Method and apparatus for information query, device and storage medium

By presenting query request labels in the interface and interacting with the intelligent agent, the problem of low response efficiency when users query product information is solved, and fast and automatic query results are presented, thus improving the user experience.

WO2026232878A1PCT designated stage Publication Date: 2026-11-12BEIJING YOUZHUJU NETWORK TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2026/074229
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-09
Filing Date
2026-01-22
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

In existing technologies, when users query product information, they need to manually enter questions through a long process and wait for the merchant to manually reply, resulting in low response efficiency and affecting user experience.

Method used

In the interface associated with the object, a label indicating the query request is presented. After the user triggers the label, they interact with the agent, which automatically replies with the query results, reducing human intervention.

Benefits of technology

By automating the query process, the user query chain is shortened, response efficiency and user experience are improved, and timely question-and-answer interaction is achieved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2026074229_12112026_PF_FP_ABST
    Figure CN2026074229_12112026_PF_FP_ABST
Patent Text Reader

Abstract

The embodiments of the present disclosure provide a method and apparatus for information query, a device, and a storage medium. The method comprises: presenting at least one tag in a first interface associated with an object, each tag indicating a query request related to the corresponding object; in response to triggering of a first tag of the at least one tag, presenting a second interface for interaction between a user and an agent; and presenting, in the second interface, a first query request indicated by the first tag and a first query result for the first query request, the first query request being presented as a question of the user, and the first query result being presented as a reply of the agent to the question.
Need to check novelty before this filing date? Find Prior Art

Description

Methods, apparatus, devices, and storage media for information retrieval

[0001] This application claims priority to Chinese Patent Application No. 202510601065.X, filed on May 9, 2025, entitled "Method, Apparatus, Device and Storage Medium for Information Retrieval", the entire contents of which are incorporated herein by reference. Technical Field

[0002] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to methods, apparatuses, electronic devices, computer-readable storage media, and computer program products for information retrieval. Background Technology

[0003] With the rapid development of information technology, various terminal devices can provide people with a variety of services in work and life. Terminal devices can offer users query functions to assist them in performing corresponding search operations on multimedia data. In some e-commerce scenarios, users can ask merchants various types of questions about objects (e.g., products). Therefore, it is desirable to provide users with convenient and fast query methods and improve the response efficiency to query requests. Summary of the Invention

[0004] In a first aspect of this disclosure, a method for information retrieval is provided, comprising: presenting at least one label in a first interface associated with an object, each label indicating a query request related to the corresponding object; in response to triggering of a first label of the at least one label, presenting a second interface for interaction between a user and an agent; and presenting in the second interface a first query request indicated by the first label and a first query result for the first query request, wherein the first query request is presented as a question from a user, and the first query result is presented as a response from an agent to the question.

[0005] In a second aspect of this disclosure, an apparatus for information retrieval is provided, comprising: a tag presentation module configured to present at least one tag in a first interface associated with an object, each tag indicating a query request related to a corresponding object; an interface presentation module configured to present a second interface for interaction between a user and an agent in response to triggering a first tag of at least one tag; and a query result presentation module configured to present a first query request indicated by a first tag and a first query result for the first query request in the second interface, wherein the first query request is presented as a question from a user, and the first query result is presented as a response from an agent to the question.

[0006] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.

[0008] According to a fifth aspect of this disclosure, a computer program product is provided, including computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method of the first aspect.

[0009] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0011] Figure 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0012] Figure 2 shows a flowchart of an information retrieval process according to some embodiments of the present disclosure;

[0013] Figures 3A to 3F show schematic diagrams of example interfaces for information retrieval according to some embodiments of the present disclosure;

[0014] Figure 4 shows a block diagram of an apparatus for information retrieval according to some embodiments of the present disclosure; and

[0015] Figure 5 shows a block diagram of an electronic device capable of implementing one or more embodiments of the present disclosure. Detailed Implementation

[0016] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0017] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0018] In this document, unless explicitly stated otherwise, performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.

[0019] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0020] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and user authorization should be obtained.

[0021] For example, in response to receiving a user's active request, a prompt message is sent to the user to clearly inform the user that the requested operation will require the acquisition and use of the user's personal information, thereby enabling the user to choose whether to provide personal information to the software or hardware such as electronic devices, applications, servers or storage media that perform the operation of the technical solution disclosed herein, based on the prompt message.

[0022] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0023] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0024] As used in this paper, the term "model" refers to a model that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs using multiple layers of processing units. A neural network model is an example of a deep learning-based model. In this paper, "model" may also be referred to as a "machine learning model," "learning model," "machine learning network," or "learning network," and these terms are used interchangeably.

[0025] In this disclosure, "trigger" refers to one or more interactive actions performed by a user on a terminal device. Furthermore, these interactive actions may be triggered within the same user interface / pop-up window or within different user interfaces / pop-up windows. This disclosure is not limited in this respect.

[0026] Example embodiments of this disclosure are described below with reference to the accompanying drawings.

[0027] Figure 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In environment 100, one or more users 110-1, 110-2, 110-3, ..., 110-N can perform query operations through their respective associated terminal devices 120-1, 120-2, ..., 120-N. For ease of discussion, users 110-1, 110-2, ..., 110-N may be collectively referred to as user 110 or individually, and terminal devices 120-1, 120-2, ..., 120-N may be collectively referred to as terminal device 120 or individually.

[0028] In some scenarios, user 110 can initiate a query request through terminal device 120, such as asking questions about an object (e.g., a product). In some embodiments, user 110 may also be referred to as a merchant. That is, user 110 can publish the object so that other users can perform operations related to the object, such as initiating a query request related to the product, purchasing the product, rating the product, adding the product to their favorites, etc. In this document, the object can be a physical or virtual object, such as a physical or virtual product, service, or electronic work.

[0029] In some embodiments, among all users 110, one or more users, such as user 110-1, can publish products through an associated terminal device 120-1. In some embodiments, user 110-1 may include the user corresponding to an e-commerce store. In some embodiments, the user performing the information query may include user 110-1 and one or more other users 110-2 to 110-N. Users 110-2 to 110-N may be consumers.

[0030] In some embodiments, the terminal device 120 may have applications installed that provide query services, or may have access to websites that provide query services. The user 110 may operate the terminal device 120 to access the corresponding applications or websites. Accordingly, the terminal device 120 may display corresponding query pages, object presentation pages, interactive pages for interacting with intelligent agents, search pages, and so on.

[0031] In some embodiments, terminal device 120 can also communicate with server 130 via network 132 to provide query services. Server 130 can provide functions such as application or website management, configuration, and maintenance. In some embodiments, if server 130 receives a query request from user 110 via terminal device 120, it can provide corresponding query results to user 110. In some embodiments, server 130 can invoke a machine learning model to determine the query results corresponding to the query request, as a response from the agent to user 110. In some embodiments, the agent can be deployed in server 130 or in each terminal device 120 to provide query services.

[0032] In embodiments of this disclosure, the intelligent agent may possess intelligent dialogue and task processing capabilities. A terminal device provides an interface that can present interactions with the intelligent agent. In the interface, users can submit query requests to the intelligent agent by inputting natural language input (text or voice input), and can also upload online or offline files as input information to initiate various requests to the intelligent agent. In some embodiments, the intelligent agent may be built based on one or more machine learning models. In some embodiments, the machine learning model upon which the intelligent agent is based may include at least a language model (LM). These machine learning models include content-generative models capable of generating corresponding outputs based on model inputs. In some embodiments, the language model-based machine learning model can receive text-modal model inputs (e.g., natural language and / or machine language) and / or non-text-modal model inputs (e.g., images, voice, video, etc.), and can obtain corresponding model outputs based on the model inputs and prompts, thereby completing task execution. Here, prompts are used to guide the machine learning model to generate user queries that can resolve the user queries indicated by the model inputs. In application scenarios supporting user dialogue, user input may be provided to the machine learning model as at least a part of the model inputs (other parts may include prompts). This user input is considered a question or query request. Based on the model output, the corresponding response can be provided to the user.

[0033] Terminal device 120 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 120 may also support any type of user-facing interface (such as "wearable" circuitry).

[0034] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications that support queries in terminal device 120.

[0035] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0036] As briefly mentioned earlier, users can ask merchants various types of questions about objects (e.g., products). Typically, users need to go through a lengthy process to ask merchants questions about the product, such as storage and usage questions, or ingredient preparation questions. Question input usually needs to be manually initiated. Furthermore, merchants need to manually answer the user's questions. This approach results in low merchant response efficiency, thus impacting the user experience.

[0037] According to some embodiments of this disclosure, an improved scheme for information retrieval is proposed. According to the scheme of this disclosure, at least one label is presented in a first interface associated with an object, each label indicating a query request related to the corresponding object. If a trigger is received for the first label of the at least one label, a second interface for interaction between the user and the agent is presented. Further, the second interface presents a first query request indicated by the first label and a first query result for the first query request. The first query request is presented as a user's question, and the first query result is presented as the agent's answer to the question.

[0038] In this way, by presenting labels indicating object-related query requests on the interface, users can easily and quickly ask questions about objects. This shortens the query process for users, thereby improving the user experience. Furthermore, based on the user's question, the intelligent agent can respond to the user's questions in a timely manner, thus improving response efficiency. Moreover, for preset query requests, the corresponding query results can often be predetermined, enabling more real-time question-and-answer interaction.

[0039] The following description will continue with a detailed description of some exemplary embodiments of this disclosure with reference to the accompanying drawings. It should be understood that the pages shown in the drawings are merely examples, and various page designs are possible in practice. The various graphic elements on the page may have different arrangements and different visual representations, one or more elements may be omitted or replaced, and one or more other elements may also be present. The embodiments of this disclosure are not limited in this respect. Furthermore, in the following description, exemplary embodiments will be primarily described with respect to terminal device 120. It should be understood that the actions described with respect to terminal device 120 may also be performed by an application on terminal device 120, or may be performed by the application in conjunction with its server (e.g., server 130).

[0040] In this document, terminal device 120 may be equipped with an application that supports object query functionality, allowing user 110 to perform query operations. The application can provide user 110 with objects (e.g., products). User 110 can perform interactive operations on these objects through the application, such as purchasing, browsing, viewing, saving, searching, etc. These objects may be provided by user 110-1 (e.g., a merchant). User 110-2 (e.g., a consumer) can use the application to ask the merchant questions about these objects, such as how the objects are stored, how they are processed, etc. In some examples, the application may be an e-commerce application and may have query or Q&A functionality for e-commerce products. In some examples, the application may be a browser application that provides access to e-commerce related websites.

[0041] The process for information retrieval according to this disclosure will continue to be described below with reference to FIG2. FIG2 shows a flowchart of a process 200 for information retrieval according to some embodiments of this disclosure. For ease of discussion, these embodiments will be described with reference to the environment 100 of FIG1. ​​These embodiments may be implemented at the terminal device 120 of FIG1.

[0042] In the discussion of process 200, for better understanding, some embodiments of the present disclosure for information retrieval will be explained and illustrated with reference to Figures 3A to 3F. Figures 3A to 3F show schematic diagrams of example interfaces 300A to 300F for information retrieval according to some embodiments of the present disclosure.

[0043] In process 200, at block 210, terminal device 120 presents at least one label in a first interface associated with an object, each label indicating a query request (also referred to as a "question") associated with the corresponding object. Terminal device 120 may present labels indicating query requests associated with objects in the interface associated with objects. In some embodiments, each label presented by terminal device 120 may indicate a question that user 110 may ask the merchant regarding an object (e.g., object 311 or any other suitable object).

[0044] In some examples, the labels presented by terminal device 120 for food products (such as fruits and vegetables) can indicate storage methods, cooking methods, and how to determine whether a product is raw or cooked, etc. For example, referring to the example interface 300A shown in FIG3A, label 312 can indicate to user 110, regarding object 311 (e.g., watermelon), "What desserts can be made with watermelon?" Label 313 can indicate to user 110, regarding object 311, "How long can watermelon be stored?", and so on. In other examples, the labels presented by terminal device 120 for clothing and home textile products can indicate cleaning methods, storage methods, etc. The labels presented by terminal device 120 for electronic products can indicate usage methods, maintenance, etc. These are merely exemplary and are not intended to limit the scope of this disclosure.

[0045] Referring to Figure 3A, terminal device 120 can display labels 312, 313, etc., in an order interface 300A associated with the order status of object 311. In some examples, order interface 300A can indicate the interface in the merchant's ready-to-ship state after user 110 purchases object 311. Order interface 300A can indicate the interface in the merchant's already-shipped state after user 110 purchases object 311. Additionally, order interface 300A can indicate the interface in the object's arrived state after user 110 purchases object 311. Order interface 300A can also indicate the interface in the user 110's received object 311 state.

[0046] Referring to the example interface 300B shown in Figure 3B, the terminal device 120 can display tags 312, 313, etc., in the details interface 300B of object 311. In some examples, while user 110 is viewing the details of object 311, user 110 can determine whether to perform the next interactive operation, such as purchasing, adding to favorites, or sharing object 311, based on the tags presented in the details interface 300B. Referring to the example interface 300C shown in Figure 3C, the terminal device 120 can display tags 312, 313, etc., in the search interface 300C associated with object 311. In the scenario where user 110 searches for fruit, the terminal device 120 can display some tags associated with object 311 belonging to fruit in the search interface 300C. In some examples, user 110 can determine whether to perform the next interactive operation, such as purchasing, adding to favorites, or sharing object 311, based on the questions indicated by these tags and the corresponding answers. These are merely exemplary, and this disclosure does not limit the scope of the activity. For ease of discussion, the information retrieval scheme disclosed herein will be described with reference to the order interface 300A (i.e., the first interface).

[0047] In some embodiments, the labels 312 and 313 displayed by the terminal device 120 in the order interface 300A can indicate questions that the user 110 might have regarding object 311. For example, the user 110 might inquire about the methods for handling object 311 or how object 311 is stored. This eliminates the need for the user 110 to open a conversation with the merchant to input their needs, allowing for convenient and quick access to information about object 311, thereby improving the user experience.

[0048] The following describes how terminal device 120 determines the label that indicates a query request related to an object.

[0049] In some embodiments, the terminal device 120 can determine prompt words for generating tags based on the category of the object. Based on the prompt words, the terminal device 120 uses a first machine learning model to generate multiple query requests associated with the object. Accordingly, the terminal device 120 can determine multiple tags that respectively indicate the query requests. In some examples, if the terminal device 120 determines that the object belongs to the fruit category, it can determine prompt words for generating query requests related to fruit objects (or specific fruit varieties). Further, the terminal device 120 can use the first machine learning model to generate query requests related to fruit objects based on the prompt words. Accordingly, the terminal device 120 presents the query requests related to fruit objects with their corresponding tags.

[0050] In some embodiments, terminal device 120 may utilize a first machine learning model to pre-generate query requests associated with objects based on prompts. Accordingly, terminal device 120 pre-determines and stores tags corresponding to these query requests. Subsequently, terminal device 120 presents these tags while displaying the order interface 300A.

[0051] In some embodiments, terminal device 120 may present a query identifier associated with a tag in a first interface. As shown in FIG3A, terminal device 120 may present a query identifier 314 associated with tag 312 in an order interface 300A. Terminal device 120 may present query identifier 314 in a magnifying glass style. This informs user 110 that tag 312 can be triggered for querying. In some embodiments, terminal device 120 may present at least one of the prompts for the agent associated with a tag in the first interface. The prompts for the agent indicate interaction with the agent, i.e., prompting user 110 to click on these tags to interact with the agent. As shown in FIG3A, terminal device 120 may present prompt information 315 associated with tags 312, 313, etc. in an order interface 300A. This informs user 110 that after purchasing item 311, they can click on tags 312, 313 to engage in dialogue with the agent. As shown in Figure 3B, the terminal device 120 can display prompt information 321 associated with tags 312, 313, etc., in the details interface 300B. This informs the user 110 that they can click on tags 312 and 313 to initiate a dialogue with the agent. The following will describe in detail how to interact with the agent with reference to Figures 3A and 3E to 3F.

[0052] The following will describe how to present the labels, with reference to Figures 3A and 3D.

[0053] In some embodiments, the number of characters included in each label presented by the terminal device 120 is less than a predetermined number of characters (e.g., 15 or any other suitable number of characters). In some embodiments, the terminal device 120 may present the labels in different ways depending on the number of characters in the labels and the number of multiple labels. In some embodiments, referring to FIG3A, if the terminal device 120 determines that the number of text lines of multiple labels (e.g., label 312 and label 313) is less than a predetermined number of text lines (e.g., two lines or any other suitable number of text lines), it may present label 312 and label 313 in area 316.

[0054] In some embodiments, if the terminal device 120 determines that the number of text lines for multiple labels (e.g., label 312, label 313, etc.) is greater than a predetermined number of text lines (e.g., two lines or any other suitable number of text lines), it may display a portion of the multiple labels (e.g., label 312 and label 313) in area 316. In some embodiments, if the terminal device 120 determines that the number of text lines for multiple labels is greater than a predetermined number of text lines (e.g., two lines or any other suitable number of text lines), it may display a viewing control 317 in area 316.

[0055] Referring to the example interfaces 300A and 300D shown in Figures 3A and 3D, if the terminal device 120 receives a trigger on the viewing control 317, it can display all labels (e.g., label 312, label 313, label 341, label 342, label 343) in area 316. In some embodiments, the number of characters in the labels displayed by the terminal device 120 is less than the number of characters included in a single text line. In some examples, if the number of characters in label A is less than the number of characters included in the text line, and the number of characters in label B is greater than the remaining number of characters included in the text line, label B will be displayed on another text line. For example, if the number of characters that a single text line can include is 20, the number of characters in label A is 14, and the number of characters in label B is 8, label B will be displayed on another text line.

[0056] In some embodiments, for some tags already presented to user 110 in the order interface 300A, when user 110 views the order interface 300A again, terminal device 120 can present other tags different from these tags in the order interface 300A. That is, multiple tags related to the object determined by terminal device 120 for user 110 can be presented in a round-robin fashion in the order interface 300A. In some examples, for some tags already presented to user 110 in the order interface 300A, when user 110 views the order interface 300A again, these previously presented tags will be placed at the bottom. That is, when user 110 views the order interface 300A again, terminal device 120 presents other tags different from the previously presented tags. In this way, various tags can be presented in the first interface to facilitate user queries for object-related questions, thereby improving the user experience.

[0057] The preceding text described how to present the labels. The following text, referring to Figures 2, 3A, and 3E through 3F, will continue to describe how to perform information retrieval.

[0058] Continuing process 200, in block 220, if terminal device 120 receives a trigger on a first tag among at least one of the tags, it presents a second interface for interaction between the user and the agent. That is, if the provided first tag is triggered in the first interface, the user can jump from the first interface to the second interface where they can interact with the agent, etc. In block 230, terminal device 120 presents a first query request indicated by the first tag and a first query result for the first query request in the second interface.

[0059] As shown in the example interfaces 300A and 300E of Figures 3A and 3E, if the terminal device 120 receives a trigger from the user 110 on tag 312 (i.e., the first tag), it can present interface 300E for interacting with the agent. That is, the user 110 can click on any tag (e.g., tag 312) to engage in dialogue with the agent. In some examples, the user 110 can click on any tag (e.g., tag 312) to initiate a query request indicated by that tag to the agent. The terminal device 120 can present the query request 351 indicated by tag 312 and the query result 352 for the query request 351 in interface 300E. In embodiments of this disclosure, the query request 351 is presented as a question from the user 110. Correspondingly, the query result 352 is presented as the agent's response to the user 110's question.

[0060] In some embodiments, user 110 can click on tag 312 to send a question indicated by tag 312 to the agent, such as "What desserts can be made with watermelon?" In this scenario, terminal device 120 can present a query request 351 corresponding to the question on interface 300E. Accordingly, terminal device 120 can present a query result 352 on interface 300E to determine it as the agent's answer to the question. Thus, by utilizing the agent to answer the user's question, the merchant does not need to manually answer the user, thereby improving the efficiency of answering the user's question.

[0061] In some embodiments, query results for a query request can be generated in the following ways. In some embodiments, if the terminal device 120 receives a trigger on tag 312, it can extract object information of the object (e.g., object 311). In some examples, object information may include the object's title, image, descriptive text, attribute information, etc. Further, the terminal device 120 generates query results using a second machine learning model based on the object information and the query request. In some embodiments, the first and second machine learning models may be the same or different machine learning models, and this disclosure does not limit this. Subsequently, the terminal device 120 can present the query results on the interface 300E. In some embodiments, query results corresponding to the query requests indicated by each tag can be pre-generated and stored. In this way, when a user triggers a tag, the corresponding query results, i.e., responses, can be quickly provided and presented on the interface where the user interacts with the agent.

[0062] In some embodiments, the query results corresponding to the query requests indicated by the tags can be pre-generated. That is, the terminal device 120 can invoke a machine learning model to pre-generate the query results corresponding to each query request indicated by a tag. If the terminal device 120 detects a trigger on any tag (e.g., tag 312), it can present the query request 351 indicated by tag 312 and its corresponding query result 352 on the interface 300E. In this way, based on object information and query requests, the second machine learning model can generate query results more comprehensively.

[0063] In some embodiments, user 110 can continue to send query requests on interface 300E (i.e., the second interface) to obtain query results corresponding to the query request. In some examples, user 110 can enter text in the input boxes included in interface 300E to initiate a query request. User 110 can also initiate query requests on interface 300E by voice, taking a photo, etc. This is merely exemplary, and this disclosure does not limit it.

[0064] Referring to the example interface 300F shown in Figure 3F, if the terminal device 120 receives a query request 361 related to object 311 in interface 300F (i.e., the second interface), it can obtain the query result 362 of query request 361. In some embodiments, the terminal device 120 can utilize a second machine learning model to generate the query result 362 of query request 361. Accordingly, the terminal device 120 can present the query result 362 in interface 300F as a response from the agent to the question indicated by query request 361. When initiating further queries, the response to subsequent query requests can be determined based on the information presented in the first interface, the object information of the object itself, and / or the previous query request and query result.

[0065] In summary, by presenting labels indicating object-related query requests on the interface, users can easily and quickly ask questions about objects. This shortens the query process and improves the user experience. Furthermore, based on the user's question, the intelligent agent can respond promptly, thereby improving response efficiency.

[0066] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes.

[0067] Figure 4 shows a schematic structural block diagram of an apparatus 400 for information retrieval according to certain embodiments of the present disclosure. The apparatus 400 may be implemented as or included in the terminal device 120. The various modules / components in the apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0068] As shown in Figure 4, the device 400 includes a label presentation module 410 configured to present at least one label in a first interface associated with an object, each label indicating a query request related to the corresponding object. The device 400 also includes an interface presentation module 420 configured to present a second interface for interaction between a user and an agent in response to the triggering of a first label containing at least one label. The device 400 further includes a query result presentation module 430 configured to present a first query request indicated by a first label and a first query result for the first query request in the second interface, wherein the first query request is presented as a user's question, and the first query result is presented as the agent's response to the question.

[0069] In some embodiments, the apparatus 400 further includes a query identifier presentation module configured to present at least one of a query identifier and a prompt message to an agent in a first interface, the prompt message indicating interaction with the agent.

[0070] In some embodiments, the query result presentation module 430 is further configured to, in response to receiving a second query request related to an object in the second interface, obtain a second query result for the second query request; and present the second query result in the second interface as a response from the agent to the second query request.

[0071] In some embodiments, the first interface includes one of the following: an order interface associated with the order status of an object; a details interface of an object; or a search interface associated with an object.

[0072] In some embodiments, the label presentation module 410 is further configured to present at least one label in a first area of ​​a first interface in response to the number of text lines of at least one label being less than a predetermined number of text lines; or to present a portion of the labels in the first area in response to the number of text lines of at least one label being greater than a predetermined number of text lines.

[0073] In some embodiments, the label rendering module 410 is further configured to render a viewing control in a first area in response to the number of text lines of at least one label being greater than a predetermined number of text lines; and to render the entirety of at least one label in the first area in response to a triggering of the viewing control.

[0074] In some embodiments, the number of characters included in each label of at least one label is less than a predetermined number of characters.

[0075] In some embodiments, when a first interface is presented to a user, the label presentation module 410 is further configured to present at least one other label, different from at least one label, in the first interface in response to the first interface being presented to the user again.

[0076] In some embodiments, at least one label is determined by: determining a prompt word for generating at least one label based at least on the category of the object; generating at least one query request associated with the object using a first machine learning model based on the prompt word; and determining at least one label that respectively indicates at least one query request.

[0077] In some embodiments, the query result presentation module 430 is configured to extract object information of an object in response to the triggering of a first tag; generate a first query result using a second machine learning model based on the object information and a first query request; and present the first query result in a second interface.

[0078] The units and / or modules included in device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units and / or modules in device 400 can be implemented at least partially by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), and so on.

[0079] It should be understood that one or more steps in the above methods can be performed by appropriate electronic devices or combinations of electronic devices. Such electronic devices or combinations of electronic devices may, for example, include the terminal device 120 and the server 130 in FIG1.

[0080] Figure 5 shows a block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 500 shown in Figure 5 is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. The electronic device 500 shown in Figure 5 can be used to implement the terminal device 120 or server 130 of Figure 1.

[0081] As shown in Figure 5, the electronic device 500 is in the form of a general-purpose electronic device. Components of the electronic device 500 may include, but are not limited to, one or more processing units or processors 510, memory 520, storage devices 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processor 510 may be a physical or virtual processor and is capable of performing various processes according to the programs stored in the memory 520. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0082] Electronic device 500 typically includes multiple computer storage media. Such media can be any available media accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media capable of storing information and / or data and accessible within electronic device 500.

[0083] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 5, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks may be provided. In these cases, each drive may be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0084] Communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functionality of components of electronic device 500 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0085] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0086] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0087] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0088] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0089] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0091] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for information retrieval, comprising: At least one label is presented in the first interface associated with the object, and each label indicates a query request related to the corresponding object; In response to the triggering of a first tag on the at least one tag, a second interface for interaction between the user and the agent is presented; as well as The second interface presents a first query request indicated by the first label and a first query result for the first query request, wherein the first query request is presented as a question from the user and the first query result is presented as the agent's response to the question.

2. The method according to claim 1, further comprising: In the first interface, at least one of a query identifier and a prompt message for the agent is presented in association with the at least one label, the prompt message indicating interaction with the agent.

3. The method according to any one of claims 1 to 2, further comprising: In response to receiving a second query request related to the object in the second interface, a second query result for the second query request is obtained; as well as The second query result is presented on the second interface as the agent's response to the second query request.

4. The method according to any one of claims 1 to 3, wherein the first interface comprises one of the following: An order interface associated with the order status of the object; The object's details interface; or The search interface associated with the object.

5. The method according to any one of claims 1 to 4, wherein presenting the at least one label in the first interface comprises: In response to the fact that the number of text lines of the at least one label is less than a predetermined number of text lines, the at least one label is presented in a first area of ​​the first interface; or In response to the fact that the number of text lines of the at least one label is greater than a predetermined number of text lines, a portion of the at least one label is presented in the first area.

6. The method of claim 5, wherein presenting at least one label in a first interface associated with the object comprises: In response to the fact that the number of text lines of the at least one label is greater than a predetermined number of text lines, a viewing control is presented in the first area; as well as In response to a triggering of the viewing control, the entirety of the at least one label is presented in the first area.

7. The method according to any one of claims 1 to 6, wherein the number of characters included in each of the at least one tag is less than a predetermined number of characters.

8. The method according to any one of claims 1 to 7, wherein the first interface is presented to the user, the method further comprising: In response to the first interface being presented to the user again, at least one other label, different from the first label, is presented in the first interface.

9. The method according to any one of claims 1 to 8, wherein the at least one label is determined by: Based at least on the category of the object, determine the prompt words used to generate the at least one tag; Based on the prompt words, at least one query request associated with the object is generated using a first machine learning model; as well as Determine the at least one tag that respectively indicates the at least one query request.

10. The method according to any one of claims 1 to 9, wherein presenting the first query result for the first query request in the second interface includes: In response to the triggering of the first tag, extract the object information of the object; Based on the object information and the first query request, the first query result is generated using a second machine learning model; as well as The first query result is displayed on the second interface.

11. An apparatus for information retrieval, comprising: The label rendering module is configured to render at least one label in a first interface associated with an object, each label indicating a query request related to the corresponding object; The interface presentation module is configured to present a second interface for interaction between the user and the agent in response to the triggering of a first tag of the at least one tag. as well as The query result presentation module is configured to present a first query request indicated by the first label and a first query result for the first query request in the second interface, wherein the first query request is presented as a question from the user and the first query result is presented as a response from the agent to the question.

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

13. A computer-readable storage medium having stored thereon computer-executable instructions that can be executed by a processor to implement the method according to any one of claims 1 to 10.

14. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 10.