Interaction method and device based on accommodation, equipment and storage medium

Abstract

The embodiment of the invention provides an accommodation-based interaction method and device, equipment and a storage medium. The method comprises the step of providing user input which is received in a session interface of a target application and is associated with an accommodation service request of a target object to a large model. Obtaining output information from the large model, including one of recommendation information for the accommodation service request, the recommendation information indicating an accommodation recommendation result, or feedback information for the accommodation service request; wherein the output information is generated by the large model by invoking an accommodation reservation function based at least on the type of the accommodation service request indicated by the user input. And presenting the output information in the target application via the session interface. Therefore, the accommodation reservation efficiency and accuracy are improved.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to accommodation-based interactive methods, apparatuses, devices, and storage media. Background Technology

[0002] With the widespread use of smart applications, users have gradually become accustomed to booking accommodations through these applications. Taking business travel as an example, under traditional booking methods, if a user has diverse accommodation needs, they need to access the accommodation booking program designated by their organization (the user's company or group), repeatedly searching and comparing the accommodation lists and details presented in the program before finally booking a suitable option. For users, this booking process is often cumbersome and time-consuming. Summary of the Invention

[0003] In a first aspect of this disclosure, an accommodation-based interaction method is provided. The method may include: providing user input received in a session interface of a target application, associated with an accommodation service request from a target object, to a large model. Obtaining output information from the large model, including one of the following: recommendation information for the accommodation service request, indicating accommodation recommendation results, or feedback information for the accommodation service request; wherein the output information is generated by the large model, at least based on the type of accommodation service request indicated by the user input, by invoking an accommodation booking function. Presenting the output information in the target application via a session interface.

[0004] In a second aspect of this disclosure, an accommodation-based interactive device is provided. The device may include: a user input receiving module configured to provide a large model with user input received in a session interface of a target application, associated with an accommodation service request from a target object; an output information determining module configured to obtain output information from the large model, including one of: recommendation information for the accommodation service request, indicating accommodation recommendation results, or feedback information for the accommodation service request; wherein the output information is generated by the large model by invoking an accommodation booking function, at least based on the type of accommodation service request indicated by the user input; and a result presentation module configured to present the output information in the target application via a session interface.

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

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

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

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

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

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

[0011] Figure 2 A schematic diagram illustrating the interaction principle of a accommodation-based interaction method according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A schematic diagram of the interaction process of a accommodation-based interaction method according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A flowchart of a accommodation-based interactive method according to some embodiments of the present disclosure is shown;

[0014] Figure 5 A flowchart illustrating the adjustment of interactive content according to some embodiments of this disclosure is shown;

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0031] In some embodiments, the implementation of at least some functions of the target application 120, and / or the implementation of at least some functions of the digital assistant 122 within the target application 120, may be based on the target model 155. During the operation of the target application 120, one or more target models 155 may be invoked, such as the capabilities of the target model 155. Within the target application 120, the digital assistant 122 may utilize the target model 155 to understand user input and provide responses to the end user 140 based on the output of the target model 155.

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

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

[0034] The process of confirming accommodation often consumes a significant amount of time and effort for users. There are two main reasons for this: First, the sheer number of filtering options is overwhelming. Users need to consider multiple factors when choosing a hotel, including price, brand, star rating, location, distance, room type, breakfast, facilities, invoicing options, and user reviews. This forces users to repeatedly select filters on the booking list page and then view details on the product page. Only after multiple comparisons can they finally find a hotel that meets their needs, making the entire process extremely time-consuming. Second, the process is complex and carries the risk of booking failure. Users must navigate from the homepage of the booking platform to the accommodation list page, filter for suitable options, and then view the details. If they are not satisfied with the accommodation, they need to return to the list page to filter again. Even after finding a suitable option, completing the order process may result in no stock, forcing users to return to the list page to continue filtering until the order is successfully placed.

[0035] Furthermore, the accommodation booking platform faces several challenges in the process. Firstly, the lack of a clear feedback loop and untimely data analysis and strategy adjustments prevent the systematic recording, categorization, and processing of user-reported accommodation issues. This results in problematic accommodation options continuing to appear in the recommendation list. Secondly, the absence of intelligent filtering and optimization mechanisms means the platform may be unable to employ suitable algorithms to optimize the filtering and recommendation process based on user feedback. For instance, while the platform should reduce the exposure and recommendation of frequently complained-about accommodation options, the lack of intelligent filtering mechanisms means these options may continue to be repeatedly recommended to other users. In conclusion, these issues prevent accommodation booking platforms from promptly addressing user-reported accommodation problems, impacting the quality of recommended accommodations.

[0036] In embodiments of this disclosure, an improved interaction scheme based on accommodation is proposed. The scheme includes: providing user input received in the target application's session interface, associated with an accommodation service request from the target object, to a large model. Output information is obtained from the large model, including one of the following: recommendation information for the accommodation service request, indicating accommodation recommendation results, or feedback information for the accommodation service request; wherein the output information is generated by the large model by invoking an accommodation booking function, at least based on the type of accommodation service request indicated by the user input. The output information is presented in the target application via a session interface.

[0037] Through the above process, by utilizing large-scale model analysis of user input and combining it with specific user feedback, the system adjusts accommodation recommendations to better align with users' actual needs. Based on user feedback, the system can quickly adjust the ratings and reviews of accommodation options, ensuring that subsequent recommendations reflect the latest user experience and improving the timeliness and accuracy of accommodation reviews.

[0038] The scenarios shown in some embodiments of this disclosure may include scenarios where the end user is an enterprise user, and the accommodation recommendations may correspond to the accommodation needs of scenarios such as project inspection, customer visit, training and seminar. Figure 2 A schematic diagram 200 illustrating the interaction principle of an accommodation-based interactive method according to some embodiments of the present disclosure is shown. The end user 140 can interact via a digital assistant 122. The digital assistant 122 can invoke a target model 155 to parse the user input. If the parsing result determines that accommodation needs are included, the target model 155 can query and book accommodation options by invoking the accommodation booking function 220. Since the functions of the target model 155 can be accomplished by a larger model in the above process, the larger model can also be referred to as the target model 155.

[0039] Terminal device 110 can utilize various information to recommend accommodation options. For example, this information may include basic information 231 and information corresponding to management services 233. Basic information 231 may be related to terminal user 140, such as the name and identity attribute information of terminal user 140. Identity attribute information may include the date of employment and position of terminal user 140 within the company, etc. Information corresponding to management services 233 may include accommodation booking standards corresponding to different identity attribute information.

[0040] After the end user 140 confirms the accommodation recommendation, they can use the accommodation booking function 210 to complete the accommodation booking on the relevant accommodation booking platform. After the booking is completed, the order information 232 corresponding to the booking will be displayed on the interface 142 to the end user 140.

[0041] During the accommodation option recommendation process, terminal device 110 can also utilize relevant information from the accommodation options to complete the recommendation. Taking a hotel as an example, the relevant information for the accommodation options may include hotel data 241, inventory data 242, price data 243, room type data 244, discount data 245, promotional data 246, profile data 247, review data 248, and rating data 249, etc. For example, hotel data 241 can indicate basic hotel information, such as name, address, star rating, facilities, and services. Inventory data 242 can indicate the number of available rooms in the hotel, updating the inventory status in real time. Price data 243 can indicate the virtual resource consumption information (virtual resources can be such as virtual points) for each room type in the hotel at different time periods. Room type data 244 can indicate the hotel room type, size, bed type, and other facility configurations. Discount data 245 can indicate the discounts currently offered by the hotel. Promotional data 246 can indicate specific promotional activities of the hotel, such as complimentary breakfast, free room upgrades, or buy three nights get one free promotional night. Profile data 247 can indicate the hotel's characteristic representation. Evaluation data 248 indicates other users' reviews of the hotel. Rating data 249 indicates the score results obtained by combining various user feedback on factors such as hotel service, facilities, and cleanliness.

[0042] Figure 3 A schematic diagram 300 illustrates the interaction process of an accommodation-based interaction method according to some embodiments of the present disclosure. In block 310, the end user 140 interacts with the digital assistant 122. In block 311, the terminal device 110 uses a large model to determine the intent of the interaction. In block 312, the terminal device 110 determines whether the interaction of the end user 140 is related to accommodation based on the results output by the large model. If not related, in block 315, corresponding suggestion information is presented on the interface 142. If related, in block 313, accommodation-related parameters, such as check-in date, check-out date, etc., are determined based on the interaction content. In block 314, the terminal device 110 needs to determine whether the accommodation-related parameters are complete. For example, it can determine this based on preset necessary accommodation-related parameters. If complete, in block 320, the identity attributes of the end user 140 are verified. If incomplete (e.g., missing check-in date or missing number of stays), a prompt message needs to be presented on the interface 142 to prompt the end user 140 to complete the accommodation-related parameters.

[0043] In box 321, terminal device 110, using management service 233, can determine the itinerary booking criteria corresponding to terminal user 140, thereby obtaining travel application data based on the itinerary booking criteria. In box 322, terminal device 110 can determine whether the accommodation needs involved in the interaction with terminal user 140 meet the requirements. If they do, the preference attributes of terminal user 140 are obtained in box 323. Otherwise, if they do not meet the requirements, suggestion information can be presented. For example, situations that do not meet the requirements may include accommodation choices that exceed the itinerary booking criteria, destinations that restrict travel, etc.

[0044] In box 330, terminal device 110 can determine accommodation filtering parameters (such as the location of accommodation options, available services, virtual resource consumption range, etc.) based on the preferences of terminal user 140 and accommodation-related parameters. In box 331, terminal device 110 can invoke accommodation booking function 210. In box 332, terminal device 110 uses accommodation booking function 210 to obtain relevant information of each accommodation option (hotel) that meets the accommodation filtering parameters from the accommodation booking platform. In box 333, based on the relevant information of each accommodation option, the room type inventory of the accommodation options can be determined.

[0045] In box 340, terminal device 110 uses accommodation booking function 210 to obtain quotes for bookable room types and generate accommodation options. In box 341, terminal device 110 obtains feedback from terminal user 140 regarding the accommodation options. If terminal user 140 confirms, the accommodation recommendation result can be confirmed in box 342 to generate an accommodation order. Otherwise, if terminal user 140 fails to confirm, the accommodation filtering parameters can be re-determined in box 330 based on the reasons given by terminal user 140. In box 343, if terminal user 140 confirms the final accommodation recommendation result (without further requests), the process ends. Otherwise, if terminal user 140 provides further requests, the accommodation filtering parameters are re-determined in box 330 according to the further requests.

[0046] Figure 4 Example flow 400 of an accommodation-based interactive method according to some embodiments of the present disclosure is shown. The itinerary planning process described in the embodiments of the present disclosure can be implemented on a terminal device, a terminal device with a target application installed, and / or a server device corresponding to the terminal device. In the examples below, for the sake of discussion, the description is from the perspective of the terminal device, for example... Figure 1 The terminal device 110 shown.

[0047] In box 401, terminal device 110 provides a maximum model of user input received in the target application's session interface that is associated with the target object's accommodation service request.

[0048] The target application 120 can be a business travel booking application targeting enterprise users (ToB type, serving enterprise users) or a travel booking application targeting ordinary users (ToC type, serving ordinary users). In some embodiments of this disclosure, the interaction process is illustrated using the example of the target application 120 being a business travel booking application targeting enterprise users. User input can be related to accommodation tasks, such as including at least one accommodation request, or including evaluations or feedback on accommodation options. A large model is used to process the user input, parsing out key information such as check-in date, location, star rating, virtual resource consumption range, room type requirements, and other preferences. Virtual resources can be such as virtual points. Based on this key information, the terminal device 110 uses the large model to invoke the accommodation booking function 210, thereby searching for suitable accommodation options on relevant accommodation booking platforms.

[0049] In box 402, terminal device 110 obtains output information from the large model, including one of the following: recommendation information for the accommodation service request, indicating the accommodation recommendation result, or feedback information for the accommodation service request. The output information is generated by the large model by invoking the accommodation booking function, at least based on the type of accommodation service request indicated by the user input.

[0050] During the search process where terminal device 110 uses the big data model to call the accommodation booking function 210, personalized accommodation recommendations can be generated based on the historical preference data of terminal user 140, real-time hotel inventory data, virtual resource consumption information, and discount information. For example, if the user inputs "book a four-star hotel near Company A tomorrow night, with breakfast," terminal device 110 can use the big data model to determine the type of accommodation service request indicated by the user's input, such as location, star rating requirements, and other requirements. Subsequently, the big data model can call the accommodation booking function 210 to filter at least one hotel that matches the type of accommodation service request based on the description information of the candidate accommodations, and obtain recommendation information for the accommodation service request based on the terminal user 140's job title, budget, or other historical behavior. The recommendation information can indicate suitable accommodation recommendations. The recommendation information includes not only static features such as hotel name, location, contact information, room type description, facilities, and review information (evaluation information and rating information), but also information such as availability, booking (cancellation) rules, virtual resource consumption limits, and other promotional activities. In addition, the accommodation recommendation results can also present whether they match the accommodation booking criteria and the degree of matching. The accommodation booking criteria can correspond to end user 140, such as the length of time the end user 140 has been employed, their department, or their project. For example, whether the accommodation matches the booking criteria and the degree of matching can include whether the accommodation recommendation is bookable, the difference in virtual resource consumption, the amount supported for organizational or individual payments, and whether additional approval is required.

[0051] In addition, the output information may also include feedback information regarding the accommodation service request. For example, based on the received response to the accommodation recommendation results, the terminal device 110 adjusts the feedback information regarding the accommodation service request, which may instruct the updating of the evaluation of the accommodation options involved in the accommodation recommendation results or instruct the updating of the accommodation recommendation results.

[0052] Feedback information can include multiple dimensions. For example, as a first dimension, terminal device 110 can adjust the accommodation recommendations based on the responses from terminal user 140. If terminal user 140 confirms the accommodation options in the recommendations, terminal device 110 can use the accommodation booking function 210 (on the relevant accommodation booking platform) to generate a corresponding booking request and guide terminal user 140 to complete the booking. If terminal user 140 provides feedback on modifying the recommended accommodation options, terminal device 110 can use a large model to adjust the recommendations in real time based on the feedback, and re-provide accommodation options that meet the needs of terminal user 140.

[0053] In the second dimension, for accommodation recommendations, there might be cases where end user 140 has previously stayed at the hotel. Based on this, end user 140's response to the accommodation recommendation might include their experience, such as "Parking is inconvenient at this hotel" or "The breakfast wasn't as plentiful as advertised," etc. Based on this response, terminal device 110 can update its review of the hotel on the accommodation booking platform to ensure more accurate subsequent recommendations.

[0054] In box 403, terminal device 110 presents output information via a session interface in the target application.

[0055] Regarding the output information in the aforementioned two dimensions, the terminal device 110 can present the output information through a session interface in the target application 120. For example, it can present accommodation recommendation results, updated accommodation recommendation results, or evaluations of updated accommodation options.

[0056] Some embodiments of this disclosure effectively address how to respond to user feedback promptly by introducing real-time feedback and dynamic adjustment mechanisms. For example, if end user 140 reports that the accommodation option corresponding to the recommended accommodation results has inconvenient parking or unsatisfactory service quality, terminal device 110 will update the evaluation and recommendation priority of the accommodation option in real time based on this feedback, preventing these accommodation options from being repeatedly recommended. This mechanism forms a feedback loop, allowing end user 140's experience feedback to directly affect the recommendation quality.

[0057] Furthermore, through real-time data analysis and strategy adjustments, the system can respond more promptly to the actual needs of end-user 140. For example, if a recommended accommodation option frequently experiences cancellations or complaints, the terminal device 110 can reduce the recommendation frequency of that accommodation option based on the analysis results, or dynamically optimize the recommended content according to different user needs. This strategy adjustment ensures that end-user 140 receives recommendations that better meet their expectations, reducing invalid bookings.

[0058] These improvements, utilizing large models, can significantly enhance the response speed and recommendation accuracy of accommodation booking platforms, addressing the limitations of existing technologies in effectively handling user feedback and ensuring continuous improvement in recommendation quality.

[0059] The determination of accommodation recommendation results may include the following process: Terminal device 110 can utilize a large model to determine the keyword information corresponding to the user input. Based on the keyword information, the booking parameters required to execute the accommodation booking function are filled in, resulting in a filled result. Based on the filled result, the accommodation booking function is invoked to determine the recommendation information for the accommodation service request.

[0060] By parsing user input using a large model, keyword information related to the needs of end user 140 can be obtained. For example, keyword information may include check-in date, location preferences (such as city or specific landmark), virtual resource consumption range, etc. The large model can correspond to the target model 155.

[0061] Based on keyword information, terminal device 110 can use a large model to fill in the booking parameters required to perform the accommodation booking function 210. Specifically, these parameters may include check-in date, location preference (such as city or specific landmark), virtual resource consumption range, hotel class, room type requirements, etc.

[0062] Based on the input results, terminal device 110 can use a large model to determine at least one accommodation recommendation that matches the user's input. Through this process, terminal device 110 can quickly and efficiently provide end user 140 with accommodation recommendations that meet their needs. This automated process based on a large model not only improves the accuracy of recommendations but also reduces the operation time of end user 140 in the filtering process, greatly improving booking efficiency.

[0063] During the process of filling in the reservation parameters required for the accommodation reservation function, if there are any required reservation parameters that have not been filled in the filling results, the terminal device 110 will display a prompt message on the interface 142, indicating that supplementary information should be entered. In response to the received supplementary information corresponding to the prompt message, the filling results are updated until all required reservation parameters are filled.

[0064] If the terminal device 110 detects any required pre-assigned parameters that have not been filled in during the completion process, it will promptly display a prompt message. This prompt message reminds the terminal user 140 which key information is currently missing and guides the terminal user 140 to input the necessary supplementary information. For example, if the terminal user 140 does not specify the check-in date or hotel location in the input, the terminal device 110 will guide the terminal user 140 to supplement these necessary parameters.

[0065] In response to supplementary information provided by end user 140, terminal device 110 will automatically update the previous fill-in results to ensure that all required parameters are fully filled. Terminal device 110 can continuously check the fill-in results until all required booking parameters have been filled. Only after all necessary parameters are complete can terminal device 110 continue to execute the subsequent booking process to ensure that the recommended accommodation results are accurate and meet the needs of end user 140.

[0066] Through this real-time prompting and dynamic update mechanism, the terminal device 110 can significantly reduce the occurrence of booking failures or bookings that do not meet user expectations due to incomplete information, ensuring that the generation process of each recommendation result is efficient and reliable.

[0067] The preceding example illustrated the process of determining accommodation recommendation results based on booking parameters. Furthermore, the process of determining accommodation recommendation results can also be accomplished using user identity attribute information. For example, terminal device 110 determines accommodation booking criteria corresponding to the user's identity attribute information based on the user's input. Based on the accommodation booking criteria, the search parameters for the accommodation booking function are adjusted using a large model. Based on the search results from the accommodation booking function, recommendation information is determined for the accommodation service request.

[0068] Identity attribute information can include a user's job title, length of employment, department level, etc. Different identity attribute information can have corresponding accommodation booking standards. For example, a higher accommodation booking standard may correspond to a higher-level hotel, a better room type in the hotel, or a more lenient budget limit. In addition, accommodation booking standards may also indicate whether it is allowed to book hotels in a certain target area, the difference in standards between different target areas (cities, counties), whether it is possible to book beyond the standard, payment method restrictions (organizational payment, individual payment, joint payment by organization and individual), hotel star rating restrictions, advance booking number restrictions, whether (user's) place of residence is eligible for booking restrictions, whether to prioritize booking specific hotels, whether booking requires approval, restrictions on sharing accommodation, restrictions on multiple people and multiple difference in standards, etc.

[0069] Based on accommodation booking standards, terminal device 110 can adjust the search parameters of the accommodation booking function. These search parameters may include the range of virtual resource consumption, room type selection, hotel rating, etc. For example, terminal device 110 may recommend accommodation options with higher virtual resource consumption and better room types to terminal users 140 with relatively higher accommodation booking standards, while recommending accommodation options with more economical virtual resource consumption but still meeting basic needs to terminal users 140 with relatively lower accommodation booking standards.

[0070] Through this dynamic adjustment based on identity attribute information, terminal device 110 can ensure that the accommodation recommendation results not only meet the needs of end user 140 and enterprise standards, but also effectively control the consumption of virtual resources, optimize resource allocation, and improve the personalization and accuracy of booking.

[0071] If multiple candidate accommodation recommendations match the user input during the process of determining the accommodation recommendation result, the terminal device 110 can utilize a large model to determine the feature representation of each candidate accommodation recommendation result based on the descriptive information of each candidate accommodation recommendation result. Based on the degree of matching between the feature representation corresponding to the user's preference attributes and the feature representation of each candidate accommodation recommendation result, at least one accommodation recommendation result is determined from the multiple candidate accommodation recommendation results. The user includes the user corresponding to the user input (e.g., terminal user 140).

[0072] The descriptive information may include the geographical location, virtual resource consumption, room type, star rating, facilities, user reviews, etc., corresponding to each candidate accommodation recommendation. The terminal device 110 can use a large model to generate a feature representation for each candidate accommodation recommendation based on this descriptive information.

[0073] Furthermore, terminal device 110 utilizes a large model to generate feature representations corresponding to the user's preference attributes based on the user's preference attributes. The user's preference attributes may include their historical booking behavior, preferred hotel types, preferred geographical locations or room types, and frequently selected virtual resource consumption range, etc. Terminal device 110 can then use the large model to calculate the matching degree between the feature representations corresponding to the user's preference attributes and the feature representations of each candidate accommodation recommendation result.

[0074] Based on the matching degree calculation, terminal device 110 selects at least one accommodation recommendation that meets the user's needs from multiple candidate accommodation recommendations. For example, if terminal user 140 prefers a four-star hotel close to the city center and reasonably priced, terminal device 110 will prioritize recommending candidate hotels that meet these conditions. This feature-based matching degree recommendation ensures that the recommendation results highly match the preferences of terminal user 140, improving the accuracy and personalization of the recommendation results.

[0075] In this way, when faced with multiple candidate accommodation recommendations, the terminal device 110 can efficiently filter out the accommodation recommendation that best meets the needs of the end user 140.

[0076] For example, the descriptive information for each candidate accommodation recommendation indicates at least one of the following: static feature information and dynamic feature information. Static feature information may indicate the location information of the accommodation option involved in each candidate accommodation recommendation, the name of the accommodation option involved in each candidate accommodation recommendation, accommodation description, contact information, location information, environmental information, user reviews, user ratings, etc.

[0077] The accommodation description can indicate when the candidate accommodation recommendations were created, their qualifications, features, etc. The location information of the accommodation option can indicate its geographical location or nearby landmarks. The environmental information of the accommodation option can indicate the surrounding transportation, scenery, interior decoration, etc.

[0078] Dynamic feature information can indicate the services offered by each candidate accommodation recommendation, the booking status of the accommodation, virtual resource consumption information, promotional information, etc.

[0079] For example, the service information provided by the accommodation options can indicate whether breakfast, gym, swimming pool, etc., are included. The booking status information of the accommodation options can indicate the availability of various room types. Virtual resource consumption information can indicate the virtual resource consumption corresponding to the accommodation option. Promotional information can indicate whether there are any promotional activities in the candidate accommodation recommendations, and the details of those activities. This information helps the large model to perform more accurate matching based on rich descriptive information when filtering candidate accommodation recommendations.

[0080] In some embodiments of this disclosure, obtaining output information from the large model may include: In response to receiving a response message regarding the recommendation information, the terminal device 110 uses the large model to determine an evaluation result of the accommodation recommendation results involved in the recommendation information, wherein the response message includes comments on the accommodation recommendation results. Based on the evaluation result, feedback information is generated for the accommodation service request.

[0081] In response to the user's reply, terminal device 110 can utilize a large model to invoke the accommodation booking function 210, dynamically updating the evaluation results of accommodation options in the accommodation booking system. When terminal user 140 provides reply information regarding a specific accommodation option involved in a certain accommodation recommendation, terminal device 110 will determine the evaluation result of that accommodation option based on the reply information. The review may involve the hotel's service, facilities, room quality, or other related experiences.

[0082] For example, end user 140's response might include "The hotel room was clean, but the service was just average." Terminal device 110 will analyze this response, synthesize the information, and generate an overall rating or review of the accommodation option in the accommodation booking system. This mechanism ensures real-time updates to the reviews, making the recommendations more reliable and allowing for continuous optimization based on user feedback.

[0083] Furthermore, terminal device 110 responds to the reply information by adjusting the accommodation recommendation results. Using a large model based on the analysis of the reply information, it generates feedback information for the accommodation service request.

[0084] If the accommodation recommendations do not meet the expectations of end user 140, end user 140 may provide a response that matches their own needs, such as requesting to change to the lowest-priced accommodation option, the accommodation option closest to a specified landmark (such as a train station), the accommodation option with the best value for money, or directly specifying a particular accommodation option.

[0085] Terminal device 110 can utilize a large model to extract key information from the parsing results of terminal user 140's responses, such as the amount of virtual resources consumed, the names of accommodation options, and designated landmarks. Based on the extracted key information, terminal device 110 can use the large model to re-search and filter accommodation recommendations that meet the needs of terminal user 140, and adjust the original recommendations to better meet the personalized needs of terminal user 140.

[0086] In some embodiments of this disclosure, determining the evaluation result of accommodation options based on reviews may include: Terminal device 110 determining the response intent using a large model based on the response information; obtaining reviews of the accommodation options involved in the accommodation recommendation results corresponding to the response intent based on the response intent; and using the rating of the accommodation options determined based on the reviews as feedback information.

[0087] Terminal device 110 can analyze and determine the response intent of terminal user 140 based on at least one round of interaction content related to the response of terminal user 140. The response intent may include specific feedback from terminal user 140 on accommodation services, such as evaluations of services, facilities, room environment, etc.

[0088] Based on a determined response intent, terminal device 110 can extract reviews of accommodation options corresponding to that intent. For example, if the response intent is dissatisfaction with hotel services, terminal device 110 can use a large model to extract service quality-related content from the user's reviews and combine it with relevant accommodation rating information.

[0089] Terminal device 110 uses a large model to determine a rating for the accommodation option based on the specific content of user reviews and feedback, and uses this rating as feedback information. For example, terminal user 140 might comment that "the hotel's breakfast selection is too limited." Terminal device 110 converts this comment into a rating for "breakfast service" and, using the accommodation booking function 210, updates the overall rating of the accommodation option on the accommodation booking platform. This rating result will be displayed as feedback information to other users, allowing them to refer to the latest user review information in a timely manner.

[0090] In this way, terminal device 110 can dynamically update the evaluation and rating of accommodation options, ensuring that user feedback is fully utilized and improving the accuracy of recommendation results.

[0091] Figure 5An example flow 500 for adjusting interactive content according to some embodiments of this disclosure is illustrated. At block 310, end user 140 interacts with digital assistant 122. At block 311, terminal device 110 uses a large model to determine the intent of the interaction. At block 510, if terminal device 110 determines that the intent includes accommodation information, then at block 511 it continues to determine whether it is related to reviews of accommodation options. If it is determined to be related to reviews or ratings of accommodation options, then at block 520 it determines the review information related to the accommodation options, such as the specific review content of end user 140, and whether it involves positive or negative feedback.

[0092] In box 530, terminal device 110 uses the large model to invoke the accommodation booking function 210. In box 541, terminal device 110 uses the accommodation booking function 210 to update the overall rating of the accommodation option on the accommodation booking platform, ensuring that other users can see the latest review information. In box 541, terminal device 110 uses the accommodation booking function 210 to adjust the accommodation rating on the accommodation booking platform based on the latest user reviews, so that it is reflected in subsequent recommendations or rankings. In box 550, terminal device 110 displays suggestions based on the latest updated accommodation reviews and ratings to end user 140 on interface 142 to help end user 140 make the next decision. In addition, if the judgment result of the corresponding box 510 or box 511 is that it is not related to the accommodation inquiry or the review of the accommodation option, a prompt for irrelevant input can be presented in box 550 (such as guiding end user 140 to re-enter or select other services, such as transportation booking, activity arrangement, etc.). Based on the interaction with end user 140, terminal device 110 determines whether the current processing flow has resolved end user 140's problem. If it has, the process ends. If the problem remains unresolved, continue interacting with end user 140.

[0093] Figure 6 A schematic structural block diagram of a accommodation-based interactive device 600 according to some embodiments of the present disclosure is shown. Device 600 may be implemented in or included in terminal device 110, for example. Various modules / components in device 600 may be implemented by hardware, software, firmware, or any combination thereof.

[0094] As shown in the figure, device 600 includes a user input receiving module 601, configured to provide user input received in the session interface of the target application and associated with an accommodation service request of the target object to a large model. An output information determination module 602 is configured to obtain output information from the large model, including one of the following: recommendation information for the accommodation service request, indicating accommodation recommendation results, or feedback information for the accommodation service request; wherein the output information is generated by the large model by invoking an accommodation booking function, at least based on the type of accommodation service request indicated by the user input. A result presentation module 603 is configured to present the output information in the target application via a session interface.

[0095] In some embodiments of this disclosure, the output information determination module 602 can be configured to: determine the keyword information corresponding to the user input; fill in the reservation parameters required to execute the accommodation reservation function based on the keyword information, and obtain the filling result; and, based on the filling result, invoke the accommodation reservation function to determine recommended information for the accommodation service request.

[0096] In some embodiments of this disclosure, the output information determination module 602 may also be configured to: display a prompt message in response to the presence of unfilled required pre-defined parameters in the filling result, the prompt message indicating the input of supplementary information; and update the filling result in response to the received supplementary information corresponding to the prompt message, until all required pre-defined parameters are filled.

[0097] In some embodiments of this disclosure, the output information determination module 602 can be configured to: determine accommodation booking standards corresponding to the user's identity attribute information based on the user's input; adjust the search parameters of the accommodation booking function based on the accommodation booking standards; and determine recommended information for the accommodation service request based on the search results of the accommodation booking function.

[0098] In some embodiments of this disclosure, in response to the recommendation information indicating multiple candidate accommodation recommendation results, the output information determination module 602 can be configured to: determine the feature representation of each candidate accommodation recommendation result based on the description information of each candidate accommodation recommendation result among the multiple candidate accommodation recommendation results; and determine at least one accommodation recommendation result from the multiple candidate accommodation recommendation results to generate output information based on the degree of matching between the feature representation corresponding to the user's preference attributes and the feature representation of each candidate accommodation recommendation result, wherein the user includes the user corresponding to the user input.

[0099] In some embodiments of this disclosure, the descriptive information of each candidate accommodation recommendation result indicates at least one of the following: static feature information involved in each candidate accommodation recommendation result, and dynamic feature information involved in each candidate accommodation recommendation result.

[0100] In some embodiments of this disclosure, the result presentation module 603 may be configured to: in response to receiving a response message for the recommendation information, determine an evaluation result of the accommodation recommendation result involved in the recommendation information, wherein the response message includes comment information on the accommodation recommendation result; and generate feedback information for the accommodation service request based on the evaluation result.

[0101] In some embodiments of this disclosure, the result presentation module 603 may be specifically configured to: determine the response intent based on the response information; obtain comments on the accommodation options involved in the accommodation recommendation results corresponding to the response intent; and use the ratings of the accommodation options determined based on the comments as feedback information.

[0102] Figure 7 A block diagram of an electronic device 700 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that... Figure 7 The electronic device 700 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 7 The illustrated electronic device 700 may include or be implemented as Figure 1 The terminal device 110, or Figure 6 Device 600.

[0103] like Figure 7 As shown, electronic device 700 is in the form of a general-purpose electronic device. Components of electronic device 700 may include, but are not limited to, one or more processors or processing units 710, memory 720, storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. Processing unit 710 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 720. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 700.

[0104] Electronic device 700 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 720 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 730 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 700.

[0105] Electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 7 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 720 may include computer program product 725 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0106] The communication unit 740 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 700 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 700 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0107] Input device 750 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 760 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 700 can also communicate with one or more external devices (not shown) via communication unit 740 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 700, or with any device that enables electronic device 700 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0108] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0109] According to an exemplary implementation of this disclosure, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform... Figure 4 The methods provided are among the various optional methods available in the code, so they will not be elaborated upon here.

[0110] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0111] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0112] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0113] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0114] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An interaction method based on accommodation, comprising: The model will be based on the user input received in the target application's session interface that is associated with the target object's accommodation service request; The output information obtained from the large model includes one of the following: Recommendation information for the requested accommodation service, the recommendation information indicating accommodation recommendation results, or Feedback information in response to the accommodation service request; wherein the output information is generated by the large model based at least on the type of accommodation service request indicated by the user input, by invoking the accommodation booking function; as well as The output information is presented via the session interface in the target application.

2. The method according to claim 1, wherein obtaining output information from the large model comprises: Using the large model, determine the keyword information corresponding to the user input; Based on the keyword information, fill in the booking parameters required to execute the accommodation booking function to obtain the filling result; as well as Based on the populated results, the accommodation booking function is invoked to determine recommended information for the accommodation service request.

3. The method according to claim 2, further comprising: In response to the presence of a required predefined parameter that could not be filled in the filling result, a prompt message is displayed, indicating that supplementary information should be entered; as well as In response to the received supplementary information corresponding to the prompt information, the filling result is updated until all required predefined parameters are filled.

4. The method according to claim 1, wherein obtaining output information from the large model comprises: Based on the user's identity attribute information corresponding to the user input, determine the accommodation booking standard corresponding to the identity attribute information; Based on the aforementioned accommodation booking criteria, adjust the search parameters of the accommodation booking function; as well as Based on the search results from the accommodation booking function, recommended information is determined for the accommodation service request.

5. The method according to claim 1, wherein obtaining output information from the large model comprises: In response to the recommendation information indicating multiple candidate accommodation recommendation results, Based on the descriptive information of each candidate accommodation recommendation result among the multiple candidate accommodation recommendation results, the feature representation of each candidate accommodation recommendation result is determined respectively; as well as Based on the degree of matching between the feature representation corresponding to the user's preference attributes and the feature representation of each candidate accommodation recommendation result, at least one accommodation recommendation result is determined from the multiple candidate accommodation recommendation results to generate the output information, wherein the user includes the user corresponding to the user input.

6. The method of claim 5, wherein the descriptive information for each candidate accommodation recommendation indicates at least one of the following: The static feature information involved in each candidate accommodation recommendation result, The dynamic feature information involved in each candidate accommodation recommendation result.

7. The method of claim 1, wherein obtaining output information from the large model comprises: In response to receiving a response to the recommendation information, an evaluation result is determined on the accommodation recommendation result involved in the recommendation information, wherein the response information includes comments on the accommodation recommendation result; as well as Based on the evaluation results, feedback information is generated for the accommodation service request.

8. The method according to claim 7, wherein determining the evaluation result of the accommodation recommendation results related to the recommendation information using the large model includes: Based on the information provided in the response, determine the intent behind the response; Based on the stated response intent, obtain comments on the accommodation options involved in the accommodation recommendation results that correspond to the stated response intent; as well as The ratings of the accommodation options determined based on the reviews will be used as the feedback information.

9. An interactive device based on accommodation, comprising: The user input receiving module is configured to provide a maximum model of user input received in the target application's session interface that is associated with the target object's accommodation service request; The output information determination module is configured to obtain output information from the large model, including one of the following: Recommendation information for the requested accommodation service, the recommendation information indicating accommodation recommendation results, or Feedback information in response to the accommodation service request; wherein the output information is generated by the large model based at least on the type of accommodation service request indicated by the user input, by invoking the accommodation booking function; as well as The results presentation module is configured to present the output information via the session interface in the target application.

10. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 8.

12. A computer program product comprising computer-executable instructions that, when executed by a processor, implement the method of any one of claims 1 to 8.

Images