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

Abstract

This application discloses an information interaction method, system, device, electronic device, and storage medium. The method, applied to a server, comprises: obtaining intent information corresponding to user instruction information, and obtaining a preset task queue corresponding to the intent information; adjusting the preset task queue based on the intent information to obtain a target task queue corresponding to the user instruction information; executing each task in the target task queue to obtain a task execution result; and upon detecting completion of a task in the target task queue, generating interaction information corresponding to the user instruction information based on the task execution result. This method can improve information interaction efficiency and enhance the intelligence and flexibility of task processing.

Description

Technical Field

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

[0002] With the popularization of Internet technology, interactive systems such as voice ordering and information query have gradually become an indispensable part of people's daily lives.

[0003] However, the interactive systems in related technologies usually adopt a fixed task execution process, which requires users to strictly follow predefined steps to perform operations. The interaction method is relatively rigid and lacks flexibility, resulting in low information interaction efficiency. Summary of the Invention

[0004] The embodiments of the present application provide an information interaction method, system, device, electronic device, and storage medium, which can improve the efficiency of information interaction and enhance the intelligence and flexibility of task processing. The above technical solutions are as follows:

[0005] In a first aspect, an embodiment of the present application provides an information interaction method, applied to a server, comprising:

[0006] Obtain the intent information corresponding to the user instruction information, and obtain the preset task queue corresponding to the intent information;

[0007] Adjust the preset task queue based on the intention information to obtain the target task queue corresponding to the user instruction information;

[0008] Execute each task in the target task queue and obtain the task execution results;

[0009] After detecting that the task in the target task queue is completed, interactive information corresponding to the user instruction information is generated according to the task execution result.

[0010] In a possible implementation, the preset task queue corresponding to the intent information includes multiple standard tasks related to the intent information;

[0011] Adjust the preset task queue based on the intent information to obtain the target task queue corresponding to the user instruction information, including:

[0012] Determine whether the preset task queue contains redundant tasks based on the intent information;

[0013] In the case that the preset task queue includes redundant tasks, the redundant tasks are deleted from the preset task queue to obtain a target task queue corresponding to the user instruction information.

[0014] In one possible implementation, determining whether a preset task queue contains redundant tasks based on the intent information includes:

[0015] For each standard task in the preset task queue, determine whether the intent information includes the target data corresponding to the standard task, where the target data is the data to be generated when executing the standard task;

[0016] In a case where the intention information includes task data corresponding to the standard task, it is determined that the preset task queue includes redundant tasks, and the standard task is determined as a redundant task.

[0017] In one possible implementation, each task in the target task queue is executed to obtain a task execution result, including:

[0018] Set the initial task in the target task queue as the current task;

[0019] Execute the current task;

[0020] When the current task is detected to be completed, the task execution sub-result of the current task is determined, and the current task execution progress is determined;

[0021] If the current task execution progress indicates that the task in the target task queue is not completed, determine a new current task according to the target task queue and return to the step of executing the current task;

[0022] When the current task execution progress indicates that all tasks in the target task queue have been completed, a task execution result is generated based on the task execution sub-results corresponding to each task.

[0023] In a possible implementation, when it is detected that the current task is completed, the method further includes:

[0024] Determine whether the user provides additional intention information;

[0025] When the user provides supplementary intention information, the target task queue is updated according to the supplementary intention information to obtain an updated target task queue;

[0026] The step of determining the current task execution progress is performed based on the updated target task queue.

[0027] In a possible implementation, the intention information is product purchase intention information;

[0028] The preset task queue includes at least the following standard tasks: store query task, store selection task, product selection task, and product specification selection task;

[0029] Among them, the target data corresponding to the store query task includes the store list corresponding to the intention information, the target data corresponding to the store selection task includes the target store information selected by the user in the store list, the target data corresponding to the product selection task includes the target product information selected by the user in the target store, and the target data corresponding to the product specification selection task includes the target product specification information selected by the user for the target product.

[0030] In a possible implementation, the interaction information is order information, and the interaction information corresponding to the user instruction information is generated according to the task execution result, including:

[0031] Extract target store information, target product information, and target product specification information from the task execution results;

[0032] Construct order data based on target store information, target product information, and target product specification information;

[0033] The order data is associated with the user's identification information to generate interaction information corresponding to the user's instruction information.

[0034] In one possible implementation, the user command information is a voice command issued by the user, and obtaining the intent information corresponding to the user command information includes:

[0035] Receive user instruction information;

[0036] Perform voice recognition on user command information to obtain a voice recognition result;

[0037] Perform semantic understanding on the speech recognition results to extract the intent information corresponding to the user's command information.

[0038] In a second aspect, an embodiment of the present application provides an information interaction method, applied to a user terminal, comprising:

[0039] Receive user instruction information;

[0040] Sending the user instruction information to the server so that the server responds to the user instruction information, obtains intent information corresponding to the user instruction information, and obtains a preset task queue corresponding to the intent information, adjusts the preset task queue based on the intent information, obtains a target task queue corresponding to the user instruction information, executes each task in the target task queue, obtains a task execution result, and after detecting that the task in the target task queue is completed, generates interaction information corresponding to the user instruction information according to the task execution result, and then sends the interaction information to the user terminal;

[0041] receiving interaction information;

[0042] Display interactive information.

[0043] In a third aspect, an embodiment of the present application provides an information interaction system, which includes: a user terminal and a server; wherein,

[0044] The user terminal is used to receive user instruction information and send the user instruction information to the server;

[0045] The server is configured to respond to user instruction information, obtain intent information corresponding to the user instruction information, and obtain a preset task queue corresponding to the intent information, adjust the preset task queue based on the intent information, obtain a target task queue corresponding to the user instruction information, execute each task in the target task queue, obtain a task execution result, and after detecting that the task in the target task queue is completed, generate interaction information corresponding to the user instruction information based on the task execution result, and then send the interaction information to the user terminal;

[0046] The user terminal is also used to receive and display interaction information.

[0047] In a fourth aspect, an embodiment of the present application provides an information interaction device, applied to a server, comprising:

[0048] An acquisition module is used to obtain the intent information corresponding to the user instruction information and the preset task queue corresponding to the intent information;

[0049] An adjustment module is used to adjust the preset task queue based on the intention information to obtain the target task queue corresponding to the user instruction information;

[0050] The execution module is used to execute each task in the target task queue and obtain the task execution results;

[0051] The generation module is used to generate interaction information corresponding to the user instruction information according to the task execution result after detecting that the task in the target task queue is completed.

[0052] In a fifth aspect, an embodiment of the present application provides an information interaction device, applied to a user terminal, comprising:

[0053] A first receiving module, configured to receive user instruction information;

[0054] a sending module, configured to send the user instruction information to the server, so that the server responds to the user instruction information, obtains intent information corresponding to the user instruction information, and obtains a preset task queue corresponding to the intent information, adjusts the preset task queue based on the intent information, obtains a target task queue corresponding to the user instruction information, executes each task in the target task queue, obtains a task execution result, and after detecting that the task in the target task queue is completed, generates interaction information corresponding to the user instruction information according to the task execution result, and then sends the interaction information to the user terminal;

[0055] A second receiving module, configured to receive interaction information;

[0056] The display module is used to display interactive information.

[0057] In a sixth aspect, an embodiment of the present application provides an electronic device comprising: 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.

[0058] In the seventh aspect, an embodiment of the present application provides a computer storage medium, which stores multiple instructions, and the instructions are suitable for being loaded by a processor and executing the method steps provided in the first aspect or the second aspect of the embodiment of the present application.

[0059] The above-mentioned information interaction method, system, device, electronic device and storage medium are applied to a server, by obtaining intent information corresponding to user instruction information, and obtaining a preset task queue corresponding to the intent information; adjusting the preset task queue based on the intent information to obtain a target task queue corresponding to the user instruction information; executing each task in the target task queue to obtain the task execution result; after detecting that the task in the target task queue is completed, generating interaction information corresponding to the user instruction information according to the task execution result, which can flexibly adapt to different user needs instead of using a fixed task process, and does not need to execute tasks unrelated to user needs, thereby reducing resource consumption and system response time, improving overall task processing efficiency, and improving the intelligence and flexibility of task processing; and then executing the adjusted target task queue in sequence and generating interaction information based on the actual execution results, effectively improving the consistency of the interaction information with the user's real needs, thereby improving the information interaction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0061] Figure 1 A schematic diagram of an application environment of an information interaction method provided by an exemplary embodiment of the present application;

[0062] Figure 2 A flowchart of an information interaction method provided by an exemplary embodiment of the present application;

[0063] Figure 3 A flowchart of another task processing method provided by an exemplary embodiment of the present application;

[0064] Figure 4 A flowchart of another information interaction method provided by an exemplary embodiment of the present application;

[0065] Figure 5 A flowchart of another task processing method provided by an exemplary embodiment of the present application;

[0066] Figure 6 A flowchart of another information interaction method provided by an exemplary embodiment of the present application;

[0067] Figure 7 A flowchart of another information interaction method provided by an exemplary embodiment of the present application;

[0068] Figure 8 A flowchart of another information interaction method provided by an exemplary embodiment of the present application;

[0069] Figure 9 A flowchart of another information interaction method provided by an exemplary embodiment of the present application;

[0070] Figure 10 A schematic diagram of the architecture of an information interaction system provided by an exemplary embodiment of the present application;

[0071] Figure 11 A schematic structural diagram of an information interaction device provided by an exemplary embodiment of the present application;

[0072] Figure 12 A schematic structural diagram of another information interaction device provided by an exemplary embodiment of the present application;

[0073] Figure 13 A schematic structural diagram of an electronic device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solutions and advantages of this application more clear, 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 intended to limit this application.

[0075] In the description of this application, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood 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, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship.

[0076] The information interaction method provided in the embodiment of the present application can be applied to Figure 1 In the application environment 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 it can be placed on the cloud or other network servers. Among them, the user terminal 11 can be but is not limited to various smart phones, tablets, personal computers, laptops, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 12 can be implemented as an independent server or a server cluster consisting of multiple servers.

[0077] Taking the above-mentioned information interaction method applied to an information interaction system as an example for explanation, user terminal 11 receives user instruction information determined by the user and sends the user instruction information to server 12. Server 12 obtains the intent information corresponding to the user instruction information and the preset task queue corresponding to the intent information. Based on the intent information, server 12 adjusts the preset task queue to obtain a target task queue corresponding to the user instruction information. Server 12 then executes each task in the target task queue to obtain task execution results. After detecting that the tasks in the target task queue have been completed, server 12 generates interaction information corresponding to the user instruction information based on the task execution results.

[0078] In one embodiment, Figure 2 As shown, an information interaction method is provided, which is applied to Figure 1 Taking the user terminal 11 and the server 12 in FIG. 1 as an example, the method includes the following steps:

[0079] S201: Acquire intent information corresponding to user instruction information, and acquire a preset task queue corresponding to the intent information.

[0080] The user instruction information may 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.

[0081] In one embodiment, the user terminal 11 may receive the user instruction information and send the user instruction information to the server 12. Specifically, the user terminal 11 may package the user instruction information into a data packet in JSON format or other data formats and send the data packet to the server 12 through a network interface.

[0082] It should be noted that the user can activate the voice assistant on the user terminal 11 by issuing a voice command. When the user terminal 11 detects that the user issues the voice assistant wake-up word corresponding to the relevant application (such as an e-commerce app, information browsing app, smart home control app, education and learning app, etc.), the voice interaction assistant is activated.

[0083] Optionally, the intent information can be the target action that the user wants to achieve extracted from the user command information, such as product search intention, product order intention, logistics order intention, information viewing intention, smart home control intention, data search intention, etc.

[0084] Exemplarily, the preset task queue corresponding to the user intention information includes multiple standard tasks related to the intention information.

[0085] Optionally, the preset task queue can be a set of standardized execution tasks predefined for specific intents. Specifically, the preset task queue corresponding to the product search intent includes at least the following standard tasks: store search task, store selection task, product selection task, and product specification selection task; the preset task queue corresponding to the logistics order placement intent can include at least the following standard tasks: address determination task, logistics company selection task, logistics item type determination task, and logistics item weight determination task; the preset task queue corresponding to the information viewing intent includes at least the following standard tasks: information channel selection task, information category selection task, and information content confirmation task; and the preset task queue corresponding to the smart home control intent includes at least the following standard tasks: device selection task, control type determination task, and control parameter setting task.

[0086] Alternatively, see Figure 3 , the user can input voice commands to the voice assistant through the user terminal 11. The voice commands are received by the voice assistant as user command information. The voice assistant can recognize the voice commands and then extract the corresponding intent information. Further, based on the recognition results, the semantic structured data is transmitted to the workflow engine to trigger the start operation of the task process. The workflow engine reads the corresponding task set from the preset task queue according to the user intention and the system preset process template, and initializes the current task execution sequence. This embodiment realizes the automated processing process from voice input to system task initialization, which can improve the response speed and intelligence level of voice interaction.

[0087] S202: Adjust the preset task queue based on the intention information to obtain the target task queue corresponding to the user instruction information.

[0088] Among them, adjusting the preset task queue based on the intent information can omit redundant tasks or insert new targeted tasks based on the actual content expressed by the user. For example, if the user's instruction information has already clearly stated the product name, there is no need to perform the product selection task.

[0089] S203: Execute each task in the target task queue and obtain task execution results.

[0090] Optionally, each task in the queue can be executed in sequence, and the total result returned after each task is executed can be used as the task execution result.

[0091] S204: After detecting that the task in the target task queue is completed, generating interaction information corresponding to the user instruction information according to the task execution result.

[0092] For example, based on the task status, context dependency, and task completion flag of each task, it can be determined whether the task in the target task queue has been successfully executed and meets the conditions for generating a task execution sub-result. After detecting that the task in the target task queue has been completed, the results of multiple rounds of tasks are aggregated into a standardized data structure to serve as interactive information.

[0093] Optionally, the interactive information may include but is not limited to: order information, control instruction information, information viewing information, data search information, etc.

[0094] In one embodiment, the order information may include the target store, target product, and target product specifications selected by the user. It may also include the target store's rating, delivery time, sales volume, the quantity and price of the target product, and other attributes (such as notes, delivery method, etc.).

[0095] In another embodiment, the information viewing information may include the target information channel, target information category, and target information content item selected by the user, and may also include the title, release time, source platform, content summary, content format (such as pictures, text, video, audio), related recommended content, and other information of the information content.

[0096] The above-mentioned information interaction method, system, device, electronic device and storage medium are applied to a server, by obtaining intent information corresponding to user instruction information, and obtaining a preset task queue corresponding to the intent information; adjusting the preset task queue based on the intent information to obtain a target task queue corresponding to the user instruction information; executing each task in the target task queue to obtain the task execution result; after detecting that the task in the target task queue is completed, generating interaction information corresponding to the user instruction information according to the task execution result, which can flexibly adapt to different user needs instead of using a fixed task process, and does not need to execute tasks unrelated to user needs, thereby reducing resource consumption and system response time, improving overall task processing efficiency, and improving the intelligence and flexibility of task processing; and then executing the adjusted target task queue in sequence and generating interaction data based on the actual execution results, effectively improving the consistency of the interaction information with the user's real needs, thereby improving the information interaction efficiency.

[0097] In one embodiment, Figure 4 As shown, another information interaction method is provided, which is applied to Figure 1 Taking the user terminal 11 and the server 12 in FIG. 1 as an example, the method includes the following steps:

[0098] S401: Receive user instruction information.

[0099] Specifically, the server 12 receives the user instruction information sent by the user terminal 11 .

[0100] S402: Perform voice recognition on the user instruction information to obtain a voice recognition result.

[0101] Optionally, the user command information may be subjected to speech recognition using Automatic Speech Recognition (ASR) technology in related technologies to obtain a speech recognition result, wherein the speech recognition result may be recognized text content, for example, "I want to order a large cup of pearl milk tea."

[0102] S403: Perform semantic understanding on the speech recognition result to extract the intention information corresponding to the user instruction information.

[0103] For example, the speech recognition result can be semantically understood through natural language understanding (NLU) to extract the intent information corresponding to the user instruction information.

[0104] S404: Adjust the preset task queue based on the intention information to obtain the target task queue corresponding to the user instruction information.

[0105] Specifically, S404 is consistent with S202 and will not be repeated here.

[0106] S405: Execute each task in the target task queue and obtain the task execution result.

[0107] Specifically, S405 is consistent with S203 and will not be repeated here.

[0108] S406: After detecting that the task in the target task queue is completed, generating interaction information corresponding to the user instruction information according to the task execution result.

[0109] Specifically, S406 is consistent with S204 and will not be repeated here.

[0110] For example, see Figure 5 First, a query task (QueryTask) is executed from the pre-set task queue. The user's natural language input (user command information) is submitted to the integrated large language model for semantic analysis. This semantic analysis process extracts user requirements based on context modeling and intent recognition. For example, in the product search scenario, user requirements include but are not limited to product search terms (such as "milk tea"), product quantity information (such as "one cup"), and product specifications (such as "large cup"). Another example is that in the information viewing scenario, user requirements include but are not limited to information topic keywords (such as "artificial intelligence"), information categories (such as "technology"), information time ranges (such as "today" or "this week"), and information sources (such as XX Daily). After semantic analysis, the large language model returns a structured intent that represents the user's explicit and implicit intent and is used for subsequent task judgment. Based on this structured intent, it can be used to determine whether new tasks need to be added. For example, in the product search scenario, if a store query task is needed, a search operation can be performed based on the relevant information in the structured intent to obtain a list of candidate stores that meet the requirements (such as "milk tea shop A, milk tea shop B", etc.). The system then converts the search results into a standardized selection format and presents them to the user in a graphical interface (e.g., a card list). Once the user selects a target store, the system records the selection and dynamically adds subsequent tasks (e.g., product selection) based on the current context and intent structure, further facilitating multiple rounds of interaction.

[0111] In the above-described embodiments, through speech recognition, semantic understanding, intent extraction, and dynamic adjustment and execution of task queues, an automated process is implemented, from natural language instructions to the generation of structured interactive information. Leveraging the deep semantic understanding capabilities of a large language model, it is possible to accurately extract user requirements (such as product, quantity, and specifications), and to generate and execute multiple rounds of interactive tasks (such as store search and product selection) on demand based on structured intent, thereby enhancing the intelligence, scalability, and responsiveness of the voice interaction system.

[0112] In one embodiment, Figure 6 As shown, another information interaction method is provided, which is applied to Figure 1 Taking the user terminal 11 and the server 12 in FIG. 1 as an example, the method includes the following steps:

[0113] S601: Acquire intent information corresponding to user instruction information, and acquire a preset task queue corresponding to the intent information.

[0114] Specifically, S601 is consistent with S201 and will not be repeated here.

[0115] S602: Determine whether the preset task queue contains redundant tasks based on the intention information.

[0116] Redundant tasks can be tasks that are no longer needed in the pre-set task queue because the user's command information implicitly or explicitly provided necessary information in the current interaction round and previous interaction rounds. In other words, if the user's historical voice input already covers the input requirements of some tasks, then some of these tasks can be considered redundant.

[0117] For example, the intent information corresponding to the user command is first structured and parsed to extract known parameters, such as semantic fragments such as the product ("milk tea"), product specifications ("large cup"), and product quantity ("two cups"). The task then retrieves the input parameters (task input dependencies) required for each task in the current pre-set task queue. For example, the store selection task requires parameters related to the product search intent, the product selection task requires a store number parameter, and the specification selection task requires the product name. The input dependencies of each task are then compared against the structured intent parameters. If all input items for the task are explicitly or implicitly provided in the user command, the task can be marked as redundant.

[0118] For example, the user command information is a voice message of "I want a large cup of pearl milk tea". The user command information already contains the product name and product specifications. In this case, the product selection task and the specification selection task can be determined as redundant tasks, and there is no need to prompt the user to select again.

[0119] S603: When the preset task queue includes redundant tasks, the redundant tasks are deleted from the preset task queue to obtain a target task queue corresponding to the user instruction information.

[0120] It is understandable that after identifying redundant tasks, such tasks can be deleted from the preset task queue, and only tasks corresponding to information that requires users to supplement are retained, thereby optimizing multi-round interaction paths, reducing repeated inquiries, and significantly improving interaction efficiency.

[0121] S604: Execute each task in the target task queue and obtain task execution results.

[0122] Specifically, S604 is consistent with S203 and will not be repeated here.

[0123] S605: After detecting that the task in the target task queue is completed, generating interaction information corresponding to the user instruction information according to the task execution result.

[0124] Specifically, S605 is consistent with S204 and will not be repeated here.

[0125] In the above embodiment, by performing structured parsing of the semantic content in user command information, known parameters (such as product, specifications, quantity, etc.) are extracted and compared with the input dependencies required for each task in the preset task queue. This allows for intelligent identification and deletion of redundant tasks that have been overwritten, retaining only the necessary tasks to form the target task queue. This effectively avoids repeated inquiries, reduces ineffective interaction steps, and significantly improves the efficiency and consistency of multiple rounds of voice interaction.

[0126] In one embodiment, Figure 7 As shown, another information interaction method is provided, which is applied to Figure 1 Taking the user terminal 11 and the server 12 in FIG. 1 as an example, the method includes the following steps:

[0127] S701: Acquire intent information corresponding to user instruction information, and acquire a preset task queue corresponding to the intent information.

[0128] Specifically, S701 is consistent with S201 and will not be repeated here.

[0129] S702: For each standard task in the preset task queue, determine whether the intention information includes target data corresponding to the standard task, where the target data is data to be generated when executing the standard task.

[0130] Optionally, when the intent information is product purchase intent information, the preset task queue includes at least the following standard tasks: a store query task, a store selection task, a product selection task, and a product specification selection task. The target data corresponding to the store query task includes the store list corresponding to the intent information, the target data corresponding to the store selection task includes the target store information selected by the user in the store list, the target data corresponding to the product selection task includes the target product information selected by the user in the target store, and the target data corresponding to the product specification selection task includes the target product specification information selected by the user for the target product.

[0131] Specifically, the system can parse the explicit and implicit data in the intent information and then perform structured semantic extraction on the intent information corresponding to the user's command information, extracting explicit related words and implicit references. It then establishes a mapping relationship between semantic fields and tasks. For example, the semantic field "milk tea" corresponds to the task of selecting a product, and the semantic field "large cup" corresponds to the task of selecting a product size. Furthermore, the system can sequentially traverse the preset task queue and determine whether the target data field of each task has been identified in the current intent information.

[0132] S703: When the intention information includes task data corresponding to the standard task, it is determined that the preset task queue includes redundant tasks, and the standard task is determined as a redundant task.

[0133] Optionally, if the required fields mentioned above have clearly appeared in the semantic structure or can be inferred from the context (for example, a store has been selected in the previous round of interaction), then the target data of the task is determined to have been met; otherwise, it is deemed that it has not been provided, and the task needs to be retained to guide the user to supplement the input.

[0134] S704: When the preset task queue includes redundant tasks, the redundant tasks are deleted from the preset task queue to obtain a target task queue corresponding to the user instruction information.

[0135] Specifically, S704 is consistent with S603 and will not be repeated here.

[0136] S705: Execute each task in the target task queue and obtain the task execution result.

[0137] Specifically, S705 is consistent with S203 and will not be repeated here.

[0138] S706: After detecting that the task in the target task queue is completed, extract the target store information, target product information, and target product specification information in the task execution result.

[0139] Specifically, the target store information can be the relevant information about the store selected by the user from the displayed store list. This target store information can include attributes such as store name, store number, rating, and delivery time, which are used for merchant location and service scheduling for subsequent orders. This target store information is generated from the execution results of the store selection task. The target product can be the item selected by the user from the product list displayed in the selected target store. This target product can include attributes such as product name, product number, unit price, product category, and monthly sales volume. This target product information indicates the specific product the user wishes to purchase. The target product specification information can be the specific product specifications or customized parameters selected by the user based on the selected target product information, including but not limited to capacity (e.g., large, medium, small), flavor (e.g., low sugar, sugar-free, full sugar), and temperature (e.g., hot, room temperature, ice-free). The target product specification information is output by the product specification selection task and is used to further refine the product configuration to ensure that the order meets the user's personalized needs.

[0140] S707: Construct order data based on the target store information, target product information, and target product specification information.

[0141] Optionally, the target store information, target product information, and target product specification information may be aggregated according to a preset format to construct order data.

[0142] S708: Associating the order data with the user's identification information to generate interaction information corresponding to the user's instruction information.

[0143] Specifically, the interactive information is order information, and the user's identification information can be a user account ID, device ID, session ID, or other information that uniquely identifies the user. Based on the order data, a unique order number is assigned to the order, and the order is bound to the user ID. This formal order information is generated, including the user ID, target store information, target product information, target product specifications, and order time, for subsequent order submission, payment processing, or delivery execution.

[0144] In the above embodiment, after completing multiple rounds of interactive tasks, the user's selected target store information, target product information, and target product specifications are automatically extracted, standardized order data is constructed according to a preset structure, and then bound to the user's identification information to generate complete interactive information (i.e., order information). This achieves an automated process from semantic recognition to order generation, supports personalized product configuration and precise merchant location, avoids repeated user input, and significantly improves the response efficiency of the voice interaction process and the user ordering experience.

[0145] In one embodiment, Figure 8As shown, another information interaction method is provided, which is applied to Figure 1 Taking the user terminal 11 and the server 12 in FIG. 1 as an example, the method includes the following steps:

[0146] S801: Acquire intent information corresponding to user instruction information, and acquire a preset task queue corresponding to the intent information.

[0147] Specifically, S801 is consistent with S201 and will not be repeated here.

[0148] S802: Adjust the preset task queue based on the intention information to obtain the target task queue corresponding to the user instruction information.

[0149] Specifically, S802 is consistent with S202 and will not be repeated here.

[0150] S803: Set the initial task in the target task queue as the current task.

[0151] The initial task may be the task that is ranked first in the target task queue, and specifically may be the first task in the task chain, such as a store selection task.

[0152] S804: Execute the current task.

[0153] Among them, executing the current task may refer to starting the corresponding interactive process based on the current task, which may specifically include page rendering, data acquisition, voice prompts, and collection of user selection results.

[0154] In one embodiment, when the current task is a store selection task, executing the current task includes: obtaining the store entity corresponding to the user instruction, sending the data content of the store entity to the user terminal 11, so that the user terminal 11 generates a store display page based on the store entity rendering, and obtains the target store information determined by the user based on the store display page; obtaining the target store information returned by the user terminal 11, and using the target store information as the task execution sub-result of the current task.

[0155] In another embodiment, when the current task is a commodity selection task, executing the current task includes: obtaining the user instruction information in the current interaction round, and the commodity entity set corresponding to the target store information, and sending the data content of the commodity entity set to the user terminal 11, so that the user terminal 11 renders and generates a commodity display page based on the commodity entity set; the commodity display page is used to display multiple optional commodity options in the target store to the user, and prompt the user to perform a commodity selection operation. Furthermore, the user terminal 11 determines the target commodity information selected by the user based on the user's selection operation, and feeds the target commodity information back to the server 12. After receiving the target commodity information, the server 12 uses it as the task execution sub-result of the current commodity selection task to support subsequent specification selection tasks or order data construction operations.

[0156] In another embodiment, when the current task is a product specification selection task, executing the current task includes: obtaining a product specification entity set associated with the target product, the product specification entity set is used to characterize the optional attribute information of the target product, including but not limited to capacity, sweetness, temperature, and topping options; sending the data content of the product specification entity set to the user terminal 11, so that the user terminal 11 renders and generates a product specification display page based on the product specification entity set, and the product specification display page is used to prompt the user to select multi-dimensional specification parameters. Furthermore, the user terminal 11 receives the user's specification selection operation, and determines the target product specification information corresponding to the target product based on the operation; and returns the target product specification information to the server 12. After receiving the target product specification information, the server 12 uses it as the task execution sub-result of the current task for subsequent order construction or price calculation tasks to call.

[0157] It should be noted that the current task can be executed through the preset task execution (Work flow Task) protocol. The preset task execution protocol can be used to uniformly manage various tasks in a multi-round interactive process. This protocol is the basic interface for each task, defines the standard execution method and input and output specifications of the task, and can adapt to different types of task processing logic. Specifically, the protocol can support multiple input types, that is, its input parameters can be structured text, voice recognition results, image identification data, user selection items and other data forms, thereby improving the system's compatibility with multimodal user input. Therefore, by implementing a unified task execution interface, various tasks can be encapsulated and scheduled in a modular manner, so that the tasks have good scalability, reusability and flexible combination capabilities.

[0158] S805: When it is detected that the current task is completed, a task execution sub-result of the current task is determined, and the current task execution progress is determined.

[0159] The current task execution progress can refer to the position or proportion of completed tasks in the entire target task queue, which can be used to represent the progress of the current task process. Specifically, the current task execution progress can be determined based on the number of completed tasks and the total length of the target task queue. The current task execution progress can be expressed in the form of the number of completed tasks, execution stage identifier, execution index position, or execution percentage.

[0160] It is understandable that after executing the current task, a corresponding task execution sub-result is generated, and the task execution sub-result of the current task can be passed as input to the next task to gradually improve the order or service process.

[0161] In one embodiment, during the execution of each task, abnormal conditions such as the validity of user instruction information, the integrity of task dependencies, and the interface return status can also be periodically detected. If abnormal conditions such as task execution failure, interruption, missing information, or user response timeout are detected, the error handling process can be triggered. When an error occurs, based on the status and context information of the current task, you can choose to re-execute the current task, roll back to the previous task state, or request the user to re-enter, so that the process can be controllably restored to a stable node. In addition, the error type, error location, and context snapshot can be persistently recorded for subsequent error prompts, path adjustments, or manual intervention.

[0162] S806: When the current task execution progress indicates that the task in the target task queue is not completed, a new current task is determined according to the target task queue, and the process returns to S804: executing the current task.

[0163] Among them, the current task execution progress indicates that the task is not completed, which means that there are still unexecuted tasks in the target task queue. Then, the next unfinished task in the target task queue can be set as the new current task, and the task execution loop is returned to continue executing the new current task.

[0164] S807: When the current task execution progress indicates that all tasks in the target task queue have been completed, a task execution result is generated based on the task execution sub-results corresponding to each task.

[0165] The task execution sub-results corresponding to each task may be the task execution sub-results corresponding to each task, that is, local data generated when each task is completed, such as target product information, target product specification information, etc. Optionally, each task execution sub-result may be aggregated into a complete piece of data.

[0166] In the above embodiment, by constructing a target task queue and executing each task sequentially, the task execution sub-results of each task are dynamically obtained in conjunction with the user's progressive input or selection operations during the interaction process, and the task scheduling process is controlled based on the task execution progress. Once the task is completed, the sub-results of each task are aggregated to generate a complete task execution result (such as order information). This allows for adapting to complex semantic instructions and supporting multiple rounds of dynamic interaction, improving the system's automated processing capabilities and user experience.

[0167] In one embodiment, Figure 9 As shown, another information interaction method is provided, which is applied to Figure 1 Taking the user terminal 11 and the server 12 in FIG. 1 as an example, the method includes the following steps:

[0168] S901: Acquire intent information corresponding to user instruction information, and acquire a preset task queue corresponding to the intent information.

[0169] Specifically, S901 is consistent with S201 and will not be repeated here.

[0170] S902: Adjust the preset task queue based on the intention information to obtain the target task queue corresponding to the user instruction information.

[0171] Specifically, S902 is consistent with S202 and will not be repeated here.

[0172] S903: Set the initial task in the target task queue as the current task.

[0173] Specifically, S901 is consistent with S201 and will not be repeated here.

[0174] S904: Execute the current task.

[0175] Specifically, S904 is consistent with S803 and will not be repeated here.

[0176] S905: When it is detected that the current task is completed, determine whether the user provides additional intention information; if so, execute S906; if not, ignore it.

[0177] Among them, the supplementary intention information can be new semantic information input by the user after completing the current task. The information may include new needs or extended intentions that have not been involved before, such as "add another cup of milk tea" or "order a snack by the way".

[0178] Optionally, whether the user proposes supplementary intent information can be identified through voice detection, natural language understanding, or user interface operation behavior (such as clicking an "add" button).

[0179] S906: Update the target task queue according to the supplementary intention information to obtain an updated target task queue.

[0180] In one embodiment, if the user proposes additional intention information, new tasks, such as product selection tasks, specification selection tasks, etc., can be dynamically inserted into the target task queue to obtain an updated target task queue. This sequence is used to continue to advance the subsequent interaction process.

[0181] By introducing a task status polling mechanism, the current task queue can be re-evaluated after user input, which can support skipping unnecessary tasks or returning to the previous task for re-execution, making the interaction process more flexible and in line with user needs.

[0182] S907: Determine the current task execution progress based on the updated target task queue.

[0183] It is understandable that after the target task queue is updated, the current task execution progress needs to be re-determined based on the updated target task queue.

[0184] S908: When the current task execution progress indicates that the task in the target task queue is not completed, a new current task is determined according to the target task queue, and the process returns to S904: executing the current task.

[0185] Specifically, S908 is consistent with S803 and will not be repeated here.

[0186] S909: When the current task execution progress indicates that all tasks in the target task queue have been completed, a task execution result is generated based on the task execution sub-results corresponding to each task.

[0187] Specifically, S909 is consistent with S807 and will not be repeated here.

[0188] In the above embodiment, a task-driven process control mechanism is implemented in multiple rounds of voice interaction by dynamically adjusting the task queue. After each round of task execution is completed, it is possible to determine whether the user has provided additional intent information, and accordingly update the task queue in real time, recalculate the task execution progress, so that the user's new needs can be responded to and processed immediately. As a result, the flexibility and context-awareness of the voice interaction process are effectively improved, supporting the addition of intentions and the expansion of instructions in the user's natural expression, and significantly optimizing the interaction coherence, task execution accuracy, and user experience in complex scenarios such as voice ordering and smart shopping guides.

[0189] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0190] The following describes this application in conjunction with the specific architecture of the information interaction system.

[0191] Specifically, see Figure 10 In one embodiment, the present application provides an information interaction system, the system architecture of which is as follows: Figure 10 As 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 (Work Flow Engine), a conditional entity manager, a custom view renderer, and an intent jump engine.

[0192] The workflow engine can be used to drive the execution of multi-round interactive task processes. The workflow engine can be a control center for coordinating the collaborative operation of tasks such as scheduling, input processing, and state management.

[0193] Optionally, a workflow engine can be used to control and orchestrate multi-turn interactive task flows. Specifically, the workflow engine includes a context manager (Work Flow Context), a workflow queue (Work Flow Queue), and a large language model integration layer. The context manager manages the current interaction state, tracking the user's interaction turn and selected content. The persistent storage module within the context manager saves and restores the context state to support long-term conversations or resumed conversations. The workflow queue manages the task queue. The large language model integration layer performs large-model inference on speech semantics. The intent parser and natural language understander within the large language model integration layer are responsible for semantic recognition and structuring, and the dialogue manager generates dialogue content. Furthermore, the large language model supports multi-turn dialogues during user-system interactions, including but not limited to clarification interactions when user intent is unclear, secondary confirmation interactions when user expressions are ambiguous, and guiding users to provide supplementary intent information when necessary. For example, Prompt Engineering can restrict the model to return results in a specific format, enabling more efficient and accurate natural language understanding and intent extraction, thereby improving overall semantic recognition accuracy and system response robustness.

[0194] Optionally, the Condition Entity Manager can be used to manage and generate entity information for user selection, including text conditional entities (constructed based on plain text content, such as store names, product names, etc.), image conditional entities (display items containing graphic and text information), and mixed conditional entities (integrating multi-dimensional elements such as text, images, prices, and labels).

[0195] Optionally, a custom view renderer can be used to provide a card-style display suitable for the iOS system, including a conditional selection view and a confirmation detail view.

[0196] Optionally, the 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. The in-app navigator is used to execute 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, and then from an e-commerce app to a payment app.

[0197] Furthermore, the system can cyclically monitor the completion status of the current task and the execution progress of the target task queue to determine whether to proceed to the next task execution phase or wait for user input to provide additional intent information. When the system discovers during the polling process that a task's input dependencies have been explicitly or implicitly satisfied in the context, it can automatically skip that task to avoid redundant execution. When detecting situations such as user intent switching, error correction, or task status conflicts, the polling mechanism can reposition to the previous task phase, reactivating the historical selection steps and achieving conditional reentry and path repair in the task process.

[0198] Based on the invention concept of the above information interaction method, Figure 11 As shown, the embodiment of the present application further provides an information interaction device 1100 for implementing the above-mentioned information interaction method. The information interaction device 1100 includes:

[0199] The acquisition module 1101 is used to acquire the intention information corresponding to the user instruction information and the preset task queue corresponding to the intention information;

[0200] An adjustment module 1102 is configured to adjust a preset task queue based on the intention information to obtain a target task queue corresponding to the user instruction information;

[0201] The execution module 1103 is used to execute each task in the target task queue and obtain the task execution result;

[0202] The generating module 1104 is configured to generate interaction information corresponding to the user instruction information according to the task execution result after detecting that the task in the target task queue is completed.

[0203] In one embodiment, the preset task queue corresponding to the intent information includes multiple standard tasks related to the intent information; the adjustment module 1102 is specifically used to: determine whether the preset task queue contains redundant tasks based on the intent information; if the preset task queue contains redundant tasks, delete the redundant tasks from the preset task queue to obtain the target task queue corresponding to the user instruction information.

[0204] In one embodiment, the adjustment module 1102 is specifically used to: for each standard task in the preset task queue, determine whether the intention information includes target data corresponding to the standard task, the target data being the data to be generated when executing the standard task; if the intention information includes task data corresponding to the standard task, determine that the preset task queue contains redundant tasks, and determine the standard task as a redundant task.

[0205] In one embodiment, the execution module 1103 is specifically used to: take the initial task in the target task queue as the current task; execute the current task; when it is detected that the current task is completed, determine the task execution sub-result of the current task, and determine the current task execution progress; when the current task execution progress indicates that the task in the target task queue is not completed, determine a new current task according to the target task queue, and return to the step of executing the current task; when the current task execution progress indicates that all tasks in the target task queue are completed, generate a task execution result based on the task execution sub-results corresponding to each task.

[0206] In one embodiment, when it is detected that the current task is completed, the information interaction device also includes: a judgment module for judging whether the user provides supplementary intention information; an update module for updating the target task queue according to the supplementary intention information when the user provides supplementary intention information, to obtain an updated target task queue; and a determination module for performing steps to determine the current task execution progress based on the updated target task queue.

[0207] In one embodiment, the intention information is product purchase intention information; the preset task queue includes at least the following standard tasks: store query task, store selection task, product selection task and product specification selection task; wherein, the target data corresponding to the store query task includes the store list corresponding to the intention information, the target data corresponding to the store selection task includes the target store information selected by the user in the store list, the target data corresponding to the product selection task includes the target product information selected by the user in the target store, and the target data corresponding to the product specification selection task includes the target product specification information selected by the user for the target product.

[0208] In one embodiment, the interactive information is order information, and the generation module 1104 is specifically used to: extract the target store information, target product information and target product specification information in the task execution results; construct order data based on the target store information, target product information and target product specification information; associate the order data with the user's identification information to generate interactive information corresponding to the user instruction information.

[0209] In one embodiment, the user instruction information is a voice instruction issued by the user, and the acquisition module 1101 is specifically used to: receive the user instruction information; perform voice recognition on the user instruction information to obtain a voice recognition result; and perform semantic understanding on the voice recognition result to extract the intention information corresponding to the user instruction information.

[0210] Each module in the above-mentioned information interaction device 1100 can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0211] Based on the invention concept of the above information interaction method, Figure 12 As shown, the embodiment of the present application further provides an information interaction device 1200 for implementing the above-mentioned information interaction method. The information interaction device 1200 includes:

[0212] The first receiving module 1201 is used to receive user instruction information;

[0213] A sending module 1202 is configured to send the user instruction information to the server, so that the server responds to the user instruction information, obtains intent information corresponding to the user instruction information, and obtains a preset task queue corresponding to the intent information, adjusts the preset task queue based on the intent information, obtains a target task queue corresponding to the user instruction information, executes each task in the target task queue, obtains a task execution result, and after detecting that the task in the target task queue is completed, generates interaction information corresponding to the user instruction information based on the task execution result, and then sends the interaction information to the user terminal;

[0214] A second receiving module 1203 is configured to receive interaction information;

[0215] The display module 1204 is used to display the interactive information.

[0216] The embodiment of the present application also provides an electronic device, which may be a server, and its internal structure diagram may be as shown in FIG. Figure 13 As shown. The electronic device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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 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 an external device. 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 a computer program to implement an information interaction method.

[0217] Those skilled in the art will understand that Figure 13The structure shown in the figure is only a block diagram of a part of the structure 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0218] The present application also provides a computer storage medium having instructions stored therein that, when executed on a computer or processor, cause the computer or processor to perform one or more steps of the above-described embodiments. If the components of the electronic device described above are implemented as software functional units and sold or used as independent products, they may be stored in the computer-readable storage medium described above.

[0219] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented 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, all or part of the processes or functions described in the embodiments of the present application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer storage medium or transmitted via the computer storage medium. The computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer storage medium may be any available medium accessible by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0220] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks. The technical features of this embodiment and the implementation scheme can be combined in any manner unless they conflict.

[0221] The embodiments described above are merely preferred embodiments of the present application and are not intended to limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements made to the technical solutions of the present application by ordinary technicians in this field should fall within the scope of protection determined by the claims.

[0222] The foregoing description describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. 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 server, the method includes: Obtaining intent information corresponding to user instruction information, and obtaining a preset task queue corresponding to the intent information; Adjusting the preset task queue based on the intention information to obtain a target task queue corresponding to the user instruction information; Execute each task in the target task queue and obtain the task execution result; After detecting that the task in the target task queue is completed, generating interaction information corresponding to the user instruction information according to the task execution result; The adjusting the preset task queue based on the intention information includes: omitting redundant tasks or inserting new tasks according to the actual content expressed by the user; The executing of each task in the target task queue to obtain a task execution result includes: taking the initial task in the target task queue as the current task; executing the current task; determining the current task execution progress and judging whether the user provides supplementary intention information when detecting that the current task is completed; updating the target task queue according to the supplementary intention information to obtain an updated target task queue when the user provides the supplementary intention information; determining the current task execution progress based on the updated target task queue; determining a new current task according to the target task queue when the current task execution progress indicates that the task in the target task queue is not completed, and returning to the step of executing the current task.

2. The method according to claim 1, characterized in that The preset task queue corresponding to the intention information includes a plurality of standard tasks related to the intention information; The adjusting the preset task queue based on the intention information to obtain a target task queue corresponding to the user instruction information includes: Determining whether the preset task queue contains redundant tasks based on the intention information; In a case where the preset task queue includes the redundant task, the redundant task is deleted from the preset task queue to obtain a target task queue corresponding to the user instruction information.

3. The method according to claim 2, characterized in that The determining, based on the intention information, whether the preset task queue contains redundant tasks includes: For each standard task in the preset task queue, determining whether the intention information includes target data corresponding to the standard task, the target data being data to be generated by executing the standard task; In a case where the intention information includes task data corresponding to the standard task, it is determined that the preset task queue includes redundant tasks, and the standard task is determined as a redundant task.

4. The method according to claim 1, wherein The executing each task in the target task queue to obtain a task execution result includes: When it is detected that the current task is completed, determining a task execution sub-result of the current task; If the current task execution progress indicates that the task in the target task queue is not completed, determining a new current task according to the target task queue, and returning to the step of executing the current task; When the current task execution progress indicates that all tasks in the target task queue have been completed, a task execution result is generated based on the task execution sub-results corresponding to each task.

5. The method according to claim 3, characterized in that The intention information is commodity purchase intention information; The preset task queue includes at least the following standard tasks: store query task, store selection task, product selection task and product specification selection task; Among them, the target data corresponding to the store query task includes the store list corresponding to the intention information, the target data corresponding to the store selection task includes the target store information selected by the user in the store list, the target data corresponding to the product selection task includes the target product information selected by the user in the target store, and the target data corresponding to the product specification selection task includes the target product specification information selected by the user for the target product.

6. The method according to claim 5, characterized in that The interaction information is order information, and the generation of the interaction information corresponding to the user instruction information according to the task execution result includes: Extracting the target store information, the target product information, and the target product specification information from the task execution result; Constructing order data based on the target store information, the target product information, and the target product specification information; The order data is associated with the identification information of the user to generate interaction information corresponding to the user instruction information.

7. The method according to claim 1, characterized in that The user instruction information is a voice instruction issued by the user, and the acquiring of the intention information corresponding to the user instruction information includes: Receive user instruction information; Performing voice recognition on the user instruction information to obtain a voice recognition result; Perform semantic understanding on the speech recognition result to extract the intention information corresponding to the user instruction information.

8. An information interaction method, characterized in that: Applied to a user terminal, the method includes: Receive user instruction information; The user instruction information is sent to the server so that the server responds to the user instruction information, obtains the intent information corresponding to the user instruction information, and obtains the preset task queue corresponding to the intent information, adjusts the preset task queue based on the intent information, obtains the target task queue corresponding to the user instruction information, executes each task in the target task queue, obtains the task execution result, and after detecting that the task in the target task queue is completed, generates the interaction information corresponding to the user instruction information according to the task execution result, and then sends the interaction information to the user terminal; wherein, adjusting the preset task queue based on the intent information includes: omitting redundant tasks or inserting new tasks according to the content actually expressed by the user. task; executing each task in the target task queue to obtain a task execution result, including: taking the initial task in the target task queue as the current task; executing the current task; in the case of detecting that the current task is completed, determining the current task execution progress, and judging whether the user provides supplementary intention information; in the case of the user providing the supplementary intention information, updating the target task queue according to the supplementary intention information to obtain an updated target task queue; determining the current task execution progress based on the updated target task queue; in the case that the current task execution progress indicates that the task in the target task queue is not completed, determining a new current task according to the target task queue, and returning to the step of executing the current task; receiving the interaction information; The interaction information is displayed.

9. An information interaction system, characterized in that: The information interaction system includes: a user terminal and a server; wherein, The user terminal is used to receive user instruction information and send the user instruction information to the server; The server is configured to, in response to the user instruction information, obtain intent information corresponding to the user instruction information and a preset task queue corresponding to the intent information, adjust the preset task queue based on the intent information to obtain a target task queue corresponding to the user instruction information, execute each task in the target task queue, and obtain a task execution result. After detecting that the tasks in the target task queue are completed, the server generates interaction information corresponding to the user instruction information based on the task execution result, and then sends the interaction information to the user terminal. The server is specifically configured to omit redundant tasks or insert new tasks based on the actual content expressed by the user; set the initial task in the target task queue as the current task; execute the current task; upon detecting that the current task is completed, determine the current task execution progress and determine whether the user provides supplementary intent information; if the user provides the supplementary intent information, update the target task queue based on the supplementary intent information to obtain an updated target task queue; determine the current task execution progress based on the updated target task queue; if the current task execution progress indicates that the tasks in the target task queue are not completed, determine a new current task based on the target task queue, and return to the step of executing the current task; The user terminal is further configured to receive the interaction information and display the interaction information.

10. An information interaction device, characterized in that: Applied to a server, the device includes: An acquisition module is used to acquire the intention information corresponding to the user instruction information, and acquire the preset task queue corresponding to the intention information; An adjustment module, configured to adjust the preset task queue based on the intention information to obtain a target task queue corresponding to the user instruction information; An execution module, configured to execute each task in the target task queue and obtain a task execution result; A generating module, configured to generate, after detecting that a task in the target task queue is completed, interaction information corresponding to the user instruction information according to the task execution result; The adjustment module is specifically used to omit redundant tasks or insert new tasks according to the content actually expressed by the user; The execution module is specifically used to take the initial task in the target task queue as the current task; execute the current task; when it is detected that the current task is completed, determine the current task execution progress, and judge whether the user provides supplementary intention information; when the user provides the supplementary intention information, update the target task queue according to the supplementary intention information to obtain an updated target task queue; determine the current task execution progress based on the updated target task queue; when the current task execution progress indicates that the task of the target task queue is not completed, determine a new current task according to the target task queue, and return to the step of executing the current task.

11. 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; The sending module is used to send the user instruction information to the server, so that the server responds to the user instruction information, obtains the intent information corresponding to the user instruction information, and obtains the preset task queue corresponding to the intent information, adjusts the preset task queue based on the intent information, obtains the target task queue corresponding to the user instruction information, executes each task in the target task queue, obtains the task execution result, and after detecting that the task in the target task queue is completed, generates the interaction information corresponding to the user instruction information according to the task execution result, and then sends the interaction information to the user terminal; wherein, adjusting the preset task queue based on the intent information includes: omitting redundant tasks or inserting tasks according to the content actually expressed by the user. inserting a new task; executing each task in the target task queue to obtain a task execution result, including: taking the initial task in the target task queue as the current task; executing the current task; in the case of detecting that the current task is completed, determining the current task execution progress, and judging whether the user provides supplementary intention information; in the case of the user providing the supplementary intention information, updating the target task queue according to the supplementary intention information to obtain an updated target task queue; determining the current task execution progress based on the updated target task queue; in the case that the current task execution progress indicates that the task in the target task queue is not completed, determining a new current task according to the target task queue, and returning to the step of executing the current task; A second receiving module, configured to receive the interaction information; A display module is used to display the interaction information.

12. An electronic device, characterized in that: include: A processor and a memory; the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

13. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 8.

Images