Method, apparatus and program product for providing travel suggestion content

Abstract

One or more embodiments of the present specification provide a method, device and program product for providing travel suggestion content based on artificial intelligence. The method may comprise: providing a travel question and answer interface; receiving a first travel suggestion request constructed according to the content in the user input area; displaying travel suggestion information corresponding to the first travel suggestion request in the information display area; wherein the travel suggestion information of the first travel suggestion request comprises a specified travel object; the specified travel object corresponds to a selection control; under the condition that the selection control is triggered, filling a specified travel object corresponding to the triggered selection control into the user input area; receiving a second travel suggestion request constructed according to the content in the user input area; wherein the second travel suggestion request comprises the specified travel object; and displaying travel suggestion information corresponding to the second travel suggestion request in the information display area.

Description

Technical Field

[0001] One or more embodiments of this specification relate to the field of Internet technology, and more particularly, to a method, device, and program product for providing travel advice content. Background Art

[0002] Travel service systems can use AI (Artificial Intelligence) models to provide users with travel planning content.

[0003] In some cases, users may not be satisfied with the travel planning content provided by the AI model and want to make certain adjustments to the travel planning content.

[0004] However, in the existing technology, when adjusting the travel planning content provided by the AI model, the operation is cumbersome and the user experience is not good enough. Summary of the Invention

[0005] In view of this, one or more embodiments of this specification provide the following technical solutions:

[0006] According to a first aspect of one or more embodiments of the present specification, a method for providing travel advice content based on artificial intelligence is proposed, comprising: providing a travel question-and-answer interface having a user input area and an information display area; receiving a first travel advice request constructed based on the content in the user input area; displaying travel advice information corresponding to the first travel advice request in the information display area; wherein the travel advice information of the first travel advice request includes a specified itinerary object; the specified itinerary object corresponds to a selection control; the travel advice information of the first travel advice request is generated by calling an artificial intelligence model; when the selection control is triggered, the specified itinerary object corresponding to the triggered selection control is filled into the user input area; receiving a second travel advice request constructed based on the content in the user input area; wherein the second travel advice request includes the specified itinerary object; displaying travel advice information corresponding to the second travel advice request in the information display area; wherein the travel advice information of the second travel advice request is generated by calling the artificial intelligence model.

[0007] According to a second aspect of one or more embodiments of this specification, a computer program product is provided, comprising a computer program / instruction, which implements the steps of the method described in the first aspect when executed by a processor.

[0008] As can be seen from the above embodiments, multiple embodiments in this specification provide a selection control for a specified itinerary object in the travel suggestion information provided to the user. When the selection control is triggered by the user, the specified itinerary object is automatically filled in the user input area, thereby enabling the user to quickly build and submit a new travel suggestion request based on the specified itinerary object. This eliminates the need for the user to repeatedly manually enter or copy and paste the specified itinerary object, reducing operational complexity and improving the user's interactive experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 This is a schematic diagram of the architecture of a travel service system provided by an exemplary embodiment.

[0010] Figure 2 This is a flowchart of a method for providing travel suggestion content based on artificial intelligence provided by an exemplary embodiment.

[0011] Figure 3 It is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment.

[0012] Figure 4a 1 is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein the user input area is used to input the user's needs.

[0013] Figure 4b This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein, travel suggestion information corresponding to a first travel suggestion request is displayed in the information display area.

[0014] Figure 4c This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein the user input area is filled with a specified itinerary object.

[0015] Figure 4d This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein, the information display area displays travel suggestion information corresponding to the second travel suggestion request.

[0016] Figure 5a This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein an intention label display area is provided.

[0017] Figure 5b This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein the user input area is filled with a specified itinerary object and a travel intention label.

[0018] Figure 6 This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein the user input area includes multiple travel intention tags.

[0019] Figure 7a This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein, an operation intention label for a trip object for changing the planned time type is provided.

[0020] Figure 7b is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein Figure 7a The content in the user input area generates travel advice information corresponding to the travel advice request.

[0021] Figure 8a This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein, an operation intention label for a trip object of the cancel itinerary arrangement type is provided.

[0022] Figure 8b is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein Figure 8a The content in the user input area generates travel advice information corresponding to the travel advice request.

[0023] Figure 9a This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein a trip object operation intention label for replacing a trip object is provided.

[0024] Figure 9b is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein Figure 9a The content in the user input area generates travel advice information corresponding to the travel advice request.

[0025] Figure 10a This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein a recommendation intention label is provided.

[0026] Figure 10b is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein Figure 10a The content in the user input area generates travel advice information corresponding to the travel advice request.

[0027] Figure 11a This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein a planning intention label is provided.

[0028] Figure 11b is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein Figure 11a The content in the user input area generates travel advice information corresponding to the travel advice request.

[0029] Figure 12aThis is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein, travel intention labels generated based on the content in the information display area are provided.

[0030] Figure 12b is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein Figure 12a The travel intention label is regenerated after adding the specified itinerary object in the user input area.

[0031] Figure 13a This is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein a label changing control is provided.

[0032] Figure 13b is a schematic diagram of a travel question-and-answer interface provided by an exemplary embodiment; wherein Figure 13a The travel intent label is regenerated after the label change control is triggered.

[0033] Figure 14 It is a functional block diagram of a device provided by an exemplary embodiment.

[0034] Figure 15 An exemplary embodiment provides a device for providing travel advice content. DETAILED DESCRIPTION

[0035] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this manual are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0036] Travel services can provide various travel-related services, such as travel recommendations, travel consulting services, and / or the ability to order transportation tickets (such as air tickets, train tickets, boat tickets, bus tickets, etc.), hotels, and scenic spot tickets. Furthermore, travel services can also provide various travel-related peripheral services such as travel guide query / customization, travel blog publishing / viewing, and membership system management. Any service that has one or more of the above-mentioned service functions can be referred to as a travel service in the present invention.

[0037] Travel services can be deployed and implemented through travel service systems. Figure 1 This is a schematic diagram of the architecture of a travel service system provided by an exemplary embodiment. Figure 1As shown, the travel service system may include a server 21, a network 22, and several electronic devices, such as a PC (Personal Computer) 23, a mobile phone 24, and the like.

[0038] The server 21 may be a physical server including an independent host, or a virtual server hosted by a host cluster. During operation, the server 21 may run a server-side program of the travel service to realize the service end of the travel service, which may also be referred to as a corresponding travel service platform.

[0039] PC23 and mobile phone 24 are only some types of electronic devices that users can use. In fact, users can obviously also use electronic devices such as the following types: tablet devices, laptops, PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smart watches, etc.), etc., and one or more embodiments of this specification do not limit this. During operation, the electronic device can run the client-side program of the travel service to implement the client of the travel service. Among them, the client application of the above-mentioned travel service can be started and run on the electronic device. The client-side program can be a native application installed on the electronic device, or the client-side program can be a small program, a quick application or other similar forms. Of course, when using web page technologies such as HTML5 or similar, the relevant functions can be implemented through the page displayed by the browser. The browser here can be an independent browser application or a browser module embedded in certain applications.

[0040] Regarding the network 22 for interaction between electronic devices such as PC 23 and mobile phone 24 and server 21, communication can be achieved using a wired or wireless network based on the communication methods supported by the corresponding electronic devices, and this specification does not limit this. For example, if PC 23 supports both wired and wireless communication, communication can be achieved using either a wired or wireless network as needed, while mobile phone 24 generally only supports wireless communication and can therefore achieve communication using a wireless network.

[0041] The user can submit a travel suggestion request through the client of the travel service system. The server generates travel suggestion information based on the received travel suggestion request and provides the travel suggestion information to the client for the user to browse.

[0042] In the related art, users will use the travel service system to obtain travel advice information. Specifically, users can enter travel-related questions in the question-and-answer interface of the client, and the travel service system generates answers to the corresponding user questions through the AI model. For example, the user can operate the client to provide travel needs to the server, and the server will provide corresponding travel advice information through the AI model and provide it to the user through the client. If the user is not satisfied with part of the content in the travel advice information (such as a certain attraction or transportation option), it is necessary to manually operate the client, copy it to the user input area, and further enter the instruction text to instruct the AI model how to modify the travel advice information to obtain new travel advice information. Although this method can meet the most basic travel consultation needs, it requires multiple manual input operations, which makes the operation of modifying the travel advice information very cumbersome and the user experience is not good enough.

[0043] In summary, it is necessary to provide a method for providing travel suggestion content based on artificial intelligence to enhance the user's operating experience.

[0044] See also Figure 2 and Figure 3 In some embodiments, this specification provides a method for providing travel advice content based on artificial intelligence. The method for providing travel advice content can be applied to a travel service system, specifically to a client of the travel service system. Specifically, the method for providing travel advice content can include the following steps.

[0045] Step S110: providing a travel question-and-answer interface having a user input area and an information display area.

[0046] Step S120: receiving a first travel suggestion request constructed according to the content in the user input area.

[0047] Step S130: Displaying travel advice information corresponding to the first travel advice request in the information display area; wherein the travel advice information of the first travel advice request includes a specified itinerary object; the specified itinerary object corresponds to a selection control; the travel advice information of the first travel advice request is generated by calling an artificial intelligence model.

[0048] Step S140: when the selection control is triggered, the designated trip object corresponding to the triggered selection control is filled into the user input area.

[0049] Step S150: receiving a second travel suggestion request constructed according to the content in the user input area; wherein the second travel suggestion request includes the designated itinerary object.

[0050] Step S160: Displaying travel advice information corresponding to the second travel advice request in the information display area; wherein the travel advice information of the second travel advice request is generated by calling the artificial intelligence model.

[0051] In this implementation, the term "travel" can be used to describe travel activities involving a variety of travel purposes. For example, travel can include leisure and vacation trips, as well as various other travel needs with cross-regional itineraries, such as business trips, conferences, visits with friends and family, student migration, and medical referrals. Travel can include single-day tours, multi-day tours, local short trips, or cross-border long-distance trips. It can be independent travel, group tours, or multi-segment itineraries, providing a wide range of applications.

[0052] In this embodiment, travel advice information may refer to travel-related information that is provided as guidance or reference based on the specific travel needs or travel intentions proposed by the user after analysis and understanding. Travel advice information may include, but is not limited to: travel destination selection suggestions (such as destinations suitable for family trips, areas suitable for winter skiing), itinerary planning suggestions (such as the length of stay in each place, itinerary sequence, and attraction combinations), transportation selection suggestions (such as self-driving route recommendations, high-speed rail schedule recommendations, and flight information), accommodation recommendations (such as hotels, homestays, and campsites), food and dining suggestions (such as local specialty restaurant recommendations), travel activity recommendations (such as scenic spot tour routes, activities, or entertainment methods), and / or travel-related auxiliary tips (such as local weather conditions, local laws and regulations, and visa requirements). For example, if a user enters "What are the recommended ski resorts and hot spring hotels for skiing in Hokkaido during the Spring Festival?" in the user input area, the travel advice information may include ski resort information, recommended hotel information, and a combination of planning content such as attractions and transportation methods that meet the user's needs. Travel advice content may include, but is not limited to, travel advice information.

[0053] In this embodiment, the travel service system can provide a travel question-and-answer interface with a user input area and an information display area. The user input area can be used to receive natural language content actively input by the user or populated by the travel service system. For example, see Figure 4a , the user may enter "Recommend me a three-day, two-night itinerary suitable for traveling with children from Hangzhou during the May Day holiday." The information display area can be used to display travel suggestion information generated by the artificial intelligence model. Travel suggestion information is displayed in a structured or semi-structured natural language format. Figure 4b , such as "Day1: Hangzhou-Tokyo", "Day2: One-day tour of ancient temple culture", "Senso-ji Temple", etc.

[0054] In this embodiment, the travel service system may construct a first travel suggestion request based on the content in the user input area. The content in the user input area may include, but is not limited to, content manually entered by the user, such as via keyboard input, copy and paste, or voice input. In some embodiments, the content used to construct the first travel suggestion request may also include content automatically filled into the user input area by the travel service system after the user triggers a selection control in the travel Q&A interface.

[0055] In this embodiment, the travel service system can invoke an artificial intelligence model based on the first travel suggestion request. This artificial intelligence model, for example, can be a large language model, a sequence generation model with a travel knowledge enhancement module, or a multimodal AI model integrated with RAG (Retrieval Augmentation Generation) technology, to generate travel suggestion information corresponding to the first travel suggestion request.

[0056] In this embodiment, the information display area can be used to display travel advice information generated by the artificial intelligence model. The advice information includes one or more specified itinerary objects. A specified itinerary object can refer to a structured or semi-structured unit in the travel advice information that has independent semantic attributes and can be individually identified and operated by the user. Specified itinerary objects may include, but are not limited to: locations (such as "The Bund," "Tokyo Tower," "Sensō-ji Temple"), time information (such as "First Day Afternoon," "May 1st Morning," "3rd Day 10:00 AM"), activities (such as "Cruise," "Free Time," "Attend a Food Course"), transportation (such as "Take the High-Speed Rail to Nanjing," "Return by Subway from Nanjing Station"), accommodation arrangements (such as "Stay at Ginza Hotel," or dining arrangements (such as "Dinner Recommendation: Shinjuku Izakaya").

[0057] In this embodiment, at least some of the specified itinerary objects are associated with triggerable selection controls in the information display area. The number of specified itinerary objects associated with selection controls can be one or more. In some embodiments, a selection control can be provided for each specified itinerary object in the travel suggestion information. Alternatively, in some embodiments, a selection control can be provided for only some of the specified itinerary objects in the travel suggestion information.

[0058] In this embodiment, a selection control may refer to an interactive component within the travel Q&A interface that accepts user actions. When the selection control is triggered by the user, the specified itinerary object corresponding to the selection control may be automatically populated into the user input area as part of the next round of travel suggestion request. This population may be in the form of a plain text snippet. Of course, in some embodiments where a multimodal artificial intelligence model is used to generate travel suggestion information, the content entered into the user input area may not be limited to plain text but may also include images, audio, or video, etc., which will not be elaborated upon.

[0059] In some embodiments, the selection control can be an interactive component with an explicit feature so that the selection control can be clearly observed. For example, the selection control can be an icon corresponding to a specified trip object, such as Figure 4b , the designated itinerary object is automatically added to the user input area when the icon is triggered. In some embodiments, the designated itinerary object itself can also serve as a selection control, and can be made explicit by bolding the font, setting a background color, setting an underline, distinguishing the font color, etc. When the designated itinerary object itself is triggered, it is added to the user input area.

[0060] In some embodiments, the user can freely supplement and modify the content in the user input area based on the specified trip object entered in the user input area. For example, Figure 4c , the user triggers the selection control for the specified itinerary destination "Senso-ji Temple", fills in the user input area, and then manually enters "I prefer hiking" in the user input area.

[0061] In this embodiment, the travel service system can receive a second travel suggestion request constructed based on the content in the user input area. The second travel suggestion request includes the specified itinerary object entered in the user input area, causing the travel service system to call the artificial intelligence model again, generate a new round of travel suggestion information that matches the second travel suggestion request, and display the travel suggestion information in the information display area. For example, Figure 4d In the second travel suggestion request, the "Ancient Temple Cultural Day Tour" arrangement was cancelled and replaced with a "Mountain Hiking Day Tour", and "Senso-ji Temple" was replaced with "XX Mountain".

[0062] In various embodiments of the present specification, a selection control is provided for a specified itinerary object in the travel suggestion information provided to the user. When the selection control is triggered by the user, the specified itinerary object is automatically entered into the user input area, thereby enabling the user to conveniently construct and submit a new travel suggestion request based on the specified itinerary object. This eliminates the need for the user to repeatedly manually enter the specified itinerary object, reduces operational complexity, and enhances the user's interactive experience.

[0063] In some embodiments, the travel service system may provide a travel intention tag in the travel Q&A interface; wherein the travel intention tag is used to indicate travel needs; and when the travel intention tag is triggered, the travel intention tag is filled in the user input area.

[0064] In this embodiment, the travel service system can further provide travel intention tags in the travel question and answer interface to help users express their travel needs more efficiently. Figure 5a, there can also be an intention label display area in the travel Q&A interface.

[0065] In this specification, a travel intention tag can be a phrase or keyword tag used to express travel needs. Users do not need to enter a complete sentence by themselves, and can quickly complete the input of travel needs by simply triggering the corresponding travel intention tag. In this embodiment, the travel intention tag may include but is not limited to: tags related to itinerary adjustment, such as: "Change attractions", "Adjust tour time", "Increase free activities", "Streamline itinerary"; tags related to travel preferences, such as: "Suitable for parents and children", "Food first", "Suitable for taking pictures", "Cultural and historical recommendations"; tags related to transportation methods, such as: "High-speed rail first", "Direct flights", "Self-driving routes", "Convenient public transportation"; tags related to accommodation preferences, such as: "Close to the city center", "Highly rated hotels", "Suitable for families", "Economic accommodation".

[0066] In this embodiment, when the generated travel advice information is displayed in the information display area of the travel Q&A interface, several travel intention tags can be provided at the same time, so that the user can easily select the travel intention tag when reading the travel advice information. For example, when the "Oriental Pearl Tower" attraction is recommended in the travel advice system, travel intention tags such as "Check nearby food", "Recommendations for nearby attractions", "Adjust tour time", etc. can be provided at the same time. In some embodiments, the travel intention tag can be generated based on the context of the travel advice information, so that the travel intention tag has a good correlation with the content in the travel Q&A interface. In some embodiments, the travel intention tag can also be determined based on the content in the user input area, so that the travel intention tag can better match the user's needs. For example, the travel intention tag can be determined based on the specified itinerary object filled in the user input area. Of course, in some embodiments, the travel intention tag can be determined based on both the travel advice information and the content in the user input area.

[0067] In this embodiment, the user can trigger the travel intention tag in the travel question and answer interface. After the travel intention tag is triggered, the travel service system can automatically fill in the natural language expression or keyword phrase representing the travel intention tag into the user input area as part or all of the content for constructing the next round of travel suggestion request. For example, the travel suggestion information displayed in the information display area is: "Day 1: Arrive at the Oriental Pearl Tower in the morning and visit the Oriental Pearl Tower...", and the travel intention tag "Adjust tour time" is provided in the travel question and answer interface. The user can first trigger the selection control of "Oriental Pearl Tower", and then trigger the travel intention tag "Adjust tour time". The travel service system can automatically fill in "Oriental Pearl Tower" and "Adjust tour time" in the user input area, such as Figure 5b , users do not need to enter manually, which brings convenience to users.

[0068] In some embodiments, each travel intention tag can be used individually. For example, after a travel intention tag is entered into the user input area, the untriggered travel intention tags will be canceled in the travel Q&A interface. Of course, in some embodiments, travel intention tags can also be used in combination to form more complex and specific travel needs. For example, see Figure 6 , users can trigger a set of travel intention labels such as "suitable for parents and children", "cultural relics", and "day trip" in sequence.

[0069] In some embodiments, the travel intention tag includes a trip object operation intention tag; the travel demand expressed by the trip object operation intention tag includes: changing the planned time corresponding to the specified trip object; or canceling the trip arrangement for the specified trip object; or replacing the specified trip object; the second travel suggestion request may include the trip object operation intention tag, so that the travel suggestion information corresponding to the second travel suggestion request conforms to the travel demand expressed by the trip object operation intention tag.

[0070] In this embodiment, the travel intention label in the travel service system can be further refined into a travel object operation intention label to support users to perform direct and efficient operation expressions around the specified travel object.

[0071] In this embodiment, the itinerary object operation intention tag is a travel intention tag used to express the user's intention to edit, adjust, or replace a specific itinerary object. The itinerary object operation intention tag not only expresses the intention to modify the travel suggestion content but also specifies the method of modification, allowing the travel service system to generate travel suggestion information that better meets the user's intention.

[0072] In this embodiment, the itinerary object operation intention label may include but is not limited to the following operation types: change the planned time, which is used to express the adjustment of the time arrangement corresponding to the specified itinerary object. For example, the travel suggestion information includes "XX camping" and "hiking", and the user triggers the selection control of "XX camping" and selects the itinerary object operation intention "change to the next morning". Figure 7a and Figure 7b Cancel itinerary, used to express the desire to cancel a specific itinerary object in the travel suggestion information. For example, if the user selects the selection control corresponding to "XX Camping" in the travel Q&A interface and then selects the itinerary object operation intention label "Cancel Attractions", the "XX Camping" itinerary will be canceled in the newly generated travel suggestion information. Figure 8a and 8b; Replace itinerary object, used to express replacing the selected specified itinerary object with another itinerary object. For example, the user selects the selection control corresponding to "XX Camping" in the travel Q&A interface, and then selects the itinerary object operation intention label "Replace with XX Pedestrian Street". At this time, the regenerated travel suggestion information will replace "XX Camping" with "XX Pedestrian Street". Figure 9a and 9b .

[0073] In some embodiments, the travel intention tag includes a recommendation intention tag; the travel demand indicated by the recommendation intention tag includes: providing travel recommendation information that conforms to the travel recommendation intention expressed by the recommendation intention tag; the second travel recommendation request includes the recommendation intention tag, so that the travel recommendation information corresponding to the second travel recommendation request includes travel recommendation information that conforms to the travel recommendation intention expressed by the recommendation intention tag.

[0074] In this embodiment, the travel intention tag may include a recommendation intention tag, so that the user can conveniently express the need to obtain recommended information through the recommendation intention tag.

[0075] In this embodiment, the recommendation intention tag may refer to a travel intention tag used to express the desire to obtain recommendation information for specific travel content. The user can trigger the recommendation intention tag, and the travel service system will automatically fill in the triggered recommendation intention tag into the user input area, so that the generated travel suggestion information includes travel recommendation information that meets the travel recommendation intention expressed by the recommendation intention tag. In this embodiment, the recommendation intention tag may include but is not limited to: food recommendation intention tags, such as: "Recommend local specialty restaurants", "Night market snack recommendations", "Star restaurant recommendations"; attraction or activity recommendation intention tags, such as: "Recommendation of scenic spots suitable for taking photos", "Recommendation of nearby museums", "Alternative indoor attractions for rainy days"; shopping recommendation intention tags, such as: "Recommendation of popular shopping malls", "Recommendation of local souvenirs", "Recommendation of duty-free shops"; accommodation recommendation intention tags, such as: "Recommendation of high-rated hotels", "Recommendation of homestays", "Suitable for family accommodation", etc., which will not be repeated here.

[0076] In this embodiment, when the travel service system displays the travel suggestion information corresponding to the first travel suggestion request in the information display area, it can provide a recommendation intent tag in the travel Q&A interface for the user to select and use. For example, when the travel service system recommends the "TV Tower" attraction, the travel service system can provide a recommendation intent tag in the travel Q&A interface, such as "Specialty restaurants near the TV Tower" or "Recommended shopping spots near the TV Tower." Alternatively, when the information display area displays "Stay at XX Budget Hotel," the travel service system can provide a recommendation intent tag in the travel Q&A interface, such as "Recommended gourmet restaurants in the nearby area" or "Recommended souvenirs to buy in the surrounding area." When the user triggers a recommendation intent tag in the travel Q&A interface, the travel service system can automatically fill the corresponding recommendation intent tag content into the user input area. For example, when the user triggers the "Recommended specialty restaurants near Tokyo Tower" tag in the information display area, the travel service system can automatically fill the "Recommended specialty restaurants near Tokyo Tower" into the user input area, and the user can operate the user input area to generate a second travel suggestion request.

[0077] In this embodiment, after the travel service system receives the second travel suggestion request containing the recommendation intent tag, it can call the artificial intelligence model to generate travel suggestion information that matches the user's recommendation needs based on the second travel suggestion request, and present it to the user in the information display area. For example, after the user triggers the recommendation intent tag "special restaurants near the TV tower", the travel suggestion information displayed in the information display area may include: "Recommend the popular Sichuan restaurant XX and barbecue restaurant XX near the TV tower", for example Figure 10a and Figure 10b .

[0078] In some embodiments, the travel intention tag includes a planning intention tag; the travel demand indicated by the planning intention tag includes: providing travel recommendation information that meets the itinerary conditions expressed by the planning intention tag; wherein, the planning intention tag includes: a time planning tag indicating the itinerary duration, and / or a travel preference tag indicating travel preferences; the travel recommendation system can receive a third travel recommendation request constructed based on the content in the user input area; wherein, the third travel recommendation request includes the planning intention tag; and displaying travel recommendation information that meets the itinerary conditions expressed by the planning intention tag in the information display area.

[0079] In this embodiment, the travel intention tag may include a planning intention tag so that users can conveniently express their travel planning needs. The planning intention tag may be a tag used to express the user's travel intention for the overall itinerary plan. The user can trigger the planning intention tag to inform the travel service system of specific itinerary planning requirements.

[0080] In this embodiment, the planning intention tag may specifically include, but is not limited to: a time planning tag, which is used to express the time limit or time conditions of the trip, such as "three days and two nights", "Labor Day holiday", "two-day weekend", etc.; a travel preference tag, which is used to express the user's personal preferences, travel methods, or areas of interest when traveling, such as "suitable for family travel", "cultural theme route", or "economical route".

[0081] In this embodiment, when the travel service system displays the travel suggestion information corresponding to the first travel suggestion request in the information display area, it can provide the user with planning intention labels that match the travel suggestion information. For example, when the user views the travel suggestion information of "Hangzhou Travel Recommendation", time planning labels such as "one-day tour", "two-day tour", and "three-day tour" are provided near the information input area in the travel question and answer interface, as well as travel preference labels such as "cultural relics", "natural scenery", and "relaxed itinerary". Figure 11a and Figure 11b .

[0082] In this embodiment, a user can trigger a planning intent tag on the travel Q&A interface. The travel service system can automatically enter the content of the user-triggered planning intent tag into the user input area. When the user operates the user input area to generate a third travel suggestion request (e.g., clicks the "Send" control), the travel service system can invoke the artificial intelligence model to generate travel suggestion information corresponding to the third travel suggestion request. For example, if a user triggers the planning intent tags "three days, two nights" and "relaxed itinerary," the travel suggestion information in the third travel suggestion request may include the following: "On the first day, a leisurely morning visit of West Lake in Hangzhou, followed by an afternoon tea break... On the second day, moderate sightseeing... On the third day, the trip concludes at noon and returns to Shanghai."

[0083] In some embodiments, the travel service system can also dynamically adjust the displayed planning intention tags based on the user's past usage history of planning intention tags to better meet the user's personalized preferences. For example, if the system detects that the user frequently selects planning intention tags related to parenting, the system may automatically highlight or prioritize relevant planning intention tags such as "suitable for parent-child travel" and "parent-child education route" in subsequent travel suggestions, further enhancing the personalized level of travel planning.

[0084] In some embodiments, the travel Q&A interface provides a label change control; when the label change control is triggered, the travel service system can re-provide the travel intention label corresponding to the travel Q&A interface.

[0085] In this embodiment, the travel Q&A interface can further provide a label replacement control so that the user can actively trigger the update of the travel intention label. Specifically, the label replacement control can refer to an interactive component in the travel Q&A interface that is triggered by the user. By triggering the label replacement control, the user can actively instruct the travel service system to re-provide a more suitable travel intention label. In this embodiment, the label replacement control can adopt a display method similar to the travel intention label, that is, the label replacement control can be added to the intention label display area. For example, Figure 13a and Figure 13b , the label change control is "Change", the travel advice information provided in the information display area involves traveling with children, and the intention label display area provides travel intention labels such as "Recommend restaurants in the park" and "Adjust the order of play", and the label change control is "Change". When the label change control "Change" is triggered, the travel intention labels in the intention label display area are replaced with travel intention labels such as "Parent-child interactive project recommendation" and "Parent-child theme restaurant recommendation" that are more in line with the user's current needs. Of course, the label change control is not limited to a display method similar to the travel intention label. The label change control can also be displayed in other suitable areas of the travel Q&A interface, such as setting the label change control in the user input area.

[0086] In some embodiments, the tag change control may also support multiple triggers by the user, so that the user can try and browse different travel intent tag combinations multiple times until finding the intent tag that best suits the needs.

[0087] In various embodiments provided herein, users can access travel recommendations tailored to their travel needs within a travel Q&A interface. While browsing these recommendations, users may find themselves dissatisfied with some of the itineraries and wish to make adjustments, such as adjusting the schedule for a particular attraction. In this case, the user can conveniently trigger a selection control within the travel Q&A interface to automatically populate the user input area with the specified itinerary, eliminating the need for the user to manually enter content into the user input area. The user can then further specify their desired operations for the specified itinerary in the user input area.

[0088] However, in some cases, there are differences in language expression ability between different users, so that when inputting operation requirements into the user input area, the input content of different users may also be different, and the resulting adjustment results are also different. Furthermore, although it is convenient to input the specified itinerary object by setting the selection control corresponding to the specified itinerary object, it is still difficult for some users to quickly adjust the travel suggestion information to the desired result. Furthermore, it is also a relatively cumbersome operation for the user to manually input the operation requirements into the user input area. The embodiment of this specification further provides a travel intention tag. The user can trigger the travel intention tag to automatically fill in the travel intention tag into the user input area. The user does not need to think about how to express his or her needs, which brings convenience to the user. Furthermore, after the travel intention tag is filled into the user input area, the travel suggestion request generated based on the content in the user input area can more accurately express the user's travel needs, and thus can more accurately provide the user with travel suggestion information that meets the expectations.

[0089] Furthermore, in various embodiments of this specification, the provided travel intent tags can dynamically adapt to the content within the travel Q&A interface, ensuring that the travel intent tags provided to the user within the travel Q&A interface are more aligned with the user's needs and more accurately match the content they desire. For example, if a user selects a designated itinerary object representing a scenic spot, a travel intent tag can be provided within the travel Q&A interface to match the user's desired action for the designated itinerary object. Furthermore, after the user triggers the itinerary object action intent tag, expressing their explicit action request, a recommendation intent tag can be provided. By triggering the recommendation intent tag, the user can automatically populate the user input area with the recommendation intent tag. The travel recommendation request generated based on the content within the user input area can accurately express the action for the designated itinerary object and the need for further recommendations. This allows the travel recommendation information provided to the user to not only meet the user's action request for the designated itinerary object but also include the recommended information they desire. As can be seen, in various embodiments provided herein, by providing a selection control for designated itinerary objects and providing travel intent tags, a highly user-friendly experience is provided.

[0090] In some embodiments, the travel service system may, in response to a specified itinerary object being filled in the user input area, display a itinerary object operation intention label corresponding to the specified itinerary object in the travel Q&A interface; and / or, in response to a specified itinerary object and a itinerary object operation intention label being filled in the user input area, display a recommended intention label corresponding to the filled-in specified itinerary object and itinerary object operation intention label in the travel Q&A interface.

[0091] In this embodiment, the travel service system can dynamically display appropriate itinerary object operation intention labels and recommended intention labels in the travel Q&A interface based on the content entered in the user input area. In this embodiment, the travel service system can pre-establish a correspondence between itinerary objects and itinerary object operation intention labels. In this way, when a specified itinerary object is entered in the user input area, the itinerary object operation intention label corresponding to the specified itinerary object can be displayed in the travel Q&A interface based on the aforementioned correspondence. In some embodiments, the travel service system can also pre-establish itinerary objects and itinerary object operation intention labels as a combination, and further corresponding recommended intention labels. When a combination of a specified itinerary object and a itinerary object operation intention label appears in the user input area, a corresponding recommended intention label is provided in the travel Q&A interface.

[0092] For example, the travel service system assigns action intent labels such as "Adjust Tour Time" and "Cancel Trip" to the specified itinerary object "Forbidden City, Beijing." Assuming the travel suggestion displayed in the information display area is "Visit the Forbidden City, Beijing in the morning and the Temple of Heaven Park in the afternoon on the first day," and the user triggers the selection control corresponding to "Forbidden City, Beijing," "Forbidden City, Beijing" is entered into the user input area. The travel service system can then immediately display action intent labels corresponding to "Forbidden City, Beijing" in the travel Q&A interface, such as "Adjust Tour Time" and "Cancel Trip." At this point, the user might trigger the action intent label "Cancel Trip," and the travel service system will then enter the action intent label "Cancel Trip" into the user input area. Assuming the travel service system assigns the recommendation intent labels "Recommend Museums Suitable for Families" and "Recommend Nearby Cultural Attractions" to the combination of "Forbidden City, Beijing" and "Cancel Trip," the recommendation intent labels "Recommend Museums Suitable for Families" and "Recommend Nearby Cultural Attractions" can be displayed in the travel Q&A interface to facilitate the user's expression of their travel intentions.

[0093] In some embodiments, when a user is in the travel Q&A interface, they first trigger a selection control for a specific itinerary object, thereby entering the specified itinerary object into the user input area. At this point, a trip object action intention label corresponding to the specified itinerary object is provided in the travel Q&A interface to provide the user with appropriate action suggestions. Furthermore, after a user triggers a trip object action intention label, the specified itinerary object and the trip object action intention label can be combined to provide a corresponding recommended action intention label. That is, after a user selects a specific itinerary object and the trip object action intention label, it can be assumed that the user needs to make certain adjustments to the specified itinerary object in the travel recommendation information. The trip object action intention label can more accurately represent the user's adjustment needs. Furthermore, based on this combination, a recommended action intention label can be provided to provide recommendations to the user. After a user triggers a recommended action intention label, the recommended action intention label is entered into the user input area. This allows the travel recommendation request generated based on the content in the user input area to more conveniently and accurately instruct the artificial intelligence model to generate travel recommendation information that meets the user's needs.

[0094] In some embodiments, the travel service system can call the intention prediction model based on the content in the travel Q&A interface to obtain a travel intention label corresponding to the travel Q&A interface; when a specified change occurs to the content in the user input area, the intention prediction model is called based on the content after the specified change in the user input area to obtain an updated travel intention label; wherein, the specified change includes the user input area being added to a specified itinerary object, or being added to a travel intention label, or the input content in the user input area includes specified keywords.

[0095] In this embodiment, the travel service system can also realize the automatic dynamic update of the travel intention label in the travel question and answer interface by calling the intention prediction model. In this embodiment, the intention prediction model can be an analysis model built based on artificial intelligence technology, which can be used to predict the user's possible travel demand intentions and generate travel intention labels. The intention prediction model can be a pre-trained deep learning model, such as a large language model with a Transformer structure, or it can be an integrated model that combines RAG (retrieval enhanced generation) technology, historical user behavior analysis or other machine learning algorithms to ensure that the generated intent labels can be closely integrated with the current display content and user demand scenarios. In some embodiments, in order to improve the response speed of the intention prediction model, a small-scale model base can be selected for training to obtain the intention prediction model.

[0096] In some embodiments, the specified changes may include but are not limited to the user input area being added to a specified itinerary object, or being added to a travel intention label, or the input content in the user input area including specified keywords. For example, when the information display area displays "Arrived at the Oriental Pearl Tower for a tour of the Oriental Pearl Tower on the morning of the first day...", the intention prediction model may automatically generate travel intention labels such as "Add restaurant recommendations", "Change afternoon itinerary" and other travel intention labels based on the content in the information display area. After the user triggers the selection control of "Oriental Pearl Tower" and fills in "Oriental Pearl Tower" in the user input area, the intention prediction model is called to regenerate the travel intention label. At this time, the travel intention labels "Cancel attractions", "Change time arrangements" and "Recommend nearby food" are displayed on the travel Q&A interface, such as Figure 12a and Figure 12b To better suit the needs of users. Of course, further, the user may further trigger the travel intention label "change time schedule", at which time the travel intention label "change time schedule" will be filled in the user input area. As the content of the user input area increases with the travel intention label, the intention prediction model can be called again to regenerate the travel intention label.

[0097] In some cases, the user may input content through the keyboard in the user input area. At this time, the content input by the user can be recognized, and when the specified keyword is recognized, the intention prediction model can be called to regenerate the travel intention label based on the content in the user input area. In this embodiment, the specified keyword can be a pre-set vocabulary. The user manually inputs in the user input area: "Recommend parent-child attractions around Tokyo Tower." The travel service system recognizes that the input content contains the pre-set specified keyword "parent-child attractions". The travel service system can automatically call the intention prediction model and regenerate a more suitable travel intention label based on the user input content. At this time, the travel intention labels updated and displayed in the intention label display area may include: "Recommendations for parent-child activities near Tokyo Tower", "Attractions suitable for children near Tokyo Tower" or "Recommendations for parent-child theme pavilions or interactive projects" and so on.

[0098] In some embodiments, the travel service system may first invoke an intent prediction model based on the travel advice information displayed in the information display area of the travel Q&A interface. The intent analysis model analyzes semantic information and travel characteristics to generate an appropriate travel intention label. Of course, in some embodiments, the intent prediction model may also be invoked to generate a travel intention label based on the travel advice information displayed in the information display area and the content in the user input area. Furthermore, the user may interact with the travel Q&A interface to change the content in the user input area. When the content in the user input area changes as a result of a user operation, the travel service system may re-invoke the intent prediction model using only the changed content in the user input area to generate and update the travel intention label. Of course, the travel service system may also invoke the intent prediction model based on both the changed content in the information display area and the travel advice information in the information display area to generate and update the travel intention label in the travel Q&A interface. This allows the travel intention label in the travel Q&A interface to be more tailored to the user's needs.

[0099] In some embodiments, the travel advice information includes a structured entity, which is obtained by structured identification of the travel advice information of the first travel advice request; wherein, at least part of the structured entity expressing time and / or place is used as the designated itinerary object, and a selection control with explicit features is set corresponding to the designated itinerary object in the travel Q&A interface.

[0100] In this embodiment, structured entities may refer to core elements with independent semantic attributes within travel advice information. Natural language processing algorithms or structured recognition modules can be used to parse travel advice information and extract entity units with clear semantic labels as structured entities. These structured entities may include, but are not limited to, travel-related elements such as location, time, activities, transportation arrangements, accommodation information, and restaurant recommendations.

[0101] In this embodiment, the travel service system can use the AI model to generate travel recommendations and, in conjunction with the entity recognition module, perform structured processing on the generated results to obtain a structured entity set. For example, if the AI model generates the sentence "After arriving in Kyoto on the morning of the first day, we will visit Fushimi Inari Taisha Shrine," the AI model can identify the location entity "Fushimi Inari Taisha Shrine," the time entity "first morning," and the activity entity "visit." It can then specify "Fushimi Inari Taisha Shrine" and "first morning" as specific itinerary items, with corresponding selection controls configured.

[0102] In some embodiments, the travel service system may receive a reference travel suggestion access address input in the user input area; wherein the reference travel suggestion access address is used to access resources expressing the reference travel suggestion; and generate travel suggestion information in combination with the resources corresponding to the reference travel suggestion access address.

[0103] In this embodiment, the travel service system may further support users entering a reference travel suggestion access address in the user input area so that travel suggestion information can be generated by integrating external resources. In this embodiment, the reference travel suggestion access address may be any one or more of the following reference travel suggestion access addresses. For example, an address identifier for accessing an external resource, such as a web link (URL), a resource URI, or a redirect address within a specific application. The resources corresponding to the reference travel suggestion access address typically include, but are not limited to, travel websites, travel blogs, travel guide posts on social media, travel e-books, or travel guide app pages.

[0104] In some embodiments, users can enter recommended travel addresses into the user input area of the travel Q&A interface by manually entering, copying and pasting, or directly sharing through a third-party application. For example, if a user sees a travel route of interest on another website or application, they can directly enter or paste the URL of the route page into the user input area to more conveniently express their specific travel needs.

[0105] Figure 14 It is a schematic structural diagram of a device provided by an exemplary embodiment. Please refer to Figure 10. At the hardware level, the device includes a processor 1002, an internal bus 1004, a network interface 1006, a memory 1008 and a non-volatile memory 1010. Of course, it may also include hardware required for other functions. One or more embodiments of this specification can be implemented based on software, such as the processor 1002 reading the corresponding computer program from the non-volatile memory 1010 into the memory 1008 and then running it. Of course, in addition to software implementation, one or more embodiments of this specification do not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0106] Please refer to Figure 15 The travel suggestion content providing device provided in this embodiment can be applied to Figure 14 The device shown in the figure is used to implement the technical solution of this specification. The device for providing travel suggestion content may include: an interface providing module, a first receiving module, a first suggestion display module, an input module, a second receiving module and a second suggestion display module.

[0107] The interface providing module is used to provide a travel question-and-answer interface with a user input area and an information display area.

[0108] The first receiving module is configured to receive a first travel suggestion request constructed according to the content in the user input area.

[0109] A first suggestion display module is configured to display travel suggestion information corresponding to the first travel suggestion request in the information display area; wherein the travel suggestion information of the first travel suggestion request includes a specified itinerary object; the specified itinerary object corresponds to a selection control; and the travel suggestion information of the first travel suggestion request is generated by calling an artificial intelligence model.

[0110] The input module is used to fill the specified travel object corresponding to the triggered selection control into the user input area when the selection control is triggered.

[0111] The second receiving module is configured to receive a second travel suggestion request constructed according to the content in the user input area; wherein the second travel suggestion request includes the designated itinerary object.

[0112] A second suggestion display module is used to display travel suggestion information corresponding to the second travel suggestion request in the information display area; wherein the travel suggestion information of the second travel suggestion request is generated by calling the artificial intelligence model.

[0113] Based on the same concept as the above method, this specification also provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor implements the steps of the method described in any of the above embodiments by running the executable instructions.

[0114] Based on the same concept as the above method, this specification also provides a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0115] Based on the same concept as the above method, this specification also provides a computer program product, including a computer program / instruction, which implements the steps of the method described in any of the above embodiments when executed by a processor.

Claims

1. A method for providing travel advice content based on artificial intelligence, characterized in that: include: Provide a travel question-and-answer interface with a user input area and an information display area; receiving a first travel suggestion request constructed based on the content in the user input area; Displaying travel advice information corresponding to the first travel advice request in the information display area; wherein the travel advice information of the first travel advice request includes a specified itinerary object; the specified itinerary object corresponds to a selection control; and the travel advice information of the first travel advice request is generated by calling an artificial intelligence model; When the selection control is triggered, the specified trip object corresponding to the triggered selection control is filled into the user input area; receiving a second travel suggestion request constructed according to the content in the user input area; wherein the second travel suggestion request includes the designated itinerary object; Travel advice information corresponding to the second travel advice request is displayed in the information display area; wherein the travel advice information of the second travel advice request is generated by calling the artificial intelligence model.

2. The method according to claim 1, characterized in that Also includes: Providing a travel intention tag on the travel question-and-answer interface; wherein the travel intention tag is used to indicate travel needs; When the travel intention tag is triggered, the travel intention tag is filled into the user input area.

3. The method according to claim 2, characterized in that The travel intention tag includes a trip object operation intention tag; the travel demand expressed by the trip object operation intention tag includes: changing the planned time corresponding to the specified trip object; or canceling the travel arrangement for the specified trip object; or replacing the specified trip object; in the step of receiving a second travel suggestion request constructed based on the content in the user input area, the second travel suggestion request includes the trip object operation intention tag, so that the travel suggestion information corresponding to the second travel suggestion request meets the travel demand expressed by the trip object operation intention tag; And / or, the travel intention tag includes a recommendation intention tag; the travel demand indicated by the recommendation intention tag includes: providing travel recommendation information that meets the travel recommendation intention expressed by the recommendation intention tag; in the step of receiving a second travel recommendation request constructed according to the content in the user input area, the second travel recommendation request includes the recommendation intention tag, so that the travel recommendation information corresponding to the second travel recommendation request includes travel recommendation information that meets the travel recommendation intention expressed by the recommendation intention tag; And / or, the travel intention tag includes a planning intention tag; the travel demand indicated by the planning intention tag includes: providing travel suggestion information that meets the itinerary conditions expressed by the planning intention tag; wherein, the planning intention tag includes: a time planning tag indicating the itinerary duration, and / or, a travel preference tag indicating travel preferences; the method further includes: receiving a third travel suggestion request constructed based on the content in the user input area; wherein, the third travel suggestion request includes the planning intention tag; and displaying the travel suggestion information that meets the itinerary conditions expressed by the planning intention tag in the information display area.

4. The method according to claim 2, characterized in that The travel Q&A interface provides a label change control; the method further includes: When the label change control is triggered, the travel intention label corresponding to the travel question and answer interface is re-provided.

5. The method according to claim 3, characterized in that The method further comprises: In response to the user inputting a specified itinerary object into the input area, displaying a itinerary object operation intention label corresponding to the specified itinerary object in the travel question-and-answer interface; and / or, In response to the user inputting a designated itinerary object and a itinerary object operation intention label, a recommended intention label corresponding to the designated itinerary object and itinerary object operation intention label is displayed in the travel question-and-answer interface.

6. The method according to claim 2, characterized in that The illustrated method further includes: Based on the content in the travel Q&A interface, calling the intention prediction model to obtain a travel intention label corresponding to the travel Q&A interface; In the event that a specified change occurs to the content in the user input area, the intention prediction model is called based on the changed content in the user input area to obtain an updated travel intention label; wherein the specified change includes the user input area being added to a specified itinerary object, or being added to a travel intention label, or the input content in the user input area including specified keywords.

7. The method according to claim 1, characterized in that The travel advice information includes a structured entity, and the structured entity is obtained by performing structured identification on the travel advice information of the first travel advice request; Among them, at least part of the structured entity expressing time and / or place is used as the designated itinerary object, and a selection control with explicit features is set corresponding to the designated itinerary object in the travel question-and-answer interface.

8. The method according to claim 1, characterized in that The method further comprises: receiving a reference travel suggestion access address input in the user input area; wherein the reference travel suggestion access address is used to access a resource expressing the reference travel suggestion; Travel suggestion information is generated by combining the resources corresponding to the reference travel suggestion access address.

9. A computer device, characterized in that: The computer device includes a memory and a processor, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the method according to any one of claims 1 to 8.

10. A computer program product, characterized in that The method comprises computer instructions for implementing the method according to any one of claims 1 to 8.

Images