Scene Service Triggering Method and Device for Multi-Fence Interaction Scenarios

Abstract

The present application discloses a method and device for triggering scenario services in a multi-fence interaction scenario. The method includes: obtaining the current travel information of the user ID to be monitored, determining the electronic fences involved by the user ID to be monitored based on the travel information, and fitting the overlapping areas of the electronic fence interactions; when it is detected that the user enters the overlapping area, obtaining the historical business trip data corresponding to the user ID to be monitored and inputting it into a pre-trained behavior sequence prediction model to output the action sequence in the multi-fence interaction scenario; according to the action sequence, dynamically generating the service trigger priorities of the electronic fences of each service provider; sorting the scenario services of the electronic fences of each service provider according to the service trigger priorities to obtain a scenario service trigger list; triggering the scenario services in the trigger list to generate a notification message and feedback it to the client. Therefore, by adopting the embodiments of the present application, the problem of disordered service order in the multi-fence interaction scenario can be solved, and the accuracy of service triggering and the service experience can be improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to a method and device for triggering scenario services in a multi-fence interaction scenario. Background Art

[0002] With the rapid development of the global tourism industry, the demand of travelers for services related to hotels, meal reservations, and transportation means is increasing day by day. Against this background, the associated services among hotels, meal reservations, and transportation means become particularly important, and travelers expect to enjoy seamless connection and personalized service arrangements among hotels, meal reservations, and transportation means.

[0003] In the related art, the associated services among hotels, meal reservations, and transportation means mainly rely on manual or simple automated systems to implement. With the wide application of intelligent devices and location services, providing customized services based on the real-time geographical location of users has become a new trend. As one of the applications, the electronic fence technology can trigger corresponding services when a user enters or leaves a specific geographical area.

[0004] However, although the electronic fence technology provides a service triggering mechanism based on geographical location, the existing systems have obvious limitations and deficiencies. For example, in a city, due to the density of buildings and areas, different service providers will set their own electronic fences at the same or similar geographical locations. In this case, multi-fence interaction will occur, and the service order will be disordered. For example, if a user is used to having a meal first after getting off the plane, the system will misjudge that the user will go to the hotel first, and then trigger the reception of services, unable to solve the problem of disordered service order in the multi-fence interaction scenario, thus reducing the accuracy of service triggering and the service experience of travelers. Summary of the Invention

[0005] The embodiments of this application provide a method and device for triggering scenario services in a multi-fence interaction scenario. To have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary part is not a general review, nor is it intended to identify key / important constituent elements or delineate the protection scope of these embodiments. Its sole purpose is to present some concepts in a simple form as a preamble to the subsequent detailed description.

[0006] In a first aspect, the embodiments of this application provide a method for triggering scenario services in a multi-fence interaction scenario, which is applied to a server. The method includes:

[0007] Obtain the current travel information of the user ID to be monitored, and based on the current travel information, determine the electronic fences belonging to each service provider involved in the user ID to be monitored, and fit out the overlapping areas of the electronic fence interactions of each service provider;

[0008] When it is detected that the user ID to be monitored enters the overlapping area, obtain the historical user business travel data corresponding to the user ID to be monitored;

[0009] Input the historical user business travel data into a pre-trained action sequence prediction model, and output the action sequence of the user ID to be monitored in the multi-fence interaction scenario; the pre-trained action sequence prediction model is obtained through machine learning based on the historical action sequence labels and historical data of each target user ID in the multi-fence interaction scenario. The historical data includes historical behavior data, historical context information related to user behavior, and historical user profile information, and the historical user profile information is used to characterize the basic information and preferences of the user;

[0010] According to the action sequence, dynamically generate the service trigger priorities of the electronic fences of each service provider;

[0011] Sort the scenario services of the electronic fences of each service provider according to the service trigger priorities of the electronic fences of each service provider to obtain a scenario service trigger list;

[0012] Trigger the scenario services in the scenario service trigger list to generate a notification message and feedback it to the clients belonging to each service provider.

[0013] Optionally, generate a pre-trained action sequence prediction model according to the following steps, including:

[0014] Collect and preprocess the historical behavior data, historical context information related to user behavior, and historical user profile information of each target user ID in the multi-fence interaction scenario;

[0015] Obtain the historical action sequence labels of each target user ID in the multi-fence interaction scenario;

[0016] Create an action sequence prediction model, and the sequence prediction model includes a decision tree network;

[0017] Generate model training samples based on the historical behavior data, historical context information, and historical user profile information;

[0018] Input the model training samples into the decision tree network for machine learning, and obtain the pre-trained action sequence prediction model after the learning is completed.

[0019] Optionally, the action sequence prediction model further includes a trend chart fitting module, an interest point area determination module, a preference degree generation module, a coding association module, a feature coding module, a data annotation module, and a decision tree network;

[0020] Generate model training samples based on the historical behavior data, historical context information, and historical user profile information, including:

[0021] Based on historical behavior data, the trend chart fitting module fits the factor trend charts of multiple preset selection factors of the target users belonging to each target user ID within a period of time. The preset selection factors are used to describe the basic information of hotels, meal reservations, and transportation means, and the factor trend charts are used to characterize the change in the selection degree of each preset selection factor by the target users at different times;

[0022] The interest point area determination module determines the area where the selection factor with the most selection times is located from the factor trend chart as the interest point area;

[0023] The preference degree generation module generates the preference degree of each target user for the selection factor according to the interest point area;

[0024] The coding association module performs coding association processing on the preference degree of each target user for the selection factor and the historical context information of each target user to obtain the first feature;

[0025] The feature coding module performs feature coding on the basic information and preferences used to characterize the user of each target user to obtain the second feature;

[0026] The data annotation module annotates the first feature and the second feature of each target user with the historical action sequence label of each target user ID to obtain model training samples.

[0027] Optionally, based on historical behavior data, fitting the factor trend charts of multiple preset selection factors of the target users belonging to each target user ID within a period of time includes:

[0028] Determine the time range to be analyzed, and divide the historical behavior data into target behavior data of different time windows based on the time range;

[0029] Extract the features related to the preset selection factors from the target behavior data;

[0030] Obtain the user selection data of each preset selection factor within different time windows;

[0031] Perform trend analysis on the user selection data to identify the trend changing with time and obtain the trend analysis result;

[0032] Use the extracted features and the trend analysis result to draw a trend chart for each preset selection factor to obtain the factor trend charts of multiple preset selection factors of the target users belonging to each target user ID within a period of time.

[0033] Optionally, generating the preference degree of each target user for the selection factor according to the interest point area includes:

[0034] Aggregate the access frequency, stay duration, and consumption records of users included in the behavior data within the point of interest area to obtain aggregated data;

[0035] Extract the number of visits, average stay time, and consumption amount of the target user at the point of interest from the aggregated data to obtain the behavior pattern of each target user at the point of interest;

[0036] Use a clustering algorithm to cluster the behavior patterns of the target user at the point of interest to group similar behavior patterns into one category and obtain multiple categories of information;

[0037] For each category of information, determine the cluster center, which is used to characterize the high-frequency preferences of each target user in each category of information;

[0038] Adopt the activity frequency, activity duration, and consumption amount of each target user at the cluster center to set calculation metrics;

[0039] According to the calculation metrics, generate the preference intensity of each cluster center as the preference degree of each target user for the selection factor; where,

[0040] The calculation formula for the preference intensity of each cluster center is:

[0041]

[0042] Where, is the preference intensity of the th cluster center, is the set of all users of the th cluster center, is the activity frequency or consumption amount of user at the cluster center, is the total stay time of user at the cluster center.

[0043] Optionally, the model training samples include key-value pairs of feature factors and historical action sequence labels of each target user ID in the multi-fence interaction scenario, and the feature factors are generated based on historical behavior data, historical context information, and historical user profile information;

[0044] Input the model training samples into a decision tree network for machine learning, and after the learning is completed, obtain a pre-trained behavior sequence prediction model, including:

[0045] Input the key-value pairs into the decision tree network for machine learning and output the loss value;

[0046] When the loss value reaches the minimum, a pre-trained behavioral sequence prediction model is generated; or, when the loss value does not reach the minimum, the step of inputting key-value pairs into the decision tree network for machine learning is continued until the loss value reaches the minimum;

[0047] Among them, the loss function of the decision tree network is:

[0048]

[0049] Among them, is the loss value, N is the number of key-value pairs, C is the number of categories of historical action sequence labels, represents whether the historical action sequence label of the th key-value pair is the th category, is the probability that the historical action sequence label of the th key-value pair predicted by the decision tree network is the th category.

[0050] Optionally, according to the action sequence, the service trigger priorities of the electronic fences of each service provider are dynamically generated, including:

[0051] Number the priorities of each action step in the action sequence;

[0052] Map each action step with a priority number to the electronic fences of each service provider to obtain the initial priorities of the electronic fences of each service provider;

[0053] Obtain the context information and real-time location data of the user ID to be detected;

[0054] According to the context information and real-time location data, adjust the initial priorities of the electronic fences of each service provider to generate the service trigger priorities of the electronic fences of each service provider; among them, the context information includes itinerary arrangements, current time, arrival time, weather forecast information, and traffic condition information.

[0055] Optionally, trigger the scenario services in the scenario service trigger list, including:

[0056] Obtain the trigger conditions of each scenario service in the scenario service trigger list;

[0057] Starting from the scenario service with the highest priority in the scenario service trigger list, sequentially determine whether the context information meets the corresponding trigger conditions;

[0058] If so, trigger the scenario service with the highest priority, and continue to execute the steps of obtaining the context information and real-time location data of the user ID to be detected, so as to dynamically adjust the initial priorities of the electronic fences of each service provider; The method further includes:

[0059] In the case that it is monitored that the user ID to be monitored does not enter the overlapping area and enters the electronic fence of any one service provider, obtain the target trigger condition of the entered electronic fence;

[0060] In the case that the context information meets the target trigger condition, obtain the target scenario service of the entered electronic fence;

[0061] Trigger the target scenario service.

[0062] Optionally, determining the electronic fences belonging to each service provider involved by the user ID to be monitored based on the current travel information includes:

[0063] Extract key data from the current travel information, where the key data is used to represent each service node in the itinerary;

[0064] According to each service node in the itinerary, match the corresponding service provider to obtain each service provider involved by the user ID to be monitored;

[0065] According to each service provider involved by the user ID to be monitored, obtain the corresponding electronic fence from the pre-established mapping relationship between the service provider and the electronic fence, so as to obtain the electronic fences belonging to each service provider involved by the user ID to be monitored.

[0066] In a second aspect, an embodiment of the present application provides a scenario service triggering device for a multi-fence interaction scenario, and the device includes:

[0067] An overlapping area fitting module, configured to obtain the current travel information of the user ID to be monitored, and based on the current travel information, determine the electronic fences belonging to each service provider involved by the user ID to be monitored, and fit out the overlapping area of the interaction of the electronic fences of each service provider;

[0068] A business trip information acquisition module, configured to obtain the historical user business trip data corresponding to the user ID to be monitored in the case that it is monitored that the user ID to be monitored enters the overlapping area;

[0069] A model processing module, configured to input historical user business trip data into a pre-trained action sequence prediction model, and output the action sequence of the corresponding user ID to be monitored in a multi-fence interaction scenario; the pre-trained action sequence prediction model is obtained by machine learning based on the historical action sequence labels and historical data of each target user ID in the multi-fence interaction scenario, and the historical data includes historical behavior data, historical context information related to user behavior, and historical user profile information, and the historical user profile information is used to represent the basic information and preferences of the user;

[0070] A service trigger priority generation module, configured to dynamically generate the service trigger priorities of the electronic fences of each service provider according to the action sequence;

[0071] A scenario service sorting module, configured to sort the scenario services of the electronic fences of each service provider according to the service trigger priorities of the electronic fences of each service provider, so as to obtain a scenario service trigger list;

[0072] A scenario service trigger module, configured to trigger the scenario services in the scenario service trigger list, so as to generate a notification message and feedback it to the clients belonging to each service provider.

[0073] The technical solution provided by the embodiment of the present application may include the following beneficial effects:

[0074] In the embodiment of the present application, by obtaining the current travel information of the user and determining the electronic fences of each service provider involved by the user and their overlapping areas, the server can more accurately monitor the position change of the user. After the user is located in the overlapping area, by combining the historical user business trip data and the pre-trained action sequence prediction model, the server can accurately predict the action sequence of the user, and dynamically generate the service trigger priority accordingly. At this time, the server can trigger the scenario services in the correct order, avoiding the problem of disordered service order, thereby improving the accuracy of service triggering. The service provider can receive the service notification that conforms to the user's personalization, improving the user experience.

[0075] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] The accompanying drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0077] Figure 1 It is a schematic flowchart of a method for triggering scenario services in a multi-fence interaction scenario provided by an embodiment of the present application;

[0078] Figure 2It is the data representation intention of the historical behavior data of a user provided by an embodiment of the present application;

[0079] Figure 3 It is a schematic diagram of the model architecture of a behavior sequence prediction model provided by the present application;

[0080] Figure 4 It is a user selection factor trend chart provided by the present application;

[0081] Figure 5 It is the data representation intention of priority adjustment provided by the present application;

[0082] Figure 6 It is a schematic diagram of the structure of a scenario service trigger device for a multi-fence interaction scenario provided by the present application;

[0083] Figure 7 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0084] The following description and drawings fully illustrate the specific implementation manners of the present application, enabling those skilled in the art to practice them.

[0085] It should be clear that the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0086] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all the implementation manners consistent with the present application. On the contrary, they are only examples of the devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0087] In the description of the present application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances. In addition, in the description of the present application, unless otherwise specified, "a plurality of" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0088] Currently, the associated services of hotels, meal reservations, and transportation mainly rely on manual or simple automated systems to be realized. With the wide application of smart devices and location services, providing customized services based on the real-time geographical location of users has become a new trend. As one of the applications, the electronic fence technology can trigger corresponding services when a user enters or leaves a specific geographical area.

[0089] The inventors have realized that although the electronic fence technology provides a service triggering mechanism based on geographical location, the existing systems have obvious limitations and deficiencies. For example, in a city, due to the density of buildings and areas, different service providers will set their respective electronic fences at the same or similar geographical locations. In this case, there will be a situation of multi-fence interaction, and the service order will be disordered. For example, a user is accustomed to having a meal first after getting off the plane, but at this time the system will misjudge that the user goes to the hotel first, and then trigger the reception service. It cannot solve the problem of disordered service order in the multi-fence interaction scenario, thus reducing the accuracy of service triggering and the service experience of passengers.

[0090] To solve the above problems, the present application provides a scenario service triggering method and device for multi-fence interaction scenarios to solve the problems existing in the above related technical problems. In the embodiments of the present application, by obtaining the current travel information of the user and determining the electronic fences and their overlapping areas of each service provider involved by the user, the server can more accurately monitor the position change of the user. After the user is located in the overlapping area, by combining the historical business trip data of the user and the pre-trained behavior sequence prediction model, the server can accurately predict the action sequence of the user, and dynamically generate the service trigger priority accordingly. At this time, the server can trigger the scenario service in the correct order, avoiding the problem of disordered service order, thereby improving the accuracy of service triggering. The service provider can receive service notifications that meet the user's personalization, improving the user experience. The following will be described in detail with exemplary embodiments.

[0091] The following will be combined with the attached Figure 1 - attached Figure 5 to introduce in detail the scenario service triggering method for multi-fence interaction scenarios provided by the embodiments of the present application. This method can be implemented depending on a computer program and can run on a scenario service triggering device for multi-fence interaction scenarios based on the von Neumann architecture. This computer program can be integrated in an application or run as an independent tool class application.

[0092] Please refer to Figure 1 , which is a schematic flowchart of a scenario service triggering method for multi-fence interaction scenarios provided by the embodiments of the present application and is applied to the server. As Figure 1 shown, the method of the embodiments of the present application may include the following steps:

[0093] S101. Obtain the current travel information of the user ID to be monitored, and based on the current travel information, determine the electronic fences belonging to each service provider involved by the user ID to be monitored, and fit out the overlapping areas of the interaction of the electronic fences of each service provider;

[0094] Among them, the user ID to be monitored refers to the unique identifier of a specific user that the server plans to track and serve. The current travel information refers to the current travel-related data and information of the user, including but not limited to the departure place, destination, departure time, arrival time, transportation mode, etc. An electronic fence is a virtual geographical boundary, usually defined by GPS or other positioning technologies. When the user's device enters or leaves this virtual boundary, preset actions or services can be triggered. A service provider refers to a company or organization that provides specific services, such as hotels, restaurants, transportation services, etc. Each service provider may set its own electronic fence to identify its service area and provide services when the user enters these areas. The overlapping area refers to the geographical area where two or more electronic fences intersect. In a multi-fence interaction scenario, the movement of the user may cause them to be within the electronic fences of multiple service providers at the same time.

[0095] In some embodiments, for example, traveler A (user ID to be monitored: U12345) plans to travel from home to the airport, then take a plane to another city, and has booked a hotel and dinner at the destination. The server obtains the current travel information of user U12345 from traveler A's mobile application, email communication, and online booking platform, including flight details (departure time, arrival time, airport code), hotel reservation information (hotel location, check-in time), and dinner reservation (restaurant location, reservation time). The server identifies the service providers related to the itinerary of user U12345, including the airline, hotel, and restaurant. The server matches the electronic fences of each service provider. For example, the airport fence is set within a range of 1 - 5 kilometers around the airport, the hotel fence is set within a range of 100 - 500 meters around the hotel, and the restaurant fence is set within a range of 100 - 500 meters around the restaurant. Using GIS technology, the server analyzes and determines the overlapping areas of the airport, hotel, and restaurant electronic fences. For example, if the hotel and the restaurant are both near the airport, their fences may overlap.

[0096] In an embodiment of the present application, the specific process of determining the electronic fences belonging to each service provider related to the user ID to be monitored based on the current travel information includes: extracting key data from the current travel information, where the key data is used to characterize each service node in the itinerary; matching the corresponding service providers according to each service node in the itinerary to obtain each service provider related to the user ID to be monitored; and obtaining the corresponding electronic fences from the pre-established mapping relationship between the service providers and the electronic fences, so as to obtain the electronic fences belonging to each service provider related to the user ID to be monitored.

[0097] Among them, the key data is the data points extracted from the current travel information that are crucial for service provision, such as flight numbers, hotel names, restaurant reservation times, etc. These data are used to determine the important nodes in the user's itinerary. A service node refers to a location or time point in the user's itinerary that requires specific services, such as an airport boarding gate, a hotel entrance, a restaurant table, etc. The mapping relationship between the service provider and the electronic fence is a pre-established database or mapping table that records the relationship between each service provider and the electronic fence set by it, and is used for quick lookup and matching.

[0098] In some embodiments, the server extracts key data from the travel information of user U12345, including: the flight information is flight number XY123, the departure time is 08:00, and the departure place is the Capital International Airport. The hotel information is that the hotel name is "Central Hotel" and the expected arrival time is 14:00. The restaurant reservation is for dinner at "Gourmet Restaurant" and the reservation time is 19:00. The server identifies the service nodes in the user's itinerary, including: the boarding gate of the Capital International Airport, the entrance of "Central Hotel", and the table in "Gourmet Restaurant". The server matches the corresponding service providers according to the service nodes: the airline provides flight services, "Central Hotel" provides accommodation services, and "Gourmet Restaurant" provides catering services. The server queries the pre-established mapping relationship between the service providers and the electronic fences to obtain the following electronic fences: the electronic fence corresponding to the boarding gate of the Capital International Airport of the airline, the electronic fence corresponding to the hotel entrance of "Central Hotel", and the electronic fence corresponding to the restaurant area of "Gourmet Restaurant".

[0099] S102. In the case of detecting that the user ID to be monitored enters the overlapping area, obtain the historical user business travel data corresponding to the user ID to be monitored;

[0100] Among them, the historical user business travel data refers to the data records generated by the user during past travels, including but not limited to flight records, hotel check-in history, dining consumption habits, transportation mode selection, etc.

[0101] In some embodiments, the user's smartphone or other positioning device sends location updates to the server in real time. The server monitors the user's location through the GIS system to determine when the user enters an overlapping area. For example, the user approaches both the airport and the reserved hotel simultaneously. Once it is detected that user U12345 enters the overlapping area, the server retrieves the historical travel data of user U12345 from the database, including: Past flight records: The number of flights user U12345 has taken in the past year, the preferred airline, the preferred seat type, etc. Hotel check-in history: The accommodation preferences of user U12345, such as room type, whether additional services are required (such as fitness center, laundry service). Dining consumption habits: The dining preferences of user U12345 during travel, such as the types of dishes usually ordered, the preferred restaurant style. The historical travel data of different users is as follows Figure 2 as shown.

[0102] S103, input the historical user travel data into a pre-trained behavior sequence prediction model, and output the action sequence of the corresponding monitored user ID in the multi-fence interaction scenario; the pre-trained behavior sequence prediction model is obtained through machine learning based on the historical action sequence labels and historical data of each target user ID in the multi-fence interaction scenario. The historical data includes historical behavior data, historical context information related to user behavior, and historical user profile information. The historical user profile information is used to characterize the user's basic information and preferences;

[0103] Among them, the pre-trained behavior sequence prediction model is a model pre-trained using machine learning technology. It can predict the action sequence of the user in the future multi-fence interaction scenario based on the user's historical travel data. The monitored user ID refers to the unique identifier of a specific user that the server plans to track and serve. The multi-fence interaction scenario refers to a geographical area where there are multiple electronic fences, which may belong to different service providers. The actions of the user in this area may trigger the services of multiple fences. The action sequence refers to the expected action steps and sequence of the user in the multi-fence interaction scenario. For example, first check in at the hotel, then have dinner at the restaurant, and finally go to the convention center.

[0104] In some embodiments of the present application, the server uses the historical business travel data of different users and combines the travel patterns of other similar users to train a behavioral sequence prediction model. When a new itinerary of user U12345 is confirmed, the server inputs the specific information of this itinerary into the behavioral sequence prediction model. The model analyzes the itinerary information and historical preferences of user U12345 and predicts his action sequence in the multi-fence interaction scenario. The model outputs the prediction result, predicting that user U12345 will act in the following order: arriving at the airport fence (triggering flight information service), going to the hotel fence (triggering hotel check-in service), attending the meeting fence (triggering meeting information service), and finally going to the restaurant fence (triggering catering service).

[0105] In some embodiments of the present application, a pre-trained behavioral sequence prediction model can be generated according to the following steps, specifically including: collecting and preprocessing the historical behavior data, historical context information related to user behavior, and historical user profile information of each target user ID in the multi-fence interaction scenario; obtaining the historical action sequence labels of each target user ID in the multi-fence interaction scenario; creating a behavioral sequence prediction model, and the sequence prediction model includes a decision tree network; generating model training samples based on the historical behavior data, historical context information, and historical user profile information; inputting the model training samples into the decision tree network for machine learning, and obtaining a pre-trained behavioral sequence prediction model after the learning ends.

[0106] Among them, historical context information refers to environmental or situational information related to user behavior, such as time, weather, traffic conditions, etc., which may affect user behavior. Historical user profile information refers to data describing user characteristics and preferences, such as age, gender, consumption habits, etc., and is used to construct user profiles. Historical action sequence labels refer to records of the historical action sequences of users in the multi-fence interaction scenario and are used to train the prediction model. The decision tree network is a machine learning model composed of multiple decision trees and is used for classification and regression tasks. Model training samples refer to the data sets used to train machine learning models, including input features and corresponding labels.

[0107] In the embodiments of the present application, by collecting and preprocessing the historical behavior data, context information, and user profile information of users and using these data to train a decision tree network model, a pre-trained behavioral sequence prediction model can be created. This model can accurately predict the action sequence of users in the multi-fence interaction scenario, thereby realizing the dynamic adjustment and optimization of personalized services, improving the timeliness and relevance of services, and ultimately enhancing user satisfaction and the overall service experience.

[0108] Among them, for example Figure 3As shown in the figure, the behavior sequence prediction model further includes a trend chart fitting module, an interest point area determination module, a preference degree generation module, a coding association module, a feature coding module, a data annotation module, and a decision tree network.

[0109] In the embodiment of the present application, the specific process of generating model training samples based on historical behavior data, historical context information, and historical user profile information includes: The trend chart fitting module fits the factor trend charts of multiple preset selection factors of each target user within a period of time based on the historical behavior data. The preset selection factors are used to describe the basic information of hotels, meal ordering, and transportation means. The factor trend chart is used to characterize the change in the selection degree of each preset selection factor by the target user at different times; The interest point area determination module determines, from the factor trend chart, the area where the selection factor with the most selection times is located as the interest point area; The preference degree generation module generates the preference degree of each target user for the selection factor according to the interest point area; The coding association module performs coding association processing on the preference degree of each target user for the selection factor and the historical context information of each target user to obtain the first feature; The feature coding module performs feature coding on the basic information and preferences used to represent the user of each target user to obtain the second feature; The data annotation module annotates the first feature and the second feature of each target user with the historical action sequence label of each target user ID to obtain the model training sample.

[0110] Among them, the preset selection factor is a variable used to describe the basic information of service providers (such as hotels, restaurants, transportation means), such as the star rating of hotels, the cuisine of restaurants, the type of transportation means, etc. The factor trend chart is a chart that describes the change in the selection degree of each preset selection factor by the user at different time points and is used to visualize the change in user preferences over time. The interest point area is the area where the selection factor with the most selection times by the user is located, reflecting the main interests and preferences of the user. Feature coding is to convert the original data into a format suitable for machine learning models to process, such as converting categorical data into numerical data.

[0111] In the embodiment of the present application, by analyzing the historical behavior data of each target user and fitting the factor trend chart, the interest point area and preference degree of the user can be identified, and then feature coding can be generated in combination with the user's context information and basic information. This process not only enhances the understanding of the user's personalized needs, but also improves the accuracy of the behavior prediction model and the responsiveness of personalized services by creating labeled model training samples, thereby providing a more accurate and considerate customized service experience for users.

[0112] In some embodiments of the present application, the specific process of fitting the factor trend charts of multiple preset selection factors of the target user belonging to each target user ID over a period of time based on historical behavior data includes: determining the time range to be analyzed, and dividing the historical behavior data into target behavior data of different time windows based on the time range; extracting features related to the preset selection factors from the target behavior data; obtaining the user selection data of each preset selection factor in different time windows; performing trend analysis on the user selection data to identify the trends changing over time and obtaining the trend analysis results; using the extracted features and the trend analysis results to draw trend charts for each preset selection factor, thereby obtaining the factor trend charts of multiple preset selection factors of the target user belonging to each target user ID over a period of time. Among them, the factor trend chart is, for example Figure 4 as shown

[0113] Among them, the time range refers to a period of time span determined for a specific analysis purpose. For example, it can be one day, one week, one month or one year. The time window is a smaller time period obtained by further subdividing the time range and is used to analyze user behavior in more detail. For example, if analyzing the user behavior of one day, one day can be divided into three time windows: morning, noon and evening. The target behavior data refers to the user behavior data collected within a specific time window, which is the focus of the analysis and is used to extract information related to user behavior patterns and preferences. Feature extraction is to identify and extract information related to the preset selection factors from the target behavior data, and this information can be used to describe the user behavior patterns and preferences. The user selection data refers to the actual selection records of the user for each preset selection factor in different time windows, and these data reflect the actual behavior of the user. Trend analysis is to analyze the user selection data to identify the behavior patterns and trends changing over time. The factor trend chart is a chart drawn for each preset selection factor based on the extracted features and the trend analysis results, and shows the change in the degree of the user's selection of these factors over time.

[0114] Specifically, the specific process of generating the preference degree of each target user for the selection factor according to the point of interest area includes: aggregating the access frequency, stay duration, and consumption records of users included in the behavior data within the point of interest area to obtain aggregated data; extracting the number of visits, average stay time, and consumption amount of the target user at the point of interest from the aggregated data to obtain the behavior pattern of each target user at the point of interest; using a clustering algorithm to cluster the behavior patterns of the target user at the point of interest to classify similar behavior patterns into one category and obtain multiple categories of information; for each category of information, determining the clustering center, where the clustering center is used to characterize the high-frequency preference of each target user in each category of information; setting calculation indicators using the activity frequency, activity duration, and consumption amount of each target user at the clustering center; and generating the preference intensity of each clustering center according to the calculation indicators as the preference degree of each target user for the selection factor.

[0115] Among them, the calculation formula for the preference intensity of each clustering center is:

[0116]

[0117] Among them, is the preference intensity of the th clustering center, is the set of all users of the th clustering center, is the activity frequency or consumption amount of user at the clustering center, is the total stay time of user at the clustering center.

[0118] Among them, the model training sample includes key-value pairs of feature factors and historical action sequence labels of each target user ID in the multi-fence interaction scenario, and the feature factors are generated based on historical behavior data, historical context information, and historical user portrait information.

[0119] In some embodiments of the present application, the specific process of inputting the model training sample into the decision tree network for machine learning and obtaining the pre-trained behavior sequence prediction model after the learning is completed includes: inputting the key-value pairs into the decision tree network for machine learning and outputting a loss value; generating the pre-trained behavior sequence prediction model when the loss value reaches the minimum; or, when the loss value does not reach the minimum, continuing to execute the step of inputting the key-value pairs into the decision tree network for machine learning until the loss value reaches the minimum.

[0120] Among them, the loss function of the decision tree network is:

[0121]

[0122] Among them, is the loss value, N is the number of key-value pairs, and C is the number of categories of historical action sequence tags. Indicates whether the historical action sequence tag of the th key-value pair is the th category (1 if yes, 0 if no). is the probability that the historical action sequence tag of the th key-value pair predicted by the decision tree network is the th category.

[0123] S104. Dynamically generate the service trigger priorities of the electronic fences of each service provider according to the action sequence.

[0124] Among them, the service trigger priority refers to the order of determining which services should be provided or executed first in the case where multiple services may be triggered.

[0125] In some embodiments of the present application, the specific process of dynamically generating the service trigger priorities of the electronic fences of each service provider according to the action sequence includes: numbering the priority of each action step in the action sequence; mapping each action step with a priority number to the electronic fences of each service provider to obtain the initial priorities of the electronic fences of each service provider; obtaining the context information and real-time location data of the user ID to be detected; adjusting the initial priorities of the electronic fences of each service provider according to the context information and real-time location data to generate the service trigger priorities of the electronic fences of each service provider; among them, the context information includes itinerary arrangements, current time, arrival time, weather forecast information, and traffic condition information.

[0126] Among them, the priority number is to assign a number to each action step in the action sequence to represent their execution priorities. An action step refers to a single activity or event in the action sequence, such as "check into a hotel" or "take a flight". A service provider is a company or organization that provides specific services, such as hotels, catering services, transportation services, etc. The initial priority is the initial priority order assigned to the electronic fences of each service provider based on the priority numbers in the action sequence. The context information is environmental or situational information related to user behavior, such as itinerary arrangements, current time, arrival time, weather forecast information, traffic condition information, etc.

[0127] For example, user U12345 plans to complete multiple action steps in a day, including: departing from home and going to the airport (step 1), taking a plane to reach the destination (step 2), going from the airport to the hotel (step 3), and dining at a restaurant near the hotel (step 4). The server numbers the action sequence according to the itinerary of user U12345. For example: step 1 (going to the airport): priority 1, step 2 (taking a plane): priority 2, step 3 (going to the hotel): priority 3, step 4 (dining): priority 4. The server maps each action step to the electronic fence of the corresponding service provider and sets the initial priority: airport fence: priority 1, airplane service fence: priority 2, hotel fence: priority 3, restaurant fence: priority 4. The server collects the context information and real-time location data of user U12345, including: itinerary: the detailed itinerary of user U12345, current time: the departure time is 8 am, arrival time: it is expected that the plane will arrive at 1 pm, weather forecast information: there will be rain in the destination in the afternoon, traffic condition information: traffic congestion in the destination. The server adjusts the service trigger priority of the electronic fence according to the context information and real-time location data: since it is expected to rain in the afternoon, the priority of the hotel fence is increased so that the user can check in quickly after arrival; considering the traffic congestion, the priority of the restaurant fence is increased so that dining service can be provided in time after the user arrives at the hotel; according to the real-time location data, when user U12345 is approaching the airport, the priority of the airport fence is increased. The server generates the adjusted service trigger priority of the electronic fence of each service provider: airport fence (after adjustment): priority 1, hotel fence (after adjustment): priority 2, restaurant fence (after adjustment): priority 3, airplane service fence: priority 4. Among them, the adjusted service trigger priority of the electronic fence of each service provider is as follows Figure 5 as shown

[0128] S105, sort the scenario services of the electronic fences of each service provider according to the service trigger priority of the electronic fences of each service provider to obtain a scenario service trigger list;

[0129] In some embodiments, for example, the server determines the service trigger priorities of the electronic fences of various service providers based on the travel arrangements and context information (such as time, weather, etc.) of user U12345. For example: Airport fence: Priority 1 (because the user first needs to check in), Hotel fence: Priority 2 (the user needs to check in after arriving at the destination), Restaurant fence: Priority 3 (the user dines after settling in the hotel). At this time, the server sorts the scenario services of the electronic fences of various service providers according to the determined priorities: Scenario service trigger list, Flight information service triggered by the airport fence, Check-in reminder service triggered by the hotel fence, Ordering service triggered by the restaurant fence. The server generates the final scenario service trigger list: The system triggers the flight information service, the system triggers the check-in reminder service, and the system triggers the ordering service.

[0130] S106, trigger the scenario services in the scenario service trigger list to generate a notification message and feedback it to the clients belonging to each service provider.

[0131] In some embodiments of the present application, the specific process of triggering the scenario services in the scenario service trigger list includes: obtaining the trigger conditions of each scenario service in the scenario service trigger list; starting from the scenario service with the highest priority in the scenario service trigger list, sequentially determining whether the context information meets the corresponding trigger conditions; if so, trigger the scenario service with the highest priority, and continue to execute the steps of obtaining the context information and real-time location data of the user ID to be detected to dynamically adjust the initial priorities of the electronic fences of various service providers.

[0132] In some embodiments of the present application, in the case where it is monitored that the user ID to be monitored does not enter the overlapping area and enters the electronic fence of any one service provider, obtain the target trigger condition of the entered electronic fence; in the case where the context information meets the target trigger condition, obtain the target scenario service of the entered electronic fence; trigger the target scenario service.

[0133] In the embodiments of the present application, by obtaining the user's current travel information and determining the electronic fences of various service providers involved by the user and their overlapping areas, the server can more accurately monitor the user's location changes. After the user is located in the overlapping area, by combining historical user business trip data and a pre-trained behavior sequence prediction model, the server can accurately predict the user's action sequence and dynamically generate service trigger priorities accordingly. At this time, the server can trigger the scenario services in the correct order, avoiding the problem of disordered service order, thereby improving the accuracy of service triggering. The service providers can receive service notifications that meet the user's personalization, enhancing the user experience.

[0134] The following is an embodiment of the device of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the device embodiment of the present application, please refer to the method embodiment of the present application.

[0135] Please refer to Figure 6 , which shows a schematic structural diagram of a scenario service trigger device provided in an exemplary embodiment of the present application for a multi-fence interaction scenario. The scenario service trigger device for the multi-fence interaction scenario can be implemented as all or part of an electronic device through software, hardware, or a combination of both. The device 1 includes an overlapping area fitting module 10, a business trip information acquisition module 20, a model processing module 30, a service trigger priority generation module 40, a scenario service sorting module 50, and a scenario service trigger module 60.

[0136] The overlapping area fitting module 10 is configured to obtain the current travel information of the user ID to be monitored, and based on the current travel information, determine the electronic fences belonging to each service provider involved by the user ID to be monitored, and fit the overlapping area of the interaction of the electronic fences of each service provider;

[0137] The business trip information acquisition module 20 is configured to obtain the historical user business trip data corresponding to the user ID to be monitored when it is detected that the user ID to be monitored enters the overlapping area;

[0138] The model processing module 30 is configured to input the historical user business trip data into a pre-trained action sequence prediction model, and output the action sequence of the user ID to be monitored in the multi-fence interaction scenario; the pre-trained action sequence prediction model is obtained by machine learning based on the historical action sequence tags and historical data of each target user ID in the multi-fence interaction scenario, and the historical data includes historical behavior data, historical context information related to user behavior, and historical user portrait information, and the historical user portrait information is used to represent the basic information and preferences of the user;

[0139] The service trigger priority generation module 40 is configured to dynamically generate the service trigger priorities of the electronic fences of each service provider according to the action sequence;

[0140] The scenario service sorting module 50 is configured to sort the scenario services of the electronic fences of each service provider according to the service trigger priorities of the electronic fences of each service provider to obtain a scenario service trigger list;

[0141] The scenario service trigger module 60 is configured to trigger the scenario services in the scenario service trigger list to generate a notification message and feedback it to the clients belonging to each service provider.

[0142] It should be noted that when the above-described scenario service triggering device for multi-fence interaction scenarios executes the scenario service triggering method for multi-fence interaction scenarios, only the division of the above functional modules is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the scenario service triggering device for multi-fence interaction scenarios provided in the above embodiments and the embodiments of the scenario service triggering method for multi-fence interaction scenarios belong to the same concept. The implementation process is detailed in the method embodiments and will not be repeated here.

[0143] The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0144] In the embodiments of the present application, by obtaining the user's current travel information and determining the electronic fences of each service provider involved by the user and their overlapping areas, the server can more accurately monitor the position change of the user. After the user is located in the overlapping area, by combining historical user business trip data and a pre-trained behavior sequence prediction model, the server can accurately predict the user's action sequence and dynamically generate a service trigger priority accordingly. At this time, the server can trigger the scenario service in the correct order, avoiding the problem of disordered service order, thereby improving the accuracy of service triggering. The service provider can receive a service notification that conforms to the user's personalization, improving the user experience.

[0145] The present application also provides a computer-readable medium, on which program instructions are stored. When the program instructions are executed by a processor, the scenario service triggering method for multi-fence interaction scenarios provided in each of the above method embodiments is implemented.

[0146] The present application also provides a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the scenario service triggering method for multi-fence interaction scenarios in each of the above method embodiments.

[0147] Please refer to Figure 7 , which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 7 shown, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0148] Among them, the communication bus 1002 is used to realize the connection and communication between these components.

[0149] Among them, the user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may further include standard wired interfaces and wireless interfaces.

[0150] Among them, the network interface 1004 may optionally include standard wired interfaces and wireless interfaces (such as WI-FI interfaces).

[0151] Among them, the processor 1001 may include one or more processing cores. The processor 1001 connects various parts within the entire electronic device 1000 through various interfaces and circuits. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005, the processor 1001 performs various functions of the electronic device 1000 and processes data. Optionally, the processor 1001 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 1001 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001 and may be implemented separately through a single chip.

[0152] Among them, the memory 1005 may include a Random Access Memory (RAM), or may include a Read-Only Memory. Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above method embodiments, etc.; the data storage area may store the data involved in the above method embodiments. Optionally, the memory 1005 may also be at least one storage system located far from the aforementioned processor 1001. As Figure 7 shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a scenario service trigger application for a multi-fence interaction scenario.

[0153] In Figure 7 the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user to obtain the data input by the user; and the processor 1001 can be used to call the scenario service trigger application stored in the memory 1005 for the multi-fence interaction scenario, and specifically perform the following operations:

[0154] Obtain the current travel information of the user ID to be monitored, and based on the current travel information, determine the electronic fences belonging to each service provider involved in the user ID to be monitored, and fit out the overlapping areas of the electronic fence interactions of each service provider;

[0155] When it is detected that the user ID to be monitored enters the overlapping area, obtain the historical user business trip data corresponding to the user ID to be monitored;

[0156] Input the historical user business trip data into a pre-trained action sequence prediction model, and output the action sequence of the user ID to be monitored in the multi-fence interaction scenario; the pre-trained action sequence prediction model is obtained by machine learning based on the historical action sequence labels and historical data of each target user ID in the multi-fence interaction scenario. The historical data includes historical behavior data, historical context information related to user behavior, and historical user profile information. The historical user profile information is used to characterize the basic information and preferences of the user;

[0157] According to the action sequence, dynamically generate the service trigger priorities of the electronic fences of each service provider;

[0158] Sort the scenario services of the electronic fences of each service provider according to the service trigger priorities of the electronic fences of each service provider to obtain a scenario service trigger list;

[0159] Trigger the scenario services in the scenario service trigger list to generate a notification message and feedback it to the clients belonging to each service provider.

[0160] In one embodiment, when the processor 1001 executes to generate a pre-trained behavior sequence prediction model, the following operations are specifically performed:

[0161] Collect and preprocess the historical behavior data, historical context information related to user behavior, and historical user profile information of each target user ID in the multi-fence interaction scenario;

[0162] Obtain the historical action sequence labels of each target user ID in the multi-fence interaction scenario;

[0163] Create a behavior sequence prediction model, and the sequence prediction model includes a decision tree network;

[0164] Generate model training samples based on the historical behavior data, historical context information, and historical user profile information;

[0165] Input the model training samples into the decision tree network for machine learning, and after the learning ends, obtain a pre-trained behavior sequence prediction model.

[0166] In one embodiment, when the processor 1001 executes to generate model training samples based on the historical behavior data, historical context information, and historical user profile information, the following operations are specifically performed:

[0167] The trend chart fitting module fits the factor trend charts of multiple preset selection factors of the target user to which each target user ID belongs within a period of time based on the historical behavior data. The preset selection factors are used to describe the basic information of hotels, meal ordering, and transportation means, and the factor trend charts are used to characterize the change in the selection degree of each preset selection factor by the target user at different times;

[0168] The point of interest area determination module determines, from the factor trend charts, the area where the selection factor with the most selection times is located as the point of interest area;

[0169] The preference degree generation module generates the preference degree of each target user for the selection factor according to the point of interest area;

[0170] The encoding association module performs encoding association processing on the preference degree of each target user for the selection factor and the historical context information of each target user to obtain a first feature;

[0171] The feature encoding module encodes the basic information and preferences used to represent the user for each target user to obtain a second feature;

[0172] The data annotation module annotates the first feature and the second feature of each target user using the historical action sequence tags of each target user ID to obtain model training samples.

[0173] In one embodiment, when the processor 1001 executes fitting the factor trend chart of multiple preset selection factors of the target user belonging to each target user ID based on historical behavior data over a period of time, it specifically performs the following operations:

[0174] Determine the time range to be analyzed, and divide the historical behavior data into target behavior data of different time windows based on the time range;

[0175] Extract features related to the preset selection factors from the target behavior data;

[0176] Obtain the user selection data of each preset selection factor within different time windows;

[0177] Perform trend analysis on the user selection data to identify the trend over time and obtain the trend analysis result;

[0178] Use the extracted features and the trend analysis result to draw a trend chart for each preset selection factor, and obtain the factor trend chart of multiple preset selection factors of the target user belonging to each target user ID over a period of time.

[0179] In one embodiment, when the processor 1001 executes generating the preference degree of each target user for the selection factor according to the point of interest area, it specifically performs the following operations:

[0180] Aggregate the access frequency, stay duration, and consumption records of the users included in the behavior data within the point of interest area to obtain aggregated data;

[0181] Extract the number of visits, average stay time, and consumption amount of the target user at the point of interest from the aggregated data to obtain the behavior pattern of each target user at the point of interest;

[0182] Use a clustering algorithm to cluster the behavior patterns of the target user at the point of interest to group similar behavior patterns into one category and obtain multiple categories of information;

[0183] For each category of information, determine the clustering center, and the clustering center is used to represent the high-frequency preferences of each target user in each category of information;

[0184] Adopt the activity frequency, activity duration, and consumption amount of each target user at the clustering center to set calculation metrics;

[0185] According to the calculation index, generate the preference intensity of each cluster center as the preference degree of each target user for the selection factor; wherein,

[0186] The calculation formula for the preference intensity of each cluster center is:

[0187]

[0188] wherein, is the preference intensity of the th cluster center, is the set of all users of the th cluster center, is the activity frequency or consumption amount of user in the cluster center, is the total stay time of user in the cluster center.

[0189] In one embodiment, when the processor 1001 executes inputting the model training samples into the decision tree network for machine learning and obtaining the pre-trained behavior sequence prediction model after the learning ends, it specifically performs the following operations:

[0190] Input the key-value pairs into the decision tree network for machine learning and output the loss value;

[0191] In the case where the loss value reaches the minimum, generate the pre-trained behavior sequence prediction model; or, in the case where the loss value does not reach the minimum, continue to execute the step of inputting the key-value pairs into the decision tree network for machine learning until the loss value reaches the minimum;

[0192] wherein, the loss function of the decision tree network is:

[0193]

[0194] wherein, is the loss value, N is the number of key-value pairs, C is the number of categories of the historical action sequence labels, indicates whether the historical action sequence label of the th key-value pair is the th category (1 for yes, 0 for no), is the probability that the historical action sequence label of the th key-value pair predicted by the decision tree network is the th category.

[0195] In one embodiment, when the processor 1001 executes dynamically generating the service trigger priorities of the electronic fences of each service provider according to the action sequence, it specifically performs the following operations:

[0196] Number the action steps in the action sequence with priorities;

[0197] Map each action step with a priority number to the electronic fences of each service provider to obtain the initial priorities of the electronic fences of each service provider;

[0198] Obtain the context information and real-time location data of the user ID to be detected;

[0199] Adjust the initial priorities of the electronic fences of each service provider according to the context information and real-time location data to generate the service trigger priorities of the electronic fences of each service provider; where the context information includes itinerary arrangements, current time, arrival time, weather forecast information, and traffic condition information.

[0200] In one embodiment, when the processor 1001 executes the scenario service in the trigger scenario service trigger list, it specifically performs the following operations:

[0201] Obtain the trigger conditions of each scenario service in the scenario service trigger list;

[0202] Starting from the scenario service with the highest priority in the scenario service trigger list, sequentially determine whether the corresponding trigger conditions are met through the context information;

[0203] If so, trigger the scenario service with the highest priority, and continue to execute the step of obtaining the context information and real-time location data of the user ID to be detected to dynamically adjust the initial priorities of the electronic fences of each service provider; The method further includes:

[0204] In the case where it is monitored that the user ID to be monitored does not enter the overlapping area and enters the electronic fence of any one service provider, obtain the target trigger condition of the entered electronic fence;

[0205] In the case where the context information meets the target trigger condition, obtain the target scenario service of the entered electronic fence;

[0206] Trigger the target scenario service.

[0207] In one embodiment, when the processor 1001 executes to determine the electronic fences belonging to each service provider involved by the user ID to be monitored based on the current travel information, it specifically performs the following operations:

[0208] Extract key data from the current appearance information, and the key data is used to characterize each service node in the itinerary;

[0209] According to each service node in the itinerary, match the corresponding service provider to obtain each service provider involved by the user ID to be monitored;

[0210] According to each service provider involved in the user ID to be monitored, obtain the corresponding electronic fence from the pre-established mapping relationship between the service provider and the electronic fence, and obtain the electronic fences belonging to each service provider involved in the user ID to be monitored.

[0211] In the embodiment of the present application, by obtaining the current travel information of the user and determining the electronic fences of each service provider involved in the user and their overlapping areas, the server can more accurately monitor the position change of the user. After the user is located in the overlapping area, by combining the historical business trip data of the user and the pre-trained behavior sequence prediction model, the server can accurately predict the action sequence of the user and dynamically generate the service trigger priority accordingly. At this time, the server can trigger the scenario service in the correct order, avoiding the problem of disordered service order, thereby improving the accuracy of service trigger. The service provider can receive the service notification that meets the user's personalization, improving the user experience.

[0212] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program for scenario service trigger in the multi-fence interaction scenario can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium of the program for scenario service trigger in the multi-fence interaction scenario can be a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.

[0213] The above-disclosed are only the preferred embodiments of the present application. Of course, the scope of the rights of the present application cannot be limited thereby. Therefore, the equivalent changes made according to the claims of the present application still fall within the scope covered by the present application.

Claims

1. A scene service triggering method for a multi-fence interaction scene, characterized in that: Applied to the server, the method includes: Acquire current travel information of the user ID to be monitored, and determine the electronic fences of each service provider involved in the user ID to be monitored based on the current travel information, and fit the overlapping areas of the electronic fences of each service provider; When it is detected that the user ID to be monitored enters the overlapping area, obtaining historical user travel data corresponding to the user ID to be monitored; Input the historical user travel data into a pre-trained behavior sequence prediction model, and output the action sequence corresponding to the monitored user ID in the multi-fence interaction scenario; the pre-trained behavior sequence prediction model is obtained by machine learning based on the historical action sequence labels and historical data of each target user ID in the multi-fence interaction scenario, the historical data includes historical behavior data, historical context information related to user behavior, and historical user portrait information, and the historical user portrait information is used to characterize the user's basic information and preferences; Dynamically generate the service triggering priority of the electronic fence of each service provider according to the action sequence; According to the service triggering priority of the electronic fence of each service provider, the scene services of the electronic fence of each service provider are sorted to obtain a scene service triggering list; Trigger the scene services in the scene service trigger list to generate notification messages and feed them back to the clients belonging to each service provider; wherein, The following steps are used to generate a pre-trained behavior sequence prediction model, including: Collect and preprocess the historical behavior data, historical context information related to user behavior, and historical user profile information of each target user ID in multi-fence interaction scenarios; Obtain the historical action sequence labels of each target user ID in the multi-fence interaction scenario; Creating a behavior sequence prediction model, wherein the sequence prediction model includes a decision tree network; Generate a model training sample based on the historical behavior data, the historical context information, and the historical user portrait information; The model training samples are input into the decision tree network for machine learning, and a pre-trained behavior sequence prediction model is obtained after the learning is completed.

2. The method according to claim 1, characterized in that The behavior sequence prediction model also includes a trend chart fitting module, an interest point area determination module, a preference degree generation module, a coding association module, a feature coding module, a data annotation module and a decision tree network; The generating a model training sample based on the historical behavior data, the historical context information and the historical user portrait information includes: The trend chart fitting module fits the factor trend chart of multiple preset selection factors of the target user to which each target user ID belongs within a period of time based on the historical behavior data, wherein the preset selection factors are used to describe basic information of hotels, meal reservations and transportation tools, and the factor trend chart is used to represent the change in the selection degree of the target user for each preset selection factor at different times; The interest point region determination module determines, from the factor trend graph, a region where the selection factor with the most selection times is located as the interest point region; The preference level generating module generates the preference level of each target user for the selection factor according to the interest point area; The coding association module performs coding association processing on the preference degree of each target user for the selection factor and the historical context information of each target user to obtain a first feature; The feature encoding module performs feature encoding on the basic information and preferences of each target user used to characterize the user to obtain a second feature; The data labeling module uses the historical action sequence label of each target user ID to label the first feature and the second feature of each target user to obtain a model training sample.

3. The method according to claim 2, characterized in that The factor trend chart of fitting multiple preset selection factors of the target user to which each target user ID belongs within a period of time based on the historical behavior data includes: Determine a time range to be analyzed, and divide the historical behavior data into target behavior data of different time windows based on the time range; Extracting features related to preset selection factors from the target behavior data; Obtaining user selection data for each preset selection factor within the different time windows; Performing trend analysis on the user selection data to identify trends that change over time and obtain trend analysis results; Using the extracted features and the trend analysis results, a trend chart is drawn for each preset selection factor to obtain factor trend charts of multiple preset selection factors of the target user to which each target user ID belongs within a period of time.

4. The method according to claim 2, characterized in that: Generating the preference degree of each target user for the selection factor according to the interest point area includes: Aggregate the user's visit frequency, stay duration and consumption record included in the behavior data in the POI area to obtain aggregated data; Extracting the visit times, average stay time and consumption amount of the target user at the point of interest from the aggregated data to obtain the behavior pattern of each target user at the point of interest; Clustering the behavior patterns of the target users at the points of interest using a clustering algorithm to classify similar behavior patterns into one category, thereby obtaining multiple categories of information; For each type of information, determine a cluster center, where the cluster center is used to characterize the high-frequency preference of each target user in each type of information; The calculation index is set by using the activity frequency, activity duration and consumption amount of each target user in the cluster center; According to the calculation index, the preference strength of each cluster center is generated as the preference degree of each target user for the selection factor; wherein, The calculation formula for the preference strength of each cluster center is: in, For the The preference strength of the cluster centers, It is The set of all users in the cluster center, Is a user Activity frequency or consumption amount in the cluster center, Is a user The total dwell time at the cluster center.

5. The method according to claim 1, characterized in that The model training samples include a key-value pair of a feature factor and a historical action sequence label of each target user ID in a multi-fence interaction scenario, wherein the feature factor is generated based on the historical behavior data, the historical context information, and the historical user portrait information; The step of inputting the model training samples into the decision tree network for machine learning, and obtaining a pre-trained behavior sequence prediction model after the learning is completed, comprises: Input the key-value pair into the decision tree network for machine learning, and output a loss value; When the loss value reaches the minimum, generating a pre-trained behavior sequence prediction model; or, when the loss value does not reach the minimum, continuing to perform the step of inputting the key-value pair into the decision tree network for machine learning until the loss value reaches the minimum; Among them, the loss function of the decision tree network is: in, is the loss value, N is the number of key-value pairs, C is the number of categories of historical action sequence labels, Indicates Is the historical action sequence label of the key-value pair the kind, The decision tree network predicts The historical action sequence label of the key-value pair is The probability of the class.

6. The method according to claim 1, characterized in that The dynamically generating the service triggering priority of the electronic fence of each service provider according to the action sequence includes: Prioritize each action step in the action sequence; Mapping each action step with a priority number to the electronic fence of each service provider to obtain the initial priority of the electronic fence of each service provider; Obtaining context information and real-time location data of the user ID to be monitored; According to the context information and real-time location data, the initial priority of the electronic fence of each service provider is adjusted to generate the service triggering priority of the electronic fence of each service provider; wherein the context information includes itinerary, current time, arrival time, weather forecast information, and traffic condition information.

7. The method according to claim 6, characterized in that Triggering the scene service in the scene service triggering list includes: Obtaining the triggering condition of each scene service in the scene service triggering list; Starting from the scene service with the highest priority in the scene service trigger list, determining in turn through the context information whether the trigger conditions corresponding thereto are met; If yes, trigger the scene service with the highest priority, and continue to execute the step of obtaining the context information and real-time location data of the ID to be monitored, so as to dynamically adjust the initial priority of the electronic fence of each service provider; the method also includes: When it is detected that the user ID to be monitored does not enter the overlapping area but enters the electronic fence of any service provider, obtaining the target trigger condition of the entered electronic fence; When the context information satisfies the target trigger condition, obtaining a target scene service of the entered electronic fence; The target scenario service is triggered.

8. The method according to claim 1, characterized in that The step of determining the electronic fences belonging to each service provider and involved in the user ID to be monitored based on the current travel information includes: Extracting key data from the current travel information, where the key data is used to characterize each service node in the trip; According to each service node in the itinerary, the corresponding service provider is matched to obtain each service provider involved in the user ID to be monitored; According to each service provider involved in the user ID to be monitored, the corresponding electronic fence is obtained from the pre-established mapping relationship between the service provider and the electronic fence, and the electronic fence belonging to each service provider involved in the user ID to be monitored is obtained.

9. A scene service triggering device for a multi-fence interaction scene implemented by the method described in any one of claims 1 to 8, characterized in that: The device comprises: An overlapping area fitting module, used to obtain the current travel information of the user ID to be monitored, and determine the electronic fences belonging to each service provider involved in the user ID to be monitored based on the current travel information, and fit the overlapping area of ​​the electronic fences of each service provider; A travel information acquisition module, used for acquiring historical user travel data corresponding to the user ID to be monitored when the user ID to be monitored enters the overlapping area; A model processing module is used to input the historical user travel data into a pre-trained behavior sequence prediction model, and output the action sequence corresponding to the monitored user ID in the multi-fence interaction scenario; the pre-trained behavior sequence prediction model is obtained by machine learning based on the historical action sequence label and historical data of each target user ID in the multi-fence interaction scenario, the historical data includes historical behavior data, historical context information related to user behavior, and historical user portrait information, and the historical user portrait information is used to characterize the user's basic information and preferences; A service trigger priority generation module, used to dynamically generate the service trigger priority of the electronic fence of each service provider according to the action sequence; A scene service sorting module, used to sort the scene services of the electronic fences of the service providers according to the service triggering priority of the electronic fences of the service providers, and obtain a scene service triggering list; The scene service triggering module is used to trigger the scene services in the scene service triggering list to generate notification messages and feed them back to the clients belonging to the service providers.

Images