=Max(dp[i-1][k],k∈[0,j]+trans[i][j]+emit[i][j]
[0064] Where dp[i][j] represents the probability that the i-th transaction cluster, sorted by time, occurs at the j-th stop of the bus route to be announced, trans[i][j] represents the first probability that the i-th transaction cluster occurs at the j-th stop of the bus route to be announced, and emit[i][j] represents the second probability that the i-th transaction cluster occurs at the j-th stop of the bus route to be announced.
[0065] Additionally, in some embodiments, there may be situations where a bus stop on a certain route does not have a transaction cluster. In such cases, simulated announcements are performed on these stops without transaction clusters based on ETA data. Specifically, after the step of "taking the earliest transaction time of the transaction cluster corresponding to the maximum value of the third probability value of each stop as the announcement time of that stop," the process includes the following steps: filtering out bus stops that have not generated announcement times as empty stops, obtaining the preceding announcement time of the previous stop with an announcement time for the empty stop, and calculating the announcement time of the empty stop based on the ETA data and the preceding announcement time. Since the ETA data records the travel time between stops, the announcement time of the current empty stop can be calculated based on the ETA data and the preceding announcement time.
[0066] Of course, in some embodiments, after obtaining the announcement time of each stop for the bus route data, unreasonable data is corrected for accuracy to facilitate subsequent data management. For example, if the announcement time of a later stop is earlier than the announcement time of an earlier stop, it indicates that the announcement data of that bus route data must be incorrect.
[0067] Example 2
[0068] Based on the same concept, referencing Figure 3 This application also proposes a bus stop announcement generation device based on passenger profiles and ETA data, comprising:
[0069] The route record acquisition unit is used to acquire at least one bus route record data, which includes bus number, bus stop, and bus time period.
[0070] The probability prediction unit is used to statistically analyze the transaction clusters of bus routes in the bus route data within a historical time period. Based on the passenger profile in the transaction cluster, it obtains a first probability that the transaction cluster will occur at the station to be announced. Based on the ETA data corresponding to the transaction cluster, it obtains a second probability that the transaction cluster will occur at the station to be announced. The passenger profile records the passenger's bus ride transactions in the historical time period and the boarding frequency at the station to be announced. The ETA data records the travel time between station pairs of bus routes in the historical time period.
[0071] The station announcement generation unit is used to calculate the third probability of the transaction cluster occurring at the station to be announced using the Viterbi algorithm based on the first probability and the second probability, and take the earliest transaction time of the transaction cluster corresponding to the maximum value of the third probability value of the station to be announced as the station announcement time of the station to be announced.
[0072] The content of this second embodiment that is the same as that of the first embodiment will not be repeated here, but will be described in detail above.
[0073] Example 3
[0074] This embodiment also provides an electronic device, see reference. Figure 4 It includes a memory 304 and a processor 302, the memory 304 storing a computer program and the processor 302 being configured to run the computer program to perform the steps in any of the embodiments of the bus announcement generation method based on passenger profiles and ETA data described above.
[0075] Specifically, the processor 302 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.
[0076] The memory 304 may include a mass storage device for data or instructions. For example, and not limitingly, the memory 304 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 304 may include removable or non-removable (or fixed) media. Where appropriate, the memory 304 may be internal or external to a data processing device. In a particular embodiment, the memory 304 is non-volatile memory. In a particular embodiment, the memory 304 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.
[0077] The memory 304 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 302.
[0078] The processor 302 reads and executes computer program instructions stored in the memory 304 to implement any of the bus stop announcement generation methods based on passenger profiles and ETA data in the above embodiments.
[0079] Optionally, the electronic device may further include a transmission device 306 and an input / output device 308, wherein the transmission device 306 is connected to the processor 302 and the input / output device 308 is connected to the processor 302.
[0080] The transmission device 306 can be used to receive or send data via a network. Specific examples of the network described above may include wired or wireless networks provided by the communication provider of the electronic device. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 306 may be a Radio Frequency (RF) module used for wireless communication with the Internet.
[0081] The input / output device 308 is used to input or output information. In this embodiment, the input information may be bus route data, etc., and the output information may be station announcement times, etc.
[0082] Optionally, in this embodiment, the processor 302 can be configured to perform the following steps via a computer program:
[0083] Obtain at least one bus route data, which includes bus number, bus stop, and bus time period;
[0084] The system statistically analyzes the transaction clusters of bus routes in the historical time period of the bus route data. Based on the passenger profile in the transaction cluster, it obtains the first probability that the transaction cluster occurs at the station to be announced. Based on the ETA data corresponding to the transaction cluster, it obtains the second probability that the transaction cluster occurs at the station to be announced. The passenger profile records the boarding frequency of users taking bus routes in the historical time period and the station to be announced. The ETA data records the travel time between station pairs of bus routes in the historical time period.
[0085] Based on the first probability and the second probability, the Viterbi algorithm is used to calculate the third probability of the transaction cluster occurring at the station to be reported. The earliest transaction time of the transaction cluster corresponding to the maximum value of the third probability at the station to be reported is taken as the reporting time of the station to be reported.
[0086] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.
[0087] Generally, various embodiments can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects of the invention can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that, by way of non-limiting example, these blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.
[0088] Embodiments of the present invention can be implemented by computer software, which may be executable by a data processor of a mobile device, such as a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products), including software routines, applets, and / or macros, can be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. A computer program product may include one or more computer-executable components configured to perform embodiments when the program is run. One or more computer-executable components may be at least one piece of software code or a portion thereof. Additionally, it should be noted that any block in the logical flow of the figures may represent a program step, or interconnected logical circuitry, blocks and functions, or a combination of program steps and logical circuitry, blocks and functions. The software may be stored on physical media such as memory chips or blocks of storage implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as, for example, DVDs and their data variants, CDs, etc. The physical medium is a non-transient medium.
[0089] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0090] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for generating bus stop announcements based on passenger profiles and ETA data, characterized in that, include: Obtain at least one bus route data, which includes bus number, bus stop, and bus time period; The bus route data is statistically analyzed for transaction clusters of bus routes within a historical time period. Based on the passenger profile, the boarding frequency of each passenger at the station to be announced is obtained, and the occurrence probability of each passenger at the station to be announced is obtained. The first probability of the station to be announced is obtained by taking the product of the boarding frequency of each passenger and the occurrence probability of each passenger and the occurrence probability of all passengers together. ETA data includes the start time of the bus service at the starting station, the difference between the average transaction time of each transaction cluster and the start time of the bus service, the travel time from the start time of the bus service to the station to be announced and the variance of the travel time, and a second probability of the station to be announced is calculated based on the difference, the travel time and the variance. The passenger profile records the passenger's bus service transactions and the boarding frequency of the station to be announced in historical time. The ETA data records the travel time between station pairs of bus services in historical time. Based on the first probability and the second probability, the Viterbi algorithm is used to calculate the third probability of the transaction cluster occurring at the station to be reported. The earliest transaction time of the transaction cluster corresponding to the maximum value of the third probability at the station to be reported is taken as the reporting time of the station to be reported.
2. The bus stop announcement generation method based on passenger profiles and ETA data according to claim 1, characterized in that, In the step of "obtaining at least one bus route data", the preset announcement time of the bus route generated by the simulated announcement system is obtained, and the bus route data is matched according to the preset announcement time and the bus route data that cannot be matched is filtered out.
3. The bus stop announcement generation method based on passenger profiles and ETA data according to claim 1, characterized in that, Stations with no announced times are selected as empty stations. The preceding announced time of the station with an announced time is obtained, and the announced time of the empty station is calculated based on the ETA data and the preceding announced time.
4. The bus stop announcement generation method based on passenger profiles and ETA data according to claim 1, characterized in that, The transaction clusters are obtained by clustering passenger ride transactions within a historical period according to the transaction time. The ride transactions include bus routes, boarding stations, passenger information, and the time of the transaction.
5. A bus stop announcement generation device based on passenger profiles and ETA data, characterized in that, include: The route record acquisition unit is used to acquire at least one bus route record data, which includes bus number, bus stop, and bus time period. The probability prediction unit is used to statistically analyze the transaction clusters of bus routes in the historical time period of the bus route data. Based on the passenger profile, it obtains the boarding frequency of each passenger at the station to be announced, obtains the probability of each passenger appearing at the station to be announced, and takes the product of the boarding frequency and the probability of each passenger's appearance and the probability of all passengers appearing together as the quotient to obtain the first probability of the station to be announced. The ETA data includes the start time of the route from the starting station, obtains the difference between the average transaction time of each transaction cluster and the start time of the route, obtains the travel time from the start time of the route to the station to be announced and the variance of the travel time, and calculates the second probability of the station to be announced based on the difference, the travel time and the variance. The passenger profile records the historical user bus ride transactions and the boarding frequency of the station to be announced, and the ETA data records the travel time between station pairs of bus routes in the historical time. The station announcement generation unit is used to calculate the third probability of the transaction cluster occurring at the station to be announced using the Viterbi algorithm based on the first probability and the second probability, and take the earliest transaction time of the transaction cluster corresponding to the maximum value of the third probability value of the station to be announced as the station announcement time of the station to be announced.
6. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the bus stop announcement generation method based on passenger profiles and ETA data as described in any one of claims 1 to 4.
7. A readable storage medium, characterized in that, The readable storage medium stores a computer program, the computer program including program code for controlling the process to execute the process, the process including the bus announcement generation method based on passenger profiles and ETA data according to any one of claims 1 to 4.