Information interaction method, system and device, electronic equipment and storage medium

Abstract

The invention discloses an information interaction method, system and device, electronic equipment and a storage medium. The method comprises the following steps: receiving user instruction information and sending the user instruction information to a server, so that the server determines a corresponding option based on the user instruction information; receiving an option sent by the server, and displaying the option through a preset slot position; in response to a selection operation of a user on the target option, judging whether the target option contains a next-level option; if the target selection item contains the next-level selection item, updating the selection item displayed in the preset slot position according to the next-level selection item, and returning to the step of judging whether the target selection item contains the next-level selection item in response to the selection operation of the user on the target selection item; and if the target option does not include the next-level option, generating interaction information according to selection information of the user in each interaction round. By adopting the method, the development and maintenance cost can be reduced, and the flexibility of content display is improved.

Description

Technical Field

[0001] This application relates to the field of mobile Internet technologies, and in particular, to an information interaction method, system, device, electronic device, and storage medium. Background Art

[0002] With the increasing complexity of mobile application functions, the interaction requirements between users and systems are continuously rising. The traditional intent processing frameworks in related technologies are insufficient in terms of adaptability and scalability. For example, developers need to develop corresponding intent processing logics for each scenario separately, resulting in serious code redundancy and high maintenance costs. In addition, the native intent user interface presentation ability of the system is limited, making it difficult to effectively meet the brand personalization display requirements and the user interaction requirements in complex scenarios. Therefore, there is an urgent need to propose a flexible, efficient, and scalable interaction processing solution. Summary of the Invention

[0003] Embodiments of this application provide an information interaction method, system, device, electronic device, and storage medium, which can improve the adaptability and scalability of the information interaction system, and also improve the flexibility of content display and enhance the overall user interaction experience. The above technical solutions are as follows: In a first aspect, an embodiment of this application provides an information interaction method, which is applied to a user terminal and includes: Receiving user instruction information and sending the user instruction information to a server, so that the server determines corresponding selection items based on the user instruction information, where the selection items are items for the user to select in the current interaction round; Receiving the selection items sent by the server and displaying the selection items through a preset slot, where the preset slot is a general selection container for repeated use in multiple interaction rounds; In response to a user's selection operation on a target selection item, determining whether the target selection item includes sub-selection items; If the target selection item includes sub-selection items, updating the selection items displayed in the preset slot according to the sub-selection items, and returning to execute the step of determining whether the target selection item includes sub-selection items in response to the user's selection operation on the target selection item; If the target selection item does not include sub-selection items, generating interaction information according to the user's selection information in each interaction round.

[0004] In a possible implementation, displaying the selection items through a preset slot includes: Loading the data content of the selection items into the preset slot, where the preset slot is a general selection container for repeated use in multiple interaction rounds; Rendering and generating a first display page according to the data content of the selection items loaded in the preset slot, so as to display the selection items through the first display page.

[0005] In a possible implementation, the interaction information is order information, and the selection items correspond to any one of the following types of entities: store entity, commodity entity, commodity specification entity. Among them, the selection items corresponding to the commodity entity are the next-level selection items included in the selection items corresponding to the store entity, and the selection items corresponding to the commodity specification entity are the next-level selection items included in the selection items corresponding to the commodity entity.

[0006] In a possible implementation, updating the selection items displayed in the preset slot according to the next-level selection items includes: Loading the data content of the next-level selection items into the preset slot and using the next-level selection items as the updated selection items; Rendering and generating a second display page according to the data content corresponding to the updated selection items loaded in the preset slot, so as to display the updated selection items through the second display page.

[0007] In a possible implementation, when the entity corresponding to the target selection item is a store entity, the data content corresponding to the next-level selection items is the detailed data of the commodities included in the store entity corresponding to the target selection item; or, When the entity corresponding to the target selection item is a commodity entity, the data content corresponding to the next-level selection items is the detailed data of the specifications corresponding to the commodity entity corresponding to the target selection item.

[0008] In a possible implementation, after displaying the selection items through the preset slot, the method further includes: Receiving the voice information of the user; Determining the semantic recognition result corresponding to the voice information; If the semantic recognition result indicates that the user selects the target selection item, it is determined that a selection operation of the user on the target selection item is detected, where the target selection item is any selection item.

[0009] In a possible implementation, generating interaction information according to the selection information of the user in each interaction round includes: Aggregating the target selection items selected by the user in the interaction round; Extracting the required interaction data according to the aggregated target selection items; Displaying the interaction data through the preset slot; In response to the confirmation operation of the user on the interaction data, generating corresponding interaction information according to the interaction data.

[0010] In a possible implementation, after generating the interaction information according to the selection information of the user in each interaction round, the method further includes: Determining the application program corresponding to the user instruction information; Jump to the order placement page corresponding to the application, and the order placement page includes the detailed information of the interaction information.

[0011] In a second aspect, an embodiment of the present application provides an information interaction method, which is applied to a server and includes: Receiving user instruction information sent by a user terminal; Determining a corresponding selection item based on the user instruction information, where the selection item is an item for the user to select in the current interaction round; Sending the selection item to the user terminal so that the user terminal displays the selection item in a preset slot, and in response to the user's selection operation on the target selection item, determining whether the target selection item includes a next-level selection item. If the target selection item includes a next-level selection item, updating the selection item displayed in the preset slot according to the next-level selection item, and returning to execute the step of determining whether the target selection item includes a next-level selection item in response to the user's selection operation on the target selection item. If the target selection item does not include a next-level selection item, generating interaction information according to the selection information of the user in each interaction round. The preset slot is a general selection container and is used for repeated use in multiple interaction rounds.

[0012] In a possible implementation manner, determining a corresponding selection item based on the user instruction information includes: Determining the intention information of the user according to the user instruction information; Querying at least one entity corresponding to the user instruction information; Generating at least one selection item corresponding to the at least one entity; Determining the at least one selection item as the selection item corresponding to the user instruction information.

[0013] In a possible implementation manner, when the intention information is a product search intention, the entity is any one of the following types of entities: store entity, product entity, product specification entity; wherein, the selection item corresponding to the product entity is the next-level selection item included in the selection item corresponding to the store entity, and the selection item corresponding to the product specification entity is the next-level selection item included in the selection item corresponding to the product entity.

[0014] In a third aspect, an embodiment of the present application provides an information interaction system, including: a user terminal and a server; wherein, The user terminal is configured to receive user instruction information and send the user instruction information to the server; The server is configured to receive the user instruction information sent by the user terminal, determine a corresponding selection item based on the user instruction information, and send the selection item to the user terminal. The selection item is an item for the user to select in the current interaction round; The user terminal is further configured to receive the selection items sent by the server, display the selection items through a preset slot, and in response to the user's selection operation on the target selection item, determine whether the target selection item includes sub - selection items. If the target selection item includes sub - selection items, update the selection items displayed in the preset slot according to the sub - selection items, and return to execute the step of determining whether the target selection item includes sub - selection items in response to the user's selection operation on the target selection item. If the target selection item does not include sub - selection items, generate interaction information according to the selection information of the user in each interaction round. The preset slot is a general selection container for repeated use in multiple interaction rounds.

[0015] In a fourth aspect, an information interaction device provided by an embodiment of the present application is applied to a user terminal and includes: A first receiving module, configured to receive user instruction information and send the user instruction information to the server, so that the server determines corresponding selection items based on the user instruction information. The selection items are items for the user to select in the current interaction round; A second receiving module, configured to receive the selection items sent by the server and display the selection items through a preset slot. The preset slot is a general selection container for repeated use in multiple interaction rounds; A judgment module, configured to determine whether the target selection item includes sub - selection items in response to the user's selection operation on the target selection item; An update module, configured to, when the target selection item includes sub - selection items, update the selection items displayed in the preset slot according to the sub - selection items, and return to execute the step of determining whether the target selection item includes sub - selection items in response to the user's selection operation on the target selection item; A generation module, configured to generate interaction information according to the selection information of the user in each interaction round when the target selection item does not include sub - selection items.

[0016] In a fifth aspect, an information interaction device provided by an embodiment of the present application is applied to a server and includes: A third receiving module, configured to receive the user instruction information sent by the user terminal; A first determination module, configured to determine corresponding selection items based on the user instruction information. The selection items are items for the user to select in the current interaction round; A sending module, configured to send options to a user terminal, so that the user terminal displays the options in a preset slot, and in response to a user's selection operation on a target option, determine whether the target option includes sub-options. If the target option includes sub-options, update the options displayed in the preset slot according to the sub-options, and return to execute the step of determining whether the target option includes sub-options in response to the user's selection operation on the target option. If the target option does not include sub-options, generate interaction information according to the user's selection information in each interaction round. The preset slot is a general selection container and is used for repeated use in multiple interaction rounds.

[0017] In a sixth aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory; wherein, the memory stores a computer program, and when the processor executes the computer program, the method steps provided in the first aspect or the second aspect of the embodiment of the present application are implemented.

[0018] In a seventh aspect, an embodiment of the present application provides a computer storage medium, which stores multiple instructions, and the instructions are adapted to be loaded and executed by a processor to execute the method steps provided in the first aspect or the second aspect of the embodiment of the present application.

[0019] The above information interaction method, system, device, electronic device and storage medium are applied to a user terminal. By receiving user instruction information and sending the user instruction information to a server, the server determines corresponding options based on the user instruction information. The options are items for the user to select in the current interaction round; receive the options sent by the server, and display the options through a preset slot. The preset slot is a general selection container and is used for repeated use in multiple interaction rounds; in response to the user's selection operation on a target option, determine whether the target option includes sub-options; if the target option includes sub-options, update the options displayed in the preset slot according to the sub-options, and return to execute the step of determining whether the target option includes sub-options in response to the user's selection operation on the target option; if the target option does not include sub-options, generate interaction information according to the user's selection information in each interaction round. By setting a general preset slot and dynamically updating the content of the slot during the interaction process, multiple selection scenarios are adapted through a single slot, realizing the reuse of the slot, significantly improving the adaptability and scalability of the system, effectively avoiding code redundancy, reducing development and maintenance costs, and improving the flexibility of content display, thus enhancing the overall interaction experience of users. Description of the Drawings

[0020] To more clearly illustrate the technical solutions in the embodiments of the present application, the accompanying drawings required for the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other accompanying drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 Schematic diagram of an application environment of an information interaction method provided by an exemplary embodiment of the present application; Figure 2 Schematic flow chart of an information interaction method provided by an exemplary embodiment of the present application; Figure 3 Schematic flow chart of another information interaction method provided by an exemplary embodiment of the present application; Figure 4 Schematic diagram of a first display page provided by an exemplary embodiment of the present application; Figure 5 Schematic flow chart of another information interaction method provided by an exemplary embodiment of the present application; Figure 6 Schematic diagram of a second display page provided by an exemplary embodiment of the present application; Figure 7 Schematic diagram of another second display page provided by an exemplary embodiment of the present application; Figure 8 Schematic diagram of an order confirmation page provided by an exemplary embodiment of the present application; Figure 9 Schematic flow chart of another information interaction method provided by an exemplary embodiment of the present application; Figure 10 Schematic diagram of the architecture of an information interaction system provided by an exemplary embodiment of the present application; Figure 11 Schematic flow chart of a specific information interaction method provided by an exemplary embodiment of the present application; Figure 12 Schematic diagram of the structure of an information interaction device provided by an exemplary embodiment of the present application; Figure 13 Schematic diagram of the structure of another information interaction device provided by an exemplary embodiment of the present application; Figure 14 Schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application. Detailed implementation manners

[0022] To make the objectives, technical solutions and advantages of this application more clear and understandable, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0023] In the description of this application, it should be understood that terms such as "first", "second", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances. In addition, in the description of this application, unless otherwise specified, "a plurality of" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0024] The information interaction method provided by the embodiments of this application can be applied to an application environment as Figure 1 shown. Among them, the user terminal 11 communicates with the server 12 through the network. The data storage system can store the data that the server 12 needs to process. The data storage system can be integrated on the server 12, or can be placed in the cloud or on other network servers. Among them, the user terminal 11 can be, but is not limited to, various smart phones, tablet computers, personal computers, laptop computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, in-vehicle intelligent devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. Specifically, the user terminal 11 is configured with an IOS operating system. The server 12 can be implemented by an independent server or a server cluster composed of multiple servers.

[0025] Taking the application of the above information interaction method to the voice ordering service of the iOS system as an example for illustration: After the user determines the user instruction information based on the user terminal 11, the user instruction information is sent to the server 12. The server 12 receives the user instruction information sent by the user terminal 11, determines the corresponding selection item based on the user instruction information, and then sends the selection item to the user terminal 11. Among them, the selection item is an item for the user to select in the current interaction round. The user terminal 11 receives the selection item sent by the server 12 and displays the selection item through a preset slot; then, in response to the user's selection operation on the target selection item, it is judged whether the target selection item includes a next-level selection item; if the target selection item includes a next-level selection item, the selection item displayed in the preset slot is updated according to the next-level selection item, and the step of judging whether the target selection item includes a next-level selection item in response to the user's selection operation on the target selection item is returned for execution; if the target selection item does not include a next-level selection item, interaction information is generated according to the selection information of the user in each interaction round.

[0026] In one embodiment, as Figure 2 shown, an information interaction method is provided. Taking the application of this method to the user terminal 11 and the server 12 in Figure 1 as an example for illustration, the method includes the following steps: S201: Receive the user instruction information and send the user instruction information to the server 12, so that the server 12 determines the corresponding selection item based on the user instruction information. The selection item is an item for the user to select in the current interaction round.

[0027] Among them, the user instruction information can be an instruction issued by the user based on any interface of the user terminal 11, such as a voice instruction, a gesture action, a text input, etc.

[0028] In one embodiment, the user starts the voice assistant on the user terminal 11 by issuing a voice instruction. When it is detected that the user issues the wake-up word of the voice assistant corresponding to the relevant application program, the voice interaction assistant is started. Among them, the relevant application program can be any APP including a hierarchical navigation scenario, including but not limited to e-commerce APPs, information browsing APPs, education and learning APPs, smart home APPs, etc.

[0029] For example, when the user inputs "XX (voice assistant wake-up word), I want to order a cup of milk tea" by voice, the corresponding application program can be determined based on the voice assistant wake-up word first. Then, the voice assistant interface layer forwards the user instruction information "I want to order a cup of milk tea" to the general intent processor corresponding to the application program. Then, the user instruction information is sent to server 12 through the general intent processor. This server 12 can be a server that provides services for the application program. After receiving the user instruction information, server 12 performs semantic understanding and judgment, and thus returns multiple selectable options. Among them, the general intent processor can be an entry node for information interaction between the application program and the user, and can be used to receive user instruction information, coordinate the work of each component, and return subsequent processing results.

[0030] In one embodiment, in a product search scenario (such as ordering food, online shopping, etc.), the options can correspond to any of the following types of entities: store entity, product entity, product specification entity. Among them, the option corresponding to the product entity is a sub-option included in the option corresponding to the store entity, and the option corresponding to the product specification entity is a sub-option included in the option corresponding to the product entity.

[0031] It can be understood that the options are not just a simple text, but have certain data meanings, and each data item is associated with a specific entity. An entity can have independent attributes. For example, a store entity has attributes such as store name and address, a product entity has attributes such as product name and price, and a product specification entity has attributes such as size and color.

[0032] Optionally, the store entity can refer to a specific store that has entered the e-commerce APP, such as a coffee shop, milk tea shop, supermarket, etc. of a certain brand. During the interaction process, if the option returned by server 12 is the option corresponding to the store entity, then the items for the user to select in the current interaction round are a set of store options that meet the user's intention, such as "Milk Tea Shop A" and "Milk Tea Shop B". The product entity refers to a specific product item, such as a cup of "latte coffee" or a cup of "bubble milk tea".

[0033] Optionally, the product entity can belong to a certain store, that is to say, the product appears on the basis of the store. First, the target store selected by the user is determined in the previous interaction round, and then the specific products in the target store that can be selected are provided for the user in the current interaction round.

[0034] Optionally, the product specification entity may refer to a further subdivision of the product entity, such as a large cup, medium cup, or small cup for a certain latte, or different temperature and sweetness options. The product specification appears on the basis of the product. For example, if the target product selected by the user is determined in the previous interaction round, specific product specifications corresponding to the target product can be provided for the user to select in the current interaction round.

[0035] For another example, in the smart home control scenario, the user terminal 11 can be connected to smart devices such as household appliances (such as air conditioners), lighting, and access control to achieve unified control and management of various smart devices. When the user inputs "XX (voice assistant wake-up word), I want to turn on the air conditioner" by voice, the smart home APP can be determined based on the voice assistant wake-up word first. Then, the voice assistant interface layer forwards the user instruction information "I want to turn on the air conditioner" to the general intent processor corresponding to the application program. Then, the user instruction information is sent to the server 12 through the general intent processor. After receiving the user instruction information, the server 12 performs semantic understanding and judgment, and thus returns multiple selectable options. Among them, the general intent processor can be the entry node for information interaction between the application program and the user, and can be used to receive user instruction information, coordinate the work of each component, and return subsequent processing results. In this scenario, the option can correspond to any of the following types of entities: air conditioner entity, working mode entity, temperature entity, etc. Among them, the air conditioner entity indicates the specific device that the user needs to control, which is an air conditioner device with a unique identifier and can include the device name, installation location (such as "living room air conditioner"), etc.; the working mode entity such as "cooling", "heating", "dehumidifying" or "automatic", etc.; the temperature entity represents the target temperature value that the user expects to set, which can be specifically an integer or floating-point data (for example, "26°C"). It can be understood that the options corresponding to the air conditioner mode entity are the next-level options included in the options corresponding to the air conditioner entity, and the options corresponding to the temperature entity are the next-level options included in the options corresponding to the air conditioner mode entity.

[0036] Specifically, the user terminal 11 can package the options into a data packet in JSON format or other data formats and send it to the server 12 through the network interface.

[0037] In one embodiment, the server 12 receives the user instruction information sent by the user terminal 11, determines the corresponding options based on the user instruction information, and then sends the options to the user terminal 11.

[0038] Optionally, the server 12 determines corresponding options based on the user instruction information, including: the server 12 determines the user's intention information according to the user instruction information; queries at least one entity corresponding to the user instruction information; generates at least one option corresponding to the at least one entity; and determines the at least one option as the option corresponding to the user instruction information.

[0039] Optionally, the intention information can be the target action that the user wants to achieve extracted from the user instruction information, such as the intention of commodity search, the intention of placing an order for a commodity, the intention of placing an order for logistics, the intention of browsing information, the intention of controlling smart home, etc.

[0040] In the case where the intention information is the intention of commodity search, the entity is any one of the following types of entities: store entity, commodity entity, commodity specification entity. Among them, the store entity can be determined based on the user's location information, and the store entity is used to indicate the store closer to the user's location information.

[0041] Specifically, the server 12 can perform structured analysis on the intention information through a preset model (such as a large language model) (such as extracting "drink = milk tea"). Then, a drink candidate list (such as: pearl milk tea, taro ball milk tea, etc.) is generated through a conditional entity generator according to the context request.

[0042] In one embodiment, in the case where the intention information is the intention of browsing information, the entity is any one of the following types of entities: information channel entity, information category entity, information content entity, etc. Among them, the information channel entity is used to indicate the information release platform or information source that the user is interested in; the information category entity is used to describe the theme category to which the information content belongs, such as "cutting-edge technology", "entertainment hotspots", etc.; the information content entity can represent specific information articles or video content, and specifically can include attributes such as title, release time, content summary, author information, source link, etc. The server 12 can, based on the user instruction information, perform intention recognition and entity extraction on the user's expression through a preset semantic understanding model (such as a large language model). For example, when the user inputs "I want to see today's technology news" by voice, the intention of browsing information can be recognized, and the information category entity "technology" can be extracted from it, and further an information channel entity and corresponding options matching this category are generated for the user to select or directly display.

[0043] In this embodiment, the server receives the user instruction information sent by the user terminal 11, uses a preset model to perform intent recognition and structured analysis on the instruction, extracts relevant elements therefrom, and generates a corresponding candidate entity list in combination with the context. This process enables the system to more accurately understand the user's needs, dynamically generate selection items that better fit the user's intent, and improve the relevance and personalization of product recommendations or information push. Additionally, through entity structuring and hierarchical design (store, product, specification), the system interaction is more logical and guiding, effectively improving the user experience and interaction efficiency.

[0044] S202: Receive the selection items sent by the server 12 and display the selection items through a preset slot. The preset slot is a general selection container for repeated use in multiple interaction rounds.

[0045] Optionally, the selection items sent by the server 12 can be one or more. When there are multiple selection items sent by the server 12, probability evaluation can be performed on the multiple selection items based on the user's historical interaction data and the current conversation context information, the selection item that matches the user's intent can be determined, and the selection item that matches the user's intent can be used as the default recommended value for priority display or pre-selection, thereby improving the user interaction efficiency and optimizing the user experience.

[0046] In one embodiment, the user's historical interaction behavior data can be modeled to identify their behavior patterns in specific scenarios; in the current interaction round, based on the user's behavior patterns, the user's possible next selection items can be predicted, and before the user actually initiates a selection operation, the entity data and page resources related to the prediction result can be pre-loaded to reduce the response latency and improve the interaction efficiency and system response fluency.

[0047] Among them, a slot can refer to a user interface (UI) / voice display container for carrying interaction information. Specifically, it can be a module in the visual UI, such as: a list box, a tab, a button group, or it can also be the voice synthesis broadcast area, such as: "Do you want to drink: pearl milk tea, red bean milk tea, or nata de coco milk tea?"

[0048] S203: In response to the user's selection operation on the target selection item, determine whether the target selection item contains sub-selection items.

[0049] Among them, the target selection item is any one of the selection items sent by the server 12.

[0050] Optionally, the selection operation can be at least one of the following: voice confirmation (such as "the first one", indicating that the user selects the selection item ranked first), click on a button (such as an interaction button displaying "Tea Shop A"), gesture interaction confirmation, etc.

[0051] It is understandable that determining whether the target option contains sub-options at the next level, that is, checking whether there are still sub-options (sub-options at the next level) available for further selection in the target option, which also means determining whether to enter the next interaction round. If the target option contains sub-options at the next level, the next interaction round can be entered; if the target option does not contain sub-options at the next level, the interaction information confirmation link can be entered.

[0052] Taking the options corresponding to the above-mentioned store entity, product entity, and product specification entity as examples, when the target option corresponds to the store entity, the target option includes sub-options at the next level, and the sub-options at the next level correspond to the product entities in the selected target store. When the target option corresponds to the product entity, the target option may or may not include sub-options at the next level. Specifically, when the product has optional specifications (such as cup type, sweetness, temperature, etc.), the sub-options at the next level correspond to the product specification entities in the selected target product; when the product has no changeable specifications (such as a single product with fixed specifications), the target option does not include sub-options at the next level. When the target option corresponds to the product specification entity, the target option does not include sub-options at the next level, and the subsequent order confirmation or execution process can be directly entered based on the current selection result.

[0053] Taking the above-mentioned smart home control scenario as an example, when the target option corresponds to the air conditioner entity, it means that the user has selected the specific air conditioner device to be controlled. At this time, the target option may contain sub-options at the next level, that is, the controllable parameters associated with the air conditioner device, such as the working mode, and the corresponding sub-options at the next level are the working mode entities. When the target option corresponds to the working mode entity, it can be determined whether the user can further configure parameters (such as setting temperature, wind speed, etc.) under this working mode. If it is supported, the target option contains sub-options at the next level, and the next interaction round can be entered to display sub-options at the next level corresponding to entities such as temperature entity and wind speed entity. For example, after the user selects "cooling" (working mode), the user is further guided to set the temperature. When the target option corresponds to the temperature entity, if the target option does not contain sub-options at the next level, a control instruction can be directly generated based on the current complete control path (such as: living room air conditioner - cooling - 26°C), and the subsequent instruction sending or execution process can be entered. Through this judgment mechanism, the depth of the process can be flexibly controlled in multi-round interactions, redundant guidance can be avoided, and the user control efficiency can be improved.

[0054] S204: If the target option contains sub-options at the next level, update the options displayed in the preset slot according to the sub-options at the next level, and return to the step of determining whether the target option contains sub-options at the next level in response to the user's selection operation on the target option.

[0055] Optionally, if the target selection item includes sub - level selection items, the preset slot used in the previous interaction round can be continued to display new selection items (i.e., the sub - level selection items in the previous interaction round).

[0056] In one embodiment, a single - slot loop processing mechanism can be used to achieve unified display and management of different types of selection items in multi - round interactions. Specifically, a slot variable (e.g., Condition1) can be preset, which is used to dynamically carry different types of selection item sets in each interaction round. In the specific implementation process, after the user makes a selection based on the selection items displayed in the current interaction round, it is judged whether there are sub - level selection items according to the selected target selection item. If there are sub - level selection items, the system continues to use the preset slot adopted in the previous interaction round, binds the sub - level selection items to this slot, and updates the slot content to display new selection items in the interface or voice interaction interface, so as to guide the user to perform the selection operation in the next interaction round.

[0057] In this embodiment, through the single - slot loop processing mechanism, in different interaction rounds, there is no need to separately allocate new slots for selection items at each level. Instead, through the content update of a single slot, the dynamic adaptation and presentation of multi - type and multi - round selection items are realized, effectively reducing the complexity of slot management and system resource consumption, while improving the coherence and fluency in the multi - round interaction process. Further, the slot variable can adapt to different types of entity selection items, including but not limited to store entities, commodity entities and commodity specification entities, air - conditioner entities, working mode entities, temperature entities, information channel entities, information category entities, information content entities, etc. By dynamically switching the content bound to the slot, it can support the interaction mode of gradually deepening in the hierarchical navigation. And in each round of interaction process, the user operates on the same slot, thus improving the consistency of the interaction experience and the coherence of user operations. In addition, due to slot reuse, the system can maintain a low memory overhead and high response efficiency during multi - round interactions, which is especially suitable for resource - constrained mobile terminal device environments, such as smart phones, tablets, etc.

[0058] S205: If the target selection item does not include sub - level selection items, generate interaction information according to the selection information of the user in each interaction round.

[0059] Optionally, the interaction information may include, but is not limited to, order information, control instruction information, information viewing information, search request information, etc. Among them, the order information may be information generated in a product search scenario based on the target store, target product, and target product specifications selected by the user; the control instruction information may be information generated in a smart home control scenario based on the target device, target working mode, target temperature, etc. selected by the user, and is used to send a control instruction to the corresponding smart device for execution; the information viewing information may be information generated in an information browsing scenario based on the target information channel, target information category, target information content, etc. selected by the user, and is used for front-end content loading or jump display.

[0060] Among them, the target selection item does not include a sub-selection item, indicating that the current selection item is the final level (such as product specifications or fixed single items), and there is no entity that needs to be further refined for selection. Therefore, it can be aggregated according to the selections made by the user in each previous interaction round (such as the target store, target product, target product specifications, etc.) to generate interaction information.

[0061] The above information interaction method receives user instruction information and sends the user instruction information to the server, so that the server determines the corresponding selection item based on the user instruction information; receives the selection item sent by the server, and displays the selection item through a preset slot; in response to the user's selection operation on the target selection item, determines whether the target selection item includes a sub-selection item; if the target selection item includes a sub-selection item, updates the selection item displayed in the preset slot according to the sub-selection item, and returns to execute the step of determining whether the target selection item includes a sub-selection item in response to the user's selection operation on the target selection item; if the target selection item does not include a sub-selection item, generates interaction information according to the selection information of the user in each interaction round. Thus, by setting a general preset slot and dynamically updating the content of the slot during the interaction process, multiple selection scenarios are adapted through a single slot, realizing the reuse of the slot, significantly improving the adaptability and scalability of the system, effectively avoiding code redundancy, reducing the development and maintenance costs, and improving the flexibility of content display, thereby enhancing the overall interaction experience of the user.

[0062] In one embodiment, as Figure 3 shown, another information interaction method is provided. Taking the method applied to the user terminal 11 and the server 12 in Figure 1 as an example for illustration, it includes the following steps: S301: Receive user instruction information and send the user instruction information to the server 12, so that the server 12 determines the corresponding selection item based on the user instruction information, and the selection item is an item for the user to select in the current interaction round.

[0063] Specifically, S301 is the same as S201, and will not be elaborated here.

[0064] S302: Receive the option sent by server 12, and load the data content of the option into a preset slot. The preset slot is a general selection container for reuse in multiple interaction rounds.

[0065] Among them, the data content of the option may include but is not limited to the following data: entity identification information (such as store entity code, product entity code, etc.), display information (such as entity name, picture, description text, label, etc.), extended information (such as promotion information, sales volume, delivery duration of the store entity; price, sales volume of the product entity; attributes of the product specification entity, etc.).

[0066] S303: Render and generate a first display page according to the data content of the option loaded in the preset slot, so as to display the option through the first display page.

[0067] That is to say, based on the data content in the preset slot, an interaction interface (which can be a pop-up window, list, grid or custom card-style UI, etc.) is constructed, and then the option is displayed to the user, so that the user can perform a selection operation on the first display page.

[0068] In one embodiment, after receiving the data content of the option sent by server 12, first parse the data content to extract the structured option data; then, bind the parsed option data set to the preset slot. During this process, a set of data structures, such as arrays, lists or mapping tables, can be maintained inside the preset slot to store the detailed data content of each option. By updating the data set of the slot, the loading operation of the option is completed, and a display page (i.e., the first display page) is generated based on the data content of the preset slot to present each option to the user.

[0069] Exemplarily, please refer to Figure 4 , in the first current page 40 of the user terminal 11, there is a first display page 41. The first display page 41 can be a card-style list interface. Specifically, the first display page 41 can display the options corresponding to the store entity to the user. The specific data content may include store name, store rating, store sales volume, store delivery duration, etc. For example, the store with the store name of Coffee Shop 1 has a store rating of 5.0, a store sales volume of more than 1000 per month, and a store delivery duration of 26 minutes; the store with the store name of Coffee Shop 2 has a store rating of 4.7, a store sales volume of more than 900 per month, and a store delivery duration of 25 minutes; the store with the store name of Coffee Shop 3 has a store rating of 4.9, a store sales volume of more than 2000 per month, and a store delivery duration of 25 minutes. In addition, the first display page 41 can also display a prompt such as "Please select a store" to prompt the user to perform a selection operation.

[0070] S304: In response to the user's selection operation on the target selection item, determine whether the target selection item includes sub - level selection items. If so, execute S305; if not, execute S306.

[0071] Specifically, S304 is the same as S203, and will not be elaborated here.

[0072] S305: Update the selection items displayed in the preset slot according to the sub - level selection items, and return to execute the step of S304: In response to the user's selection operation on the target selection item, determine whether the target selection item includes sub - level selection items.

[0073] Specifically, S305 is the same as S204, and will not be elaborated here.

[0074] S306: Generate interaction information according to the user's selection information in each interaction round.

[0075] Specifically, S306 is the same as S205, and will not be elaborated here.

[0076] In the above - mentioned embodiments, by loading the selection item data returned by the server into a reusable preset slot and rendering a unified display page based on the slot content, the structured presentation and dynamic update of the selection items are realized, improving the flexibility and reusability of the front - end interface. At the same time, the slot mechanism is used to maintain the complete data content of the selection items, supporting the continuous management and cascaded display of data in multiple - round interactions (such as store - product - specification), making the user's selection path clear and the interaction experience smooth, effectively improving the system response efficiency and user operation convenience.

[0077] In one embodiment, as Figure 5 shown, another information interaction method is provided. Taking the method applied to the Figure 1 user terminal 11 and server 12 as an example, it includes the following steps: S501: Receive the user instruction information and send the user instruction information to the server 12 so that the server 12 determines the corresponding selection items based on the user instruction information. The selection items are the items for the user to select in the current interaction round.

[0078] Specifically, S501 is the same as S201, and will not be elaborated here.

[0079] S502: Receive the selection items sent by the server 12 and display the selection items through the preset slot.

[0080] Specifically, S502 is the same as S202, and will not be elaborated here.

[0081] S503: In response to the user's selection operation on the target selection item, determine whether the target selection item includes sub - level selection items. If so, execute S504; if not, execute S506.

[0082] Specifically, S503 is the same as S203, which will not be elaborated here.

[0083] S504: Load the data content of the sub - level selection item into a preset slot, and use the sub - level selection item as the updated selection item.

[0084] Optionally, the data content of the sub - level selection item can overwrite the selection item data already existing in the preset slot, so as to bind / assign the data content of the new sub - level selection item to the preset slot. For example, assign the obtained set of sub - level selection items to a slot variable (such as Condition1).

[0085] In one embodiment, in the commodity search scenario, the entity corresponding to the target selection item is a store entity, and the data content corresponding to the sub - level selection item is the detailed data of the commodities included in the store entity corresponding to the target selection item; or, when the entity corresponding to the target selection item is a commodity entity, the data content corresponding to the sub - level selection item is the detailed data of the specifications corresponding to the commodity entity corresponding to the target selection item.

[0086] Among them, the detailed data of the commodity can refer to the set of detailed description information of the commodities under the store entity; the detailed data of the specifications corresponding to the commodity entity can refer to the attribute information describing different specifications of the commodity, such as specification name, price increase amount, selectable status, etc.

[0087] S505: Render and generate a second display page according to the data content corresponding to the updated selection item loaded in the preset slot, so as to display the updated selection item through the second display page, and then return to execute S503.

[0088] Optionally, a new display page, that is, the second display page, can be rendered and generated according to the data content loaded in the updated preset slot, and the second display page can overwrite the first display page for the user to perform a new selection operation in the current interaction round. Furthermore, after the second display page is rendered, return to execute the previous step S503 to continue processing based on the user's selection in the new round of interaction.

[0089] Further, the second display page can be set as the new first display page for continuous use in subsequent interaction rounds, so as to maintain the page update coherence and state consistency in the interaction process.

[0090] Optionally, please refer to Figure 6, in the second current page 60 of the user terminal 11, a first sub-page 61 is included. The first sub-page 61 is a new display page rendered according to the data content loaded in the updated preset slot, that is, the corresponding second display page in the current interaction round. The first sub-page 61 can be a card list interface. Specifically, the first sub-page 61 can display options corresponding to the commodity entity (the next-level options of the options corresponding to the store entity) for the user. The specific data content can include the commodity name, commodity price, monthly sales volume of the commodity, etc. For example, the price of latte coffee is 20 yuan and the monthly sales volume is 100 copies; the price of flat white coffee is 20 yuan and the monthly sales volume is 47 copies; the price of mocha coffee is 25 yuan and the monthly sales volume is 7 copies. In addition, the first sub-page 61 can also display a prompt message such as "Please select a commodity" to prompt the user to perform a selection operation.

[0091] Further, the first sub-page 61 can be set as the new first display page. In the subsequent interaction process, the new second display page can be used to display the specifications corresponding to the target commodity selected by the user. Please refer to Figure 7 , in the third current page 70 of the user terminal 11, a second sub-page 71 is included. The second sub-page 71 is a new display page rendered again according to the data content loaded in the updated preset slot, that is, the corresponding second display page in the new interaction round. The second sub-page 71 can be a card list interface. Specifically, the second sub-page 71 can display options corresponding to the commodity specification entity (the next-level options of the options corresponding to the commodity entity) for the user. The specific data content can include cup size, sweetness, etc. For example, large cup, medium cup, and small cup. In addition, the second sub-page 71 can also display a prompt message such as "Please select commodity specifications" to prompt the user to perform a selection operation.

[0092] In the above embodiments, by judging whether there are next-level options for the user selection options and loading the corresponding data content into the preset slot and rendering and displaying it as a new display page, the dynamic iterative update and hierarchical display of the selection options are realized. Each interaction round generates corresponding display pages (such as commodity lists, specification lists) based on the slot mechanism, which not only improves the interface rendering efficiency but also enhances the coherence of the page state and data consistency. This mechanism supports users to gradually complete the complex selection process in multiple rounds of interaction, improving the system flexibility, interaction coherence, and user experience.

[0093] S506: Aggregate the target selection options selected by the user in the interaction round.

[0094] Among them, aggregating the target selection options selected by the user in the interaction round means unifying and summarizing the selection results scattered in different interaction rounds to form a complete set of interaction data.

[0095] S507: Extract the required interaction data according to the aggregated target options.

[0096] Optionally, the interaction data can be order data, which can include but is not limited to: the name of the target store, the name of the target product, the price of the target product, the quantity of the target product, the detailed information of the target product specification, and the total order price.

[0097] In addition, the interaction data can also be control instruction data, information viewing data, search request data, etc. The control instruction data can include data such as the identifier of the target device; the information viewing data can include the identifier of the target information content, the source platform, the release time, the content summary, etc. The specific data content can be flexibly determined according to the actual scenario and requirements, and the present application does not make specific limitations on this.

[0098] S508: Display the interaction data through a preset slot.

[0099] Optionally, load the data content of the aggregated target options into the preset slot, and then render a confirmation page to display the interaction data. Specifically, it can be rendered through a custom view renderer.

[0100] S509: In response to the user's confirmation operation on the interaction data, generate corresponding interaction information according to the interaction data.

[0101] Optionally, the confirmation operation can be at least one of the following: voice confirmation, click the confirmation button, gesture interaction confirmation, etc.

[0102] Exemplarily, please refer to Figure 8 , the interaction data is order data, the above confirmation page is an order confirmation page, the fourth current page 80 in the user terminal 11 includes an order confirmation page 81, and the order confirmation page 81 can be a card-style list interface. Specifically, the order confirmation page 81 can display order data to the user. For example, the name of the target store is "Coffee Shop 1", the rating of the target store is "5.0 points", the monthly sales volume of the target store is "1000+ (orders)", the delivery duration of the target store is "26 minutes", the name of the target product is "Latte", the price of the target product is "20 (yuan)", the quantity of the target product, the detailed information of the target product specification is "large cup", and the total order price is "20 yuan". In addition, the order confirmation page 81 can also display the name, icon of the application program, and a slogan such as "Provide you with services such as intelligent order placement and delivery". Optionally, the order confirmation page 81 can also display a cancel button 811 and a payment button 812. The cancel button 811 is used for the user to trigger to cancel the current order placement operation, and the payment button 812 is used for the user to trigger to jump to the relevant payment application program to complete the payment.

[0103] In the above embodiments, by aggregating the target selection items selected by the user in multiple interaction rounds, structured interaction data is extracted and generated, and after being loaded into a preset slot, it is displayed as a confirmation page, realizing a closed-loop process from step-by-step selection to the generation of complete interaction information. This mechanism supports the unified collation and visual display of multi-dimensional entity information, enabling the user to intuitively confirm the content of the interaction data on the final page, enhancing the clarity of the interaction and the convenience of decision-making. At the same time, various forms of confirmation operations (voice, button, gesture) further improve the adaptability of the system and the user experience, providing a more efficient, controllable, and intelligent interaction solution for multi-round interaction applications such as ordering, e-commerce, and information browsing.

[0104] In one embodiment, as Figure 9 shown, another information interaction method is provided. Taking the application of this method to Figure 1 the user terminal 11 and the server 12 as an example for illustration, it includes the following steps: S901: Receive the user instruction information and send the user instruction information to the server 12, so that the server 12 determines the corresponding selection item based on the user instruction information. The selection item is an item for the user to select in the current interaction round.

[0105] Specifically, S901 is the same as S201 and will not be elaborated here.

[0106] S902: Receive the selection item sent by the server 12 and display the selection item through a preset slot.

[0107] Specifically, S902 is the same as S202 and will not be elaborated here.

[0108] S903: Receive the voice information of the user.

[0109] Optionally, the voice information of the user may include the selection information of the user for each currently displayed selection item, such as "I want the first one", "Choose the medium cup", etc.

[0110] S904: Determine the semantic recognition result corresponding to the voice information.

[0111] In one embodiment, the semantic recognition result may be a structured intention obtained through Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU) processing.

[0112] S905: If the semantic recognition result indicates that the user selects a target selection item, it is determined that a selection operation of the user for the target selection item is detected, where the target selection item is any selection item.

[0113] It should be noted that this embodiment supports users to perform interactive selection operations through natural language expressions, not limited to traditional click-based selection operations. Specifically, taking the product search scenario as an example, when entering a certain interaction round, several selection items are first displayed on the display page. The selection items can include store entities, product entities, product specification entities, etc. Subsequently, the system enters the detection state, receives the voice information input by the user, and after receiving the voice information, performs speech recognition and natural language understanding processing on the voice information to determine the semantic recognition result corresponding to the voice information. The semantic recognition result can include the user's interaction intention and target pointing information, and the target pointing information can be implicitly or explicitly specified in the form of natural language description. For example, the user can make selections through natural languages such as "I want the first one", "Select the medium cup", "Order this", etc., which are non-standard imperative natural languages. After determining the semantic recognition result, it is judged whether the recognition result indicates that the user has completed the selection operation of a certain target selection item. If it is confirmed that the user's intention clearly points to a certain selection item currently displayed, the target selection item is recorded, and this selection operation is processed as an effective interaction operation. Further, after confirming the selection, subsequent interaction processing is continued based on the target selection item.

[0114] In the above embodiment, through speech recognition and natural language understanding technologies, users can perform non-click-based interactive selections on the currently displayed selection items in a natural language manner, making the human-computer interaction more natural, flexible, and intelligent. Users can complete the selection operation through colloquial expressions, and the system automatically recognizes the semantics and maps them to specific target selection items, thereby reducing the operation threshold, improving the interaction efficiency, and significantly enhancing the user experience and system adaptation ability.

[0115] S906: In response to the user's selection operation on the target selection item, determine whether the target selection item includes sub-selection items; if so, execute S907, if not, execute S908.

[0116] Specifically, S906 is the same as S203, and will not be elaborated here.

[0117] S907: Update the selection items displayed in the preset slot according to the sub-selection items, and return to execute the step of determining whether the target selection item includes sub-selection items in response to the user's selection operation on the target selection item.

[0118] Specifically, S907 is the same as S204, and will not be elaborated here.

[0119] S908: Generate interaction information according to the user's selection information in each interaction round.

[0120] Among them, when the interaction information is order information, the order information may include: the target store, target product, and target product specifications selected by the user. Additionally, it may also include the rating, delivery duration, and sales volume of the target store, the quantity, price, and other attributes of the target product (such as remarks, delivery method, etc.).

[0121] It can be understood that the selection information of the user in multiple rounds of interaction is recorded. After the user completes the last selection, the selection content of each interaction round is integrated to generate the interaction information. Specifically, the selection information of the user in multiple rounds of interaction (such as store selection, product selection, specification selection) can be stored in the context manager within the workflow engine, where the context manager is used to store the data status and data set during the interaction process.

[0122] S909: Determine the application corresponding to the user instruction information.

[0123] Optionally, the corresponding application can be determined based on the voice assistant wake-up word included in the user instruction information.

[0124] S910: Jump to the interaction page corresponding to the application, and the interaction page includes the detailed information of the interaction information.

[0125] In one embodiment, the application can be opened by calling the relevant jump interface within the application, and the interaction page is displayed after the jump. Among them, the detailed information of the interaction information may include the specific content of the target selection item selected by the user, such as the target store, target product, and target product specifications. Additionally, it may also include the quantity, price, and other attributes of the target product (such as remarks, delivery method, etc.).

[0126] Optionally, the interaction page can be used for the user to view the details of the interaction information. The interaction page may also include interaction controls for the user to trigger. Specifically, the interaction page may include but is not limited to the order placement page, control instruction trigger page, information display page, etc. Among them, the order placement page may include interaction controls for submitting an order and may also include interaction controls for modifying remarks, etc.

[0127] In one embodiment, by establishing a logical binding relationship between the open intent (Open App Intent) and the main intent, it can be achieved that after the user completes the confirmation operation of the main intent (product search intent), it can automatically jump to the associated application, thereby linking the dual intents (product search intent and product order placement intent).

[0128] It should be noted that a dedicated context transfer structure can be pre-deployed to transmit context data between multiple intents, so that during the multi-round jump interaction process of the user, its historical selection information, intent status, and slot data can be seamlessly connected to avoid information loss.

[0129] Furthermore, a shared storage area (such as a global context container) can be set up to achieve state sharing and synchronization among multiple asynchronous intents, solve the problems of state isolation and data asynchronization among native intents of the system, and improve the continuity and stability of multi-intent interaction.

[0130] In the above embodiments, after the user completes each interaction round by voice selection, the system automatically aggregates the selection information to generate complete interaction information, and combines with the context manager to record and maintain the interaction state, improving the coherence and accuracy of the data. At the same time, the application program is automatically determined by recognizing the voice wake-up word, and finally jumps to the confirmation page of the application program to display the detailed interaction information, realizing the voice-driven dual-intent (product search intent and product order intent) operation process, simplifying the user operation path, and enhancing the practicality and intelligence of voice interaction.

[0131] The following describes the present application in conjunction with the specific architecture of the information interaction system.

[0132] Specifically, please refer to Figure 10 , in one embodiment, the present application provides an information interaction system, and its system architecture is as Figure 10 shown. The system includes a user input layer, a voice assistant interface layer, a general intent processor, and a workflow execution subsystem. The workflow execution subsystem includes a workflow engine, a condition entity manager, a custom view renderer, and an intent jump engine.

[0133] Optionally, the workflow engine can be used to control and orchestrate multi-round interactive task processes. Specifically, the workflow engine includes a context manager, a workflow queue, and a large language model integration layer. Among them, the context manager can be used to manage the current interaction state, track the user's turn, selected content, etc., and the persistent storage module in the context manager can be used to save and restore the context state to support long-term sessions or interrupted connections. The workflow queue can be used to manage the task queue, the large language model integration layer can be used to perform large model reasoning on speech semantics, the intent parser and natural language understander under the large language model integration layer are used for semantic recognition and structuring, and the dialogue manager is used to generate dialogue content. In addition, the large language model can also support multi-round dialogues during the interaction between the user and the system, including but not limited to clarification interactions when the user's intention is unclear, secondary confirmation interactions when the user's expression is vague, and guiding the user to provide additional intent information when necessary to improve the accuracy of overall semantic recognition and the robustness of system response. Furthermore, a prompt word generation module may be included, which is used to dynamically generate and construct prompt words for driving the large language model response based on the current context information and workflow execution status, so that the response content generated by the large language model can fit the current scenario, process node and user intention, and improve the consistency and practicality of the model output. Optionally, the large language model integration layer can intelligently identify and accurately match the user's vague, irregular or non-standard expressions, thereby improving the system's fault tolerance and interactive robustness for natural language input.

[0134] Optionally, the Condition Entity Manager can be used to manage and generate entity information that can be selected by users, including text condition entities (based on plain text content, such as store names, product names, etc.), image condition entities (display items containing graphic information), and mixed condition entities (integrating multi-dimensional elements such as text, pictures, prices, and labels). In addition, the Condition Entity Manager can support dynamic inheritance and expansion of multiple scenarios, allowing the system to adapt to changing user needs. For example, entities can be expanded for related scenarios such as logistics order intent (express delivery, errands, etc.).

[0135] Optionally, a custom view renderer can be used to provide a card-style display suitable for the iOS system, including a conditional selection view (such as a first display page and a second display page) and a confirmation detail view (such as an order confirmation page).

[0136] Optionally, an intent jump engine can be used to determine the target execution action based on the current context and user instruction information. The intent jump engine specifically includes an in-app navigator and an inter-app navigator. Among them, the in-app navigator is used to perform specific page jumps within the application, and the inter-app navigator is used to jump across applications, such as jumping from a voice assistant to an e-commerce APP, or for example, jumping from an e-commerce APP to a payment APP.

[0137] Further, referring to Figure 11 , such as Figure 11 shown, a specific information interaction method is provided. For example, Figure 11 , the user can evoke the voice assistant and enter a natural language request, such as "Help me order a mobile milk tea". This natural language request is captured by the voice assistant as user instruction information and forwarded to the general intent processor. After receiving the voice request, the general intent processor initializes the workflow engine and converts the user request into structured semantic data. The workflow engine notifies the large language model to perform a deep analysis of the semantics, identify the intent information, and the context manager creates the corresponding conversation context. The system calls the conditional entity generator according to the identified intent information to generate options for entity data related to the intent information. The entity data is passed back to the workflow engine and rendered as the UI of the first-round selection page (the first display page) through the preset slot mechanism. The user selects the target option (such as the target store) in the first interaction round, and the system records this target option, updates the context, and continues to call the conditional entity generator to request options for the next-level entity (such as the product entity). The user selects the target option (such as the target product) in the second interaction round, and the system repeats a similar process, updates the context, and generates options for the entity (such as the product specification entity) corresponding to the third interaction round. The user selects the target option (such as the target product specification) in the third interaction round and confirms the order. After the user confirms, the system aggregates the selection data of each interaction round and updates the final context. The workflow engine notifies the application jump engine to generate order information based on the selected target store, target product, and target product specification, and calls the in-app jump interface or inter-app jump interface to jump to the corresponding order placement page or payment application.

[0138] Exemplarily, by utilizing the call characteristics of the intent framework dynamic library of the iOS system, the voice assistant can be integrated with the main application in the form of a dynamic library; this dynamic library can be independently loaded and run in the voice assistant environment and interact with the data structure of the main application through a shared interface, thus overcoming the limitations in aspects such as the integration path of the dynamic library and resource access permissions in traditional mobile operating systems, and achieving seamless communication and functional collaboration between the voice assistant and the main application.

[0139] It should be noted that a custom Context Detail View component can be constructed to replace the native iOS confirmation interface, enabling flexible display and dynamic rendering of order information, target selection items, and additional interactive content. This view component supports data aggregation, structured rendering, and personalized UI configuration across interaction rounds, thus breaking through the limitations of the native system interface functions and providing richer display capabilities and higher user interaction freedom.

[0140] Through the mechanisms of speech recognition, semantic parsing, context management, and hierarchical conditional entity generation, the above embodiments achieve an intelligent order placement process without manual input. The system uses natural language as the input method, combined with multi-round interaction and visual option display, greatly enhancing the user's interaction experience and being applicable to multi-scenario voice interaction systems such as takeout, e-commerce, and smart retail.

[0141] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily have to be completed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or in rotation with at least some of the steps or stages in other steps or other steps.

[0142] Based on the inventive concept of the above information interaction method, as Figure 12As shown in the figure, the embodiment of the present application further provides a first information interaction device 1200 for implementing the information interaction method involved above. The first information interaction device 1200 includes: a first receiving module 1201, configured to receive user instruction information and send the user instruction information to the server, so that the server determines a corresponding selection item based on the user instruction information, and the selection item is an item for the user to select in the current interaction round; a second receiving module 1202, configured to receive the selection item sent by the server and display the selection item through a preset slot; a judgment module 1203, configured to judge whether the target selection item includes a next-level selection item in response to the user's selection operation on the target selection item; an update module 1204, configured to, when the target selection item includes a next-level selection item, update the selection item displayed in the preset slot according to the next-level selection item, and return to execute the step of judging whether the target selection item includes a next-level selection item in response to the user's selection operation on the target selection item; a generation module 1205, configured to, when the target selection item does not include a next-level selection item, generate interaction information according to the selection information of the user in each interaction round.

[0143] In one embodiment, the second receiving module 1202 is specifically configured to load the data content of the selection item into a preset slot, and the preset slot is a general selection container for repeated use in multiple interaction rounds; and render and generate a first display page according to the data content of the selection item loaded in the preset slot, so as to display the selection item through the first display page.

[0144] In one embodiment, the interaction information is order information, and the selection item corresponds to any one of the following types of entities: a store entity, a commodity entity, and a commodity specification entity, where the selection item corresponding to the commodity entity is a next-level selection item included in the selection item corresponding to the store entity, and the selection item corresponding to the commodity specification entity is a next-level selection item included in the selection item corresponding to the commodity entity.

[0145] In one embodiment, the update module 1204 is specifically configured to load the data content of the next-level selection item into the preset slot and use the next-level selection item as the updated selection item; and render and generate a second display page according to the data content corresponding to the updated selection item loaded in the preset slot, so as to display the updated selection item through the second display page.

[0146] In one embodiment, when the entity corresponding to the target selection item is a store entity, the data content corresponding to the next-level selection item is the detailed data of the commodities included in the store entity corresponding to the target selection item; or, when the entity corresponding to the target selection item is a commodity entity, the data content corresponding to the next-level selection item is the detailed data of the specifications corresponding to the commodity entity corresponding to the target selection item.

[0147] In one embodiment, the first information interaction device 1200 further includes: a third receiving module, configured to receive voice information of a user; a second determining module, configured to determine a semantic recognition result corresponding to the voice information; and a third determining module, configured to determine that a selection operation of a user on a target selection item is detected when the semantic recognition result indicates that the user selects the target selection item, where the target selection item is any selection item.

[0148] In one embodiment, the generating module 1205 is specifically configured to aggregate the target selection items selected by the user in an interaction round; extract required interaction data according to the aggregated target selection items; display the interaction data through a preset slot; and generate corresponding interaction information according to the interaction data in response to a confirmation operation of the user on the interaction data.

[0149] In one embodiment, the first information interaction device 1200 further includes: a fourth determining module, configured to determine an application program corresponding to user instruction information; and a jump module, configured to jump to an order placement page corresponding to the application program, where the order placement page includes detailed information of the interaction information.

[0150] Each module in the first information interaction device 1200 described above can be implemented in whole or in part by software, hardware, and a combination thereof. Each of the above modules can be embedded in a processor in a computer device in a hardware form or be independent of the processor, or can be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to each of the above modules.

[0151] Please refer to Figure 13 In addition, an embodiment of the present application further provides a second information interaction device 1300 for implementing the information interaction method involved above. The second information interaction device 1300 includes: a third receiving module 1301, configured to receive user instruction information sent by a user terminal; a first determining module 1302, configured to determine a corresponding selection item based on the user instruction information, where the selection item is an item for the user to select in the current interaction round; and a sending module 1303, configured to send the selection item to the user terminal, so that the user terminal displays the selection item through a preset slot, and in response to a selection operation of the user on a target selection item, determine whether the target selection item includes a next-level selection item. If the target selection item includes a next-level selection item, update the selection item displayed through the preset slot according to the next-level selection item, and return to execute the step of determining whether the target selection item includes a next-level selection item in response to the selection operation of the user on the target selection item. If the target selection item does not include a next-level selection item, generate interaction information according to the selection information of the user in each interaction round.

[0152] In one embodiment, the first determination module 1302 is specifically configured to determine the user's intent information according to the user instruction information; query at least one entity corresponding to the user instruction information; generate at least one option corresponding to the at least one entity; and determine the at least one option as the option corresponding to the user instruction information.

[0153] In one embodiment, when the intent information is a product search intent, the entity is any one of the following types of entities: a store entity, a product entity, a product specification entity; wherein, the option corresponding to the product entity is a sub-option included in the option corresponding to the store entity, and the option corresponding to the product specification entity is a sub-option included in the option corresponding to the product entity.

[0154] The embodiment of the present application also provides an electronic device, which may be a server, and its internal structure diagram may be as Figure 14 shown. The electronic device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the electronic device is used to exchange information between the processor and external devices. The communication interface of the electronic device is used to communicate with an external terminal through a network connection. The processor of the electronic device executes the computer program to implement an information interaction method.

[0155] Those skilled in the art can understand that Figure 14 the structure shown in

[0156] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0157] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer storage medium or transmitted through the computer storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a Digital Versatile Disc (DVD)), or a semiconductor medium (for example, a Solid State Disk (SSD)), etc.

[0158] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The foregoing storage medium includes: various media such as ROM, RAM, magnetic disks, or optical discs that can store program codes. Without conflict, the technical features in this embodiment and the implementation solutions can be combined arbitrarily.

[0159] The above-described embodiments are merely described in a preferred implementation manner of the present application and do not limit the scope of the present application. Without departing from the design spirit of the present application, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present application shall fall within the protection scope determined by the claims.

[0160] The foregoing describes particular embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An information interaction method, characterized in that, Applied to a user terminal, the method includes: Receiving user instruction information and sending the user instruction information to a server, so that the server determines a corresponding option based on the user instruction information, where the option is an item for the user to select in the current interaction round; Receiving the option sent by the server and displaying the option through a preset slot, where the preset slot is a general selection container for repeated use in multiple interaction rounds; In response to a user's selection operation on a target option, determining whether the target option includes a next-level option; If the target option includes the next-level option, updating the option displayed in the preset slot according to the next-level option, and returning to execute the step of determining whether the target option includes a next-level option in response to the user's selection operation on the target option; If the target option does not include the next-level option, generating interaction information according to the user's selection information in each interaction round.

2. The method according to claim 1, characterized in that, The displaying the option through a preset slot includes: Loading the data content of the option into the preset slot; Rendering and generating a first display page according to the data content of the option loaded in the preset slot to display the option through the first display page.

3. The method according to claim 1, characterized in that, The interaction information is order information, and the option corresponds to any one of the following types of entities: a store entity, a product entity, and a product specification entity. Among them, the option corresponding to the product entity is a next-level option included in the option corresponding to the store entity, and the option corresponding to the product specification entity is a next-level option included in the option corresponding to the product entity.

4. The method according to claim 1, wherein The updating the option displayed in the preset slot according to the next-level option includes: Loading the data content of the next-level option into the preset slot and using the next-level option as the updated option; Rendering and generating a second display page according to the data content corresponding to the updated option loaded in the preset slot to display the updated option through the second display page.

5. The method according to claim 3, characterized in that, When the entity corresponding to the target option is the store entity, the data content corresponding to the next-level option is the detailed data of the products included in the store entity corresponding to the target option; Or, When the entity corresponding to the target option is a product entity, the data content corresponding to the next-level option is the detailed data of the specifications corresponding to the product entity corresponding to the target option.

6. The method according to claim 1, wherein After the option is displayed through the preset slot, the method further includes: Receiving the user's voice information; Determining a semantic recognition result corresponding to the voice information; If the semantic recognition result indicates that the user selects a target option, determining that a selection operation of the user on the target option is detected, where the target option is any of the options.

7. The method according to claim 1, wherein The generating interaction information according to the user's selection information in each interaction round includes: Aggregating the target options selected by the user in the interaction round; Extract the required interaction data according to the aggregated target options; Display the interaction data through the preset slot; In response to the user's confirmation operation on the interaction data, generate corresponding interaction information according to the interaction data.

8. The method according to claim 1, characterized in that After generating the interaction information according to the user's selection information in each interaction round, the method further includes: Determine the application corresponding to the user instruction information; Jump to the interaction page corresponding to the application, and the interaction page includes the detailed information of the interaction information.

9. An information interaction method, characterized in that, Applied to a server, the method includes: Receive the user instruction information sent by the user terminal; Based on the user instruction information, determine the corresponding option, where the option is an item for the user to select in the current interaction round; Send the option to the user terminal, so that the user terminal displays the option through the preset slot, and in response to the user's selection operation on the target option, determine whether the target option includes a next-level option. If the target option includes the next-level option, update the option displayed in the preset slot according to the next-level option, and return to execute the step of determining whether the target option includes a next-level option in response to the user's selection operation on the target option. If the target option does not include the next-level option, generate interaction information according to the user's selection information in each interaction round. The preset slot is a general selection container and is used for repeated use in multiple interaction rounds.

10. The method according to claim 9, characterized in that The determining the corresponding option based on the user instruction information includes: Determine the intention information of the user according to the user instruction information; Query at least one entity corresponding to the user instruction information; Generate at least one option corresponding to the at least one entity; Determine the at least one option as the option corresponding to the user instruction information.

11. The method according to claim 10, wherein When the intention information is a product search intention, the interaction information is order information, and the entity is any one of the following types of entities: store entity, product entity, product specification entity; wherein, the option corresponding to the product entity is a next-level option included in the option corresponding to the store entity, and the option corresponding to the product specification entity is a next-level option included in the option corresponding to the product entity.

12. An information interaction system, characterized in that, Includes: A user terminal and a server; wherein, The user terminal is configured to receive the user instruction information and send the user instruction information to the server; The server is configured to receive the user instruction information sent by the user terminal, determine the corresponding option based on the user instruction information, and send the option to the user terminal. The option is an item for the user to select in the current interaction round; The user terminal is further configured to receive the option sent by the server, display the option through a preset slot, and in response to a user's selection operation on a target option, determine whether the target option includes a next-level option. If the target option includes the next-level option, update the option displayed in the preset slot according to the next-level option, and return to execute the step of determining whether the target option includes a next-level option in response to the user's selection operation on the target option. If the target option does not include the next-level option, generate interaction information according to the selection information of the user in each interaction round. The preset slot is a general selection container for repeated use in multiple interaction rounds.

13. An information interaction device, characterized in that, Applied to a user terminal, the device includes: A first receiving module, configured to receive user instruction information and send the user instruction information to the server, so that the server determines a corresponding option based on the user instruction information. The option is an item for the user to select in the current interaction round; A second receiving module, configured to receive the option sent by the server and display the option through a preset slot. The preset slot is a general selection container for repeated use in multiple interaction rounds; A judgment module, configured to determine whether the target option includes a next-level option in response to a user's selection operation on the target option; An update module, configured to, when the target option includes the next-level option, update the option displayed in the preset slot according to the next-level option, and return to execute the step of determining whether the target option includes a next-level option in response to the user's selection operation on the target option; A generation module, configured to, when the target option does not include the next-level option, generate interaction information according to the selection information of the user in each interaction round.

14. An information interaction device, characterized in that, Applied to a server, the device includes: A third receiving module, configured to receive user instruction information sent by a user terminal; A first determination module, configured to determine a corresponding option based on the user instruction information. The option is an item for the user to select in the current interaction round; A sending module, configured to send the option to the user terminal, so that the user terminal displays the option through a preset slot, and in response to a user's selection operation on a target option, determine whether the target option includes a next-level option. If the target option includes the next-level option, update the option displayed in the preset slot according to the next-level option, and return to execute the step of determining whether the target option includes a next-level option in response to the user's selection operation on the target option. If the target option does not include the next-level option, generate interaction information according to the selection information of the user in each interaction round. The preset slot is a general selection container for repeated use in multiple interaction rounds.

15. An electronic device, characterized in that, Includes: A processor and a memory; the memory stores a computer program, and when the processor executes the computer program, the method steps of any one of claims 1-11 are implemented.

16. A computer storage medium, characterized in that, The computer storage medium stores a plurality of instructions, and the instructions are adapted to be loaded and executed by a processor to perform the method steps of any one of claims 1-11.

Images