Interaction method and device for route planning, equipment and storage medium

Abstract

The embodiment of the invention provides an interaction method and device for route planning, equipment and a storage medium. The method includes providing a user input associated with a travel task received in a target application to the large model. Obtaining a target itinerary planning result matched with the user input from the large model, the target itinerary planning result being determined from a plurality of candidate itinerary planning results based on the determined preference attribute of the user corresponding to the user input, the plurality of candidate travel planning results are generated at least according to travel modes between adjacent travel nodes, and the travel nodes comprise a travel starting point, a travel ending point and at least one intermediate node between the travel starting point and the travel ending point which are determined based on user input. And presenting the target journey planning result. Therefore, the efficiency of route planning is improved.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and more particularly to interactive methods, apparatuses, devices, and storage media for trip planning. Background Technology

[0002] With the widespread adoption of smart applications, people have become accustomed to using them to book travel or accommodation. Taking business travel as an example, in the traditional way, if a user has diverse travel needs, they need to access the travel booking program designated by their organization (the user's company or group), repeatedly searching and comparing the travel (and accommodation) lists and details presented in the program before finally completing the booking. For users, this booking process is extremely cumbersome. Summary of the Invention

[0003] In a first aspect of this disclosure, an interactive method for trip planning is provided. The method may include: providing a large model of user input associated with a travel task in a target application; obtaining a target trip planning result matching the user input from the large model, the target trip planning result being determined from multiple candidate trip planning results based on user preference attributes corresponding to the user input, the multiple candidate trip planning results being generated at least based on travel modes between adjacent trip nodes, the trip nodes including a trip origin, a trip destination, and at least one intermediate node between the trip origin and the trip destination determined based on the user input; and presenting the target trip planning result.

[0004] In a second aspect of this disclosure, an interactive device for trip planning is provided. The device may include: a user input receiving module configured to provide a large model of user input received in a target application and associated with a travel task; a target trip planning result determination module configured to obtain a target trip planning result matching the user input from the large model, the target trip planning result being determined from multiple candidate trip planning results based on determined user preference attributes corresponding to the user input, the multiple trip planning results being generated at least based on the travel modes between each adjacent trip node, the trip node including a trip start point, a trip end point, and at least one intermediate node between the trip start point and the trip end point determined based on the user input; and a presentation module configured to present the target trip planning result.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the electronic device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. A computer program is stored on the medium, which, when executed by a processor, implements the method of the first aspect.

[0007] In a fifth aspect of this disclosure, a computer program product is provided. The computer program product includes computer-executable instructions that, when executed by a processor, implement the method of the first aspect.

[0008] It should be understood that the description in this section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram of an example environment in which embodiments of the present disclosure can be implemented is shown;

[0011] Figure 2 A schematic diagram illustrating the interaction principle for trip planning according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A schematic diagram of an interactive process for trip planning according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A flowchart illustrating an interactive method for trip planning according to some embodiments of the present disclosure is shown;

[0014] Figure 5 A schematic diagram illustrating the process for determining candidate itinerary planning results according to some embodiments of the present disclosure is shown;

[0015] Figure 6 A schematic structural block diagram of an interactive device for trip planning according to some embodiments of the present disclosure is shown; and

[0016] Figure 7 A block diagram of an electronic device that can implement one or more embodiments of the present disclosure is shown. Detailed Implementation

[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0018] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0019] In this document, unless explicitly stated otherwise, performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.

[0020] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0021] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and authorization should be obtained from the relevant users. Among them, relevant users may include any type of rights holder, such as individuals, enterprises, and groups.

[0022] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly inform the user that the requested operation will require obtaining and using the user's information, thereby enabling the relevant user to choose whether to provide information to the software or hardware such as the electronic device, application, server, or storage medium that performs the operation of the technical solution disclosed herein based on the prompt message.

[0023] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide information to the electronic device.

[0024] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0025] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. Environment 100 relates to a terminal device 110, which can support the operation of a target application 120.

[0026] The target application 120 can be operated by one or more end users 140. End users 140 can operate and interact with the target application 120 through an associated terminal device 110. End users 140 may be referred to as end users of the target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.

[0027] Digital Assistant 122 can be configured to have intelligent conversational capabilities. Figure 1 In the example shown, digital assistant 122 can be integrated into target application 120, serving as part of target application 120 to assist in task processing within target application 120. In other examples, digital assistant 122 can be configured to run as a standalone application, such as a web application or other type of application. In such examples, digital assistant 122 and target application 120 can be considered as the same application. Digital assistant 122 is provided to assist end user 140 in various task processing needs across different applications and scenarios. During interaction with digital assistant 122, end user 140 inputs interactive messages, and digital assistant 122 responds to end user 140's input by providing reply messages. Typically, digital assistant 122 supports end user 140 inputting questions in natural language and performs tasks and provides replies based on its understanding of natural language input and logical reasoning capabilities.

[0028] In some embodiments, the digital assistant 122 can interact with the end user 140 as a contact. For example, the digital assistant 122 can be implemented in an instant messaging (IM) application. The digital assistant 122 can interact with the end user 140 in a one-on-one chat session. In some embodiments, the digital assistant 122 can interact with multiple users in a group chat session that includes multiple users.

[0029] For each end user 140, the client of the target application 120 can present the interactive interface 142 of the target application 120 or the digital assistant 122 in the client interface, such as a conversation window with the digital assistant 122. The end user 140 can enter conversation messages in the conversation window, and the target application 120 can determine the response message of the digital assistant 122 based on the created configuration information and present it to the end user 140 in the interface 142. In some embodiments, depending on the configuration of the target application 120, the interaction messages with the target application 120 may include multimodal messages, such as text messages (e.g., natural language text), voice messages, image messages, video messages, etc.

[0030] The target application 120 can be deployed locally on the terminal device 110 of each end user 140, and / or can be supported by the server device 150. When the target application 120 runs locally on the terminal device 110, the end user 140 can directly interact with the local target application 120 using the terminal device 110. When the target application 120 runs on the server device 150, the server device 150 can provide services to the target application 120 running on the terminal device 110 based on the communication connection between it and the terminal device 110.

[0031] In some embodiments, the implementation of at least some functions of the target application 120, and / or the implementation of at least some functions of the digital assistant 122 within the target application 120, may be based on the target model 155. During the operation of the target application 120, one or more target models 155 may be invoked, such as the capabilities of the target model 155. Within the target application 120, the digital assistant 122 may utilize the target model 155 to understand user input and provide responses to the user based on the output of the target model 155.

[0032] As used herein, the term "model" refers to a model that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs using multiple layers of processing units. A neural network model is an example of a deep learning-based model. In this document, "model" may also be referred to as a "machine learning model," "learning model," "machine learning network," or "learning network," and these terms are used interchangeably. Although shown as independent of terminal device 110, one or more target models 155 may run on terminal device 110 or other remote servers.

[0033] Terminal device 110 may operate on suitable electronic equipment. This electronic equipment can be any type of computing-capable device, including terminal devices or server devices. Terminal devices can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. Server device 150 may, for example, include computing systems / servers, such as mainframes, edge computing nodes, computing devices in cloud environments, etc. It should be understood that the structure and function of environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0034] In existing technologies, users often need to filter through multiple categories (transportation, accommodation) when traveling, leading to complex processes. For example, traveling from the departure point to the destination requires choosing a train or plane, and upon arrival, booking a taxi or ride-hailing service to reach the accommodation. These operations often involve booking processes for multiple categories. Existing booking systems typically distribute bookings for different categories across different pages, forcing users to frequently switch between different pages on the booking platform to filter and perform operations.

[0035] Furthermore, users typically need to plan multiple trips when traveling, including at least outbound and return journeys, and sometimes even multiple stops along the way. Each trip requires independently selecting various services such as transportation and accommodation, making the process cumbersome and increasing repetitive tasks. Users spend a significant amount of time and energy on these repetitive operations, increasing labor costs and significantly reducing work efficiency. In this situation, existing technologies cannot provide a convenient, centralized management solution. They fail to effectively reduce the user's operational burden and repetitive labor, thus leaving significant room for improvement.

[0036] In embodiments of this disclosure, an improved interaction scheme for trip planning is proposed. This improvement scheme may include: providing a large model with user input received in the target application and associated with a travel task; obtaining a target trip planning result matching the user input from the large model, the target trip planning result being determined from multiple candidate trip planning results based on the user's determined preference attributes corresponding to the user input, the multiple candidate trip planning results being generated at least based on the travel modes between each adjacent trip node, the trip node including a trip start point, a trip end point, and at least one intermediate node between the trip start point and the trip end point determined based on the user input; and presenting the target trip planning result.

[0037] Through the above process, by combining itinerary nodes and different modes of transportation, every aspect of the user's entire travel process is covered and considered. This one-stop planning avoids users having to repeatedly filter and adjust at different stages, greatly simplifying the planning process for complex itineraries.

[0038] The scenarios shown in some embodiments of this disclosure may include scenarios where the end user is an enterprise user, and the itinerary planning may be a project inspection itinerary, a customer visit itinerary, a training and seminar itinerary, etc. Figure 2 A schematic diagram 200 illustrating the interaction principle of an interactive method for trip planning according to some embodiments of the present disclosure is shown. The end user 140 interacts through a digital assistant 122. The digital assistant 122 can invoke a target model 155 to parse the user input. The functions of the target model 155 can be accomplished by a large model; therefore, in this application, the large model can serve as the target model 155. If the parsing result includes trip planning, the target model 155 can invoke the transportation booking function 210 to query transportation options and book a specified mode of transportation. Specified modes of transportation may include airplanes, trains, ferries, ride-hailing services, etc. If the parsing result includes accommodation needs, the target model 155 can invoke the accommodation booking function 220 to query accommodation options and book accommodation.

[0039] Terminal device 110 can complete trip planning based on multiple pieces of information. For example, the multiple pieces of information may include basic information 231, information corresponding to management services 233, and information corresponding to map data 234. For example, basic information 231 may be relevant information about terminal user 140, such as the name and identity attribute information of terminal user 140. Identity attribute information may include the date of employment and position of terminal user 140 in the company, etc. Information corresponding to management services 233 may include trip booking standards (e.g., travel standards and accommodation standards) corresponding to different identity attribute information. Information corresponding to map data 234 may include static geographic information related to the trip. For example, information corresponding to map data 234 may include the administrative division of the destination city, the geographical location of various transportation hubs (such as airports and train stations), the geographical location of company offices, the geographical location of partners, the geographical location of partner hotels, etc.

[0040] After the end user 140 confirms the accommodation and transportation options, the terminal device 110 can use the corresponding accommodation booking platform 241 to complete the booking for the accommodation option and the transportation booking platform 242 to complete the booking for the corresponding mode of transportation. After the booking is completed, the order information 232 corresponding to the booking will be displayed on the interface 142.

[0041] Figure 3 A schematic diagram 300 illustrates the interaction process of an interaction method for trip planning according to some embodiments of the present disclosure. In block 310, the end user 140 interacts with the digital assistant 122. In block 311, the terminal device 110 determines the intent of the interaction using a target model 155 (large model). In block 312, the terminal device 110 determines whether the interaction of the end user 140 is related to trip planning based on the output of the target model 155. If it is not related, corresponding suggestion information is presented in block 315. If it is related to trip planning, in block 313, the terminal device 110 determines the parameters related to trip planning based on the interaction content. Examples include origin, destination, departure time, etc. In block 314, the terminal device 110 needs to determine whether the parameters related to trip planning are complete. For example, this can be done by comparing them with preset necessary parameters related to trip planning. If complete, the identity attributes of the end user 140 are verified in block 320. If the information is incomplete (e.g., the origin or departure time is missing), a prompt message needs to be displayed on interface 142 to remind the end user 140 to complete the trip planning parameters.

[0042] In box 321, terminal device 110 uses management service 233 to determine the itinerary booking criteria corresponding to terminal user 140, thereby obtaining travel application data based on the itinerary booking criteria. In box 322, terminal device 110 can determine whether the itinerary planning involved in the user interaction meets the requirements. If it does, the preference attributes of terminal user 140 are obtained in box 323. Otherwise, if it does not meet the requirements, suggestion information can be presented. For example, situations that do not meet the requirements may include the selection of transportation or accommodation options that exceed the itinerary booking criteria, restrictions on travel destinations, etc.

[0043] In box 330, terminal device 110 determines filtering parameters based on the preferences of terminal user 140 and parameters related to trip planning. In box 331, terminal device 110 determines whether transportation bookings are included based on the filtering parameters. If included, transportation booking data related to transportation bookings is obtained in box 332, such as origin, destination, departure time, expected duration, etc. If not included, it determines whether accommodation bookings are included in box 333. If accommodation bookings are included, accommodation booking data related to accommodation bookings is obtained in box 334, such as location requirements, accommodation dates, service requirements, etc.

[0044] In box 340, terminal device 110 determines at least one itinerary planning result based on transportation and / or accommodation booking results. In box 341, feedback from terminal user 140 regarding the at least one itinerary planning result is assessed. If terminal user 140 confirms, the final itinerary planning result is determined in box 342. If terminal user 140 modifies, the itinerary planning parameters are redefined according to the modification suggestions in box 330. In box 343, if terminal user 140 confirms the final itinerary planning result, the process ends. Otherwise, if terminal user 140 provides supplementary requests, the itinerary planning parameters are redefined according to the supplementary requests in box 330.

[0045] Figure 4 An example flow of an interactive method 400 for trip planning according to some embodiments of the present disclosure is shown. The trip planning process described in the embodiments of the present disclosure can be implemented on a terminal device, a terminal device with a target application installed, and / or a server device corresponding to the terminal device. In the examples below, for the sake of discussion, the description is from the perspective of the terminal device, for example... Figure 1 The terminal device 110 shown.

[0046] In box 401, terminal device 110 provides a maximum model of user input received in the target application that is associated with the travel task.

[0047] Terminal device 110 can be used to receive user input for target application 120, and the user input corresponds to the travel task. Target application 120 can be a business travel booking application for enterprise users (ToB type, serving enterprise users) or a travel booking application for ordinary users (ToC type, serving ordinary users).

[0048] End user 140 can interact with digital assistant 122 to input travel requests in natural language, such as "Help me book a flight from city A to city B tomorrow, and I also need accommodation," etc. This user input includes specific travel information, including departure city, destination, travel time, and accommodation requirements. Terminal device 110 can use a large model to parse this user input and identify at least one travel request from end user 140, such as flight booking and hotel booking, etc.

[0049] In box 402, terminal device 110 obtains a target trip planning result matching the user input from a large model. The target trip planning result is determined from multiple candidate trip planning results based on the user's preference attributes corresponding to the user input. The multiple candidate trip planning results are generated at least based on the travel modes between each adjacent trip node. The trip node includes the trip start point, trip end point, and at least one intermediate node between the trip start point and trip end point, determined based on the user input.

[0050] Terminal device 110 uses a large model to determine multiple candidate trip planning results based on the input of terminal user 140. These multiple candidate trip planning results are generated based on the travel modes between adjacent trip nodes. A trip node includes a trip origin, a trip destination, and at least one intermediate node. For example, when terminal user 140 travels from city A to city B, the trip origin could be terminal user 140's home or workplace, the trip destination could be a hotel in city B, and intermediate nodes could include train stations, airports, and long-distance bus stations in city A, and train stations, airports, and long-distance bus stations in city B, etc.

[0051] Using a large model, terminal device 110 can combine different travel modes, pick-up and drop-off options, accommodation options, and other elements to generate multiple itinerary planning options. For example, the outbound journey may have multiple train or plane options, and the pick-up service may include taxis or ride-hailing services. By permuting and combining these possible elements, terminal device 110 can generate all itineraries. Among all itinerary planning options, at least one candidate itinerary planning result can be selected for each dimension based on multiple criteria such as highest cost-effectiveness, shortest travel time, and least virtual resource consumption. Virtual resources can include virtual currency, virtual points, etc.

[0052] Based on the preference attributes of end user 140, terminal device 110 can use a large model to filter out the target itinerary planning result from multiple candidate itinerary planning results. The preference attributes of end user 140 may include historical booking habits, common travel modes, accommodation preferences, budget constraints, etc. Terminal device 110 filters candidate itineraries according to these preference attributes and selects the itinerary planning result that best matches the needs of end user 140. For example, if end user 140 prefers a cost-effective option, terminal device 110 will prioritize a lower-priced itinerary option that also meets other requirements of end user 140 as the target itinerary planning result.

[0053] In box 403, terminal device 110 presents the target itinerary planning results. Terminal device 110 displays detailed information corresponding to the target itinerary planning results to end user 140 through interface 142. For example, the detailed information may include departure time, mode of transportation, accommodation arrangements, and corresponding costs, etc. End user 140 can view, confirm, or further modify the specific content of the itinerary plan through interface 142 to ensure that the recommended itinerary meets their needs.

[0054] Through the above process, terminal device 110 ensures that every aspect of the entire travel process for end user 140 is covered and considered by combining travel nodes and different modes of transportation. This one-stop planning avoids end user 140 repeatedly filtering and adjusting at different stages, greatly simplifying the planning process for complex trips.

[0055] The following details the method and process for determining candidate trip planning results. Terminal device 110, based on user input, uses a large model to determine multiple trip nodes. It then determines at least one mode of transportation between each adjacent trip node. By processing the trip planning option set, multiple candidate trip planning results are obtained. The trip planning option set is obtained by combining at least one mode of transportation between each adjacent trip node. For example, the large model can correspond to… Figure 1 and Figure 2 The target model is 155.

[0056] Typically, user input is a piece of natural language. For example, user input might be, "Help me arrange a business trip from city A to city B tomorrow; I need hotel and transportation arrangements." The big data model first parses this natural language, extracting key information such as "city A" as the departure point, "city B" as the destination, and "tomorrow" as the travel time. Next, based on the parsed information, the big data model automatically determines the various intermediate nodes in the itinerary. For example, the starting point could be the user's home or workplace, and the big data model can determine the corresponding intermediate nodes based on the context, such as "the airport in city A" or "the train station in city A." Similarly, for the destination "city B," the big data model will determine the corresponding intermediate nodes, such as "the airport in city B" or "the train station in city B."

[0057] Using a large model, terminal device 110 can determine at least one mode of transportation for each adjacent trip node. These modes of transportation can include trains, airplanes, long-distance buses, taxis, or ride-hailing services. The large model can match suitable transportation for each trip based on the needs of end user 140, the feasibility of transportation modes, and other factors.

[0058] Terminal device 110 generates a set of travel planning options by combining travel modes between these travel nodes. The set of travel planning options can include multiple travel planning options, each covering different combinations of transportation modes and routes, such as taking a train out of town (n1 train options), providing car pick-up and drop-off services (n2 vehicle types), and taking a plane back (n3 flight options). Subsequently, terminal device 110 can filter candidate travel planning results from the multiple travel planning options in the set of travel planning options based on different filtering dimensions. In this way, terminal device 110 can provide users with a variety of different travel plans for end user 140 to choose the most suitable travel plan.

[0059] As mentioned earlier, travel modes can include trains, airplanes, long-distance buses, taxis, or ride-hailing services. The following uses a given travel mode as an example to illustrate the process of determining the set of trip planning options. It's easy to understand that a given travel mode can be any one of these. Based on the transportation booking function corresponding to the given travel mode, multiple trip options are determined. The differences between these trip options can include at least one of the following: differences in departure time, differences in trip duration, and differences in virtual resource consumption. Combining the multiple trip options corresponding to each of at least one travel mode yields the set of trip planning options.

[0060] Taking airplane as an example, terminal device 110 can use the transportation (airplane) booking function to obtain multiple itinerary options related to airplane flights. Each itinerary option differs in departure time, flight duration, and fare. Taking train as another example, terminal device 110 can use the transportation (train) booking function to obtain itinerary options related to train services. For example, each itinerary option differs in departure time, travel time (such as the speed difference between high-speed rail and regular trains), and virtual resource consumption. Virtual resource consumption can include virtual currency consumption, virtual points consumption, etc. Terminal device 110 arranges and combines these itinerary options to generate multiple complete itinerary planning results. Candidate itinerary planning results can be selected from the complete itinerary planning results through different filtering dimensions.

[0061] Taking an example of adjacent travel nodes including 3 train travel options, 2 car pick-up travel options, 2 car drop-off travel options, and 3 flight travel options, 36 combinations can be obtained through these combinations. That is, the travel planning option set can include 36 travel planning options. Subsequently, the terminal device 110 can filter candidate travel planning results from the multiple travel planning options in the travel planning option set according to different filtering dimensions. For example, the candidate travel planning result with the lowest price, the candidate travel planning result with the highest cost-effectiveness, and so on.

[0062] In addition to travel modes between adjacent travel nodes, the accommodation requirements corresponding to the travel destination can also be included. Therefore, besides combining at least one travel mode between adjacent travel nodes to obtain a travel planning option set, a travel planning option set can also be obtained by combining accommodation options corresponding to the accommodation requirements.

[0063] In response to the user's input of an accommodation request corresponding to the destination of their trip, terminal device 110 determines at least one accommodation option corresponding to the accommodation request based on the accommodation booking function 220 that matches the request. Terminal device 110 combines multiple travel options corresponding to each of at least one mode of transportation with at least one accommodation option corresponding to the accommodation request to obtain a travel planning option set. Therefore, the travel planning options in the travel planning option set include not only the user's selected mode of transportation but also the corresponding accommodation arrangements.

[0064] Using the previous example, let's take a scenario where adjacent trip nodes include 3 train trip options, 2 car pick-up / drop-off trip options, 3 accommodation options, 2 car drop-off / drop-off trip options, and 3 flight trip options. With the addition of 3 accommodation options, this results in 108 possible combinations. In other words, the trip planning option set can include 108 trip planning options.

[0065] The following details how to determine multiple candidate itinerary planning results based on different screening dimensions. Terminal device 110 evaluates each itinerary planning option in the itinerary planning option set using multiple evaluation dimensions, obtaining at least one itinerary planning result corresponding to each evaluation dimension. Based on at least one itinerary planning result corresponding to each evaluation dimension, multiple candidate itinerary planning results are determined.

[0066] Figure 5 A schematic diagram 500 illustrates the process of determining candidate itinerary planning results according to some embodiments of the present disclosure. An accommodation option list 511 may correspond to multiple accommodation options. Similarly, a train schedule option list 512, a flight option list 513, and a ride-hailing option list 514 may each correspond to different itinerary options.

[0067] By permuting and combining all the trip options, a trip planning option set 520 is obtained. The terminal device 110 can use multiple evaluation dimensions to evaluate each trip planning option in the trip planning option set 520, and each evaluation dimension can correspond to at least one trip planning result.

[0068] Evaluation dimensions may include multiple factors, such as lowest price (531), best experience (532), and highest cost-effectiveness (533), etc. Each evaluation dimension can yield at least one trip planning result as a candidate trip planning result. Therefore, multiple evaluation dimensions can evaluate multiple candidate trip planning results (540).

[0069] Taking the "best experience" dimension as an example, the evaluation items could at least include accommodation (hotel) and surrounding services, whether the accommodation includes free breakfast, train journey length, train seating class, flight journey length, aircraft cabin class, transfer waiting time, number of transfers, ride-hailing (taxi) vehicle model, waiting time, etc. For each evaluation item, there would be preset evaluation criteria. For example, accommodation within 20 kilometers of a train station or airport could be considered the best experience, 20 to 40 kilometers could be considered average, and more than 40 kilometers could be considered a poor experience. Similarly, taking train journey length as an example again, less than 3 hours could be considered the best experience, 3 to 5 hours could be considered average, and more than 5 hours could be considered a poor experience.

[0070] By evaluating each assessment item, the terminal device 110 can obtain a corresponding score for each trip planning option. Finally, based on the scores, the terminal device 110 can select at least one trip planning result corresponding to the dimension with the best experience. This trip planning result can then be used as one of the candidate trip planning results.

[0071] Taking the dimension of highest cost-effectiveness as an example, the evaluation items can at least include accommodation (hotel) costs and facility quality, transportation fares and service quality, total trip time, number and duration of transfers, vehicle service fees and comfort, etc. For each evaluation item, pre-set evaluation criteria will also be used to ensure a balance of cost-effectiveness. For example, the evaluation of accommodation costs and facilities can be as follows: if the virtual resources consumed by the accommodation are below average, but the quality of the facilities provided is high (such as including free breakfast, free internet, free gym, etc.), it can be rated as high cost-effectiveness. If the virtual resources consumed by the accommodation are moderate and the services provided are commensurate with the price, it is rated as average cost-effectiveness. If the virtual resources consumed by the accommodation are high but the services are below expectations, it will be rated as poor cost-effectiveness. Similarly, the number of transfers and waiting time can also be used as cost-effectiveness evaluation criteria. For example, a trip with few transfers and short waiting times can effectively save time and is considered high cost-effectiveness. A trip with moderate number of transfers and waiting times is considered average cost-effectiveness. If the transfers are cumbersome and the waiting time is long, even if the price is low, it will be rated as poor cost-effectiveness.

[0072] Similar to the previous example, terminal device 110 can select at least one trip planning result corresponding to the dimension with the highest cost-effectiveness. This trip planning result can also be used as one of the candidate trip planning results.

[0073] In some embodiments of this disclosure, determining the target trip planning result from multiple candidate trip planning results includes: the terminal device 110 using a large model to determine the feature representation corresponding to each candidate trip planning result among the multiple candidate trip planning results. The target trip planning result is determined based on the degree of matching between the feature representation corresponding to the preference attributes of the terminal user 140 and the feature representation corresponding to each candidate trip planning result.

[0074] Terminal device 110 can utilize a large model to generate corresponding feature representations for each candidate trip planning result. These feature representations can indicate different dimensions of the candidate trip planning result, such as travel mode, time, accommodation options, price, comfort, etc. The feature representation of each candidate trip planning result is a description and abstraction of its overall characteristics.

[0075] On the other hand, terminal device 110 utilizes a large model to generate feature representations corresponding to the preference attributes of terminal user 140. These preference attributes may include terminal user 140's historical choices, frequently chosen modes of transportation, preferred accommodation types, and sensitivity to virtual resource consumption. By analyzing these preference attributes, terminal device 110 can generate a feature representation for terminal user 140 to describe terminal user 140's travel preferences and needs.

[0076] Terminal device 110 can calculate the matching degree between the feature representation corresponding to the preference attributes of terminal user 140 and the feature representation of each candidate trip planning result. Based on the matching degree calculation result, terminal device 110 can filter out the target trip planning result that matches the user's needs. The above process ensures that the final recommended target trip planning result can highly match the user's actual needs in multiple dimensions, achieving more personalized trip planning.

[0077] The above describes the process of determining candidate itinerary planning results based on travel modes between itinerary nodes. In addition, candidate itinerary planning results can also be determined based on the identity attribute information of the terminal user 140. For example, the terminal device 110 determines the itinerary booking criteria corresponding to the user's identity attribute information. Based on the itinerary booking criteria, multiple candidate itinerary planning results are determined.

[0078] Identity attribute information may include a user's job title, length of employment, department level, and so on. Different identity attribute information can have corresponding travel booking standards. For example, travel booking standards may restrict a user's choices in terms of transportation, accommodation standards, and dining options. For instance, for users with higher travel booking standards, the standards may allow them to choose higher-level transportation or hotels.

[0079] Based on travel booking standards, terminal device 110 can automatically adjust relevant parameters of transportation booking function 210 and accommodation booking function 220. These parameters may include virtual resource consumption range, hotel class, room type selection, and train or airplane seat class selection. For example, terminal device 110 can recommend accommodation options with higher virtual resource consumption and better room types, or business class on airplanes (first class on trains), to terminal users 140 with relatively high travel booking standards. For terminal users 140 with relatively low travel booking standards, it can recommend accommodation options with more economical virtual resource consumption but still meeting basic needs, or economy class on airplanes (second class on trains).

[0080] In this determination method, terminal device 110 can provide personalized itinerary planning results based on the identity attribute information of terminal user 140, ensuring that the itinerary arrangement meets both the user's needs and the company's internal resource allocation strategy.

[0081] In some embodiments of this disclosure, the target trip planning result may further include: in response to receiving a determination instruction on the target trip planning result, the terminal device 110 generates a corresponding trip booking request based on at least one trip booking function corresponding to the target trip planning result, wherein the at least one trip booking function includes a transportation booking function and an accommodation booking function.

[0082] In response to receiving confirmation from terminal user 140 regarding the target itinerary planning result, terminal device 110 generates a corresponding itinerary booking request based on the target itinerary planning result. The itinerary booking request can be a booking operation initiated by terminal device 110 for terminal user 140.

[0083] The transportation reservation function 210 can involve booking tickets such as train tickets and plane tickets, while the accommodation reservation function 220 is responsible for booking accommodations. For example, the terminal device 110 can invoke the transportation reservation function 210 to book tickets on the corresponding transportation reservation platform. Furthermore, the terminal device 110 can also invoke the accommodation reservation function 220 to book accommodations on the corresponding accommodation reservation platform. Through this process, the terminal device 110 can ensure that the transportation and accommodation arrangements of the terminal user 140 are smoothly executed, thereby completing the comprehensive reservation process for the entire trip.

[0084] In some embodiments of this disclosure, the target trip planning result may further include: the terminal device 110, in response to receiving a modification instruction for the target trip planning result, adjusting the target trip planning result based on the update instruction, and presenting the updated target trip planning result.

[0085] Terminal device 110 updates the original target itinerary planning results based on the specific modification requests of terminal user 140 (such as adjusting the mode of transportation, changing accommodation options, or changing the departure time) to ensure that the adjusted new target itinerary planning results can meet the user's change requirements.

[0086] After completing the itinerary adjustment, the terminal device 110 will display the new target itinerary planning result on the interface 142. The terminal device 110 will ensure that all changes are accurately reflected in the new target itinerary planning result and provide detailed information for the end user 140 to view or further confirm, ensuring the flexibility and adjustability of the entire itinerary.

[0087] Figure 6 A schematic structural block diagram of an interactive device 600 for trip planning according to some embodiments of the present disclosure is shown. Device 600 may be implemented in or included in terminal device 110, for example. Various modules / components in device 600 may be implemented by hardware, software, firmware, or any combination thereof.

[0088] As shown in the figure, device 600 includes a user input receiving module 601, configured to provide a large model of user input related to a travel task received in a target application. A target trip planning result determination module 602 is configured to obtain a target trip planning result matching the user input from the large model. Each target trip planning result is determined from multiple candidate trip planning results based on the user's determined preference attributes corresponding to the user input. These multiple candidate trip planning results are generated at least based on the travel modes between adjacent trip nodes. Trip nodes include a trip start point, a trip end point, and at least one intermediate node between the trip start point and the trip end point, determined based on the user input. A presentation module 603 is configured to present the target trip planning result.

[0089] In some embodiments of this disclosure, the target trip planning result determination module 602 can be configured to: determine multiple trip nodes based on user input; determine at least one mode of transportation corresponding to each adjacent trip node; and obtain multiple candidate trip planning results by processing a set of trip planning options, wherein the set of trip planning options is obtained by combining at least one mode of transportation corresponding to each adjacent trip node.

[0090] In some embodiments of this disclosure, the target trip planning result determination module 602 may be specifically configured to: for a given travel mode among at least one travel mode, determine multiple trip options corresponding to the given travel mode based on the transportation booking function corresponding to the given travel mode, wherein the differences between the multiple trip options include at least one of the following: departure time difference, trip duration difference, and virtual resource consumption difference. The multiple trip options corresponding to each of the at least one travel mode are combined to obtain a trip planning option set.

[0091] In some embodiments of this disclosure, the target itinerary planning result determination module 602 may further be specifically configured to: respond to a user input indicating accommodation needs corresponding to the itinerary endpoint, and determine at least one accommodation option corresponding to the itinerary endpoint based on the accommodation booking function corresponding to the accommodation needs. A set of itinerary planning options is obtained by combining multiple itinerary options corresponding to each of at least one mode of transportation and at least one accommodation option corresponding to the itinerary endpoint.

[0092] In some embodiments of this disclosure, the target itinerary planning result determination module 602 may be further configured to: evaluate each itinerary planning option in the itinerary planning option set using multiple evaluation dimensions, and obtain at least one itinerary planning result corresponding to each evaluation dimension. Based on the at least one itinerary planning result corresponding to each evaluation dimension, multiple candidate itinerary planning results are determined.

[0093] In some embodiments of this disclosure, the target trip planning result determination module 602 can be configured to: utilize a large model to determine the feature representation corresponding to each candidate trip planning result among multiple candidate trip planning results; and determine the target trip planning result based on the degree of matching between the feature representation corresponding to the user's preference attributes and the feature representation corresponding to each candidate trip planning result.

[0094] In some embodiments of this disclosure, the target itinerary planning result determination module 602 can be specifically configured to: determine the itinerary booking criteria corresponding to the user's identity attribute information based on the user's identity attribute information; and determine multiple candidate itinerary planning results based on the itinerary booking criteria.

[0095] In some embodiments of this disclosure, an interaction module is also included. The interaction module may be configured to: in response to receiving a determination instruction on the target itinerary planning result, generate a corresponding itinerary booking request based on at least one itinerary booking function corresponding to the target itinerary planning result, wherein the at least one itinerary booking function includes a transportation booking function and an accommodation booking function.

[0096] In some embodiments of this disclosure, the interaction module may also be configured to: adjust the target trip planning result based on the update instruction in response to receiving a modification instruction for the target trip planning result; and present the updated target trip planning result.

[0097] Figure 7 A block diagram of an electronic device 700 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that... Figure 7 The electronic device 700 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 7 The illustrated electronic device 700 may include or be implemented as Figure 1 The terminal device 110, or Figure 6 Device 600.

[0098] like Figure 7 As shown, electronic device 700 is in the form of a general-purpose electronic device. Components of electronic device 700 may include, but are not limited to, one or more processors or processing units 710, memory 720, storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. Processing unit 710 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 720. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 700.

[0099] Electronic device 700 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 720 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 730 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 700.

[0100] Electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 7 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 720 may include computer program product 725 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0101] The communication unit 740 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 700 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 700 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0102] Input device 750 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 760 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 700 can also communicate with one or more external devices (not shown) via communication unit 740 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 700, or with any device that enables electronic device 700 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0103] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0104] According to an exemplary implementation of this disclosure, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform... Figure 4 The methods provided are among the various optional methods available in the code, so they will not be elaborated upon here.

[0105] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0106] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0107] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0109] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An interactive method for trip planning, comprising: The system will provide a large-scale model of user inputs received in the target application that are associated with the travel task. The target trip planning result matching the user input is obtained from the large model. The target trip planning result is determined from multiple candidate trip planning results based on the user's preference attributes corresponding to the user input. The multiple candidate trip planning results are generated at least according to the travel mode between each adjacent trip node. The trip node includes the trip start point, trip end point and at least one intermediate node between the trip start point and the trip end point, which are determined based on the user input. as well as Present the results of the target itinerary planning.

2. The method of claim 1, wherein the plurality of candidate itinerary planning results are determined by means of: Based on the user input, multiple trip nodes are determined; Determine at least one mode of travel between each adjacent travel node in the plurality of travel nodes; as well as The multiple candidate trip planning results are determined by processing the set of trip planning options, wherein the set of trip planning options is obtained by combining at least one mode of travel corresponding to each adjacent trip node.

3. The method of claim 2, wherein the set of itinerary planning options is determined in the following manner: For a given mode of travel among the at least one mode of travel... Based on the transportation booking function corresponding to the given travel mode, multiple trip options corresponding to the given travel mode are determined. The differences between these multiple trip options include at least one of the following: differences in departure time, differences in trip duration, and differences in virtual resource consumption; and The trip planning option set is obtained by combining multiple trip options corresponding to each of the at least one travel mode.

4. The method of claim 3, wherein the set of itinerary planning options is determined in the following manner: In response to the user's input indicating accommodation needs corresponding to the trip's destination, at least one accommodation option corresponding to the accommodation needs is determined based on the accommodation booking function corresponding to the accommodation needs; The trip planning option set is obtained by combining multiple travel options corresponding to each of the at least one travel mode and at least one accommodation option corresponding to the accommodation requirement.

5. The method of claim 2, wherein determining the plurality of candidate itinerary planning results by processing the set of itinerary planning options comprises: Each itinerary planning option in the set of itinerary planning options is evaluated using multiple evaluation dimensions to obtain at least one itinerary planning result for each evaluation dimension. as well as Based on at least one itinerary planning result corresponding to each evaluation dimension, the multiple candidate itinerary planning results are determined.

6. The method of claim 1, wherein obtaining the target trip planning result matching the user input from the large model comprises: Using the large model, determine the feature representation corresponding to each candidate itinerary planning result among the multiple candidate itinerary planning results; as well as The target itinerary planning result is determined based on the degree of matching between the feature representation corresponding to the user's preference attributes and the feature representation corresponding to each candidate itinerary planning result.

7. The method of claim 1, wherein the plurality of candidate itinerary planning results are determined by: Based on the user's identity attribute information, determine the trip booking criteria corresponding to the identity attribute information; and Based on the aforementioned itinerary booking criteria, the results of the multiple candidate itinerary planning are determined.

8. The method according to claim 1, further comprising: In response to receiving a confirmation instruction regarding the target itinerary planning result, a corresponding itinerary booking request is generated based on the itinerary booking function corresponding to the target itinerary planning result. The itinerary booking function includes transportation booking and accommodation booking functions.

9. The method according to claim 1, further comprising: In response to receiving a modification instruction for the target itinerary planning result, the target itinerary planning result is adjusted based on the update instruction; as well as The updated target itinerary planning results are presented.

10. An interactive device for trip planning, comprising: The user input receiving module is configured to provide a large model of user input related to travel tasks received in the target application; The target trip planning result determination module is configured to obtain the target trip planning result matching the user input from the large model. The target trip planning result is determined from multiple candidate trip planning results based on the user's preference attributes corresponding to the user input. The multiple candidate trip planning results are generated at least according to the travel mode between each adjacent trip node. The trip node includes the trip start point, trip end point, and at least one intermediate node between the trip start point and the trip end point, which are determined based on the user input. as well as The presentation module is configured to present the results of the target trip planning.

11. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 9.

13. A computer program product comprising computer-executable instructions that, when executed by a processor, implement the method of any one of claims 1 to 9.

Images