Interaction method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to a method and device for interaction, equipment and a storage medium. The method provided herein comprises: determining a predetermined parameter protocol for travel service recommendation, the predetermined parameter protocol comprising at least a corresponding set of necessary parameter items for different travel service types; in response to first input content which is received in the target application and is associated with the travel request of the user, providing the first input content to the large model; obtaining recommendation information for at least one travel service related to the travel request from the large model, the recommendation information being generated by the large model by calling at least one travel service function based on the corresponding set of necessary parameter items and the first input content; and presenting the recommendation information as first reply content for the first input content in the target application.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computer technology, and more specifically, to a method, apparatus, device, and storage medium for interaction. Background Technology

[0002] The widespread adoption of internet technology has provided convenient online booking platforms for travel services. Users can search, compare, and book services such as flights, hotels, and car rentals online, greatly improving travel efficiency. Mobile communication technology: With the rapid development of mobile communication technology, users can book and manage travel services anytime, anywhere through mobile platforms such as mobile apps and WeChat mini-programs, realizing the mobilization of travel services. Summary of the Invention

[0003] In a first aspect of this disclosure, a method for interaction is provided. The method includes: determining a pre-defined parameter protocol for recommending travel services, the pre-defined parameter protocol including at least a corresponding set of necessary parameter items for different travel service types; providing the first input content to a large model in response to receiving first input content associated with a user's travel request in a target application; obtaining recommendation information from the large model for at least one travel service related to the travel request, the recommendation information being generated by the large model based on the corresponding set of necessary parameter items and the first input content by invoking at least one travel service function; and presenting the recommendation information as a first response content in the target application to the first input content.

[0004] In a second aspect of this disclosure, an apparatus for interaction is provided. The apparatus includes: a predetermined parameter protocol determination module configured to determine a predetermined parameter protocol for recommending travel services, the predetermined parameter protocol including at least a corresponding set of necessary parameter items for different travel service types; an input content providing module configured to provide the first input content to a large model in response to receiving first input content associated with a user's travel request in a target application; a recommendation information acquisition module configured to acquire recommendation information from the large model for at least one travel service related to the travel request, the recommendation information being generated by the large model based on the corresponding set of necessary parameter items and the first input content by invoking at least one travel service function; and a response content presentation module configured to present the recommendation information as a first response content in the target application for the first input content.

[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 device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement 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 according to a first aspect of this disclosure.

[0008] It should be understood that the content described in this content 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 according to an embodiment of the present disclosure is shown;

[0011] Figure 2 A flowchart of an example process 200 for an interaction method according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A flowchart illustrating an example process according to some embodiments of this disclosure is shown;

[0013] Figure 4 A schematic diagram of an example process according to some embodiments of the present disclosure is shown;

[0014] Figure 5 A schematic structural block diagram of an interactive device according to some embodiments of the present disclosure is shown; and

[0015] Figure 6 A block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. Detailed Implementation

[0016] 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.

[0017] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[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. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0019] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0020] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of basic functions.

[0021] As briefly described above, users can book and manage travel services anytime, anywhere through mobile platforms such as mobile apps and WeChat mini-programs. Machine learning models based on natural language recognition, with their superior language understanding and generation capabilities, can efficiently handle complex and varied language processing tasks. By leveraging such machine learning models, users' intentions can be better understood when booking travel services, thus providing a more intelligent and personalized service experience.

[0022] However, current solutions mostly limit themselves to simply summarizing information related to travel services and presenting it to users using explanatory text or links generated by machine learning models. This approach often fails to accurately match users' actual needs, forcing them to navigate to other pages for secondary filtering. This is especially true when users need to combine multiple travel options (such as airplanes and hotels), requiring them to frequently switch between multiple pages for comparison, which undoubtedly increases their cognitive burden and time cost.

[0023] In view of this, embodiments of the present disclosure provide a scheme for interaction. According to this scheme, a pre-defined parameter protocol for travel service recommendations is first determined, the pre-defined parameter protocol including at least a corresponding set of necessary parameter items for different travel service types. After determining the pre-defined parameter protocol, in response to receiving first input content associated with a user's travel request in the target application, the first input content is provided to a large model. Then, recommendation information for at least one travel service related to the travel request is obtained from the large model, the recommendation information being generated by the large model based on the corresponding set of necessary parameter items and the first input content by invoking at least one travel service function. Once the recommendation information is obtained, it is presented as a first response to the first input content in the target application.

[0024] The following description will make it clearer that, according to the scheme disclosed herein, based on a pre-defined parameter protocol and user input, and leveraging the natural language understanding and generation capabilities of a large-scale model, recommendation information for travel requests can be quickly generated. This makes the booking process for travel services more efficient and accurate. Users no longer need to manually filter and compare various travel options; instead, they can directly obtain the optimal recommendation results from the system, thereby improving booking efficiency and accuracy. Furthermore, a set of essential parameters, as core elements for understanding user travel requests, ensures that the large-scale model more accurately grasps the user's true intentions. These parameters can cover key information such as travel date, destination, mode of transport, and budget range, enabling the large-scale model to be targeted and quickly locate the travel service details that the user cares about most when parsing user input.

[0025] The following will further describe in detail various example implementations of this scheme with reference to the accompanying drawings.

[0026] 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.

[0027] The target application 120 can be operated by one or more users 130. In some embodiments, the target application 120 may include or be implemented as a digital assistant (not shown). The digital assistant may be configured to have intelligent conversational capabilities. Figure 1 In the example shown, the digital assistant can be integrated into the target application 120 as part of the target application 120 to assist in task processing within the target application 120. In other examples, the digital assistant can be configured to run as a standalone application, such as a web application or other type of application. In such examples, the digital assistant and the target application 120 can be considered as the same application. The digital assistant is provided to assist user 130 in various task processing needs in different applications and scenarios. During interaction with the digital assistant, user 130 inputs interactive messages, and the digital assistant responds to user 130's input by providing reply messages. Typically, the digital assistant can support users 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 can interact with user 130 as a contact. For example, the digital assistant can be implemented in an instant messaging (IM) application. The digital assistant can interact with user 130 in a one-on-one chat session. In some embodiments, the digital assistant can interact with multiple users in a group chat session that includes multiple users.

[0029] For each user 130, terminal device 110 may present an interactive interface 140 of target application 120 or digital assistant, such as a conversation window with the digital assistant. User 130 may enter conversation messages in the conversation window, and target application 120 may determine the digital assistant's response message based on the created configuration information and present it to the user in interface 140. In some embodiments, depending on the configuration of target application 120, interaction messages with target application 120 may include multimodal messages, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and so on.

[0030] The target application 120 can be deployed locally on the terminal device 110 of each user 130, and / or can be supported by the server device 150. When the target application 120 runs locally on the terminal device 110, the user 130 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 the server device 150 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 in the target application 120, may be based on the target model 160. During the operation of the target application 120, one or more target models 160 may be invoked. In the target application 120, the digital assistant may utilize the target model 160 to understand user input and provide responses to the user based on the output of the target model 160.

[0032] As used in this paper, 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 paper, "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.

[0033] Although shown as independent of terminal device 110, one or more target models 160 may run on terminal device 110 or other remote servers.

[0034] Terminal device 110 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 thereof, including accessories and peripherals of these devices or any combination thereof. Server device 150 may include, for example, computing systems / servers, such as mainframes, edge computing nodes, computing devices in cloud environments, etc.

[0035] 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.

[0036] Some embodiments of this disclosure provide a method for interaction, which can be implemented on a terminal device 110. The interaction method provided in this disclosure can be applied to business travel scenarios. Business travel refers to travel activities undertaken for official business or work needs. Such travel may involve movement across cities, regions, or even national borders, with the purpose of completing specific work tasks, such as attending meetings, negotiating business, or conducting project inspections. It should be noted that, depending on actual needs, the interaction method provided in this disclosure can also be applied to other scenarios, and the embodiments of this disclosure do not limit this. For clarity, unless otherwise specified, the following description uses business travel scenarios as examples to illustrate various embodiments of this disclosure.

[0037] Figure 2 A flowchart of an example process 200 for an interactive method according to some embodiments of the present disclosure is shown. Process 200 may be implemented at a terminal device 110.

[0038] Reference Figure 2 In box 210, terminal device 110 determines a reservation parameter protocol recommended for travel services, the reservation parameter protocol including at least a set of necessary parameter items for different types of travel services.

[0039] As an example, the pre-defined parameter protocol is built upon JSON format and SQL query statements. JSON (JavaScript Object Notation) is a lightweight data-interchange format that is easy for humans to read and write, and also easy for machines to parse and generate. JSON supports various data types, including strings, numbers, booleans, arrays, and objects, meeting the needs of complex parameter transmission in travel service systems. As an example, the pre-defined parameter protocol can use JSON format to define the names, types, and value ranges of parameters. SQL (Structured Query Language) is a standard programming language specifically designed for accessing and manipulating database systems. SQL query statements have powerful data query, insertion, update, and deletion functions, meeting the diverse database operation needs of travel service systems. As an example, the pre-defined parameter protocol can contain multiple parameters related to SQL query statements, which are used to construct and execute SQL queries.

[0040] As an example, the booking parameter agreement includes a set of required parameter items corresponding to each type of travel service. Required parameter items can refer to parameters that are necessary for the corresponding travel service type. Taking a flight search function as an example, a set of required parameter items may include, but is not limited to: flight number, departure point, destination, and departure date.

[0041] In box 220, terminal device 110, in response to receiving first input content associated with a user's travel request in the target application, provides the first input content to the maximum model.

[0042] As an example, terminal device 110 can listen to and handle events of interface elements (such as buttons, forms, etc.) in the interactive interface presented by target application 120 to obtain the first input content. Specifically, when a user clicks a button or submits a form, terminal device 110 can capture these operations and determine that these operations are associated with the user's travel request, thereby receiving the first input content. As an example, the first input content can include various forms such as text, voice, and images. As an example, the large model can be a large language model (LLM) based on natural language processing.

[0043] In box 230, terminal device 110 obtains recommendation information for at least one travel service in response to a travel request from a large model. The recommendation information is generated by the large model based on a corresponding set of necessary parameter items and first input content by calling at least one travel service function.

[0044] As an example, the recommended information may include, but is not limited to, flight information (such as flight number, departure and arrival times, cabin class and fare) for recommended flights determined by the large model for travel requests, train ticket information (such as train number, departure and arrival times, seat type and fare), and hotel booking information (such as hotel name, room type, check-in and check-out dates, price and booking status).

[0045] In some embodiments, the recommendation information is generated by the large model as follows: First, the large model determines the target travel service type corresponding to the travel request based on the first input content. Then, the large model obtains the necessary parameter information of a set of target necessary parameter items corresponding to the target travel service type from the first input content. Subsequently, based on the necessary parameter information, the large model generates recommendation information by invoking the target travel service function for the target travel service type.

[0046] As an example, after receiving the first input content sent by terminal device 110, the large model can use its natural language processing capabilities to parse this first input content to determine the target travel service type corresponding to the travel request. The target travel service type may include, but is not limited to, air travel, train travel, car travel, hotel travel, and attraction tickets. By analyzing keywords, phrases, and contextual information in the first input content, the large model can accurately identify the type of travel service required by the user.

[0047] Once the target travel service type is determined, the large model can further extract essential parameter information corresponding to a set of target essential parameter items from the first input content. These essential parameter items are predefined and constitute the key data required to generate recommendation information. For example, for air travel services, essential parameter items may include departure point, destination, travel date, number of passengers, etc.; for hotel booking services, essential parameter items may include check-in date, check-out date, room type, surrounding facilities, etc.

[0048] After obtaining the necessary parameter information, the large model will invoke the target travel service function for the target travel service type based on this information. For example, for air travel services, the target travel service function might include flight search and filtering. The large model passes the necessary parameter information as input to the target travel service function and instructs it to generate recommendation information based on these parameters.

[0049] After receiving the necessary parameter information, the target travel service function performs a series of calculations and queries. For example, it can access a database to obtain relevant travel service data (such as flight information, hotel information, prices, etc.) and filter and sort it according to the necessary parameter information. Ultimately, these service functions generate a set of recommendations that meet the user's needs and return it to the larger model.

[0050] After receiving the recommendation information generated by the target travel service function, the big data model can further process and integrate it. For example, the big data model can optimize and adjust the recommendation information based on user preferences, historical behavior, and other contextual information to ensure the accuracy and personalization of the recommendations. Then, the big data model will send the processed recommendation information back to the terminal device 110 for the user to view and select.

[0051] In some embodiments, the target travel service function is associated with a corresponding query interface for the target travel service type, and the target travel service function is invoked through the corresponding query interface. As an example, the query interface can refer to an interface used to access and retrieve data for a specific type of travel service; such an interface may include, but is not limited to, an Application Programming Interface (API).

[0052] In some embodiments, in response to an indication obtained from a large model that the first input content does not conform to the predetermined travel criteria, the terminal device 110 presents the target content in the first input content that does not conform to the predetermined travel criteria in the target application.

[0053] As an example, booking travel standards can be the restrictions set by the target entity for business travel; therefore, booking travel standards can also be referred to as travel allowances. For example, booking travel standards may include the choice of mode of transportation (such as airplane, train, car, etc.), accommodation standards, and meal allowances.

[0054] The large model compares necessary parameter information with the pre-booked travel standards. If the necessary parameter information meets the pre-booked travel standards, the large model determines that the first input content conforms to the pre-booked travel standards and can provide corresponding instructions. If the necessary parameter information does not meet the pre-booked travel standards (e.g., the airfare exceeds the standard price), the large model determines that the first input content does not conform to the pre-booked travel standards. At this time, the large model can further instruct the terminal device 110 on the target content that does not conform to the travel standards, thereby enabling the terminal device 110 to provide targeted prompts. Such prompts aim to indicate which target content has not met the standards. Through such prompts, the user 130 can quickly understand the problem and adjust their travel choices accordingly to ensure compliance with travel policies.

[0055] Taking air travel services as an example, the large model can check whether the departure point, destination, and departure time in the necessary parameters are within the range specified by the constraints. If all of this information meets the booking criteria, the large model determines that the first input content meets the booking criteria; otherwise, the large model determines that the first input content does not meet the booking criteria.

[0056] In this way, terminal device 110 can complete the verification of the scheduled travel standards without using all parameters. This processing method reduces the amount of computation, making the verification process more efficient and faster.

[0057] In some embodiments, in response to an indication obtained from the large model that the first input content lacks necessary parameter information (e.g., lack of departure time or departure location), the terminal device 110 presents an indication in the target application requesting input of necessary parameter information.

[0058] As an example, the indication requesting necessary parameter information is designed to inform user 130 that their input is incomplete or lacks key information, thus preventing them from performing subsequent operations. This ensures that user 130 is promptly aware of their input problems and has the opportunity to correct or supplement them. As an example, the presentation of the indication requesting necessary parameter information can vary depending on the type of terminal device 110 and its interface design. For instance, in some smartphone applications, the prompt may appear as a pop-up window or message box, while in web applications, it may be displayed as a text prompt or warning label.

[0059] In some embodiments, in response to an indication that recommendation information cannot be obtained from a large model, the terminal device 110 presents an indication in the target application that the target travel service type corresponding to the travel request does not support recommendations.

[0060] As an example, when a user provides initial input through terminal device 110, there might be a situation where the target travel service type corresponding to the initial input is not supported. For instance, the large model might only support airline ticket booking services, but the initial input includes bus booking information. In this case, after receiving the initial input from terminal device 110, the large model will perform necessary parsing and identification. When the large model identifies that the target travel service type corresponding to the initial input is not within the supported service range, it will send an indication to terminal device 110 stating that it cannot provide recommendation information for the target travel service type.

[0061] In this way, the terminal device 110 can inform the user why the recommendation information cannot be obtained at present, thereby helping the user to better understand the scope of services currently supported.

[0062] After receiving an instruction from the large model that it cannot provide recommendation information, the terminal device 110 will present a clear prompt in the target application that the target travel service type corresponding to the travel request does not support recommendations.

[0063] In some embodiments, in response to an indication obtained from a large model that the first input content is not related to the travel service, the terminal device 110 presents an indication in the target application requesting input of content related to the travel service.

[0064] As an example, the first input should be related to travel services, such as querying flight, train ticket, or hotel booking information. However, in some cases, a user might submit a request unrelated to travel services, such as querying the price of an item. For example, when the large model receives the first input, if it recognizes that the first input is a query for the price of an item rather than information related to travel services, it will send an indication to the terminal device 110 stating that it cannot provide recommendation information for this first input (i.e., querying the price of an item). Upon receiving this indication, the terminal device 110 can present a corresponding prompt in the target application to request the user to input information related to travel services.

[0065] In some embodiments, the predefined parameter protocol further includes at least one optional parameter item. Terminal device 110 obtains additional recommendation information from a large model for at least one travel service related to the travel request. This additional recommendation information is generated by the large model based on a corresponding set of necessary parameter items, at least one optional parameter item, and the first input content, by invoking at least one travel service function. The user then presents this additional recommendation information as a first response to the first input content in the target application.

[0066] As an example, a large model can determine whether optional parameter information is included in the first input based on a predefined parameter protocol. Optional parameters can be information that can further enhance the accuracy or personalization of the service. Optional parameters include, but are not limited to, user 130's preference settings, special needs (such as non-smoking carriages, child seats, etc.), and budget constraints. Optional parameters can further optimize the recommended information to better meet user 130's personalized needs.

[0067] In some embodiments, another recommendation is generated by the large model as follows: Based on the first input content, the large model determines the target travel service type corresponding to the travel request. Then, the large model obtains the necessary parameter information for a set of target necessary parameter items corresponding to the target travel service type from the first input content. Subsequently, the large model obtains the optional parameter information corresponding to at least one optional parameter item from the first input content. Next, based on the necessary parameter information and the optional parameter information, the large model generates another recommendation by invoking the target travel service function for the target travel service type.

[0068] It should be noted that the information regarding necessary parameter information, target travel service type, and target travel service function can be found in the preceding text, and will not be repeated here in the embodiments disclosed herein. Unlike the preceding text, in addition to the necessary parameter items, the large model also obtains optional parameter information corresponding to at least one optional parameter item from the first input content. These optional parameter items may include travel time preferences, cabin class, hotel star rating, price range, etc. Although this information is not essential for generating recommendation information, it can further refine the recommendation results, making them more in line with the user's personalized needs.

[0069] After obtaining the necessary and optional parameter information, the large model will invoke the target travel service function for the target travel service type based on this information. Then, the large model will generate another recommendation based on the information returned by the target travel service function.

[0070] In some embodiments, another recommendation information (hereinafter also referred to as target recommendation information) is determined by the target travel service function based on optional parameter information, by filtering and / or sorting multiple candidate recommendation information determined based on necessary parameter information.

[0071] As an example, after receiving the necessary parameter information, the target travel service function can query the database or call the server-side device 150 to obtain multiple candidate recommendations based on these parameters. As an example, the target travel service function can also eliminate candidate recommendations that do not match user 130's preferences from the multiple candidate recommendations based on optional parameter information. For example, if user 130 chooses to only travel by high-speed rail, the target travel service function can eliminate all non-high-speed rail candidate services to complete the filtering of multiple candidate recommendations. As an example, the target travel service function can also sort the remaining candidate recommendations. The sorting can be based on factors such as price, time, and comfort, and these factors can be weighted according to user 130's preferences and optional parameter settings. Subsequently, the target travel service function can use the filtered and sorted candidate recommendations as the target recommendation information.

[0072] In this approach, the target recommendation information is determined by filtering and / or ranking multiple candidate recommendations based on optional parameters. This method can improve the personalization and accuracy of the service, thereby providing users with a more satisfactory travel experience.

[0073] As an example, the required parameters, optional filter parameters, and optional sorting parameters can be shown in Table 1.

[0074] Table 1

[0075]

[0076]

[0077] Referring to Table 1, necessary parameters may include departure point, destination, and departure time. For optional filtering parameters, assuming the first input includes the information "ticket price less than 500", then terminal device 110 can determine parameter B1 related to the filtering object based on "ticket price", parameter B2 related to the comparison relationship based on "less than", and parameter B3 related to the filtering target value based on "500". For optional sorting parameters, assuming the first input includes the information "earliest departure time flight", then terminal device 110 can determine parameter C1 related to the sorting dimension based on "departure time", and parameter C2 related to the sorting method based on "earliest". In this way, terminal device 110 will consider these factors when querying tickets. Ultimately, user 130 may see a set of ticket options that meet basic travel needs while also considering personalized preferences.

[0078] In this way, user 130's input is precisely parsed into a predefined parameter structure (necessary parameters, optional filtering parameters, and optional sorting parameters), avoiding ambiguity and misunderstanding, thus ensuring the accuracy of parameter parsing. Furthermore, this parameter structure design is highly flexible; user 130 can add new parameters or adjust existing parameters according to the necessary, optional filtering, and optional sorting parameters in their respective ways, adapting to constantly changing business needs and user 130's preferences. Moreover, the clear parameter structure and unified parsing logic greatly simplify system maintenance, enabling developers to more easily understand and modify the code.

[0079] Therefore, embodiments of this disclosure, by means of a predetermined parameter protocol, parse the input of user 130 into a predefined parameter structure (necessary parameters and optional parameters). This method ensures the accuracy, scalability, and maintainability of parameter parsing, providing strong support for scenarios such as airline tickets, train tickets, and hotel services.

[0080] In box 240, terminal device 110 presents recommendation information for at least one travel service as a first response to the first input content in target application 120.

[0081] As an example, the recommendation information can be presented in the form of cards in the first response. Furthermore, depending on actual needs, the terminal device 110 can also present the first response in other ways. For example, the terminal device 110 can choose to present the recommendation information in the first response by sorting according to price, time, or comfort level.

[0082] In some embodiments, in response to detecting second input content in response to the first response, terminal device 110 determines whether the second input content involves modification of necessary parameter information. If the second input content involves modification of necessary parameter information, terminal device 110, in response to the modified necessary parameter information meeting the predetermined parameter requirements of the target travel service function, corrects the recommendation information of at least one travel service by invoking the target travel service function, at least based on the modified necessary parameter information and utilizing a large model. Then, terminal device 110 presents the corrected recommendation information as the second response content in response to the second input content in the target application 120.

[0083] As an example, if user 130 is dissatisfied with the first response or believes that some content in the first input needs to be adjusted, they can use the interactive interface to input second input. The second input can be a correction, supplement, or a completely new request to the first input.

[0084] As an example, upon detecting a second input that involves modifications to necessary parameter information, terminal device 110 checks whether the modified necessary parameter information meets the predetermined parameter requirements of the target service function. As an example, the predetermined parameter requirements may include minimum requirements for at least one of the following: parameter format, range, and validity.

[0085] As an example, corrections to recommendation information for at least one travel service may include, but are not limited to, re-querying, re-filtering, and re-sorting. As an example, terminal device 110 presents the corrected recommendation information as a second response to the second input content in target application 120, so that user 130 can see the updated recommendation information, which will better suit user 130's adjusted needs.

[0086] In this way, terminal device 110 can respond to the second input from user 130 and correct the travel service recommendation information based on the modification of necessary parameter information. This process ensures that user 130 can obtain recommendation information that meets their adjusted needs in a timely manner.

[0087] In some embodiments, in response to detecting second input content in response to the first response, terminal device 110 determines whether the second input content involves modification of optional parameter information. If the second input content involves modification of optional parameter information, terminal device 110, based at least on the modified optional parameter information, uses a large model to correct the recommendation information of at least one travel service by invoking the target travel service function. Then, terminal device 110 presents the corrected recommendation information as a third response to the second input content in the target application 120.

[0088] As an example, if a second input is detected that involves modifications to optional parameter information, terminal device 110 can directly invoke the target travel service function again based on the modified optional parameter information using a large model. After invoking the target travel service function, the large model can correct the recommendation information of at least one target travel service based on the modified optional parameter information. Corrections to the recommendation information may include, but are not limited to, re-querying, re-filtering, and re-sorting, to ensure that the recommendation information better meets the expectations and needs of user 130.

[0089] As an example, terminal device 110 presents the corrected recommendation information as a third response to the second input in target application 120, so that user 130 can see the updated recommendation information, which are more closely aligned with their adjusted needs and preferences.

[0090] As an example, terminal device 110 can repeat the above process until user 130 obtains satisfactory recommendation information. Each time new input content is detected, the necessary parameter information and optional parameter information can be processed separately in the above manner to update the corresponding recommendation information.

[0091] It should be noted that the embodiments of this disclosure are not limited to recommending information for a single travel service. Through the methods described above, the embodiments of this disclosure can support combined recommendations for multiple travel services. For example, simultaneously recommending travel services related to "airplanes and hotels" to user 130, or simultaneously pushing travel services related to "trains and hotels" to user 130, etc. User 130 only needs to input once to simultaneously obtain recommendation results for multiple travel services. This greatly simplifies the operation process, saves user 130 the time and effort spent frequently jumping between multiple pages, thereby improving user 130's experience and travel efficiency.

[0092] In some embodiments, the output of the large model can be defined, and the association between these parsing results and the relevant operations of the terminal device 110 can be established. This association can be shown in Table 2.

[0093] Table 2

[0094]

[0095]

[0096] In this way, the embodiments of this disclosure can converge various possible parsing results of the user 130's input content in the interactive interface to a limited range. This limited range makes the processing of the parsing results more explicit and convenient, improving processing efficiency. Furthermore, the clear parsing result-operation relationship helps to parse complex business scenarios into multiple sub-scenarios. When a new business scenario needs to be added, it can be more easily integrated into the existing business scenario, thereby improving the convenience of iteration and maintenance.

[0097] Further details regarding the scheme disclosed herein will be provided below. Figure 3 and Figure 4 Describe it.

[0098] Figure 3 A flowchart of an example process 300 according to some embodiments of the present disclosure is shown.

[0099] Reference Figure 3 In box 301, terminal device 110 obtains the third input content from user 130.

[0100] In box 302, terminal device 110 can use a large model to parse the third input content in order to identify the user 130's interaction intent in the third input content.

[0101] In box 303, terminal device 110 can use a large model to determine whether the third input content instructs target application 120 to introduce itself. If the third input content instructs target application 120 to introduce itself, in box 304, terminal device 110 presents a response related to the self-introduction. If the third input content does not instruct target application 120 to introduce itself, in box 305, terminal device 110 determines whether the third input content involves a travel request.

[0102] If the third input involves a travel request, in box 306, terminal device 110 can use a large model to determine whether the travel service involved in the third input is a currently supported travel service. If the third input does not involve a travel request, in box 307, terminal device 110 presents a response message indicating that the third input does not involve a travel request.

[0103] If the travel service involved in the third input is a currently supported travel service, in box 308, terminal device 110 extracts the necessary parameters from the third input. If the travel service involved in the third input is a currently unsupported travel service, in box 309, terminal device 110 presents a response related to the unsupported travel service.

[0104] In step 310, terminal device 110 can use the large model to determine whether the necessary parameter information meets the predetermined parameter requirements of the target travel service function. If the necessary parameter information meets the predetermined parameter requirements, in step 311, terminal device 110 can use the large model to determine whether the necessary parameter information meets the predetermined travel criteria. If the necessary parameter information does not meet the predetermined parameter requirements, in step 312, terminal device 110 presents a response related to the failure of the necessary parameter information to meet the predetermined parameter requirements.

[0105] If the necessary parameter information meets the reservation travel criteria, in box 313, terminal device 110 extracts all relevant parameters (e.g., all required and optional parameters) from the third input content. If the necessary parameter information does not meet the reservation travel criteria, in box 314, terminal device 110 presents a response related to the failure of the necessary parameter information to meet the reservation travel criteria.

[0106] In box 315, terminal device 110, based on all extracted relevant parameters, utilizes a large model and determines recommendation information for at least one travel service by invoking the target travel service function.

[0107] In box 316, terminal device 110 presents the recommended information as a fourth response to the third input content.

[0108] Figure 4 A flowchart of an example process 400 according to some embodiments of the present disclosure is shown. Unlike example process 300, the fourth input content in example process 400 may involve modification of one or more parameters (mandatory or optional parameters) in the third input content.

[0109] Reference Figure 4 In step 401, terminal device 110 obtains the fourth input content from user 130.

[0110] In step 402, terminal device 110 can use the large model to parse the fourth input content in order to identify the user 130's interaction intent in the fourth input content.

[0111] In step 403, terminal device 110 can use the large model to determine whether the fourth input content indicates that the recommendation information should be regenerated without changing the necessary and optional parameter information. If the fourth input content indicates that the recommendation information should be regenerated without changing the necessary and optional parameter information, in step 404, terminal device 110 re-invokes the target travel service function based on the original necessary and optional parameter information to redetermine the recommendation information. If the fourth input content indicates that the recommendation information should be regenerated with changes to the necessary (and / or) optional parameter information, in step 405, terminal device 110 can use the large model to determine whether the fourth input content involves modification of the necessary parameter information.

[0112] If the fourth input involves modifying the necessary parameter information, in step 406, the terminal device 110 extracts the modified necessary parameter information from the fourth input. If the fourth input does not involve modifying the necessary parameter information, in step 407, the terminal device 110 corrects the recommendation information of at least one travel service based on the modified optional parameter information using a large model.

[0113] In step 408, terminal device 110 can use the large model to determine whether the modified necessary parameter information meets the predetermined parameter requirements of the target travel service function. If the modified necessary parameter information meets the predetermined parameter requirements, in step 409, terminal device 110 can use the large model to determine whether the newly modified necessary parameter information meets the predetermined travel standards. If the modified necessary parameter information does not meet the predetermined parameter requirements, in step 410, terminal device 110 presents a response related to the modified necessary parameter information not meeting the predetermined parameter requirements.

[0114] If the modified necessary parameter information meets the reservation travel criteria, in box 411, terminal device 110 re-extracts all relevant parameters from the fourth input content. If the modified necessary parameter information does not meet the reservation travel criteria, in box 412, terminal device 110 presents a response related to the modified necessary parameter information not meeting the reservation travel criteria.

[0115] In box 413, terminal device 110, based on all the re-extracted relevant parameters, uses a large model to correct the recommendation information of at least one target travel service by invoking the target travel service function.

[0116] In box 414, terminal device 110 presents the corrected recommendation information as a fifth response to the fourth input content.

[0117] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes. Figure 5 A schematic structural block diagram of an interactive device 500 according to some embodiments of the present disclosure is shown. The device 500 may be implemented as or included in a terminal device 110110. Various modules / components in the device 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0118] Reference Figure 5 The apparatus 500 includes a predetermined parameter protocol determination module 510, an input content provisioning module 520, a recommendation information acquisition module 530, and a response content presentation module 540. In some embodiments, the function determination module 510 is configured to determine a predetermined parameter protocol for travel service recommendations, the predetermined parameter protocol including at least a corresponding set of necessary parameter items for different travel service types. The input content provisioning module 520 is configured to provide the first input content to a large model in response to receiving first input content associated with a user's travel request in a target application. The recommendation information acquisition module 530 is configured to acquire recommendation information from the large model for at least one travel service related to the travel request, the recommendation information being generated by the large model based on a corresponding set of necessary parameter items and the first input content by invoking at least one travel service function. The response content presentation module 540 is configured to present the recommendation information as a first response content in the target application for the first input content.

[0119] In some embodiments, the recommendation information is generated by the large model in the following manner: based on the first input content, determining the target travel service type corresponding to the travel request; obtaining the necessary parameter information of a set of target necessary parameter items corresponding to the target travel service type from the first input content; and generating the recommendation information by calling the target travel service function for the target travel service type based on the necessary parameter information.

[0120] In some embodiments, the apparatus 500 further includes a first correction module. The first correction module is configured to: in response to detecting second input content for the first response content, determine whether the second input content involves modification of necessary parameter information; if the second input content involves modification of necessary parameter information, in response to the modified necessary parameter information meeting the predetermined parameter requirements of the target travel service function, correct the recommendation information of at least one travel service by invoking the target travel service function, at least based on the modified necessary parameter information, using a large model; and present the corrected recommendation information as a second response content for the second input content in the target application.

[0121] In some embodiments, the device 500 further includes a first prompting module. The first prompting module is configured to present an indication in the target application requesting input of necessary parameter information in response to an indication that the first input content lacks necessary parameter information obtained from the large model.

[0122] In some embodiments, the device 500 further includes a second prompting module. The second prompting module is configured to: in response to an indication that recommendation information cannot be obtained from the large model, present an indication in the target application that the target travel service type corresponding to the travel request does not support recommendations.

[0123] In some embodiments, the device 500 further includes a third prompting module. The third prompting module is configured to: in response to an indication obtained from the large model that the first input content is not related to the travel service, present an indication in the target application requesting input of content related to the travel service.

[0124] In some embodiments, the device 500 further includes a fourth prompting module. The fourth prompting module is configured to: in response to an indication obtained from the large model that the first input content does not meet the predetermined travel criteria, present the target content in the first input content that does not meet the predetermined travel criteria in the target application.

[0125] In some embodiments, the predetermined parameter protocol further includes at least one optional parameter item, and the apparatus 500 further includes an optional parameter processing module. The optional parameter processing module is configured to: obtain additional recommendation information from a large model for at least one travel service related to a travel request, the additional recommendation information being generated by the large model based on a corresponding set of necessary parameter items, at least one optional parameter item, and first input content, by invoking at least one travel service function; and present the additional recommendation information as a first response to the first input content in the target application.

[0126] In some embodiments, another recommendation is generated by the large model in the following manner: based on the first input content, determining the target travel service type corresponding to the travel request; obtaining necessary parameter information of a set of target necessary parameter items corresponding to the target travel service type from the first input content; obtaining optional parameter information corresponding to at least one optional parameter item from the first input content; and generating another recommendation based on the necessary parameter information and the optional parameter information by invoking the target travel service function for the target travel service type.

[0127] In some embodiments, another set of recommendation information is determined by the target travel service function based on optional parameter information, by filtering and / or sorting multiple candidate recommendation information determined based on necessary parameter information.

[0128] In some embodiments, the apparatus 500 further includes a second correction module. The second correction module is configured to: in response to detecting second input content in response to the first response content, determine whether the second input content involves modification of optional parameter information; if the second input content involves modification of optional parameter information, at least based on the modified optional parameter information, using a large model, correct recommendation information of at least one target travel service by invoking the target travel service function; and present the corrected recommendation information as a third response content in the target application in response to the second input content.

[0129] Figure 6 A block diagram is shown of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented. The electronic device 600 may, for example, be used to implement... Figure 1 The terminal device 110 shown. It should be understood that, Figure 6 The electronic device 600 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein.

[0130] Reference Figure 6 Electronic device 600 is in the form of a general-purpose electronic device. Components of electronic device 600 may include, but are not limited to, one or more processors or processing units 610, memory 620, storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processing unit 610 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 620. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 600.

[0131] Electronic device 600 typically includes multiple computer storage media. Such media can be any available media accessible to electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 620 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 630 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media capable of storing information and / or data and accessible within electronic device 600.

[0132] Electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 6 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 620 may include computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0133] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 600 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0134] Input device 650 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 660 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 600 can also communicate with one or more external devices (not shown) via communication unit 640 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 600, or with any device that enables electronic device 600 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] Various implementations of this disclosure have been described above. The foregoing description is exemplary and not exhaustive, nor is it 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 determined 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. A method for interaction, comprising: Determine a booking parameter protocol for travel service recommendations, the booking parameter protocol including at least a set of necessary parameter items for different types of travel services; In response to receiving first input content associated with a user's travel request in the target application, the first input content is provided to the largest model; The large model obtains recommendation information for at least one travel service for the travel request. The recommendation information is generated by the large model based on the corresponding set of necessary parameter items and the first input content by calling at least one travel service function. as well as The recommendation information is presented as a first response to the first input content in the target application.

2. The method according to claim 1, wherein the recommendation information is generated by the large model in the following manner: Based on the first input content, determine the target travel service type corresponding to the travel request; Obtain necessary parameter information for a set of target necessary parameter items corresponding to the target travel service type from the first input content; and Based on the necessary parameter information, the recommendation information is generated by calling the target travel service function for the target travel service type.

3. The method according to claim 2, further comprising: In response to detecting a second input content in relation to the first response, it is determined whether the second input content involves modification of the necessary parameter information; If the second input content involves modification of the necessary parameter information, in response to the modified necessary parameter information meeting the predetermined parameter requirements of the target travel service function, at least based on the modified necessary parameter information, the large model is used to correct the recommendation information of the at least one travel service by calling the target travel service function; as well as The corrected recommendation information is presented as a second response to the second input content in the target application.

4. The method according to claim 1, further comprising: In response to an indication that the first input content lacks necessary parameter information obtained from the large model, an indication requesting the input of the necessary parameter information is presented in the target application.

5. The method according to claim 1, further comprising: In response to an indication that recommendation information cannot be obtained from the large model, an indication is presented in the target application that the target travel service type corresponding to the travel request does not support recommendations.

6. The method according to claim 1, further comprising: In response to an indication obtained from the large model that the first input content is not related to the travel service, an indication is presented in the target application requesting input of content related to the travel service.

7. The method according to claim 1, further comprising: In response to an indication obtained from the large model that the first input content does not conform to the predetermined travel criteria, the target content in the first input content that does not conform to the predetermined travel criteria is presented in the target application.

8. The method of claim 1, wherein the predetermined parameter protocol further includes at least one optional parameter item, and the method further includes: Obtain additional recommendation information from the large model for at least one travel service related to the travel request. The additional recommendation information is generated by the large model based on the corresponding set of necessary parameter items, the at least one optional parameter item, and the first input content, by invoking the at least one travel service function. as well as The other recommendation information is presented as a first response to the first input content in the target application.

9. The method of claim 1, wherein the other recommendation information is generated by the large model in the following manner: Based on the first input content, determine the target travel service type corresponding to the travel request; Obtain the necessary parameter information of a set of target necessary parameter items corresponding to the target travel service type from the first input content; Obtain optional parameter information corresponding to the at least one optional parameter item from the first input content; as well as Based on the necessary parameter information and the optional parameter information, the other recommendation information is generated by calling the target travel service function for the target travel service type.

10. The method according to claim 9, wherein the other recommendation information is determined by the target travel service function based on the optional parameter information, by filtering and / or sorting multiple candidate recommendation information determined based on the necessary parameter information.

11. The method of claim 8, further comprising: In response to detecting a second input content in relation to the first response, it is determined whether the second input content involves modification of the optional parameter information; If the second input involves modifying the optional parameter information, the recommendation information of at least one target travel service is corrected by calling the target travel service function, based at least on the modified optional parameter information, using the large model. as well as The corrected recommendation information is presented as a third response to the second input content in the target application.

12. A device for interaction, comprising: The reservation parameter protocol determination module is configured to determine a reservation parameter protocol recommended for travel services, wherein the reservation parameter protocol includes at least a set of necessary parameter items for different types of travel services; An input content providing module is configured to provide the first input content to the large model in response to receiving first input content associated with a user's travel request in the target application; The recommendation information acquisition module is configured to acquire recommendation information for at least one travel service related to the travel request from the large model. The recommendation information is generated by the large model based on the corresponding set of necessary parameter items and the first input content by calling at least one travel service function. as well as The response content presentation module is configured to present the recommendation information as a first response to the first input content in the target application.

13. 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, the instructions causing the electronic device to perform the method according to any one of claims 1 to 11 when executed by the at least one processing unit.

14. 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 11.

15. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 11.

Images