Passenger travel push marketing method based on big data analysis

Abstract

The invention discloses a passenger travel push marketing method based on big data analysis, and particularly relates to the technical field of target extraction, by collecting stable information and processing performance information in a target extraction process and establishing an aging analysis model, the aging performance of the target extraction method is monitored and evaluated in real time, the emergency situation is rapidly adapted, and the target extraction efficiency is improved. Tracking of an accident vehicle is better handled, the reliability and timeliness of target tracking are ensured, the extracted timeliness performance comprehensive performance index is compared with a preset threshold value for analysis, abnormal signals are automatically screened, the abnormal signals are continuously monitored, and the standard deviation of the abnormal signals is calculated to assess the risk early warning level. Therefore, a manager can timely discover and respond to possible performance reduction or faults without relying on subjective judgment, the stability and reliability of the whole monitoring system are improved, and negative effects caused by target extraction failure or delay are reduced.

Description

Technical Field

[0001] The present invention relates to the field of push marketing technology, and more specifically, to a passenger travel push marketing method based on big data analysis. Background Art

[0002] The implementation of existing technical solutions is relatively simple and crude, mainly because they rely on fixed travel times for recommendation. This means that these solutions can only recommend existing itineraries for users, but cannot stimulate new travel needs of users. In addition, existing technical solutions are also unable to make incremental predictions of users' travel needs, which means that existing technologies cannot identify and meet new travel needs that users may have in advance. Therefore, it is necessary to seek more advanced and precise technical solutions to meet the ever-changing and developing travel needs of users.

[0003] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a passenger travel push marketing method based on big data analysis to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A passenger travel push marketing method based on big data analysis includes the following steps:

[0007] Step S1, obtaining purchase information and user data from the Internet platform, and uploading the information to the server;

[0008] Step S3, constructing the collected user behaviors into a large data set, analyzing it using a time series model algorithm, and generating a corresponding digital model;

[0009] Step S4, the digital model combines real-time information data to predict the user's final possible travel behavior plan; using real-time information data, the digital model can timely monitor traffic conditions, weather changes and other factors, and adjust travel recommendations according to the situation. When traffic congestion or bad weather occurs, the travel plan is adjusted in time to provide users with more suitable alternative routes or means of transportation to improve travel efficiency and comfort. With the help of deep learning and analysis of big data, the digital model can accurately predict the user's travel behavior, including departure time, mode of transportation and estimated arrival time. Based on the user's historical behavior and real-time information, the travel time and mode of transportation that the user may choose, as well as the estimated arrival time, can be predicted to provide users with reliable travel guidance;

[0010] Step S5, after receiving the possible travel plan predicted by the intelligent algorithm, the background service of the travel application will call the data of the user clicking the pop-up window to determine whether to push it;

[0011] Step S6: After receiving the push notification, the user can immediately view the pushed travel plan. After the user confirms the plan, the travel APP will automatically enter the taxi booking page and automatically bring in the destination information.

[0012] Step S7: After receiving the push notification, if the user chooses not to start the trip, the service is terminated.

[0013] Using real-time information data, digital models can monitor traffic conditions, weather changes and other factors in a timely manner, and adjust travel recommendations based on the situation. When traffic congestion or bad weather occurs, travel plans can be adjusted in a timely manner to provide users with more suitable alternative routes or means of transportation to improve travel efficiency and comfort. With deep learning and analysis of big data, digital models can accurately predict users' travel behavior, including departure time, mode of transportation and estimated time of arrival. Based on the user's historical behavior and real-time information, it can predict the travel time and mode of transportation that the user may choose, as well as the estimated arrival time, to provide users with reliable travel guidance.

[0014] Preferably, when training the digital model, a machine learning algorithm is used, and the acquired pop-up click data and travel plans are used as part of the training data, so that the model utilizes the correlation between the user's click behavior and the travel plan.

[0015] Preferably, the logic of obtaining possible travel behavior solutions of the digital model is:

[0016] Assuming that the user's travel behavior is Y, X1, X2, X3, ..., Xn represent various factors that affect the user's travel behavior, then the formula can be expressed as:

[0017] Y=β0+β1X1+β2X2+...+β n Xn+ε;

[0018] Among them, β0, β1, ..., βn are regression systems, ε is the error value, and ε is greater than 0.

[0019] Preferably, the information data includes weather data, holiday information, other memorandum itineraries or meeting itineraries. When predicting travel behavior, it is necessary to calculate the weights of real-time weather data, holiday information, other memorandum itineraries or meeting itineraries, and mark the final prediction result as S, which is expressed as:

[0020] S=w1*Y1+w2*Y2+w3*Y3+w4*Y4+......+wn*Yn;

[0021] Among them, w1, w2, w3, w4, ....., wn are meeting schedules, memorandum schedules, holiday information, and weather data respectively, and w1, w2, w3, ....., wn are all greater than 0, and Y1, Y2, Y3, ....., Yn are the prediction results of the corresponding factors.

[0022] Preferably, the detailed travel suggestion includes information such as departure time, mode of transportation, and estimated arrival time. In the travel suggestion, the departure time is accurately calculated based on the distance to the destination and the expected traffic conditions, where the departure time is accurate to 4-5 hours in advance;

[0023] Preferably, once the user clicks to depart, the system will automatically reserve a vehicle and plan a corresponding driving route, and the travel planning range will cover a distance between 1-200 kilometers.

[0024] Preferably, when determining the data of clicks on the pop-up window, the number of clicks on the pop-up window when the user needs to use the car will be obtained. If the number of clicks by the user is small, the itinerary pop-up window will be replaced, and the discount price information will be included in the new itinerary pop-up window.

[0025] Preferably, when pushing travel plans, the top three destinations by weight will be displayed for the user to choose.

[0026] Preferably, the user's purchase data is obtained through the API interface, data crawling tools, and data partners provided by the platform; after obtaining the data, the data is cleaned and processed and the processed data is imported into the database through the API interface.

[0027] Technical effects and advantages of the present invention:

[0028] 1. The present invention makes full use of advanced technologies such as big data and algorithm analysis. By deeply analyzing the user's Internet behavior, it can accurately predict the user's potential travel needs. Based on these analysis results, the system can recommend personalized travel plans to users, thereby increasing the user's travel options. Such measures will help promote the growth of online car-hailing business. At the same time, the intelligent recommendation system provides a better user experience, making users more willing to make travel arrangements on the platform, thereby improving the user stickiness of the platform.

[0029] 2. This application not only comprehensively considers the prediction results of the machine learning model, but also pays special attention to the weight of each factor. The digital model of this application can make fine adjustments based on the degree of influence of each factor on the user's travel behavior to ensure that the prediction results are more accurate and reliable, and by carefully adjusting the weight of each factor, it can better understand and explain the changes in user travel behavior and provide users with more personalized and high-quality travel suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0031] Figure 1 It is a schematic diagram of the process of the present invention;

[0032] Figure 2 It is a schematic diagram of the framework of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Figure 1-2 The present invention provides a passenger travel push marketing method based on big data analysis, comprising the following steps:

[0035] Step S1, obtain the purchase information and user data of the Internet platform, and upload the information to the server; by collecting the purchase information and user data of the Internet platform, data from different sources can be integrated into a unified data storage for easy management and analysis. Based on the collected user data, this method can provide personalized services and recommendations to users, improving user experience and satisfaction. The Internet platform purchase information includes platforms such as Meituan, 12306, Qunar, etc.

[0036] Step S3, construct the collected user behaviors into a large data set, analyze them using a time series model algorithm, and generate a corresponding digital model; the digital model constructed by the intelligent algorithm can extract useful information from a large amount of data and use this information to make decisions and predictions. They usually have the ability to adapt and self-learn, and can automatically adjust parameters and models according to the input data, thereby continuously improving the accuracy of predictions and decisions. By constructing a large data set and analyzing user behaviors in combination with the constructed digital model, it is possible to predict the user's future behavior, gain an in-depth understanding of the user's preferences, preferences, behavior patterns, etc., and improve the accuracy and reliability of decision-making.

[0037] Step S2.1, first, collect user behavior data, and clean and preprocess the data. This includes removing duplicate data, processing missing values, converting data formats, etc. to ensure data quality and consistency.

[0038] Step S2.2: Organize the cleaned user behavior data into time series data in chronological order. For each user behavior, record the timestamp of its occurrence and sort them in chronological order.

[0039] Step S2.3, feature engineering is performed on the time series data to extract meaningful features for model analysis. This may include extracting time-related features, behavior frequency features, behavior sequence pattern features, etc.

[0040] Step S2.4, select an appropriate time series model algorithm according to the purpose of analysis and data characteristics. Common time series models include time series analysis methods and models based on deep learning and long short-term memory networks.

[0041] Step S2.5, use the selected time series model algorithm to train the prepared data set. During the training process, the time series data is input into the model, and the model parameters are adjusted according to the feedback of the model so that the model can better fit the data.

[0042] Step S2.6: Evaluate the trained model to test its fitting effect and prediction ability for time series data. Optimize the model based on the evaluation results, such as adjusting model hyperparameters and improving feature engineering.

[0043] Step S2.7, use the trained time series model to predict future user behavior. Input new time series data into the model, and obtain the corresponding prediction results through the model, that is, generate a digital model.

[0044] Step S2.8, interpret and analyze the model prediction results to understand the factors and trends that affect user behavior. According to the prediction results, formulate corresponding business strategies or recommendation systems to provide users with personalized services and suggestions.

[0045] Step S4, the digital model combines the real-time information data to predict the user's final possible travel behavior plan; using real-time information data, the digital model can timely monitor factors such as traffic conditions and weather changes, and adjust travel suggestions according to the situation. When traffic congestion or bad weather occurs, the travel plan is adjusted in time to provide users with more suitable alternative routes or means of transportation to improve travel efficiency and comfort. With deep learning and analysis of big data, the digital model can accurately predict the user's travel behavior, including departure time, mode of transportation and estimated arrival time. Based on the user's historical behavior and real-time information, the travel time and transportation that the user may choose, as well as the estimated arrival time, can be predicted to provide users with reliable travel guidance.

[0046] Step S5, after the background service of the travel application receives the possible travel plan predicted by the intelligent algorithm, it will call the data of the user clicking the pop-up window to determine whether to push; determining whether to push based on the data of the user clicking the pop-up window can avoid sending push messages to users who are not interested or do not need relevant information, thereby improving the accuracy and efficiency of push. In this way, the background service of the travel application can use resources more effectively and reduce push costs and time. Based on the user's click behavior data, the background service can better understand the user's preferences and behavioral habits, and thus determine whether to push the travel plan in a personalized manner. In this way, users will receive push information that is more in line with their interests and needs, and increase users' attention to and response rate to the push content.

[0047] Step S6: After receiving the push notification, the user can immediately view the pushed travel plan. After the user confirms, the travel APP will automatically enter the taxi booking page and automatically bring in the destination information. After receiving the push notification, the user can immediately view the travel plan without waiting or additional operations. In this way, the user can quickly obtain relevant information, saving time and energy. And by automatically bringing in the destination information, the user can immediately perform the booking operation after receiving the push notification, reducing the friction on the conversion path. This quick response and seamless experience helps to improve user satisfaction.

[0048] Step S7: After receiving the push notification, if the user chooses not to start the trip, the service is terminated. Terminating the service can avoid sending unnecessary push notifications to the user or providing uninteresting services, thereby maintaining the user's experience quality.

[0049] In this embodiment, when training the digital model, a machine learning algorithm is used, and the acquired pop-up window click data and travel plan are used as part of the training data, so that the model uses the correlation between the user's click behavior and the travel plan. Pop-up window click data and travel plan data as part of the training data can help the model better understand the user's behavior patterns and preferences, thereby improving the accuracy and precision of the prediction. The model can learn under what circumstances the user is more likely to click on the pop-up window and choose which travel plan, and then provide more personalized services and suggestions.

[0050] In this embodiment, the logic of obtaining possible travel behavior solutions by the digital model is as follows:

[0051] Assuming that the user's travel behavior is Y, X1, X2, X3, ..., Xn represent various factors that affect the user's travel behavior, then the formula can be expressed as:

[0052] Y=β0+β1X1+β2X2+...+β n Xn+ε;

[0053] Among them, β0, β1, ..., βn are regression systems, ε is the error value, and ε is greater than 0.

[0054] The model adjusts the regression coefficients, β0, β1, ..., βn, to minimize the error between the predicted value Y and the true observed value, so that the model can fit the data better and strive to make its prediction results as close to the true observed value as possible to improve the accuracy and reliability of the prediction. At the same time, the linear regression model has low computational complexity and fast training speed, so it is suitable for processing large-scale data sets.

[0055] By calculating the formula of the above linear regression model, the digital model can update the prediction results at any time based on the latest data to maintain the timeliness and accuracy of the prediction. As user behavior and external environment change, the model can adjust the prediction results in time to ensure its consistency with the actual situation. This allows the model to flexibly respond to changes in data and new situations.

[0056] In this embodiment, the information data includes weather data, holiday information, other memorandum itineraries or meeting itineraries. When predicting travel behavior, it is necessary to calculate the weights of real-time weather data, holiday information, other memorandum itineraries or meeting itineraries, and mark the final prediction result as S, which is expressed as:

[0057] S=w1*Y1+w2*Y2+w3*Y3+w4*Y4+……+wn*Yn;

[0058] Among them, w1, w2, w3, w4....., wn are meeting schedules, memorandum schedules, holiday information, and weather data, respectively, and w1, w2, w3, ....., wn are all greater than 0, and Y1, Y2, Y3, ..., Yn are the prediction results of the corresponding factors. Through weighted processing, not only the prediction results of the machine learning model are comprehensively considered, but also the weights of each factor are considered. The digital model can make more detailed adjustments to the prediction results based on the degree of influence of each factor on the user's travel behavior. For example, for some users, weather may be the most important factor in travel decisions, while for other users, time or traffic conditions may be more critical. By adjusting the weights of each factor, the marketing system can achieve personalized predictions for different users and different situations, so that the prediction results are closer to the actual needs and behavior patterns of users.

[0059] For a user who needs to travel long distances, traffic conditions may be more important, so the weight of traffic conditions can be increased; while for a user who only needs to travel short distances, time may be more important, so the weight of time factors can be increased. In this way, by adjusting the weight of each factor according to the actual situation, the user's travel behavior can be predicted more accurately, and personalized services that are more in line with their actual needs can be provided.

[0060] In this embodiment, the detailed travel suggestions include information such as departure time, mode of transportation, and estimated arrival time. In the travel suggestions, the departure time will be accurately calculated based on the distance to the destination and the expected traffic conditions, where the departure time is 4-5 hours in advance. Accurately calculating the departure time based on the distance to the destination and the expected traffic conditions can help users arrange travel time more accurately. In particular, information that the departure time is 4-5 hours in advance is provided, which allows users to predict the departure time in advance so that they can fully prepare and arrange other matters. Providing detailed travel suggestions can improve user satisfaction with travel applications. Users can get accurate and timely information when using the application, so they are more willing to continue using the application, which enhances the user's stickiness to the platform.

[0061] In this embodiment, once the user clicks to start, the system will automatically reserve a vehicle and plan the corresponding route. The travel planning range will cover a distance between 1-200 kilometers. The travel planning range covers a distance between 1-200 kilometers, meeting the range of different travel needs of users. Whether it is a short trip or a long trip, users can complete reservations and planning within the system, which improves the flexibility and applicability of travel. In addition, the digital model can automatically reserve vehicles and plan routes, so that users do not need to bother to find suitable means of transportation and plan itineraries. This convenient service can improve the user's travel experience and reduce the cost and risk of travel.

[0062] In this embodiment, when determining the data of clicking the pop-up window, the number of clicks on the pop-up window when the user needs to use the car will be obtained. If the number of user clicks is small, the itinerary pop-up window will be replaced, and the preferential price information will be included in the new itinerary pop-up window. By providing personalized services and preferential activities, the digital model can attract more users to use the platform or products, thereby increasing sales and profits. At the same time, accurate recommendations and suggestions can also improve user satisfaction and loyalty, and promote long-term use and consumption of users. Monitoring the number of times users click on the pop-up window can help the platform understand the user's interests and needs. If the user clicks less, it means that he is not interested in the current itinerary pop-up window. By timely replacing the itinerary pop-up window and including preferential price information, the user's attention can be attracted, and the user's participation and click-through rate can be increased. The new itinerary pop-up window contains preferential price information, which can attract more users to click and complete the itinerary booking. Preferential price information can usually stimulate users' desire to buy, prompting them to be more willing to use the services provided by the platform, thereby improving the conversion rate of itinerary booking.

[0063] In this embodiment, when pushing travel plans, the top three destinations by weight will be displayed for the user to choose. Providing the top three destinations by weight can help users find travel plans that meet their needs more quickly, reducing the time and energy cost of users looking for travel destinations. Displaying the top three destinations by weight means that users can choose from multiple recommended travel plans. In this way, users can not only choose the destination they are most interested in, but also make decisions that are more in line with their personal preferences based on their preferences and needs, which improves the user's right to choose.

[0064] The present invention makes full use of advanced technologies such as big data and algorithm analysis, and predicts users' potential travel needs by analyzing users' Internet behaviors. Based on these prediction results, suitable travel options are recommended to users to expand their travel options and achieve the goal of promoting the growth of online car-hailing business;

[0065] The recommendation system in this application not only provides more travel options, but also improves the user experience quality. Through this intelligent recommendation system, users can more easily find travel solutions that meet their needs, thereby enhancing their satisfaction and loyalty to the platform. Moreover, the personalized and intelligent recommendation system can not only meet the actual needs of users, but also improve the user stickiness of the platform and provide support for business growth.

[0066] Glossary

[0067] Internet user behavior: refers to the actions initiated by users on the Internet, which may include search behavior, browsing behavior, purchasing behavior, etc.

[0068] Internet user behavior analysis: is a multi-faceted process that mainly involves collecting, processing and analyzing user behavior data on the Internet to understand user needs, interests and behavior patterns, thereby optimizing the quality and functionality of products or services and improving user experience and loyalty.

[0069] Big data: refers to the huge amount of Internet user behavior data.

[0070] Intelligent algorithms: They can extract useful information from large amounts of data and use this information to make decisions and predictions. They usually have the ability to adapt and self-learn, and can automatically adjust parameters and models based on the input data, thereby continuously improving the accuracy of predictions and decisions.

[0071] Example 1

[0072] User 1 bought movie tickets for himself and his girlfriend on the Meituan platform at a cinema in Dongzhimen at 4 p.m. on Saturday.

[0073] The online car-hailing platform obtains the purchase data of user 1 on the Meituan platform and uploads the data to the digital model for analysis. After analysis, it is found that the user's pop-up window click rate is high. Therefore, the system triggers a normal itinerary pop-up window and plans to send a itinerary push to user Zhang San at 2 pm on Saturday with the destination being a theater in Dongzhimen. User 1 chooses whether to start this itinerary.

[0074] Example 2

[0075] User 2 purchased a high-speed rail ticket for returning home for the Spring Festival at 5 pm on February 6 on the railway 12306 platform.

[0076] User 2 purchased a high-speed rail ticket for the Spring Festival on the railway 12306 platform at 5 pm on February 6. The online car-hailing platform will obtain the information purchased by User 2 on 12306 and upload the data to the digital model for analysis. The analysis results show that the click-through rate of user pop-ups is low. Therefore, the system will send a pop-up window containing discount information. Specifically, at 2 pm on February 6, the system will send a trip push to user Li Si with the destination as the user's departure station. User 2 chooses whether to start this trip.

[0077] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0078] The present invention makes full use of advanced technologies such as big data and algorithm analysis. By deeply analyzing the user's Internet behavior, it can accurately predict the user's potential travel needs. Based on these analysis results, the system can recommend personalized travel plans to users, thereby increasing the user's travel options. Such measures will help promote the growth of online car-hailing business. At the same time, the intelligent recommendation system provides a better user experience, making users more willing to make travel arrangements on the platform, thereby improving the user stickiness of the platform.

[0079] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0080] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0081] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A passenger travel push marketing method based on big data analysis, characterized by: The steps include: Step S1, obtaining purchase information and user data from the Internet platform, and uploading the information to the server; Step S2, constructing the collected user behaviors into a large data set, analyzing it using a time series model algorithm, and generating a corresponding digital model; Step S3, the digital model combines the real-time information data to predict the user's final possible travel behavior plan; Step S4, after receiving the possible travel plan predicted by the intelligent algorithm, the background service of the travel application will call the data of the user clicking the pop-up window to determine whether to push it; Step S5: After receiving the push notification, the user can immediately view the pushed travel plan. After the user confirms the plan, the travel APP will automatically enter the taxi booking page and automatically bring in the destination information. Step S6: After receiving the push notification, if the user chooses not to start the trip, the service is terminated.

2. A passenger travel push marketing method based on big data analysis according to claim 1, characterized in that: When training the digital model, a machine learning algorithm is used, and the acquired pop-up click data and travel plans are used as part of the training data, so that the model can utilize the correlation between the user's click behavior and the travel plan.

3. A passenger travel push marketing method based on big data analysis according to claim 2, characterized in that: The logic of obtaining possible travel behavior solutions from the digital model: Assuming that the user's travel behavior is Y, X1, X2, X3, ..., Xn represent various factors that affect the user's travel behavior, then the formula can be expressed as: Y=β0+β1X1+β2X2+...+β n Xn+e; Among them, β0, β1, ..., βn are regression systems, ε is the error value, and ε is greater than 0.

4. A passenger travel push marketing method based on big data analysis according to claim 3, characterized in that: Information data includes weather data, holiday information, other memorandum itineraries or meeting itineraries. When predicting travel behavior, it is necessary to calculate the weights of real-time weather data, holiday information, other memorandum itineraries or meeting itineraries, and mark the final prediction result as S, which is expressed as: S=w1*Y1+w2*Y2+w3*Y3+w4*Y4+......+wn*Yn; Among them, w1, w2, w3, w4, ....., wn are meeting schedules, memorandum schedules, holiday information, and weather data respectively, and w1, w2, w3, ....., wn are all greater than 0, and Y1, Y2, Y3, ....., Yn are the prediction results of the corresponding factors.

5. A passenger travel push marketing method based on big data analysis according to claim 4, characterized in that: Detailed travel suggestions include departure time, mode of transportation, estimated arrival time and other information. In the travel suggestions, the departure time will be accurately calculated based on the distance to the destination and the expected traffic conditions. The departure time is accurate to 4-5 hours in advance.

6. A passenger travel push marketing method based on big data analysis according to claim 5, characterized in that: Once the user clicks to start, the system will automatically reserve a vehicle and plan the corresponding route. The travel planning range will cover a distance between 1-200 kilometers. When pushing the travel plan, the top three destinations will be displayed for the user to choose.

7. A passenger travel push marketing method based on big data analysis according to claim 6, characterized in that: When determining the data of clicks on the pop-up window, the number of clicks on the pop-up window when the user needs to use the car will be obtained. If the number of clicks by the user is small, the itinerary pop-up window will be replaced, and the discount price information will be included in the new itinerary pop-up window.

8. The passenger travel push marketing method based on big data analysis according to claim 7 is characterized by: The user's purchase data is obtained through the API interface, data crawling tools, and data partners provided by the platform; after obtaining the data, the data is cleaned and processed and the processed data is imported into the database through the API interface.

Images