Railway passenger-oriented service information differentiated pushing method and system and storage medium

Abstract

The invention provides a service information differentiated pushing method and system for railway passengers and a storage medium. The method comprises the following steps: acquiring meteorological disaster information and position state information of passengers; outputting and obtaining a pushing time influence value of a meteorological disaster, a pushing time influence value of a passenger position state, a pushing time influence value of each service information type suitable for a passenger and a pushing time influence value of a pushing channel through an information flow pushing model; for each service information type, calculating a priority corresponding to the service information type; and if the priority is greater than a set priority threshold, calculating the optimal time of pushing the service information of the type by each pushing channel based on a pushing time influence value output by the model, otherwise, pushing the service information of the type to the passenger through each pushing channel immediately based on a pre-stored association relationship. According to the method, the problems of fragmentation and hysteresis of the current railway notification can be solved.

Description

Technical Field

[0001] This invention relates to the field of railway passenger transport safety technology, and in particular to a method and system for differentiated delivery of service information to railway passengers. Background Technology

[0002] Extreme weather events such as snowstorms and ice storms significantly impact railway passenger transport organization and passenger travel. Under severe weather conditions, the current railway passenger service information notification system suffers from limited information and channels, and may also experience delays in notification. This often leads to passengers facing information gaps and inadequate follow-up services, negatively impacting passenger service quality and passenger satisfaction.

[0003] Therefore, there is an urgent need for a service information push method for railway passengers to solve the current problems of fragmentation and lag in railway information notification. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method and system for differentiated push of service information to railway passengers, which systematically solves the problems of fragmentation and lag in current railway information notifications, helps to improve the information release capabilities of railway passenger stations and trains, and is of great significance to improving passenger satisfaction and ensuring passenger safety.

[0005] One aspect of the present invention provides a method for differentiated delivery of service information to railway passengers. For each passenger, the method includes the following steps:

[0006] Obtain information on meteorological disasters, passenger location status, and the scheduled time of the trains the passengers are traveling on;

[0007] Meteorological disaster information, passenger location status information, pre-stored correlations, and train schedules are input into a pre-trained information flow push model. This model determines the appropriate service information types and push channels for passengers based on the meteorological disaster information, passenger location status information, and correlations. It then outputs the push time impact values ​​for meteorological disasters, passenger location status, each service information type, and each push channel. The correlations refer to the correspondence between meteorological disaster information, passenger location status information, the type of service information to be pushed, and the push channel.

[0008] The priority of each service information type is calculated based on the train's scheduled time, the impact of meteorological disaster push time, the impact of passenger location status push time, and the impact of push time for each service information type.

[0009] For each type of service information, if the priority of the service information type is greater than the set priority threshold, the optimal time for each push channel to push the service information of that type is calculated based on the train's scheduled time, the impact of the push time of meteorological disasters, the impact of the push time of passenger location status, the impact of the push time of the service information type, and the impact of the push time of each push channel. If the priority of the service information type is not greater than the set priority threshold, the optimal time for each push channel to push the service information of that type is the current time.

[0010] The corresponding service information is obtained based on the various service information types applicable to passengers, and the obtained service information is pushed to passengers through the corresponding push channels at the determined optimal time.

[0011] In some embodiments of the present invention, the priority of each service information type is calculated in the following manner:

[0012] The system performs a weighted summation based on meteorological disaster information, passenger location status information, the impact value of push time for each type of service information, and the corresponding first set weight coefficient. The priority of each type of service information is then calculated based on the time difference between the train's scheduled time and the current time, as well as the result of the weighted summation.

[0013] In some embodiments of the present invention, based on the train's scheduled time, the impact of meteorological disaster push notification time, the impact of passenger location status push notification time, the impact of the push notification time for this type of service information, and the impact of the push notification time for each push channel, the optimal time for each push channel to push this type of service information is calculated, including:

[0014] The system performs a weighted summation based on meteorological disaster information, passenger location status information, the type of service information, the impact of push time from various push channels, and the corresponding second set weight coefficients, and calculates the time difference between the train's scheduled time and the current time.

[0015] The time offset is calculated based on the time difference and the weighted summation result. The sum of the time offset and the current time is used as the optimal push time for this type of service information on various push channels.

[0016] In some embodiments of the present invention, meteorological disaster information is used to measure the degree of impact of meteorological disasters. The degree of impact of meteorological disasters is determined based on at least one of meteorological disaster data, the operation of trains on the line, the operation of stations, and the operation of station equipment, and is divided into three levels: strong impact, moderate impact, and weak impact.

[0017] Passenger location status information includes: passenger has not arrived at the station, passenger is in the station, passenger is on the corresponding train, or passenger has exited the station to transfer.

[0018] Service information includes the following types of information: train operation status, weather forecasts and warnings, and travel advice;

[0019] Push channels include at least one of mobile applications, text messages, and websites, as well as telephone inquiries.

[0020] In some embodiments of the present invention, for passengers who have not yet arrived at their destination, in cases where the impact of meteorological disasters is severe, the types of service information applicable to passengers may also include: in-station services and safety reminders;

[0021] For passengers located within the station, the push channels also include: station display screens, broadcast announcements, and on-site station information; and, in cases where the impact of meteorological disasters is moderate to strong, the types of service information applicable to passengers also include: station services, safety tips, and emergency measures; in cases where the impact of meteorological disasters is weak, the types of service information applicable to passengers also include: safety tips and emergency measures.

[0022] For passengers on the corresponding trains, the push channels also include: onboard information displays and broadcast announcements; in the case of a severe impact from meteorological disasters, the types of service information applicable to passengers also include: emergency measures; in the case of a moderate or weak impact from meteorological disasters, the types of service information applicable to passengers also include: safety tips and emergency measures.

[0023] For passengers transferring at the station, the push channels also include: station display screens, in-vehicle information display screens, and broadcast announcements; the types of service information applicable to passengers also include: station services, safety tips, and emergency measures.

[0024] In some embodiments of the present invention, the method further includes: updating meteorological disaster information and passenger location status information based on the information update frequency corresponding to each service information type, and redetermining the push time of each channel applicable to the passenger based on the updated information; wherein, the information update frequency corresponding to each type of service information to be pushed is obtained based on the influence coefficient of meteorological disaster information on the information update frequency and the basic update frequency of each service information type.

[0025] In some embodiments of the present invention, the method further includes: collecting passenger evaluation feedback results on the pushed content within a set time interval; if the number of collected evaluation feedback results is greater than a set feedback amount, calculating the user feedback value through a predetermined objective function; and if the user feedback value is not greater than a set feedback threshold, updating the second set weight coefficient based on the user feedback value.

[0026] If the number of collected evaluation feedback results is not greater than the set feedback amount, the second set weight coefficient is updated based on historical data; whereby the user feedback value is determined based on user information acceptance, user accuracy, and information update delay.

[0027] In some embodiments of the present invention, the method further includes:

[0028] For the train operation status in the service information type, the time delay for train departure is calculated based on the acquired service information to be pushed for this type. If the calculated time is greater than the set delay time value, the priority corresponding to this service information type is recalculated, and the optimal push time for the service information of the train operation status type is re-determined.

[0029] Another aspect of the present invention provides a service information differentiation push system for railway passengers, including a processor, a memory, and a computer program / instructions stored in the memory. The processor is used to execute the computer program / instructions, and when the computer program / instructions are executed, the system implements the steps of the method described in any of the above embodiments.

[0030] Another aspect of the present invention provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the method described in any of the above embodiments.

[0031] The differentiated service information push method and system for railway passengers proposed in this invention can not only differentiate the push channels and passenger service information based on pre-stored associations, but also differentiate the push time by calculating the priority of the type of service information to be pushed to each passenger. The differentiated service information push method proposed in this application systematically solves the problems of fragmentation and lag in current railway information notifications, significantly improves the passenger travel experience and the timeliness of information, and can effectively cope with the inconvenience caused by severe weather.

[0032] Additional advantages, objects, and features of the invention will be set forth in part in the description which follows, and will also become apparent in part to those skilled in the art upon studying the description, or may be learned by practice of the invention. The objects and other advantages of the invention can be realized and obtained by means of the structures specifically pointed out in the description and drawings.

[0033] Those skilled in the art will understand that the objectives and advantages achievable with the present invention are not limited to those specifically described above, and that the above and other objectives achievable with the present invention will become clearer from the following detailed description. Attached Figure Description

[0034] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, are not intended to limit the scope of the invention. In the drawings:

[0035] Figure 1 This is a flowchart illustrating a method for differentiated push of service information to railway passengers according to an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the embodiments and accompanying drawings. Here, the illustrative embodiments and descriptions of this invention are used to explain the invention, but are not intended to limit the invention.

[0037] It should also be noted that, in order to avoid obscuring the invention with unnecessary details, only the structures and / or processing steps closely related to the solution according to the invention are shown in the accompanying drawings, while other details that are not closely related to the invention are omitted.

[0038] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, element, step, or component, but does not exclude the presence or addition of one or more other features, elements, steps, or components.

[0039] In the following description, embodiments of the invention will be illustrated with reference to the accompanying drawings. In the drawings, the same reference numerals represent the same or similar parts, or the same or similar steps.

[0040] Current railway passenger service information notification schemes suffer from limited information and channels, and may also be untimely, negatively impacting passenger service quality and satisfaction. Therefore, this application proposes a differentiated service information delivery method for railway passengers. This method allows for differentiated delivery strategies across dimensions such as delivery channels, the passenger service information delivered, and the delivery time. It not only solves the problems of fragmentation and delays in current railway information notifications but also enables customization, making the delivery strategy more targeted.

[0041] The differentiated service information push method proposed in this application can be used to generate differentiated push strategies for each passenger under different meteorological disaster conditions. Since the service information push method proposed in this application is implemented for railway passenger stations, it can generate differentiated push strategies for passengers corresponding to trains departing from or arriving at the station within a certain time interval. That is, the method proposed in this application can generate differentiated push strategies for passengers affected within a certain time interval.

[0042] Figure 1 This is a flowchart illustrating a method for differentiated service information delivery to railway passengers according to an embodiment of the present invention. Figure 1 As shown, for each passenger, the method includes steps S110 to S150.

[0043] Step S110: Obtain meteorological disaster information, passenger location status information (i.e., the passenger's current location status information), and the scheduled time of the train the passenger is traveling on. The scheduled train time can be the scheduled departure time, the scheduled departure time from the station, or the scheduled arrival time at the station, etc., and this invention does not specifically limit its type. As an example, since the service information push method proposed in this application is implemented for railway stations, this application can obtain meteorological disaster information within a set meteorological range to generate subsequent differentiated push strategies. The set meteorological range can be set based on the station location (e.g., obtaining meteorological disaster information for the area to which the station belongs), or it can be set based on both the station location and the passenger location; this application does not specifically limit the method of setting the meteorological range.

[0044] In some embodiments of the present invention, meteorological disaster information can be obtained from existing meteorological systems. For example, meteorological disaster information may include information on extreme weather types such as rainfall, snowfall, or strong winds. The obtained meteorological disaster information can be used to measure the degree of impact of meteorological disasters on stations and trains (trains and high-speed trains, etc.) (hereinafter referred to as the degree of meteorological disaster impact). The degree of meteorological disaster impact can be determined based on at least one of meteorological disaster data, train operation status, station operation status, and station equipment operation status. For example, meteorological disaster data may include meteorological forecasts and warnings, as well as actual meteorological data. Meteorological forecasts and warnings may include meteorological disaster warning levels and meteorological disaster forecast data (such as the expected snowfall of 25cm). Actual meteorological data may include actual snowfall, rainfall, or wind force levels, and other actual monitoring data of extreme weather events. Train operation status on railway lines may include at least one of the following: the degree of deviation between actual train operation and scheduled operation, train speed, train delays, and train cancellations. Train speed may be the current speed of the train the passenger is traveling on or the average speed calculated based on the distance the train has traveled. Station operation status may include the status of trains stopped at the station, the availability of entrances and / or temporary waiting rooms. Station equipment operation status may include indicators such as station equipment failure rate to indicate whether station equipment is operating normally.

[0045] As an example, the impact of meteorological disasters can be categorized into strong, moderate, and weak impacts (that is, classifying the impact of meteorological disasters on stations and trains into three levels: strong, moderate, and weak). Taking snowfall as an example, the classification criteria can be as follows:

[0046] ① Severe impact refers to weather conditions that seriously affect transportation safety and train operation. That is, weather conditions can severely impact stations, leading to widespread train cancellations, severe delays, or stations being unable to operate normally. Severe impact can manifest as: large-scale snowfall (e.g., snowfall exceeding 20 cm) or freezing weather; a significant reduction in train speed (e.g., below 50% of normal operating speed); more than 10 trains being cancelled due to weather at important transportation hubs (e.g., stations with a passenger flow of >100,000 people / day can be considered important transportation hubs), resulting in a large number of stranded passengers; and / or, frequent equipment failures (frequent failures of signaling systems and power supply systems, etc.).

[0047] ② Moderate impact refers to weather conditions that may affect some trains, but stations can still operate. This means that stations are moderately affected by severe weather (which can be understood as some disruption to station operations), with some trains delayed or canceled, but basic operations can be maintained. Moderate impact can manifest as: moderate snowfall (e.g., 10-20 cm); reduced train speeds (e.g., below 70%-90% of normal operating speed); some train delays, with only 1-2 trains cancelled at the station, but important transportation hubs still operating; and / or, the possibility of minor equipment malfunctions that do not affect overall safety.

[0048] ③ Minor impact refers to weather conditions having little effect on station operations and train runs. That is, weather conditions have a minimal impact on the station, and train and station operations are generally normal with no significant disruption. Minor impacts can manifest as: light snowfall (e.g., less than 10 cm); train speeds approaching normal with occasional minor delays; normal station operations and smooth passenger flow; and / or, normal equipment functionality with no significant malfunctions.

[0049] The aforementioned classification of meteorological disaster impact into three levels—strong, moderate, and weak—is merely an example. This application may also employ other classification criteria to categorize meteorological disasters into multiple levels based on their impact on stations and trains; this invention is not limited to these. Furthermore, since the differentiated push method proposed in this application is driven by weather conditions, when the impact of a meteorological disaster changes (e.g., from strong to moderate), meteorological disaster information and passenger location status information (as well as the scheduled time of the train the passenger is traveling on) are immediately reacquired, and a new differentiated push strategy is generated. For simplicity, the character S can be used. i The variable representing the degree of impact of meteorological disasters can be divided into strong impact S1, moderate impact S2 and weak impact S3.

[0050] In some embodiments of the present invention, passenger location information can be used to determine the current location of each passenger corresponding to the affected train, which can be obtained through GPS, Beidou navigation system, or the built-in navigation function in the official railway APP. For example, based on the distance between the passenger and the corresponding station (the boarding station of the train the passenger is taking), the passenger's location information can be: passenger has not arrived at the station, passenger is in the station, passenger is on the corresponding train, or passenger has exited the station to transfer. That is, passengers affected by meteorological disasters can be divided into four types: passengers who have not arrived at the station, passengers who have arrived at the station, passengers who are en route, and passengers who have exited the station to transfer. The passenger location information mentioned above is only an example; any information that can be used to indicate the passenger's location can be selected, and the present invention is not limited thereto. For simplification, the character T can be used. j This can be used to represent passenger location status variables. For example, passenger location status variables include passengers who have not arrived (T1), passengers who have arrived (T2), passengers who are en route (T3), and passengers who are transferring after exiting the station (T4).

[0051] The differentiated push method proposed in this application can be reflected in the differentiation of service information pushed to passengers and the differentiation of push channels.

[0052] As an example, passengers who haven't arrived at their destination yet need to know the train's departure status and arrival time in a timely manner to adjust their travel plans and prepare accordingly; passengers who have arrived at their destination need to obtain exit information and transfer guidance to ensure a smooth transfer to their subsequent journey or resolve any potential delays; passengers en route need to know the train's operating status and potential delay information to prepare accordingly; and passengers exiting the station or transferring need to obtain the latest transfer information, including train schedules and platform arrangements, to ensure a smooth subsequent journey. As can be seen, driven by different weather disaster conditions, the types of service information that passengers in different locations need to receive may vary.

[0053] In some embodiments of the present invention, the passenger service information to be pushed in this application includes at least three types: train operation status, weather forecast and warning information, and travel suggestions. The train operation status information can be obtained from the train dispatching system and may include at least one of the following: train delays, train cancellations, estimated arrival time at the station, and whether the train will depart on time, to help passengers plan their trips accordingly. The weather forecast and warning information information is the same as the forecast and warning information in the aforementioned meteorological disaster data, obtained from the meteorological system. This type of information may include meteorological disaster warning levels and meteorological disaster forecast data to provide information on future weather changes (such as snowfall) and temperature, allowing passengers to understand changes in the travel environment. Travel suggestions provide travel guidance to passengers and may be generated based on AI assistants or deep learning networks. For example, the travel suggestion information may provide multiple ways to reach the station based on the current weather and train status, alternative train transfer options after train cancellations, or ticket refund services to help passengers complete their trips smoothly. In addition, the train operation status and the service information to be pushed in the type of train operation status mentioned in this application may include the same information (or different information, for example, the train operation status includes the actual situation of the current train operation, while the service information to be pushed in the type of train operation status may include the actual situation of the train operation as well as the predicted situation of the train operation). However, in order to distinguish between the train-related data in the meteorological disaster impact classification standard and the train-related data in the passenger service information pushed to passengers, this application uses different names to name them.

[0054] The travel advice can be mainly divided into three types: The first type suggests travel and provides recommendations on transportation methods; the second type suggests using some modes of transportation; and the third type discourages travel and provides a refund reminder. For example, the first type might suggest, "The weather impact is minimal, and trains are expected to operate normally; passengers are advised to use subways, buses, and private cars." The second type might suggest, "Due to the current weather conditions affecting the train you are traveling on, the train is expected to be delayed; passengers are advised to use subways." The third type might suggest, "Due to the current weather conditions affecting the train you are traveling on, the train has been cancelled; passengers are advised to request a refund." Furthermore, travel advice can be issued only to passengers who have not yet arrived at their destination or those transferring at the station.

[0055] As an example, assuming the impact of meteorological disasters is categorized into strong, moderate, and weak impacts, and passengers affected by the disasters are classified as those who have not yet arrived, those who have arrived, those en route, and those transferring at the station, the following service information types are expected to be pushed to passengers who have not yet arrived: For passengers experiencing a strong impact, the types of service information to be pushed to them include: station services and safety tips; for passengers already in the station, for those experiencing a strong or moderate impact, the types of service information to be pushed to them include: station services, safety tips, and emergency measures; for those experiencing a weak impact, the types of service information to be pushed to them include: safety tips and emergency measures; for passengers en route, for those experiencing a strong impact, the types of service information to be pushed to them include: emergency measures; for those experiencing a moderate or weak impact, the types of service information to be pushed to them include: safety tips and emergency measures; and for passengers transferring at the station, the types of service information to be pushed to them include: station services, safety tips, and emergency measures.

[0056] Among these, the pending service information for station services can be obtained from the station's management platform. This information informs passengers about available ticketing and fare collection services, guidance services, and other services such as waiting areas, dining, luggage storage, and rest areas. Especially in cases of congestion, this information helps passengers understand available services. The pending service information for safety tips, generated by intelligent models such as AI assistants under certain rules, provides passengers with information on risks such as slips and falls, ensuring passenger safety. The pending service information for emergency response measures can be obtained from the station's emergency system, including emergency evacuation routes, the availability of temporary waiting areas, and / or notifications of safe zones. This information can be pushed through station guidance and broadcasts, mobile applications, and station announcements to ensure passengers receive the latest information promptly. Furthermore, emergency response measures can be divided into station emergency measures (issued to passengers who have not yet arrived, passengers who have arrived, and passengers transferring) and emergency measures for operating trains (issued to passengers on the corresponding trains).

[0057] To simplify the description, the character I is used. m This represents the type of service information to be pushed, such as train operation status I1, weather forecast and warnings I2, travel suggestions I3, station service information I4, safety tips I5, and emergency response measures I6.

[0058] Furthermore, due to the rapid development of the communications field, various push channels can be used to ensure passengers receive relevant passenger service information. With the help of push channels, the acquired passenger service information can be automatically pushed to passengers using Location-Based Services (LBS) technology. Moreover, push channels can distribute passenger service information through communication protocols or user-accessible devices. For example, the push channels mentioned in this application include at least one of mobile applications (including various apps that can distribute passenger service information, such as the official railway app, and social media apps that enable communication and information sharing among passengers), SMS, and websites (e.g., the official railway website), as well as telephone consultation. Telephone consultation can provide 24-hour online voice consultation services using voice assistants, smart speakers, or instant messaging robots. In addition, considering the portability and geographical limitations of passenger service information acquisition, this application primarily uses mobile terminals or station announcements as push channels for passenger service information, but fixed message acquisition devices such as PCs can also be used.

[0059] As an example, passengers who haven't arrived at their destination can obtain information through portable push channels (such as mobile applications, official accounts, SMS, or website queries) to meet their need to stay informed about train status. Arriving passengers can quickly obtain the latest information from the station environment through traditional media such as station displays and announcements. Passengers en route can obtain relevant passenger service information in real time through push channels suitable for use in mobile environments, such as train announcements and onboard information displays. Passengers transferring at the station should choose push channels that ensure they can stay informed when quickly switching modes of transportation. In other words, driven by different weather and disaster conditions, passengers in different locations can obtain relevant passenger service information through different push channels.

[0060] In some embodiments of the present invention, taking passengers affected by meteorological disasters as being divided into those who have not yet arrived, those who have arrived, those en route, and those transferring at the station as an example, for passengers located within the station, the push channels also include: station display screens, broadcast notifications (e.g., station broadcasts), and on-site station information; for passengers located on the corresponding train, the push channels also include: onboard information display screens and broadcast notifications (e.g., train broadcasts); for passengers transferring at the station, the push channels also include: station display screens, onboard information display screens, and broadcast notifications (e.g., including station broadcasts and train broadcasts).

[0061] The station display screens and in-vehicle information display screens can display passenger service information in text form, while broadcast announcements will display passenger service information in voice form. Furthermore, station display screens, broadcast announcements, and in-vehicle information display screens can prioritize different types of pending service information to display them sequentially. On-site station information channels can provide virtual guidance to passengers through AR or VR technology, or allow passengers to obtain the necessary pending service information by asking staff.

[0062] To simplify the description, the character M can be used. n The variable represents the message push channel. For example, push channel variables include mobile application M1, SMS M2, website M3, station display screen M4, broadcast notification M5, vehicle information display screen M6, telephone inquiry M7, and station on-site inquiry M8.

[0063] In some embodiments of the present invention, to achieve differentiated push notifications, this application can establish an association relationship to reflect the four-dimensional correspondence between meteorological disaster information, passenger location status information, the type of service information to be pushed, and the push channel. This allows for the push of the corresponding type of service information to be pushed based on different meteorological disaster conditions and passenger location status, using the push channel currently corresponding to the passenger. The correspondence between the type of service information to be pushed and the push channel may not be established; that is, each corresponding push channel can push all types of service information to be pushed. Alternatively, a correspondence may be established between the type of service information to be pushed and the push channel (i.e., the push channels corresponding to each type of service information to be pushed are pre-defined). For example, train operation status can be pushed through three channels: telephone inquiry, SMS, and broadcast notification. This application is not limited to this; a correspondence exists between the type of service information to be pushed and the meteorological disaster information-passenger location status information pair, and a correspondence exists between the push channel and the meteorological disaster information-passenger location status information pair.

[0064] The pre-stored relationships integrate four-dimensional information, including scenario-based adaptation logic driven by the degree of meteorological disaster impact, a closed-loop passenger location classification system, the content of passenger service information in notifications, and a differentiated passenger notification channel system integrated with intelligent technologies. Therefore, the relationships can serve as a multivariate collaborative model to address the problem of inaccurate information acquisition for passengers at different stages of travel under different meteorological disaster conditions. Furthermore, the relationships can be displayed or stored in matrix form, or in other forms; this application is not limited to these.

[0065] As an example, the relationships can be displayed using a decision matrix formed by meteorological disaster variables, passenger location status variables, types of service information to be pushed, and push channel variables, as shown in Table 1. The decision matrix D(S) in Table 1... i ,Tj M ij,n ,I ij,m ) is a four-dimensional binary matrix representing the degree of meteorological disaster S. i Below, for type T j The passenger, the passenger's current push channel M ij,n And the type of service information (I) currently being pushed to the passenger. ij,m The decision matrix can be defined as follows: if D(S) i ,T j M ij,n ) = 1 or D(S) i ,T j ,I ij,m If ) = 1, it indicates that the severity of the meteorological disaster S is... i and of type T j Passengers, push channel M ij,n Or, the type of service information to be pushed is I. ij,m Applicable if D(S) i ,T j M ij,n ) = 0 or D(S) i ,T j ,I ij,m If ) = 0, it indicates that the severity of the meteorological disaster S is... i and of type T j Passengers, push channel M ij,n Or, the type of service information to be pushed is I. ij,m Not applicable. Additionally, the decision matrix in Table 1 can be encoded as a lookup table, allowing it to determine the corresponding push channel and the type of service information to be pushed in subsequent steps S120–S150.

[0066] Table 1 Decision matrix of association relationships

[0067]

[0068] Step S120: Input meteorological disaster information, passenger location status information, pre-stored correlations, and the scheduled time of the train the passenger is traveling on into the pre-trained information flow push model. This allows the pre-trained information flow push model to determine the types of passenger service information to be pushed (i.e., the types of service information applicable to the passenger) and the corresponding push channels (i.e., the push channels applicable to the passenger) based on the meteorological disaster information, passenger location status information, and correlations. The model then outputs the time impact value w(S) of the meteorological disaster information push. i The impact of the push time of passenger location status information w(T) j The impact value w(I) on the push time of each type of service information to be pushed to the passenger. ij,m) and the impact value w(M) of the push time of each push channel corresponding to the passenger. ij,n ).

[0069] As an example, the pre-trained information flow push model mentioned in this application can be trained in the following way: inputting training data into an initial model and obtaining a first training model through iterative training; optimizing the first training model using an incremental learning update mechanism according to a set period (i.e., retraining the model using the complete dataset according to a set period) to obtain the information flow push model. The initial model can be a deep neural network (e.g., a perceptron) containing an attention mechanism. Furthermore, the train schedule time input into the information flow push model can be the scheduled departure time, the scheduled departure time from the station, or the scheduled arrival time at the station, etc., and the type of train schedule time during the inference stage is consistent with that used when training the information flow push model.

[0070] The push time impact value obtained through the pre-trained information flow push model, also known as the timeliness impact value, can be used to measure the degree of impact of meteorological disasters, passenger location status, the type of service information to be pushed, and the push channel on train running time. Furthermore, since this application uses meteorological disasters as a driving factor to achieve differentiated notifications, this application can limit the push time impact value for different degrees of meteorological disasters, for example, ws(S1)>ws(S2)>ws(S3).

[0071] Based on the output of the pre-trained information flow push model, it can be determined that, under the current meteorological disaster information and passenger location status information, the types of passenger service information to be pushed to the passenger and the push channels to be pushed to the passenger, as well as the push time impact values ​​of meteorological disaster information, passenger location status information, types of passenger service information to be pushed to the passenger and push channels to be pushed to the passenger, are all relevant to the current meteorological disaster information and passenger location status information.

[0072] Step S130: Based on the train's scheduled time, the impact value of the push time of meteorological disaster information, the impact value of the push time of passenger location status information, and the impact value of the push time of each type of service information to be pushed to the passenger, calculate the priority of each type of service information to be pushed to the passenger.

[0073] In some embodiments of the present invention, the priority of each type of service information to be pushed is calculated in the following manner:

[0074] The system performs a weighted summation based on the impact values ​​of the push time for meteorological disaster information and the corresponding first-set weight coefficient, the impact values ​​of the push time for passenger location status information and the corresponding first-set weight coefficient, and the impact values ​​of the push time for each type of service information to be pushed to the passenger and the corresponding first-set weight coefficient. The priority of each type of service information to be pushed to the passenger is calculated based on the time difference between the train's scheduled departure time (e.g., the scheduled departure time) and the current time (the current time mentioned in this application refers to the time when the differentiated push strategy is currently generated) and the weighted summation result. For example, the priority of each type of service information to be pushed to the passenger is... ij,m The corresponding priority calculation formula can be expressed as:

[0075] P ij,m (STMIU)=λ1*w(S i )+λ2*w(T j )+λ3*w(I ij,m )+λ4 / U;

[0076] Wherein, λ1, λ2, λ3, and λ4 represent meteorological disaster information S. i Passenger location status information T j Type I of service information to be pushed ij,m And the first preset weighting coefficient corresponding to the time difference U between the train's scheduled time and the current time. w(S) i ), w(T j ) and w(I ij,m (S) represents meteorological disaster information. i Passenger location status information T j And the type of service information to be pushed I ijm The impact of push notification time. Additionally, U is not negative.

[0077] To improve the accuracy of information delivery, the priority of information push is calculated based on information such as passenger location and the degree of weather impact. This ensures that high-priority key information is promptly communicated to the passengers who need it most in subsequent operations. Moreover, adjusting λ1, λ2, λ3, and λ4 can be understood as adjusting the weight allocation rules among variables, or as dynamically adjusting the correspondence between meteorological disaster information, passenger location status information, the type of service information to be pushed, and the push channel in the decision matrix. This helps to generate differentiated push strategies.

[0078] Step S140: For each type of service information to be pushed to the passenger, if the priority of the type of service information to be pushed is greater than the set priority threshold, then calculate the optimal time for each push channel to push the service information of that type based on the train's scheduled time, the impact value of the push time of meteorological disaster information, the impact value of the push time of passenger location status information, the impact value of the push time of the service information to be pushed, and the impact value of the push time of each push channel to push the service information of that type. Otherwise, the optimal time for each push channel to push the service information of that type is the current time.

[0079] More specifically, in addition to differentiated push channels and types of service information to be pushed, this application also designs an information flow push mechanism based on optimal time to solve the problem of when to accurately push information: Push decisions are determined based on priority and optimal push time: if P ij,m If the priority threshold θ is exceeded, push notifications are sent immediately; otherwise, the optimal push time t for each push channel is calculated. ′ In addition, a uniform priority threshold can be set, or different priority thresholds can be set for different types of service information to be pushed.

[0080] In some embodiments of the present invention, for a certain type of service information to be pushed (here, the certain type of service information to be pushed can be any type of service information currently corresponding to the passenger), the optimal time for each push channel currently corresponding to the passenger to push that type of service information is determined in the following way:

[0081] The second set weighting coefficients and push time impact values ​​corresponding to meteorological disaster information, passenger location status information, a certain type of service information to be pushed, and the second set weighting coefficients and push time impact values ​​corresponding to each push channel currently corresponding to the passenger are weighted and summed to calculate the time difference U between the train's scheduled time and the current time; the time offset Δt is calculated based on the time difference and the weighted sum. ij (STMIU) uses the sum of the time offset and the current time as the optimal push time t for this type of service information across various push channels. ij ′.

[0082] As an example, in meteorological disaster information S i Passenger location status information T j Under the condition of type I ij,m The information to be pushed to the service is defined in this application as the optimal push time t. ′ The formula can be expressed as:

[0083] t ij,mn ′=f(STMIU)=t current +Δt ij,mn (STMIU);

[0084] Among them, t current This represents the current calculation time for the push strategy, Δt represents the time adjustment amount, and U represents the scheduled time (scheduled departure time or scheduled arrival time) of the train corresponding to the passenger, relative to t. current The closer the distance, the more urgent the situation.

[0085] Furthermore, the formula for calculating the time adjustment amount is as follows:

[0086] Δt ij,mn (STMIU)=∈*U-(α*ws(S i )+β*wT(T j )+γ*wM(M ij,n )+δ*wI(I ij,m ));

[0087] Among them, wM(M ij,n ) indicates push channel M ij,n The impact value of push time, ∈, α, β, γ and δ are the time difference U, meteorological disaster information S, etc., respectively. i Passenger location status information T j Type I of service information to be pushed ij,m and push channel M ij,n The corresponding second set weighting coefficient is used to represent the degree of influence of each factor on time.

[0088] The first and second predetermined weighting coefficients in this application can be set based on expert experience, or determined by objective weighting methods such as entropy weighting and CRITIC (Criteria Importance Through Intercriteria Correlation) methods. This invention is not limited to these methods. For example, in the specific embodiment below, this application sets the first predetermined weighting coefficient ∈ [0,1], and the second predetermined weighting coefficient... Furthermore, when calculating the push time for the service information to be pushed, different types of service information I are considered. ij,m The same weighting coefficient γ can be used; for different push channels M ij,n The same weighting coefficient δ can be used.

[0089] Step S150: Obtain the corresponding push service information based on the various push service message types currently corresponding to the passenger, and push the obtained service information to the passenger through the corresponding push channel at the determined optimal time. The types of push service information obtained include the various push service information types currently corresponding to the passenger, determined based on meteorological disaster information, passenger location status information, and the pre-stored correlation between meteorological disaster information, passenger location status information, push service information types, and push channels.

[0090] As an example, to implement this method, it is also necessary to obtain the corresponding type of service information to be pushed. Passenger service information can be obtained before the push step. Furthermore, after obtaining meteorological disaster information and passenger location status information, the corresponding type of service information to be pushed can be obtained from a specific system based on pre-stored associations; alternatively, all types of service information to be pushed, such as train operation status, station service information, and safety reminders, can be obtained from existing systems first, and the corresponding type of service information to be pushed can be selected from the obtained service information based on associations before executing the push step S150. That is, this application does not limit the time and specific type of passenger service information to be pushed, as long as the push of service information to be pushed can be achieved based on associations and a push time determined by priority. In addition, this application can periodically obtain meteorological disaster information, passenger location status information, and passenger service information to be pushed from the corresponding external systems; the time interval for information acquisition is not specifically limited in this application.

[0091] In some embodiments of the present invention, due to real-time changes in weather conditions, the differentiated push method driven by meteorological disaster information in this application further includes step S160: updating meteorological disaster information, passenger location status information and various types of push service information based on the information update frequency corresponding to each type of push service information, and redetermining the optimal push time for each corresponding channel based on the updated information and pushing it.

[0092] As an example, when the type of service information to be pushed is I ij,m The corresponding information update frequency Freq(IS) ij,m When an update is required, the updated information is recalculated and pushed, i.e., steps S110 to S150 are repeated. The information update frequency for each type of service information to be pushed is obtained based on the influence coefficient of meteorological disaster information on the information update frequency and the basic update frequency of each type of service information to be pushed, as detailed below:

[0093] Considering that different types of push messages may have different update frequency requirements, the formula for calculating the information update frequency in this application can be expressed as:

[0094]

[0095] in, For type I ij,m The basic update frequency of the information to be pushed (the basic update frequency may vary depending on the type of information to be pushed), τS i For meteorological disaster information S i The influence coefficient on the update frequency. For example, τS i =1.5, then steps S110 to S150 will be executed once every 20 minutes.

[0096] For example, in addition to the information update frequency, the information update triggering mechanism can also respond to changes in meteorological disaster information by setting a threshold: a threshold ΔS is set for the change in the degree of impact of meteorological disasters; when the meteorological disaster information S obtained from the meteorological system at time q... i,q Meteorological disaster information S obtained at the previous moment p i,p When the difference between them is greater than the set change threshold ΔS, steps S110 to S150 are executed to automatically trigger the update of the push strategy (the updated content includes the latest weather forecast and warning information, the impact of weather on the station, and the notification of changes in train operation status, etc.).

[0097] In some embodiments of the present invention, to achieve personalized settings for push notifications and allow passengers to choose the content they want to follow according to their needs, this application can also update a second set weight coefficient based on real-time user feedback on the push content (e.g., information reception), thereby dynamically adjusting the correspondence between meteorological disaster information, passenger location status information, the type of service information to be pushed, and the push channel in the decision matrix. Specifically, the method further includes: collecting passenger evaluation feedback results on the push content within a set time interval T; if the number of collected evaluation feedback results is greater than a set feedback quantity, then calculating the user feedback value through a predetermined objective function and updating the association based on the user feedback value; if the number of collected evaluation feedback results is not greater than the set feedback quantity, then updating the second set weight coefficient according to historical data (e.g., historical differentiated push strategies). The set feedback quantity is a set number of user feedback results received, which can be set by the user.

[0098] As an example, the user feedback value in this application is calculated using a predetermined objective function, and the user feedback value is determined based on user information acceptance, user accuracy, and information update delay. Therefore, the objective function can be constructed based on maximizing the acquisition rate and accuracy of passenger service information and minimizing the information update delay, expressed by the formula:

[0099] Maximize Z = w1 * R ij +w2*Aij -w3*D ij ;

[0100] Furthermore, to ensure the effectiveness of the information push strategy, a real-time feedback term F can be added to the objective function. j Used to measure the position state as T j The level of passenger satisfaction with the service information received (e.g., F) j (∈[0,1], where 1 represents complete satisfaction), then the objective function can be expressed as:

[0101] aximize Z = w1 * R ij +w2*A ij -w3*D ij +w4*F j ;

[0102] Where Z represents the user feedback value, R represents the passenger service information acquisition rate, i.e. the probability that each passenger can receive the information in a timely manner, A represents the accuracy of the passenger service information (e.g., whether the information received by the passenger reflects the actual situation), D represents the delay in updating the passenger service information (e.g., the time interval between the release of the information and the passenger's receipt of it), and w1, w2, w3, and w4 are the weighting coefficients of the passenger service information acquisition rate, information accuracy, information update delay, and real-time feedback item, respectively, used to balance the importance of different objectives to the user feedback value.

[0103] In addition, the following constraints were set during the optimization of the second set weight coefficients based on user feedback: For different degrees of impact of meteorological disasters S... i and passenger location status T j The information acquisition rate must meet the minimum information acquisition rate requirement, the information accuracy must meet the minimum information accuracy requirement, and the information update delay must not exceed the maximum allowable information delay time.

[0104] Furthermore, updating the association based on user feedback values ​​includes: if the calculated user feedback value is not greater than a set feedback threshold, then updating the second set weight coefficient based on the user feedback value; otherwise, the original second set weight coefficient may not be updated.

[0105] As an example, after determining the push time for each type of service information to be pushed, the maximum push time can be considered as the upper limit of the push window. This ensures that all service information for the passenger can be pushed when the push window reaches its upper limit. Alternatively, if all types of service information to be pushed are to be pushed immediately, a push window limit can be set, such as 20 minutes after the current differentiated push strategy is generated. In this case, regardless of whether the service information is pushed at the optimal time or immediately, all service information should be pushed.

[0106] In some embodiments of the present invention, the method further includes: for the train operation status in the service information type, calculating the time delay of the train departure based on the acquired service information to be pushed of that type; if the calculated time is greater than a set delay time value (which can be set by the user), then recalculating the priority corresponding to the service information type, and re-determining the optimal push time for the service information of the type of train operation status through step S140 (pushing immediately or pushing the acquired service information of the type of train operation status at the optimal time). For example, if the expected departure delay is ≥15 minutes, then a "high priority" refresh is triggered, and the information is recalculated and pushed according to steps S130 to S150.

[0107] In a specific embodiment of the present invention, for a certain train G in station Q traveling from Q to L, assuming the scheduled departure time of the train is t... 图定 =10:00, and the latest weather forecast and warning information indicate that the train is affected by 25cm of snow accumulation (if the three types mentioned above are used, the degree of meteorological disaster impact is S1), and the estimated actual departure time of the train is t1 = 14:30. The current calculation time for the push strategy is t. current =8:00, at this time U=t 图定 -t current =2h.

[0108] For a passenger A (who is currently in a city hotel and is considered a passenger T1 who has not yet arrived), by querying the corresponding relationships, we can see that the current push channels for this passenger are: mobile application M1, SMS M2, website M3, and telephone inquiry M7; the types of service information to be pushed to this passenger are: train operation status I1, weather forecast and warnings I2, travel suggestions I3, station service information I4, and emergency handling measures I6.

[0109] The pre-trained information flow push model can output ws(S1)=1.0, wT(T1)=0.9, wI(I1)=1.0; wI(I2)=0.8; wI(I3)=0.7; wI(I4)=0.6; wI(I6)=0.9; wM(M1)=0.9, wM(M2)=0.8, wM(M3)=0.6, wM(M7)=1.0.

[0110] Assume λ1 = 0.4; λ2 = 0.3; λ3 = 0.2; λ4 = 0.1; α = 15; β = 10; γ = 8; δ = 12; ∈ = 0.5; and the set priority threshold θ = 0.9.

[0111] Based on the priority calculation formula, we can obtain:

[0112]

[0113] Similarly, we can conclude that:

[0114]

[0115]

[0116]

[0117] Therefore, the calculation process for the optimal push time of the mobile application M1 for weather forecasts and alerts I2 is as follows:

[0118] Δt 11,21 (STMIU)=0.5*120-(15*1.0+10*0.9+8*0.9+12*0.8)=19.2min;

[0119] t 11,21 ≈8:19

[0120] Similarly, we can conclude that:

[0121] For weather forecasts and alerts I2, the optimal push times for SMS M2, website M3, and telephone consultation M7 are 8:20 (Δt). 11,22 (STMIU) is 20 min), 8:22 (Δt) 11,23 (STMIU) is 21.6 min) and 8:18 (Δt) 11,27 (STMIU) is 18.4 min); for travel advice I3, the optimal push times for mobile application M1, SMS M2, website M3, and telephone consultation M7 are 8:20 (Δt) respectively. 11,31 (STMIU) is 20.4 min), 8:27 (Δt) 11,32 (STMIU) was 27.2 min, 8:23 (Δt) 11,33 (STMIU) is 22.8 min) and 8:20 (Δt) 11,37 (STMIU was 19.6 min);

[0122] For the in-site service information I4, the optimal push times for mobile application M1, SMS M2, website M3, and telephone consultation M7 are 8:22 (Δt). 11,41 (STMIU) is 21.6 min), 8:22 (Δt) 11,42 (STMIU) is 22.4 min), 8:24 (Δt) 11,43 (STMIU) is 24 min) and 8:21 (Δt) 11,47 (STMIU was 20.8 min).

[0123] Ultimately, the following differentiated push notification plan can be obtained for passenger A:

[0124] The service information to be pushed for train type I1 is "Train G is delayed due to blizzard and is expected to depart at 14:30". The information will be pushed immediately through four channels: mobile application, SMS, website and telephone inquiry.

[0125] The service information to be pushed for Emergency Response Measures I6 is "Temporary buses will be set up outside the station to serve multiple hotels in the city, with departure intervals of 30 minutes". This information will be pushed immediately through four channels: mobile application, SMS, website, and telephone consultation.

[0126] The weather forecast and warning I2 type pending push service information is "Q is under an orange blizzard warning, with current snow accumulation of 25cm", which will be pushed at 8:19, 8:20, 8:22 and 8:18 respectively via mobile application, SMS, website and telephone consultation;

[0127] The push notification for travel advice type I3 ​​is "Please consider postponing your departure or taking other means of transportation; if you need a refund, the handling fee will be waived." The notification will be sent at 8:20, 8:27, 8:23 and 8:20 respectively via mobile application, SMS, website and telephone inquiry.

[0128] The service information to be pushed for type I4 station service information is "Temporary waiting area open at station Q; catering area provides drinks 24 hours a day", which will be pushed through mobile application, SMS, website and telephone inquiry at 8:22, 8:22, 8:24 and 8:21 respectively.

[0129] In response to the current impact of meteorological disasters and the location status of passengers, this application proposes a differentiated service information push method for railway passengers. This method can determine the type of service information to be pushed and the push channel based on pre-set correlations, and can determine the push time according to the priority of each type of service information. The method proposed in this application enables affected passengers to have an immediate and comprehensive understanding of train conditions and to obtain alternative travel and emergency service options, thus solving the problems of fragmentation and lag in current railway information notifications.

[0130] Corresponding to the above method, the present invention also provides a differentiated service information push system for railway passengers. The system includes a computer device, which includes a processor and a memory. The memory stores computer programs / instructions, and the processor is used to execute the computer programs / instructions stored in the memory. When the computer programs / instructions are executed by the processor, the system implements the steps of the method described above.

[0131] This invention also provides a computer-readable storage medium storing a computer program / instructions thereon, which, when executed by a processor, implements the steps of the aforementioned edge computing server deployment method. The computer-readable storage medium can be a tangible storage medium, such as random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, floppy disks, hard disks, removable storage disks, CD-ROMs, or any other form of storage medium known in the art.

[0132] Those skilled in the art will understand that the exemplary components, systems, and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Whether implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention. When implemented in hardware, it can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the desired tasks. The programs or code segments can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave.

[0133] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0134] In this invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with or in place of features of other embodiments.

[0135] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, various modifications and variations of the embodiments of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for differentiated delivery of service information to railway passengers, characterized in that, For each passenger, the method includes the following steps: Obtain information on meteorological disasters, passenger location status, and the scheduled time of the trains the passengers are traveling on; The meteorological disaster information, passenger location status information, pre-stored correlations, and the train's scheduled time are input into a pre-trained information flow push model. This model determines the applicable service information types and push channels for passengers based on the meteorological disaster information, passenger location status information, and the correlations. It then outputs the push time impact values ​​for meteorological disasters, passenger location status, each service information type, and each push channel. The correlations refer to the correspondence between meteorological disaster information, passenger location status information, the type of service information to be pushed, and the push channel. The priority of each service information type is calculated based on the train's scheduled time, the impact value of the push time for meteorological disasters, the impact value of the push time for passenger location status, and the impact value of the push time for each service information type. For each type of service information, if the priority of the service information type is greater than the set priority threshold, the optimal time for each push channel to push the service information of that type is calculated based on the train's scheduled time, the impact value of the push time of meteorological disasters, the impact value of the push time of passenger location status, the impact value of the push time of the service information type, and the impact value of the push time of each push channel. If the priority of the service information type is not greater than the set priority threshold, the optimal time for each push channel to push the service information of that type is the current time. According to the various service information types applicable to the passengers, the corresponding service information is obtained, and the obtained service information is pushed to the passengers through the corresponding push channels at the determined optimal time.

2. The method according to claim 1, characterized in that, The priority of each service information type is calculated in the following way: The system performs a weighted summation based on meteorological disaster information, passenger location status information, the impact value of the push time of each service information type, and the corresponding first set weight coefficient. The priority of each service information type is then calculated based on the time difference between the train's scheduled time and the current time, as well as the result of the weighted summation.

3. The method according to claim 1, characterized in that, The calculation of the optimal time for each push channel to push this type of service information, based on the train's scheduled time, the impact of meteorological disaster push time, the impact of passenger location status push time, the impact of this service information type push time, and the impact of each push channel push time, includes: The system performs a weighted summation based on meteorological disaster information, passenger location status information, the type of service information, the push time impact value of each push channel, and the corresponding second set weight coefficient, and calculates the time difference between the train's scheduled time and the current time. The time offset is calculated based on the time difference and the weighted summation result. The sum of the time offset and the current time is taken as the optimal push time for this type of service information on each push channel.

4. The method according to claim 1, characterized in that, The meteorological disaster information is used to measure the degree of impact of meteorological disasters. The degree of impact of meteorological disasters is determined based on at least one of the following: meteorological disaster data, train operation status on the line, station operation status, and station equipment operation status. It is divided into three levels: strong impact, moderate impact, and weak impact. The passenger location status information includes: the passenger has not arrived at the station, the passenger is in the station, the passenger is on the corresponding train, or the passenger has exited the station to transfer. The service information includes the following types of information: train operation status, weather forecasts and warnings, and travel suggestions; The push channels include at least one of mobile applications, SMS, and websites, as well as telephone inquiries.

5. The method according to claim 4, characterized in that, For passengers who have not yet arrived at their destination, in cases where the impact of meteorological disasters is severe, the types of service information applicable to passengers also include: station services and safety reminders; For passengers located within the station, the push channels also include: station display screens, broadcast announcements, and on-site station information; and, in cases where the impact of meteorological disasters is moderate to strong, the types of service information applicable to passengers also include: station services, safety tips, and emergency measures; in cases where the impact of meteorological disasters is weak, the types of service information applicable to passengers also include: safety tips and emergency measures. For passengers on the corresponding trains, the push channels also include: onboard information displays and broadcast announcements; in the case of a severe impact from meteorological disasters, the types of service information applicable to passengers also include: emergency measures; in the case of a moderate or weak impact from meteorological disasters, the types of service information applicable to passengers also include: safety tips and emergency measures. For passengers transferring at the station, the push channels also include: station display screens, in-vehicle information display screens, and broadcast announcements; the types of service information applicable to passengers also include: station services, safety tips, and emergency measures.

6. The method according to claim 1, characterized in that, The method further includes: updating meteorological disaster information and passenger location status information based on the information update frequency corresponding to each service information type, and redetermining the push time of each channel applicable to the passenger based on the updated information; wherein, the information update frequency corresponding to each type of service information to be pushed is obtained based on the influence coefficient of meteorological disaster information on the information update frequency and the basic update frequency of each service information type.

7. The method according to claim 3, characterized in that, The method further includes: collecting passenger evaluation feedback results on the pushed content within a set time interval; if the number of collected evaluation feedback results is greater than a set feedback amount, calculating the user feedback value through a predetermined objective function; and if the user feedback value is not greater than a set feedback threshold, updating the second set weight coefficient based on the user feedback value. If the number of collected evaluation feedback results is not greater than the set feedback amount, the second set weight coefficient is updated based on historical data; wherein, the user feedback value is determined based on user information acceptance, user accuracy and information update delay.

8. The method according to claim 4, characterized in that, The method further includes: For the train operation status in the service information type, the time delay for train departure is calculated based on the acquired service information to be pushed for this type. If the calculated time is greater than the set delay time value, the priority corresponding to this service information type is recalculated, and the optimal push time for the service information of the train operation status type is re-determined.

9. A differentiated service information push system for railway passengers, comprising a processor, a memory, and a computer program / instructions stored in the memory, characterized in that, The processor is configured to execute the computer program / instructions, and when the computer program / instructions are executed, the system implements the steps of the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method as described in any one of claims 1 to 8.

Images