Travel search display interaction method and related equipment

Abstract

The invention relates to the technical field of computers, and provides a travel search display interaction method and related equipment. The travel search display interaction method comprises the following steps: in response to a travel search request, generating answer data based on a generative artificial intelligence model and a retrieval enhancement generation model; wherein the answer data comprises AI summary data and travel product data; and outputting the AI summary data in a streaming manner in a first module of the page, and displaying the travel product data in a waterfall flow manner in a second module of the page. According to the method, the retrieval and generation capability of the retrieval enhancement generation model and the intention analysis and data integration capability of the generation type artificial intelligence model are utilized, so that natural language input and complex query intention of a user are accurately understood, a comprehensive and accurate search result is obtained, and answer data is accurately matched with a travel search request; in addition, dual modes of outputting AI summary data in a stream mode and displaying travel product data in a waterfall stream mode are combined, and browsing requirements of different users are met.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and more particularly, to a travel search display interaction method and related devices. Background Art

[0002] In the search scenario of travel applications, when users search for long-tail keywords such as route play, scenic spot recommendations, and information inquiries, they often face the following problems:

[0003] Inaccurate intent recognition: Traditional keyword matching methods are difficult to deeply understand the natural language input of users, resulting in search results that cannot accurately meet the search needs of users.

[0004] Insufficient result recall: The existing technology has a limited coverage of long-tail query terms. When users search, they often face the situation of empty results or irrelevant recommended content, and need to repeatedly adjust the search terms, which affects the user experience.

[0005] Fragmented information: Traditional search results are scattered. All in-site search results are recalled according to keywords. Users need to integrate and analyze multi-source information by themselves, and the time cost and operation burden of obtaining effective content are relatively high.

[0006] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present invention, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] In view of this, the present invention provides a travel search display interaction method and related devices, which can effectively solve the problems of inaccurate intent recognition, insufficient result recall, and fragmented information in the existing search methods.

[0008] According to one aspect of the present invention, there is provided a travel search display interaction method, including: in response to a travel search request, generating answer data based on a generative artificial intelligence model and a retrieval-augmented generation model; wherein, the answer data includes AI summary data and travel product data; streaming outputting the AI summary data in a first module of the page, and presenting the travel product data in a waterfall flow in a second module of the page.

[0009] In some embodiments, the generating answer data based on a generative artificial intelligence model and a retrieval-augmented generation model includes: based on the retrieval-augmented generation model, retrieving associated matching content according to the travel search request, the associated matching content including user-generated content and professionally-generated content; based on the generative artificial intelligence model, analyzing the user intent according to the travel search request and the associated matching content, and integrating the associated matching content according to the user intent to generate the answer data.

[0010] In some embodiments, the AI summary data includes: recommended travel product information associated and matched with the travel search request; recommended user-generated content associated and matched with the travel search request; wherein, the recommended travel product information and the recommended user-generated content include multimodal data, and the multimodal data includes text, pictures, and maps; recommended questions associated and matched with the travel search request.

[0011] In some embodiments, during the process of streaming and outputting the AI summary data in the first module of the page: in response to a screen pressing operation, the front end displays a hover animation and the back end continues to stream and output the AI summary data; in response to the release of the screen pressing operation, the front end displays the already output AI summary data and continues to stream and output the remaining AI summary data.

[0012] In some embodiments, during the process of streaming and outputting the AI summary data in the first module of the page: in response to the operation of sliding the page to the second module, the front end pins the first module to the top, and displays a generating prompt and a return interaction button in the pinned area, and the back end continues to stream and output the AI summary data.

[0013] In some embodiments, after the streaming and outputting of the AI summary data in the first module of the page is completed: in response to the operation of sliding the page to the second module, the first module is pinned to the top, and a completed prompt and a return interaction button are displayed in the pinned area.

[0014] In some embodiments, when the travel product data is displayed in a waterfall flow in the second module of the page, a filtering layer is displayed at the top of the second module, and the method further includes: in response to a sliding browsing operation on the second module, hiding the filtering layer; in response to a back-sliding operation of the second module, displaying the filtering layer at the top of the second module.

[0015] According to another aspect of the present invention, there is provided a travel search display interaction device, including: a search request response module, configured to respond to a travel search request, and generate answer data based on a generative artificial intelligence model and a retrieval augmented generation model; wherein, the answer data includes AI summary data and travel product data; an answer data display module, configured to stream and output the AI summary data in the first module of the page, and display the travel product data in a waterfall flow in the second module of the page.

[0016] According to another aspect of the present invention, there is provided an electronic device, including: a processor; a memory, in which executable instructions are stored; wherein, when the executable instructions are executed by the processor, the travel search display interaction method described in any of the above embodiments is implemented.

[0017] According to another aspect of the present invention, there is provided a computer-readable storage medium for storing a program, which when executed by a processor implements the travel search display interaction method described in any of the above embodiments.

[0018] According to another aspect of the present invention, there is provided a computer program product including a computer program, which when executed by a processor implements the travel search display interaction method described in any of the above embodiments.

[0019] The beneficial effects of the present invention compared with the prior art at least include:

[0020] In the travel information search and planning scenario, the present invention uses generative artificial intelligence (AI) technology and retrieval-augmented generation (RAG) technology. By leveraging the retrieval and generation capabilities of the RAG technology and the intent analysis and data integration capabilities of the AI technology, it accurately understands the natural language input and complex query intents of users, obtains comprehensive and accurate search results, enables the answer data to precisely match the travel search requests, and provides users with efficient, comprehensive, and personalized travel information recommendation and planning services, etc., effectively solving the problems of inaccurate intent recognition, insufficient result recall, and information fragmentation in existing search methods.

[0021] In addition, based on a dual-mode browsing design, the present invention combines the streaming output of AI summary data and the waterfall flow display of travel product data. Users can choose to browse the AI summary data in a streaming manner or make the streaming-generated part stick to the top by swiping up to focus on browsing the travel product data, ensuring that different user browsing needs are met.

[0022] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present invention and used together with the specification to explain the principles of the present invention. Obviously, the following-described accompanying drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other accompanying drawings based on these drawings without creative efforts.

[0024] Figure 1 A schematic diagram showing the steps of the travel search display interaction method in an embodiment of the present invention;

[0025] Figure 2 A schematic diagram showing the page of inputting a travel search request in an embodiment of the present invention;

[0026] Figure 3 A schematic diagram showing the page of outputting answer data in an embodiment of the present invention;

[0027] Figure 4 Schematic diagram of the page where the first module is pinned to the ceiling during the process of streaming output of AI summary data in an embodiment of the present invention;

[0028] Figure 5 Schematic diagram of the page where the first module is pinned to the ceiling after the generation of AI summary data is completed in an embodiment of the present invention;

[0029] Figure 6 Schematic diagram of the page where the second module slides back to display the screening layer in an embodiment of the present invention;

[0030] Figure 7 Schematic diagram of the modules of a travel search display interaction device in an embodiment of the present invention;

[0031] Figure 8 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. Detailed implementation manners

[0032] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments described herein. On the contrary, these embodiments are provided to make the present invention more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art.

[0033] The accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0034] In addition, the processes shown in the accompanying drawings are only exemplary illustrations and do not necessarily include all steps. For example, some steps can be decomposed, some steps can be combined or partially combined, and the actual execution order may be changed according to the actual situation. The terms "first", "second" and similar terms used in the specific description do not denote any order, quantity or importance, but are only used to distinguish different components.

[0035] It should be noted that, without conflict, the features in the embodiments of the present invention and those in different embodiments can be combined with each other.

[0036] Figure 1 Schematically shows the main steps of a travel search display interaction method, referring to Figure 1As shown in the figure, the travel search display interaction method provided by the embodiments of the present invention includes:

[0037] S110, in response to a travel search request, generate answer data based on a generative artificial intelligence model and a retrieval-augmented generation model; wherein, the answer data includes AI summary data and travel product data;

[0038] S120, stream output the AI summary data in the first module of the page, and display the travel product data in a waterfall flow in the second module of the page.

[0039] The travel search display interaction method of the present invention can be executed by a server of a travel service platform such as an online travel agency. The travel search request includes various travel-related search requests such as searching for travel products such as hotels and attractions, searching for route play methods, and travel inquiries.

[0040] The generative artificial intelligence (AI) technology can not only process and analyze data, but also learn the distribution of data, and generate new content with logic and coherence according to the user's input. In the present invention, the generative artificial intelligence model can adopt a large language model (LLM), which can be used in travel search and planning scenarios through pre-training and learning to realize the analysis of user search intentions, the integration of search results, and the generation of recommendation data. The AI summary data refers to the summary data generated by the generative artificial intelligence model; the travel product data refers to the searched travel products. The technical principles and model structures of the generative artificial intelligence technology and the large language model are known, so they will not be elaborated here.

[0041] The retrieval-augmented generation (RAG) technology combines a language model and information retrieval technology. When generating text or answering questions, the RAG technology first retrieves relevant information from a large document collection, and then uses the retrieved information to guide the generation of text to improve data quality and accuracy. The retrieval-augmented generation model can be used in travel search and planning scenarios through pre-training and learning to realize searching and generating comprehensive and accurate search results based on travel search requests. The technical principles and model structures of the retrieval-augmented generation model are known, so they will not be elaborated here.

[0042] In the travel information search and planning scenario of the present invention, through the generative artificial intelligence technology and the retrieval-augmented generation technology, using the retrieval and generation capabilities of the RAG technology and the intention analysis and data integration capabilities of the AI technology, accurately understand the user's natural language input and complex query intentions, obtain comprehensive and accurate search results, make the answer data accurately match the travel search request, provide travel search services such as efficient, comprehensive, and personalized travel information recommendation and planning services for users, and effectively solve the problems of inaccurate intention recognition, insufficient result recall, and information fragmentation in the existing search methods.

[0043] In addition, the present invention is based on a dual-mode browsing design, which combines the streaming output of AI summary data and the waterfall flow display of travel product data. Users can choose to browse the AI summary data in a streaming manner, or they can make the streaming-generated part stick to the top by swiping up to focus on browsing the travel product data, ensuring that different users' browsing needs are met.

[0044] In some embodiments, answer data is generated based on a generative artificial intelligence model and a retrieval-augmented generation model, including: based on the retrieval-augmented generation model, retrieving associated matching content according to a travel search request, where the associated matching content includes user-generated content and professionally-generated content; based on the generative artificial intelligence model, analyzing the user's intention according to the travel search request and the associated matching content, and integrating the associated matching content according to the user's intention to generate answer data.

[0045] The professionally-generated content includes travel products provided by the travel service platform, and the user-generated content includes the content information published by users on the travel service platform. The RAG model combines retrieval and generation capabilities, introducing highly relevant content from the internal knowledge base into the generation process, significantly enhancing the accuracy and coverage of search results. With the support of the RAG model, the AI model can not only accurately understand the user's complex search intention, but also integrate and generate high-quality personalized recommendations, providing a more comprehensive and efficient travel information service, fundamentally optimizing the user experience.

[0046] In some embodiments, the AI summary data includes: recommended travel product information associated and matched with the travel search request; recommended user-created content associated and matched with the travel search request; wherein, the recommended travel product information and the recommended user-created content include multimodal data, and the multimodal data includes text, pictures, and maps; recommended questions associated and matched with the travel search request.

[0047] The recommended travel product information associated and matched with the travel search request can be integrated and obtained from professionally generated content, and the recommended user-generated content associated and matched with the travel search request can be integrated and obtained from user-generated content. The present invention combines AI technology and RAG technology, which can effectively optimize the user experience in travel search scenarios such as searching for travel routes, asking information inquiries, and scenic spot recommendations, and provide users with more intelligent and efficient services. The combination of AI technology and RAG technology in the present invention can achieve: Intelligent summary: Deeply analyze the travel search request, integrate user-generated content (UGC), professionally generated content (PGC), and other information sources, and generate a concise and summary answer. For example, for the question of "the best travel route in xx place", provide a comprehensive best route suggestion; Present in a vivid and illustrated way: Combine various forms such as text, pictures, and maps to enhance the information presentation effect and help users quickly understand and obtain key information; Efficiently recall relevant content: Accurately identify the user's search intention, recall relevant UGC posts, scenic spot activities, hotels and other travel products, and provide one-stop reservation and planning services. Through the above functions, the present invention can effectively reduce the user operation cost and improve the efficiency and experience of travel information search and planning.

[0048] The present invention realizes multi-modal information presentation. For the scenario-based design of travel search requirements, the answer data integrates multi-modal information such as text, pictures, and maps. The text can be used to outline the itinerary, activities, or scenic spots, the pictures can provide an intuitive feeling, and the map is used to show the rationality of the route planning. The multi-modal display method not only improves the user's information understanding efficiency but also greatly enhances the effectiveness of assisting user decision-making.

[0049] The present invention also realizes the recommendation and guidance of related questions. During the process of generating the answer data, based on the user's travel search request, potential related questions are derived. For example, if the travel search request is "three-day travel plan in xx place", recommended questions such as "must-try restaurants in xx place" and "special activities in xx place in the current season" can be generated. Users can further customize the search through the recommended questions or modify the search content to achieve dynamic adjustment of information acquisition.

[0050] For example, in the search scenario for travel information inquiries. When a user searches for questions like "opening hours of xx scenic spot", the present invention provides accurate answers for different dates on the search result page through the AI summary function, including detailed information on the opening hours. At the same time, it generates recommended extended questions related to the user's current needs, such as "what scenic spots are near xx scenic spot after visiting?", "what special activities are there at xx scenic spot?", to guide the user to explore more possible needs. In addition, in combination with the user's intention, relevant products are recommended from the product layer (such as scenic spot tickets, entertainment activities, etc.) to form recommended travel product information, and valuable information is provided from the content layer (such as experience sharing of other users or relevant posts) to form recommended user-generated content, helping the user make a quick decision.

[0051] For the search scenario of itinerary planning. When a user searches for "three-day route recommendation for xx place", the present invention provides detailed daily itinerary suggestions on the search result page through the AI summary function: the specific arrangements for the first day to the third day, presented in a combination of text and pictures. At the same time, an itinerary route map is attached to help the user intuitively judge the distance between scenic spots and the visiting order. Further, the present invention also recommends questions related to the user's needs, such as "must-try restaurants in xx place", "special activities in xx place during spring and autumn seasons", to provide more comprehensive travel suggestions for the user. In addition, in combination with the user's search intention, day tour products (such as scenic spot packages, special activities, etc.) are recommended from the product layer to form recommended travel product information, and the sharing of other users' tour experiences in this place is pushed from the content layer to form recommended user-generated content, providing a richer one-stop service experience for the user.

[0052] Figure 2 It shows the input of a travel search request on the page, Figure 3 It shows the output of answer data on the page; referring to Figure 2 and Figure 3 , the user can input a travel search request through the search box 200 on the page. After the system generates the answer data, the AI summary data is streamed out in the first module 310 of the page, and the travel product data is displayed in a waterfall flow in the second module 320 of the page.

[0053] Thus, the present invention utilizes LLM technology and RAG technology to generate accurate answers according to the questions input by the user, and at the same time recalls relevant content according to the AI's breakdown of the user's intention, realizing the deep integration of AI search and traditional search and making up for the problem of insufficient current search efficiency. The user can quickly obtain high-value information without manually screening a large number of search results. Through in-depth semantic analysis of the user's query by AI, integrating multi-dimensional information sources such as UGC (user-generated content) and PGC (professionally-generated content), it provides a one-stop and efficient answer for the user.

[0054] In some embodiments, during the process of streaming AI summary data in the first module of a page: in response to a screen pressing operation, the front end displays a hover animation effect, and the back end continues to stream the AI summary data; in response to the release of the screen pressing operation, the front end displays the already output AI summary data, and if there is remaining AI summary data that has not been output completely, the front end continues to stream the remaining AI summary data.

[0055] The screen pressing operation can include only pressing, or can also include swiping and pressing. Refer to Figure 3 As shown, to solve the conflict between the rhythm of AI-generated content and user interaction, when the user operation is synchronized with the generation rhythm, a rhythm adaptation mechanism for generating content is designed for the pressing and releasing of the user operation. When the user presses the screen (such as swiping the screen and pressing with a finger), the front end will automatically pause the streaming output of the AI-generated content and prompt the current state through the hover animation effect 311; at this time, the back end continues to stream the AI summary data. After the user releases the finger, the front end displays the already output AI summary data, and in the case where the AI summary data has not been output completely, the generated content continues to be output in a streaming manner, ensuring the precise matching of the user swiping process and the generation rhythm, and avoiding the situation that the AI generation is too fast during the upward swipe process, resulting in the user's upward swipe speed being unable to catch up with the AI generation speed.

[0056] In some embodiments, during the process of streaming AI summary data in the first module of a page: in response to the operation of swiping the page to the second module, the front end pins the first module to the top and displays a generating prompt and a return interaction button in the pinned area, and the back end continues to stream the AI summary data.

[0057] The discrimination mechanism for swiping the page to the second module can be set according to requirements. For example, when the top of the second module reaches the set position of the page, it can be determined that there is an operation of swiping the page to the second module; another example is that when the proportion of the second module in the page reaches a preset ratio, it can be determined that there is an operation of swiping the page to the second module.

[0058] Figure 4 Schematically shows that the first module is pinned to the top during the process of streaming AI summary data; in combination with Figure 3 and Figure 4 As shown, during the process of streaming AI summary data in the first module 310 of a page, if the user swipes the page upward until the main part of the page displays the second module 320, the front end stops output, pins the first module 310 to the top, avoids the first module 310 from becoming longer and affecting the lower modules, and displays a generating prompt and a return interaction button 313 in the pinned area 312; after the front end pins to the top, the back end streaming output continues. When the user clicks the return interaction button 313, it can return to Figure 3 the state to continue streaming the AI summary data.

[0059] In this way, if the user is interested in the AI summary content, they can continuously view the stream-generated content in place and focus on the AI summary mode; if the user loses patience with the generated content, they can slide up to pin the AI summary part to the top, so as to focus on browsing the waterfall flow results. When the user slides up to the waterfall flow area, the AI summary part is automatically pinned to the top, and the front-end display of the stream output pauses, avoiding interference with the user's browsing rhythm caused by content generation, and realizing a smooth switching mode interaction design.

[0060] In some embodiments, after the AI summary data is stream-output in the first module of the page: in response to the operation of sliding the page to the second module, pin the first module to the top, and display a completion prompt and a return interaction button in the pinned area. Figure 5 Schematically shows that the first module is pinned to the top after the AI summary data is generated; combined with Figure 3 and Figure 5 As shown, when the AI summary data is generated, the user slides up the page to view the waterfall flow data of the second module 320, then the first module 310 is pinned to the top, and a completion prompt and a return interaction button 313 are displayed in the pinned area 312. The user can click the return interaction button 313 to quickly return to the top to view the AI summary content.

[0061] In some embodiments, when the second module of the page shows travel product data in a waterfall flow, a filtering layer is shown at the top of the second module. The method further includes: in response to the sliding browsing operation on the second module, hiding the filtering layer; in response to the back-sliding operation of the second module, showing the filtering layer at the top of the second module.

[0062] Figure 6 Schematically shows showing the filtering layer when the second module is back-slid; combined with Figure 3 and Figure 6 As shown, in the initial state, when the second module 320 shows travel product data in a waterfall flow, a filtering layer 322 is shown at the top of the second module 320, so as to quickly filter the corresponding travel products through the keywords shown in the filtering layer 322; combined with 4 and Figure 5 As shown, when the user slides and browses the second module 320, the filtering layer 322 is hidden to avoid affecting the user's browsing of the waterfall flow content. If the user performs a back-sliding operation to return to Figure 3 or Figure 6 the initial state of the second module 320 shown, the filtering layer 322 will be shown again for quick filtering.

[0063] In summary, the travel search display interaction method of the present invention can solve the following problems: (1) Insufficient search efficiency and experience. In the current mode of traditional search engines, users need to manually screen and refine useful content from a vast amount of information and cannot efficiently obtain accurate answers. At the same time, although AI search has a generation ability, its combination with traditional search results is not tight enough, which easily leads to content fragmentation and inconsistent experience. (2) Compatibility problem between generative content and real-time interaction. During the process of AI generating content, users may lose patience due to the long waiting time or have doubts about the credibility of the generated content. Moreover, the continuous output of generated content may also interfere with the user's browsing of in-site products & content (such as waterfall flow recommended content), resulting in a fragmented experience. (3) Conflict between the rhythm of generated content and user interaction. When users browse generated content, the rhythm of the sliding operation may not match the speed of the content streaming generation, leading to an unsmooth user experience. Especially when the user swipes up, the generated content is faster than the swiping-up speed, resulting in the inability to focus on the current content. (4) Integration problem of multi-modal content display. In the search route scenario, users need not only text answers but more an intuitive feeling of whether the attractions are interesting. The information combining text and pictures can effectively help users make decisions. Map information can help users judge whether the route is reasonable. However, the existing content generation and display modes often lack the organic combination of multi-modalities, resulting in a reduced efficiency of information understanding. Through the deep integration of AI technology and RAG technology, the present invention greatly improves the search efficiency, accurately understands the user's intention, and provides high-value information; at the same time, it optimizes the accuracy of traditional search, bringing users an intelligent assisted experience of one-stop travel product and information search and itinerary planning.

[0064] The embodiment of the present invention further provides a travel search display interaction device, which can be used to implement the travel search display interaction method described in any of the above embodiments. The features and principles of the travel search display interaction method described in any of the above embodiments can be applied to the following embodiments of the travel search display interaction device. In the following embodiments of the travel search display interaction device, the features and principles of the travel search display interaction that have been clarified will not be repeated.

[0065] Figure 7 Schematically shows the main modules of the travel search display interaction device; refer to Figure 7 As shown, the travel search display interaction device 500 provided by the embodiment of the present invention includes: a search request response module 510, configured to respond to a travel search request and generate answer data based on a generative artificial intelligence model and a retrieval-augmented generation model; wherein, the answer data includes AI summary data and travel product data; an answer data display module 520, configured to stream output the AI summary data in the first module of the page and display the travel product data in a waterfall flow in the second module of the page.

[0066] Furthermore, the travel search display interaction device 500 may further include modules for implementing other process steps of the above-described embodiments of the travel search display interaction methods. The specific principles of each module may be referred to the descriptions of the above-described embodiments of the travel search display interaction methods, and will not be repeated here.

[0067] The travel search display interaction device of the present invention can utilize the retrieval and generation capabilities of the RAG technology and the intent analysis and data integration capabilities of the AI technology to accurately understand the natural language input and complex query intents of users, obtain comprehensive and accurate search results, and provide users with efficient, comprehensive, and personalized travel information recommendation and planning services, etc., to effectively solve the problems of inaccurate intent recognition, insufficient result recall, and information fragmentation in existing search methods. In addition, it can also implement dual-mode browsing, combining the dual modes of streaming output of AI summary data and waterfall flow display of travel product data. Users can choose to browse the AI summary data in a streaming manner, or make the streaming generated part stick to the top by swiping up to focus on browsing the travel product data, ensuring that different users' browsing needs are met.

[0068] The embodiment of the present invention also provides an electronic device, including a processor and a memory. An executable instruction is stored in the memory. When the executable instruction is executed by the processor, the travel search display interaction method described in any of the above embodiments is implemented.

[0069] The electronic device of the present invention can be deployed on a travel service platform to utilize the retrieval and generation capabilities of the RAG technology and the intent analysis and data integration capabilities of the AI technology to accurately understand the natural language input and complex query intents of users, obtain comprehensive and accurate search results, and provide users with efficient, comprehensive, and personalized travel information recommendation and planning services, etc., to effectively solve the problems of inaccurate intent recognition, insufficient result recall, and information fragmentation in existing search methods. In addition, it can also implement dual-mode browsing, combining the dual modes of streaming output of AI summary data and waterfall flow display of travel product data. Users can choose to browse the AI summary data in a streaming manner, or make the streaming generated part stick to the top by swiping up to focus on browsing the travel product data, ensuring that different users' browsing needs are met.

[0070] Figure 8 is a schematic structural diagram of the electronic device in the embodiment of the present invention. It should be understood that Figure 8 only schematically shows each module. These modules can be virtual software modules or actual hardware modules. The combination, splitting, and addition of other modules are all within the protection scope of the present invention.

[0071] Such as Figure 8As shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 that connects different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0072] The storage unit 620 stores program code, and the program code can be executed by the processing unit 610, enabling the processing unit 610 to execute the steps of the travel search display interaction method described in any of the above embodiments. For example, the processing unit 610 can execute steps as Figure 1 shown.

[0073] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.

[0074] The storage unit 620 may also include a program / utilities 6204 having one or more program modules 6205. Such program modules 6205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0075] The bus 630 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0076] The electronic device 600 can also communicate with one or more external devices. The external devices can be one or more of devices such as a keyboard, a pointing device, a Bluetooth device, etc. These external devices enable a user to interact and communicate with the electronic device 600. The electronic device 600 can also communicate with one or more other computing devices. The shown computer devices include a router and a modem. Such communication can be carried out through an input / output (I / O) interface 650. And, the electronic device 600 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 660. The network adapter 660 can communicate with other modules of the electronic device 600 through the bus 630. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0077] An embodiment of the present invention also provides a computer-readable storage medium for storing a program, which when executed implements the travel search display interaction method described in any of the above embodiments.

[0078] The storage medium of the present invention can be executed by a processor deployed on a travel service platform to implement the retrieval and generation capabilities of the RAG technology and the intent analysis and data integration capabilities of the AI technology, accurately understand the natural language input and complex query intent of users, obtain comprehensive and accurate search results, and provide users with efficient, comprehensive, and personalized travel information recommendation and planning services, etc., travel search services, effectively solving the problems of inaccurate intent recognition, insufficient result recall, and information fragmentation in existing search methods. In addition, it can also implement dual-mode browsing, combining the dual modes of streaming output of AI summary data and waterfall flow display of travel product data. Users can choose to browse the AI summary data in a streaming manner, or slide up to make the streaming-generated part stick to the top to focus on browsing the travel product data, ensuring that different user browsing needs are met.

[0079] The storage medium can be a portable compact disc read-only memory (CD-ROM) and include program code, and can run on a terminal device, such as a personal computer. However, the storage medium of the present invention is not limited thereto, and it can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0080] The storage medium can adopt any combination of one or more readable media. The readable media can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the readable storage medium include, but are not limited to: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0081] A readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium can also be any readable medium other than a readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable signal medium can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above.

[0082] The program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device, for example, by using an Internet service provider to connect through the Internet.

[0083] An embodiment of the present invention also provides a computer program product, including a computer program, which when executed by a processor implements the travel search display interaction method described in any of the above embodiments.

[0084] When the computer program product of the present invention runs on a terminal device, it can implement the retrieval and generation capabilities of the RAG technology and the intent analysis and data integration capabilities of the AI technology, accurately understand the user's natural language input and complex query intent, obtain comprehensive and accurate search results, and provide users with efficient, comprehensive, and personalized travel information recommendation and planning services, etc., such as travel search services, effectively solving the problems of inaccurate intent recognition, insufficient result recall, and information fragmentation in existing search methods. In addition, it can also implement dual-mode browsing, combining the dual modes of streaming output of AI summary data and waterfall flow display of travel product data. Users can choose to browse the AI summary data in a streaming manner, or they can make the streaming-generated part stick to the top by swiping up to focus on browsing the travel product data, ensuring that different users' browsing needs are met.

[0085] The above content is a further detailed description of the present invention in combination with specific preferred embodiments. It cannot be determined that the specific implementation of the present invention is only limited to these descriptions. For those of ordinary skill in the technical field to which the present invention pertains, without departing from the concept of the present invention, several simple deductions or substitutions can still be made, and all should be regarded as falling within the protection scope of the present invention.

Claims

1. A travel search and display interactive method, characterized in that: include: In response to a travel search request, generating answer data based on a generative artificial intelligence model and a retrieval-enhanced generative model; Wherein, the answer data includes AI summary data and travel product data; The AI ​​summary data is output in a streaming manner in the first module of the page, and the travel product data is displayed in a waterfall flow in the second module of the page.

2. The travel search and display interactive method according to claim 1, characterized in that: The generating answer data based on the generative artificial intelligence model and the retrieval enhancement generation model includes: Based on the retrieval enhancement generation model, retrieve relevant matching content according to the travel search request, wherein the relevant matching content includes user-generated content and professionally generated content; Based on the generative artificial intelligence model, the user intention is analyzed according to the travel search request and the associated matching content, and the associated matching content is integrated according to the user intention to generate the answer data.

3. The travel search and display interactive method according to claim 1, characterized in that: The AI ​​summary data includes: Recommended travel product information associated with and matching the travel search request; Recommended user-generated content associated with and matching the travel search request; Wherein, the recommended travel product information and the recommended user-generated content include multimodal data, and the multimodal data includes text, pictures and maps; A matching recommended question is associated with the travel search request.

4. The travel search and display interactive method according to claim 1, characterized in that: In the process of streaming output of the AI ​​summary data in the first module of the page: In response to the screen pressing operation, the front end displays the hovering effect and the back end continues the streaming output of AI summary data; In response to the release of the screen pressing operation, the front end displays the outputted AI summary data and continues to stream-output the remaining AI summary data.

5. The travel search and display interactive method according to claim 1, characterized in that: In the process of streaming output of the AI ​​summary data in the first module of the page: In response to the operation of sliding the page to the second module, the front end mounts the first module to the ceiling and displays a generating prompt and a return interaction button in the ceiling area, and the back end continues the streaming output of the AI ​​summary data.

6. The travel search and display interactive method according to claim 1, characterized in that: After the first module of the page stream outputs the AI ​​summary data, it is completed: In response to the operation of sliding the page to the second module, the first module is suspended on the ceiling, and a completion prompt and a return interaction button are displayed in the ceiling area.

7. The travel search and display interactive method according to claim 1, characterized in that: When the travel product data is displayed in the waterfall flow of the second module of the page, a screening layer is displayed on the top of the second module, and the method further includes: In response to a sliding browsing operation on the second module, hiding the screening layer; In response to a sliding back operation of the second module, the screening layer is revealed on top of the second module.

8. A travel search and display interactive device, characterized in that: include: A search request response module, for responding to travel search requests and generating answer data based on a generative artificial intelligence model and a retrieval enhancement generation model; Wherein, the answer data includes AI summary data and travel product data; The answer data display module is used to stream output the AI ​​summary data in the first module of the page and to display the travel product data in a waterfall flow in the second module of the page.

9. An electronic device, characterized in that: include: processor; A memory, wherein executable instructions are stored in the memory; Wherein, when the executable instructions are executed by the processor, the travel search display interaction method described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the travel search display interaction method described in any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the travel search display interaction method according to any one of claims 1 to 7 is implemented.

Images