Intelligent question answering method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to a smart question and answer method, device, electronic equipment and storage medium. The method comprises: displaying a main chat window, wherein the main chat window is a question and answer interaction window of a question and answer party, and the main chat window contains a smart question and answer control. In response to a triggering operation on the smart question and answer control, an auxiliary chat window is displayed. The auxiliary chat window is a question and answer interaction window of an artificial intelligence model corresponding to the question and answer party; the main chat window and the auxiliary chat window are used to input a target question to carry out a question and answer conversation. The method improves the question and answer interaction efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to an intelligent question-answering method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the increasing complexity of corporate organizational structures and the diversification of business needs, cross-departmental collaboration has become a normalized working model in modern enterprise operations. During project implementation, it is often necessary to integrate the professional resources and manpower of multiple departments, achieving predetermined goals through close cooperation between teams.

[0003] In traditional technologies, when cross-departmental projects are carried out, members of each department need to frequently exchange information and coordinate business processes. Specifically, when a department encounters problems related to its professional field or business processes during project execution, it needs to request consultation from professionals in the relevant departments; at the same time, the requested party also needs to provide timely professional answers and business guidance to ensure the smooth progress of the project.

[0004] However, in traditional technologies, this two-way question-and-answer mechanism not only consumes the time cost of employees on both sides of the question and answer, but also, due to the unequal availability of each employee, the efficiency of the question and answer process is often constrained by factors such as communication channels and response speed, resulting in low efficiency. Summary of the Invention

[0005] This disclosure provides an intelligent question-answering method, apparatus, electronic device, and storage medium to at least address the problem in related technologies where unequal available time among employees leads to low efficiency in question-answering processes, often constrained by factors such as communication channels and response speed. The technical solution of this disclosure is as follows:

[0006] According to a first aspect of the present disclosure, an intelligent question-answering method is provided, the method comprising:

[0007] Display the main chat window, which is a question-and-answer interaction window for the person answering the question, and the main chat window contains intelligent question-and-answer controls;

[0008] In response to the triggering operation of the intelligent question-and-answer control, an auxiliary chat window is displayed; the auxiliary chat window is a question-and-answer interaction window of the artificial intelligence model corresponding to the question responder; the main chat window and the auxiliary chat window are used to input the target question and conduct a question-and-answer dialogue.

[0009] In one embodiment, the intelligent question-and-answer control includes intelligent question-and-answer icons and intelligent question-and-answer cards, and the display of the main chat window includes:

[0010] In response to the first question-and-answer request initiated by the questioner, a main chat window is displayed, which includes a smart question-and-answer icon and / or a smart question-and-answer card.

[0011] In one embodiment, displaying an auxiliary chat window in response to a triggering operation on the smart question-and-answer control includes:

[0012] In response to a trigger operation on the intelligent question-and-answer identifier, an auxiliary chat window is displayed; or,

[0013] In response to the triggering operation of the smart question-and-answer card, an auxiliary chat window is displayed.

[0014] In one embodiment, the method further includes:

[0015] In response to an input operation on the target question, the target question is displayed in the auxiliary chat window;

[0016] Based on the target question, the artificial intelligence model parses and extracts the response content from the corpus corresponding to the question responder, and displays the response content in the auxiliary chat window.

[0017] In one embodiment, displaying the target question in the auxiliary chat window in response to an input operation on the target question includes:

[0018] Display an auxiliary chat window, which contains question and answer cards, and the question and answer cards contain candidate questions;

[0019] In response to a triggering action on the target question among the candidate questions, the target question is displayed in the auxiliary chat window.

[0020] In one embodiment, the auxiliary chat window includes input controls, and displaying the target question in the auxiliary chat window in response to an input operation on the target question includes:

[0021] In response to a triggering operation on the input control, an input tool for entering the target question is displayed;

[0022] In response to the input of a target question through the input tool, the target question is displayed in the auxiliary chat window.

[0023] In one embodiment, the method further includes:

[0024] Display the corpus management page, which includes content addition controls;

[0025] In response to a triggering operation on the content addition control, a content addition page is displayed, which includes content management options;

[0026] Based on the category and segmentation options in the content management options, the target material information is obtained and uploaded, and the local corpus is updated based on the target material information.

[0027] In one embodiment, obtaining and uploading target material information based on the category and segmentation options in the content management options includes:

[0028] Based on the triggering operation of the category option in the content management options, the file type and storage format of the target material information to be uploaded are displayed;

[0029] Based on the file type and storage format, the target material information is obtained, and based on the triggering operation of the segmentation option in the content management options, the text segmentation format of the target material information is displayed;

[0030] Based on the aforementioned text segmentation format, the material segmentation results of the target material information are displayed on the corpus display page.

[0031] In one embodiment, the method further includes:

[0032] In response to the question-and-answer interaction between the local artificial intelligence model and the questioner, the target question and the corresponding answer content are obtained during the interaction process. Each target question and the answer content are constructed into a question-and-answer corpus pair and stored in the local corpus.

[0033] The question-and-answer corpus pairs from each question-and-answer session are displayed on the corpus configuration page.

[0034] In one embodiment, the corpus configuration page includes a configuration management control for corpus pairs, the configuration management control includes a labeling control, and the method further includes:

[0035] In response to the triggering operation of the annotation control of the target question-answer corpus pair in the question-answer corpus pair, the annotation configuration page for the target question-answer corpus pair is displayed;

[0036] In response to the annotation operation on the target question-and-answer corpus pair on the annotation configuration page, the annotated target question-and-answer corpus pair is displayed.

[0037] According to a second aspect of the present disclosure, an intelligent question-answering device is provided, comprising:

[0038] The first display unit is configured to display the main chat window, which is a question-and-answer interaction window with the question responder, and the main chat window contains intelligent question-and-answer controls;

[0039] The second display unit is configured to display an auxiliary chat window in response to a trigger operation on the intelligent question-and-answer control; the auxiliary chat window is a question-and-answer interaction window of the artificial intelligence model corresponding to the question responder; the main chat window and the auxiliary chat window are used to input target questions and conduct question-and-answer dialogues.

[0040] In one embodiment, the intelligent question-answering control includes intelligent question-answering identifiers and intelligent question-answering cards, and the first display unit includes:

[0041] The first display subunit is configured to display a main chat window in response to a first question-and-answer request initiated by the questioner. The main chat window includes a smart question-and-answer icon and / or a smart question-and-answer card.

[0042] In one embodiment, the second display unit includes:

[0043] The second display subunit is configured to perform an operation in response to a trigger on the intelligent question-and-answer identifier, displaying an auxiliary chat window; or,

[0044] The third display subunit is configured to display an auxiliary chat window in response to a trigger operation on the smart question-and-answer card.

[0045] In one embodiment, the device further includes:

[0046] The third display unit is configured to display the target question in the auxiliary chat window in response to an input operation on the target question.

[0047] The fourth display unit is configured to perform tasks based on the target question, using the artificial intelligence model to parse and extract the response content from the corpus corresponding to the question responder, and display the response content in the auxiliary chat window.

[0048] In one embodiment, the second display unit includes:

[0049] The fourth display subunit is configured to display an auxiliary chat window, which contains question and answer cards containing candidate questions;

[0050] The fifth display subunit is configured to perform a triggering operation on the target question among the candidate questions, displaying the target question in the auxiliary chat window.

[0051] In one embodiment, the auxiliary chat window includes input controls, and the second display unit includes:

[0052] The sixth display subunit is configured to perform an input tool for inputting a target question in response to a triggering operation on the input control;

[0053] The seventh display subunit is configured to perform an operation in response to inputting a target question through the input tool, displaying the target question in the auxiliary chat window.

[0054] In one embodiment, the device further includes:

[0055] The fifth display unit is configured to display the corpus management page, which includes content addition controls;

[0056] The sixth display unit is configured to perform a trigger operation in response to the content addition control, and display a content addition page, which includes content management options;

[0057] The update unit is configured to execute the classification and segmentation options in the content management options, obtain and upload target material information, and update the local corpus based on the target material information.

[0058] In one embodiment, the updating unit includes:

[0059] The eighth display subunit is configured to perform a trigger operation based on the category option in the content management options to display the file type and storage format of the target material information to be uploaded;

[0060] The ninth display subunit is configured to perform actions based on the file type and storage format to obtain the target material information, and to display the target material information in text segmentation format based on the triggering operation of the segmentation option in the content management options;

[0061] The tenth display subunit is configured to perform the material segmentation result of the target material information on the corpus display page based on the text segmentation form.

[0062] In one embodiment, the device further includes:

[0063] The storage unit is configured to perform a question-and-answer interaction in response to a local artificial intelligence model and a questioner, acquire the target question and the corresponding answer content during the interaction, construct each target question and the answer content into a question-and-answer corpus pair, and store it in the local corpus.

[0064] The seventh display unit is configured to display question-and-answer corpus pairs from previous question-and-answer sessions in the corpus configuration page.

[0065] In one embodiment, the corpus configuration page includes a configuration management control for corpus pairs, the configuration management control includes a labeling control, and the device further includes:

[0066] The eighth display unit is configured to perform a trigger operation in response to the annotation control of the target question-answer corpus pair in the question-answer corpus pair, and display the annotation configuration page for the target question-answer corpus pair;

[0067] The ninth display unit is configured to perform an annotation operation on the target question-and-answer corpus pair in response to the annotation configuration page, and display the annotated target question-and-answer corpus pair.

[0068] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0069] processor;

[0070] Memory used to store the processor's executable instructions;

[0071] The processor is configured to execute the instructions to implement the intelligent question-answering method described in the first aspect above.

[0072] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, which, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the intelligent question-answering method described in the first aspect.

[0073] According to a fifth aspect of the present disclosure, a computer program product is provided, the computer program product including instructions that, when executed by a processor of an electronic device, enable the electronic device to perform the intelligent question-answering method described in the first aspect.

[0074] The technical solutions provided by the embodiments of this disclosure bring at least the following beneficial effects:

[0075] By setting up intelligent Q&A controls in the main chat window, and then triggering the display of auxiliary chat windows through these controls, questioners can ask questions based on the main chat window and / or auxiliary chat windows. Artificial intelligence models assist question respondents in answering questions, increasing communication channels and improving response speed and efficiency.

[0076] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0077] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0078] Figure 1 This is a flowchart illustrating an intelligent question-answering method according to an exemplary embodiment.

[0079] Figure 2 This is a flowchart illustrating a step of displaying a main chat window according to an exemplary embodiment.

[0080] Figure 3 This is a flowchart illustrating a step of displaying an auxiliary chat window using different intelligent question-and-answer controls, according to an exemplary embodiment.

[0081] Figure 4 This is a schematic diagram of an interface for displaying a main chat window with intelligent question-and-answer identifiers, according to an exemplary embodiment.

[0082] Figure 5 This is a flowchart illustrating a question-and-answer interaction step in an auxiliary chat window according to an exemplary embodiment.

[0083] Figure 6 This is a flowchart illustrating a method for displaying a target question in an auxiliary chat window according to an exemplary embodiment.

[0084] Figure 7 This is a schematic diagram of an interface for displaying a main chat window with a first question and answer card, according to an exemplary embodiment.

[0085] Figure 8 This is a flowchart illustrating another method for displaying a target question in an auxiliary chat window using an input tool, according to an exemplary embodiment.

[0086] Figure 9 This is a flowchart illustrating a step of updating a local corpus based on target material information, according to an exemplary embodiment.

[0087] Figure 10 This is a schematic diagram of an interface for adding content to a page, according to an exemplary embodiment.

[0088] Figure 11 This is a flowchart illustrating a step of uploading and classifying target material information according to an exemplary embodiment.

[0089] Figure 12 This is a schematic diagram illustrating an interface for displaying a file upload management page with segmentation options, according to an exemplary embodiment.

[0090] Figure 13 This is a schematic diagram of the interface of a corpus display page according to an exemplary embodiment.

[0091] Figure 14 This is a flowchart illustrating a step of displaying a question-and-answer corpus of previous questions and answers, according to an exemplary embodiment.

[0092] Figure 15 This is a schematic diagram of an auxiliary chat window that includes annotation controls for question-and-answer dialogue, according to an exemplary embodiment.

[0093] Figure 16 This is a schematic diagram of an auxiliary chat window including a label input box, according to an exemplary embodiment.

[0094] Figure 17 This is a schematic diagram of an interface that allows for the inclusion of an auxiliary chat window with labeled icons in the lower part of the response content, according to an exemplary embodiment.

[0095] Figure 18 This is a schematic diagram of the interface of a corpus configuration page according to an exemplary embodiment.

[0096] Figure 19 This is a flowchart illustrating a step of similarity labeling for a question-and-answer dialogue according to an exemplary embodiment.

[0097] Figure 20 This is a schematic diagram of an interface including a label configuration page, according to an exemplary embodiment.

[0098] Figure 21 This is a block diagram illustrating an intelligent question-answering device according to an exemplary embodiment.

[0099] Figure 22 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0100] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0101] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0102] It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0103] Figure 1 This is a flowchart illustrating an intelligent question-answering method according to an exemplary embodiment, such as... Figure 1 As shown, the intelligent question-answering method used in the terminal includes the following steps.

[0104] In step S110, the main chat window is displayed.

[0105] The main chat window is the question-and-answer interaction window for the person answering the question, and it contains intelligent question-and-answer controls.

[0106] In implementation, during daily work, members of different departments and different members of the same department frequently need to exchange information and conduct business collaborations. When a user needs to exchange information or conduct business collaborations with a member of a specific department, the user triggers the main chat window of the target object (i.e., the person responding to the question) in the application or client integrated into the terminal for information exchange. This is used to conduct a question-and-answer dialogue with the target object (i.e., the person responding to the question). This main chat window also contains an intelligent question-and-answer control, which is used to trigger and display an auxiliary chat window. Through the auxiliary chat window where the AI ​​model corresponding to the person responding to the question resides, intelligent question-and-answer interaction can be conducted with the AI ​​model, assisting the person responding to the question in conducting information exchange and business collaborations.

[0107] In step S120, in response to the triggering operation of the smart question-and-answer control, an auxiliary chat window is displayed side by side with the main chat window.

[0108] The auxiliary chat window serves as the question-and-answer interaction window for the AI ​​model corresponding to the question responder. Both the main chat window and the auxiliary chat window are used to input the target question and initiate a question-and-answer dialogue.

[0109] In implementation, to facilitate information exchange and business collaboration among members, each member can pre-train their own proprietary AI model. This involves providing the AI ​​model with relevant corpus information and materials, allowing it to learn about the member's specific technical areas, business projects, and related expertise. This AI model then serves as an auxiliary tool for the member to interact with other members and facilitate business collaboration. When other members raise specific questions, in addition to the member's response, the pre-trained AI model can also answer related questions about their specific technical area and business projects.

[0110] Specifically, when the current user, acting as the questioner, needs to interact with the target (i.e., the question responder) for information exchange and / or business communication, the user can, in addition to directly interacting with the question responder in the main chat window, choose to trigger the intelligent Q&A control displayed in the main chat window. This triggers an auxiliary chat window, allowing the user to interact with the AI ​​model corresponding to the question responder in the auxiliary chat window. For example, if the question responder is busy and unable to reply immediately, the user can use the intelligent Q&A control in the main chat window to trigger the responder's AI model, thus displaying the auxiliary chat window and engaging in a Q&A dialogue with the responder's pre-trained AI model. Alternatively, even if the responder can reply promptly, the user can still choose to trigger the responder's AI model assistant through the intelligent Q&A control in the main chat window, triggering the auxiliary chat window and engaging in a Q&A dialogue with both the main chat window and the auxiliary chat window simultaneously.

[0111] Optionally, a main chat window and an auxiliary chat window can be displayed simultaneously on the terminal display interface. The current user can send the same or different questions to both the question responder and the question responder's pre-trained artificial intelligence model, conducting information interaction dialogues with the same or different content within the same time period. Alternatively, the user can ask questions only to the question responder or only to the artificial intelligence model, with different questions being conducted on different chat pages. This application embodiment does not limit the target of the current user's questions or the number of target users within the same time period.

[0112] In the above-mentioned intelligent question-and-answer method, an intelligent question-and-answer control is set in the main chat window, and then the auxiliary chat window is displayed through the intelligent question-and-answer control. This allows the questioner to ask questions based on the main chat window and / or the auxiliary chat window, increasing the channels for question-and-answer communication. The artificial intelligence model assists the question responder in answering questions, thereby improving the response speed and efficiency of question-and-answer.

[0113] In one exemplary embodiment, such as Figure 2 As shown, the main chat window contains a smart question-and-answer control, which can include various display formats. For example, the smart question-and-answer control includes smart question-and-answer icons and smart question-and-answer cards. In step S110, displaying the main chat window can be achieved through the following steps:

[0114] In step S211, in response to the first question-and-answer request initiated by the questioner, the main chat window is displayed.

[0115] The main chat window includes a smart question and answer icon and / or a smart question and answer card.

[0116] In implementation, when a user wants to initiate a question-and-answer dialogue with a target, the user acts as the questioner, and the target, acting as the question asker, answers the user's question. Therefore, the user initiates the first question-and-answer request, and the terminal responds by displaying the main chat window. This main chat window contains interactive controls for question-and-answer interaction, and also includes intelligent question-and-answer controls for opening an auxiliary chat window. These intelligent question-and-answer controls can be intelligent question-and-answer icons. For example, an intelligent question-and-answer icon might be displayed behind the question asker's icon in the main chat window, triggering the display of the auxiliary chat window. Alternatively, an intelligent question-and-answer card might be displayed in the content display area of ​​the main chat window, containing intelligent question-and-answer options that can also trigger the display of the auxiliary chat window. In this way, the user can trigger the display of the auxiliary chat window and initiate question-and-answer interaction through an artificial intelligence model using either an intelligent question-and-answer icon or an intelligent question-and-answer card.

[0117] In this embodiment, by adding an entry point for question-and-answer interaction of the artificial intelligence model, namely intelligent question-and-answer icon and intelligent question-and-answer card, to the main chat window, an auxiliary chat window is displayed by triggering the intelligent question-and-answer icon or intelligent question-and-answer card, and question-and-answer interaction is carried out in the auxiliary chat window, so as to increase the user's question-and-answer communication channels and thus improve the efficiency of question-and-answer.

[0118] In one exemplary embodiment, such as Figure 3As shown, since the main chat window contains an entry point for triggering the auxiliary chat window, this entry point can be represented in the form of a smart question-and-answer control. The smart question-and-answer control includes smart question-and-answer icons and smart question-and-answer cards, etc. In step S120, in response to the triggering operation of the smart question-and-answer control, the specific processing procedure for displaying the auxiliary chat window includes:

[0119] In step 301, in response to a triggering operation on the smart question-answering identifier, an auxiliary chat window is displayed. Alternatively,

[0120] In implementation, a main chat window is displayed on the terminal's screen. This main chat window displays the avatar of the person responding to the question, clearly identifying them. The main chat window also includes a smart question-and-answer indicator, such as... Figure 4 As shown, the intelligent question-and-answer icon is displayed as a tag behind the avatar icon of the person answering the question. Figure 4 The identifier 411 indicates that the intelligent question-and-answer identifier is one type of intelligent question-and-answer control. In this way, the questioner (the current user) can trigger the intelligent question-and-answer identifier. In response to the triggering operation of the intelligent question-and-answer identifier, the terminal displays an auxiliary chat window, which is a question-and-answer interaction window of the artificial intelligence model corresponding to the question responder.

[0121] Optionally, the terminal's display interface can simultaneously (or side-by-side) display the main chat window and the auxiliary chat window, or it can only display a single chat window. That is, when the user triggers the intelligent question-and-answer control in the main chat window, the terminal's display interface jumps from the main chat window to the auxiliary chat window. Regardless of whether the main chat window and the auxiliary chat window are displayed simultaneously, or the main chat window is displayed first and then the user jumps to the auxiliary chat window, the question-and-answer dialogue between the user and the question responder in the main chat window can be automatically copied and forwarded to the auxiliary chat window before the next dialogue is triggered. This helps the AI ​​model corresponding to the question responder to quickly understand the communication context between the questioner and the question responder.

[0122] In step 302, in response to the triggering operation of the smart question and answer card, an auxiliary chat window is displayed.

[0123] In implementation, a smart Q&A card can be pre-displayed on the main chat window's content display page. This smart Q&A card contains trigger options for displaying an auxiliary chat window. It can also contain guidance information to guide the user to conduct Q&A dialogue using the auxiliary chat window where the artificial intelligence model is located. Thus, if the current user triggers the trigger option in the smart Q&A card, the terminal responds to the trigger operation on the smart Q&A card and displays the auxiliary chat window.

[0124] In this embodiment, an intelligent question-and-answer control is added to the main chat window. By using different types of intelligent question-and-answer controls, users can enter the artificial intelligence model through different paths, which enriches the ways to start a question-and-answer dialogue with the artificial intelligence model corresponding to the question responder and improves the efficiency of asking questions.

[0125] In one exemplary embodiment, such as Figure 5 As shown, since the artificial intelligence model integrated into the auxiliary chat window can assist the questioner in the main chat window by providing answers or responses to the target question, the method is described using the questioner conducting a question-and-answer dialogue in the auxiliary chat window as an example. The method also includes:

[0126] In step S501, in response to the input operation of the target question, the target question is displayed in the auxiliary chat window.

[0127] In practice, in the auxiliary chat window, the user inputs the target question they want to ask through preset input controls (such as input boxes, input cards, candidate input options, etc.). The terminal responds to the trigger operation of the target question and displays the target question in the content display area of ​​the auxiliary chat window.

[0128] In step S502, based on the target question, the artificial intelligence model is used to parse and extract the response content from the corpus corresponding to the question responder, and the response content is displayed in the auxiliary chat window.

[0129] In implementation, an AI model corresponding to the respondent is pre-trained on the terminal where the respondent is located. The respondent also pre-builds a corpus corresponding to this AI model. Respondents upload relevant content information (e.g., project documents, management rules, technical manuals, guidelines, etc.) related to their target technical fields and business projects, storing this information in the corpus as response material for their AI model. There is no need to pre-build question-and-answer corpus pairs for the AI ​​model. When a user enters a target question, the AI ​​model on the terminal queries the corpus for the uploaded response material information based on that question, parses and extracts response content related to the target question, and then formats the extracted content to generate response content suitable for display in the chat window. After obtaining the response content, the terminal can display the response content corresponding to the target question below the target question displayed in the auxiliary chat window.

[0130] In this embodiment, in the auxiliary chat window, the terminal uses an artificial intelligence model to parse and extract the response content from the corpus, and achieves a rapid response to the target question, which significantly shortens the time for users to obtain the response content, thereby improving the user's question-and-answer efficiency.

[0131] In one exemplary embodiment, such as Figure 6 As shown, there are multiple ways for a user to input a target question in the auxiliary chat page. This embodiment of the disclosure provides one such method. In step S501, the specific processing procedure for displaying the target question in the auxiliary chat window in response to the input operation of the target question includes:

[0132] In step S601, an auxiliary chat window is displayed.

[0133] In implementation, a question-and-answer card is displayed in the auxiliary chat window, containing various candidate questions, such as... Figure 7 As shown, the first question and answer card is displayed in the content display area of ​​the auxiliary chat window. Figure 7 The first question-and-answer card, indicated by 711, contains various types of candidate questions and question options. Each question option also corresponds to a different type of candidate question. These candidate questions can be extracted and summarized by an artificial intelligence model based on pre-uploaded materials from the respondent, or they can be historical or frequently asked questions recorded during the question-and-answer process. This guides users to quickly identify their target question based on these candidate questions, thus enabling rapid querying of the target question.

[0134] In step S602, in response to the triggering operation of the target question among the candidate questions, the target question is displayed in the auxiliary chat window.

[0135] In practice, when a user selects a target question from an information card by clicking or dragging, the terminal responds to the triggering operation of the target question in the information card by displaying the target question in the content display area of ​​the auxiliary chat window, thus realizing one method of target question input.

[0136] Optionally, the auxiliary chat window of the artificial intelligence model provided in this disclosure supports multi-round information interaction between the user and the artificial intelligence model. Specifically, when a single question and answer session cannot resolve the user's problem, the terminal can analyze and make decisions based on the current question and answer context of the auxiliary chat window, and provide a new round of question cards. These question cards contain a new round of candidate questions. The user can further filter out the target question based on the candidate questions in the new round of question and answer cards, input it into the auxiliary chat window, and conduct a new round of question and answer dialogue until the user obtains all the information they need based on the question and answer dialogue, at which point the information interaction stops.

[0137] In this embodiment, by displaying question and answer cards in the auxiliary chat window, users are provided with candidate questions to ask. Users can quickly find the target question from the candidate questions without manual input, shortening the question input time and enabling quick questioning. Furthermore, with the help of the candidate questions in the question cards, the system supports multi-round interaction for complex inquiry business, gradually guiding users to obtain complete answers and improving question and answer efficiency.

[0138] In one exemplary embodiment, such as Figure 8 As shown, there are multiple ways for users to input the target question in the auxiliary chat page. This embodiment of the disclosure provides another way to input the target question, namely, the auxiliary chat window contains input controls. Then, the specific processing procedure in step 501, which responds to the input operation of the target question, to display the target question in the auxiliary chat window includes:

[0139] In step S801, in response to a triggering operation on the input control, an input tool for inputting the target question is displayed.

[0140] In implementation, the terminal pre-includes an input control for entering the target question. By triggering this input control, the user can display an input tool in an auxiliary chat window to enter the target question, thus enabling them to input the question. Specifically, this input control can be a type of input box. For example... Figure 7 As shown, taking a soft keyboard as the input tool as an example, an input box (input control) for entering the target question is displayed in the lower display area of ​​the auxiliary chat window. When the user triggers this input box, the terminal responds to the trigger operation on the output box by displaying the soft keyboard (input tool) for entering the target question in the auxiliary chat window, allowing the user to input the target question through the soft keyboard.

[0141] Optionally, in addition to a soft keyboard as an input tool, the input tool may also include a voice input tool, a scanning input tool, a touchpad input, etc. The embodiments of this disclosure do not limit the types and number of input tools included in the input control.

[0142] In step S802, in response to the operation of inputting the target question through the input tool, the target question is displayed in the auxiliary chat window.

[0143] In implementation, users input the target question using an input tool. For example, after inputting the target question on the soft keyboard, users can send the target question to the content display area of ​​the auxiliary chat window by triggering the send option on the soft keyboard. In this way, the terminal responds to the user's input of the target question using the input tool and displays the target question in the auxiliary chat window.

[0144] In this embodiment, by triggering the input control to display the input tool, the user can input the target question based on the input tool. The auxiliary chat window provides real-time feedback based on the input of the target question, which enhances the user's sense of control and participation, and improves the efficiency of question-and-answer interaction.

[0145] In one exemplary embodiment, each member of the enterprise has a dedicated AI model. Each member provides their AI model with technical content, expertise, and other relevant knowledge related to their specific technical fields and business projects, thereby constructing their own corpus and a domain-specific intelligent question-answering AI model. Thus, when a member asks a question, they can ask questions to the AI ​​models of other members; and when a member answers a question, their corresponding AI model can provide response services to other users, such as... Figure 9 As shown, this method is described with the current user as the responder. It also includes:

[0146] In step S901, the corpus management page is displayed.

[0147] The corpus management page includes a content addition control.

[0148] In implementation, an information interaction platform is integrated into the user's current terminal. This platform pre-builds a corpus corresponding to the local (user's current terminal device) artificial intelligence model. A corpus management page is displayed on the terminal's screen corresponding to this corpus. Figure 10 As shown, the corpus management page displays the corpus content of each partition according to a preset partitioning rule, when corpus is stored. Furthermore, the corpus management page also includes content addition controls, such as... Figure 10 The "Add Control" option displayed in the upper right corner, denoted by 1110, triggers the addition of corpus content by adding a control through this option.

[0149] In step S902, in response to the triggering operation of the content addition control, the content addition page is displayed.

[0150] The content addition page includes content management options.

[0151] In practice, when users initially build the corpus or update it daily, they can trigger the content addition control on the corpus management page. The terminal responds to the user's triggering operation of the content addition control and displays the content addition page.

[0152] Optionally, the content addition page can be a pop-up page or drawer page displayed above the corpus management page, or it can be a separate content addition page that requires navigation from the corpus management page. For example... Figure 10 As shown, above the corpus management page, a content addition page is displayed in the form of a pop-up window. This content addition page contains content management options for uploading material information. These content management options include category options for uploading files by category, as well as segmentation options for storing files in segments.

[0153] Step S903: Based on the category and segmentation options in the content management options, obtain and upload the target material information, and update the local corpus based on the target material information.

[0154] In implementation, the content management options include categorization and segmentation options. When a user uploads target material information, they can use the categorization option to filter candidate files based on target file type and storage format from the preset storage space. Then, the terminal selects the target file to be uploaded from the candidate files, obtains and uploads that file as the target material information. Next, the terminal uses the segmentation option to segment the selected target material information, storing the segmented target material areas in the target storage area of ​​the local corpus, thereby updating the local corpus.

[0155] In this embodiment, by displaying a corpus management page and providing content addition controls, users can efficiently manage corpus content. The categorization and segmentation options on the content addition page can structure target material information according to needs, ensuring the organization and searchability of the corpus content. Furthermore, the real-time updating of the local corpus by the terminal ensures the timeliness and completeness of the corpus content.

[0156] In one exemplary embodiment, such as Figure 11 As shown, the specific process of obtaining and uploading target material information based on the category and segmentation options in the content management options in step S903 includes:

[0157] In step S1101, based on the trigger operation of the category option in the content management options, the file type and storage format of the target material information to be uploaded are displayed.

[0158] In implementation, the terminal displays the file type and storage format of the target material to be uploaded based on the triggered operation of the category option in the content management options. For example... Figure 12As shown, the content addition page includes two category options: document type and table type. Different category options correspond to different file types. Each file type is further divided into different file storage formats. For example, the file storage formats for document type include: local file, Docs online document, and Docs knowledge base; the file storage formats for table type include: local file and Docs online table. In this way, the content addition page divides files of different types and storage formats into different upload paths. When uploading target material information, users can select a target category option in the category options. Based on the file type and storage format corresponding to that target category option, users can select the target material information in the candidate files for upload. That is, the file type and storage format of the target material information to be uploaded can be pre-displayed on the terminal display interface.

[0159] In step S1102, target material information is obtained based on file type and storage format, and the text segmentation format of the target material information is displayed based on the trigger operation of the segmentation option in the content management options.

[0160] In implementation, after clarifying the file type and storage format of the target material information to be uploaded, the upload path is determined based on this file type and storage format. The terminal then retrieves the target material information from the storage area corresponding to this upload path. Thus, after uploading the target material information, the content management options are updated to display segmented options for selecting the segmented format of the target material information. For example... Figure 12 As shown, the file upload progress is displayed at the top of the file upload management page. Below the upload progress, different segmentation options are shown. These options include: an automatic segmentation option (automatically segmented according to default rules) and a custom segmentation option. Each segmentation option corresponds to a different text segmentation method. Users can select a specific text segmentation method for the target material information based on its text characteristics (i.e., select the target segmentation option), thus displaying the target material information in segmented form.

[0161] In step S1103, based on the text segmentation format, the material segmentation results of the target material information are displayed on the corpus display page.

[0162] In implementation, the terminal segments the uploaded target material information based on the text segmentation format corresponding to the selected target segmentation option, obtaining the material segmentation result for the target material information. Then, the terminal displays the material segmentation result for the target material information on the corpus display page. For example... Figure 13As shown, on the corpus display page, the target material information is divided into 12 segments according to the selected text segmentation method, and different segments are stored in different partitions of the corpus.

[0163] In this embodiment, by triggering the classification option in the content management options, the file type and storage format of the target material information to be uploaded are clearly displayed. By triggering the segmentation option, users can intuitively view and manage the structured division of the material content. Finally, based on the selected text type, storage format and segmentation method, the material division results of the target material information are displayed on the corpus display page, ensuring the organization and searchability of the corpus content.

[0164] In one exemplary embodiment, such as Figure 14 As shown, the method also includes:

[0165] In step S1401, in response to the question-and-answer interaction between the local artificial intelligence model and the questioner, the target question and the corresponding answer content are obtained during the interaction process. Each target question and answer content is constructed into a question-and-answer corpus pair and stored in the local corpus.

[0166] In implementation, the current user's terminal has a local artificial intelligence (AI) model. When this AI model assists the current user in engaging in question-and-answer dialogues with other users, the terminal can record and store these dialogues. Specifically, when the local AI model interacts with the questioner, the terminal responds by acquiring the target question and its corresponding answer. Then, the terminal constructs each target question and its corresponding answer into a question-and-answer corpus pair and stores this corpus pair in its local database.

[0167] Or, as Figure 15 As shown, the auxiliary chat window displays various question-and-answer dialogues generated when the AI ​​model interacts with the questioner. Within each dialogue, the response below the target question includes a control for annotating that dialogue. The current user can trigger this annotation control to add annotations to the response. For example... Figure 16As shown, when a user triggers the annotation control, the terminal responds to the user's triggering operation by displaying an annotation input box. Below the annotation input box are cancel and confirm options for modifying and confirming the content within the input box. Thus, after the current user enters annotation content for the response in the annotation input box, they can confirm the entered annotation content using the confirm option below the input box, thereby completing the annotation of the response content. The annotation content entered by the current user can be a supplement or correction to the response content provided by the artificial intelligence model; this embodiment does not limit the annotation content entered by the current user.

[0168] Therefore, for question-and-answer dialogues with added annotations, the terminal automatically constructs question-and-answer pairs and stores them in the local corpus as a supplement to the material information of the responses in the local corpus. Optionally, to avoid duplicate data storage, before storing the annotated question-and-answer pairs in the local corpus, a query is performed in the local corpus based on the target question in the question-and-answer pairs. If the target question of that type or a related type does not exist in the local corpus, then the question-and-answer pair is stored.

[0169] In the content display area of ​​the auxiliary chat window, the responses in the question-and-answer dialogue are marked, such as... Figure 17 As shown, the answer content is marked with an "Annotated" tag, while the actual annotation content is hidden to save display space in the auxiliary chat window. When a user asks a question about the target question in the Q&A dialogue, since the annotated Q&A dialogue has been constructed as a question-and-answer corpus and stored in the local corpus, this corpus can be used as the basis for the answer content. The annotated answer content is displayed in the content display area of ​​the auxiliary chat window, and it also carries an "Annotated" tag. The user asking the question can view the hidden annotation content through the "Annotated" tag.

[0170] Each question-and-answer corpus can be further divided according to the questioner asking the same question, or according to the time when the question-and-answer corpus was generated. This embodiment of the disclosure does not limit the classification and storage rules for each question-and-answer corpus. In this way, the question-and-answer corpus obtained through each question-and-answer process enriches the response content resources of the local corpus.

[0171] Optionally, the question-and-answer pairs stored in the local corpus can also be used as the basis for the AI ​​model to generate responses, supporting responses to new target questions. Specifically, when other users, as question askrs, send a target question to the local AI model corresponding to the current user (question responder), the local AI model calculates the similarity between the target question and the questions in each question-and-answer pair, determining whether the current target question belongs to the same question as the questions in each question-and-answer pair. When a question in a certain question-and-answer pair is similar to the current target question, the model can quickly reply to the current target question in the auxiliary chat window based on the response content in that question-and-answer pair.

[0172] In step S1402, the question-and-answer corpus pairs of each question and answer session are displayed on the corpus pair configuration page.

[0173] In implementation, the question-and-answer pairs generated during each question-and-answer process are not only stored in a local corpus, but the terminal can also configure these pairs. Specifically, the corpus configuration page displays all question-and-answer pairs generated by the interactions between the questioner and the AI ​​model within a preset time period. Optionally, the question-and-answer corpus objects can be displayed in list or table format on the corpus configuration page.

[0174] like Figure 18 As shown, Figure 18 This is a configuration page for a corpus. In the terminal's display interface, each question-and-answer corpus is arranged and displayed in a list format according to its generation time. Each question-and-answer corpus is presented as an item in the list, facilitating querying and searching of the corpus pairs.

[0175] In this embodiment, by automatically extracting the target question and its corresponding answer, and constructing them into structured question-and-answer pairs, which are then stored in a local corpus, the workload of manually organizing the corpus pairs is reduced, while ensuring the real-time updating and expansion of the corpus. Furthermore, the local corpus can continuously accumulate high-quality question-and-answer pairs, providing rich corpus support for the iterative training of the artificial intelligence model, thereby improving the accuracy and generalization ability of the AI ​​model.

[0176] In one exemplary embodiment, such as Figure 19 As shown, in addition to configuring annotations for the responses in the question-and-answer corpus pairs within the auxiliary chat window, configuration management for each question-and-answer corpus pair can also be performed on a dedicated corpus pair configuration page. This corpus pair configuration page includes a configuration management control for the corpus pairs, which contains annotation controls. The method also includes:

[0177] In step S1901, in response to the triggering operation of the annotation control of the target question-answer corpus pair in the question-answer corpus pair, the annotation configuration page for the target question-answer corpus pair is displayed.

[0178] In implementation, Figure 18 The question-and-answer corpora on the configuration page are arranged in a list format. Each question-and-answer corpus entry has a corresponding annotation control, including edit and delete controls. Furthermore, each question-and-answer corpus entry can also contain attribute information such as creation time, hit count, and associated tags. Therefore, when a user wants to annotate a specific question-and-answer corpus (the target corpus), they can trigger the annotation control for that corpus. The terminal then responds to this trigger by displaying the annotation configuration page for that target corpus. Figure 20 As shown, the annotation configuration page can be a pop-up page displayed on top of the corpus configuration page. This annotation configuration page can include a similarity editor for setting the question matching similarity. The similarity editor includes a movable slider, which is used to determine the similarity between the target questions in the question-answer corpus and the target questions in the local corpus by the user sliding the slider on the similarity editor, so as to confirm whether different expressions belong to the same question.

[0179] In step S1902, in response to the annotation operation on the target question-answer corpus pair on the annotation configuration page, the annotated target question-answer corpus pair is displayed.

[0180] In practice, after the current user performs annotation operations on the target question-and-answer corpus pair through the similarity editor in the annotation configuration page, the terminal responds to the annotation operation on the target question-and-answer corpus pair by displaying the annotated target question-and-answer corpus pair in the corpus pair configuration page.

[0181] In this embodiment, by triggering the annotation control of the target question-and-answer corpus pair, the annotation configuration page is displayed, enabling users to perform fine-grained annotation operations on the target question-and-answer corpus pair. After the annotation operation is completed, the annotated target question-and-answer corpus pair is displayed, facilitating the verification of the accuracy of the annotation results. This improves the overall performance and scalability of the information interaction platform on which the terminal resides.

[0182] It should be understood that, although Figures 1-3 , Figure 5 , Figure 6 , Figure 8 , Figure 9 , Figure 11 , Figure 14 , Figure 19The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figures 1-3 , Figure 5 , Figure 6 , Figure 8 , Figure 9 , Figure 11 , Figure 14 , Figure 19 At least some of the steps in the process may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0183] It is understood that the same / similar parts between the various embodiments of the methods described above in this specification can be referred to each other. Each embodiment focuses on the differences from other embodiments, and relevant parts can be referred to the description of other method embodiments.

[0184] Figure 21 This is a block diagram illustrating an intelligent question-answering device according to an exemplary embodiment. (Refer to...) Figure 21 The device 2100 includes:

[0185] The first display unit 2101 is configured to display the main chat window, which is a question-and-answer interaction window with the question responder and contains intelligent question-and-answer controls.

[0186] The second display unit 2102 is configured to display an auxiliary chat window in response to a trigger operation on the intelligent question-and-answer control; the auxiliary chat window is a question-and-answer interaction window of the artificial intelligence model corresponding to the question responder; the main chat window and the auxiliary chat window are used to input the target question and conduct a question-and-answer dialogue.

[0187] In one embodiment, the intelligent question-answering control includes intelligent question-answering identifiers and intelligent question-answering cards, and the first display unit 2101 includes:

[0188] The first display subunit is configured to respond to a first question-and-answer request initiated by the questioner by displaying a main chat window, which contains a smart question-and-answer icon and / or a smart question-and-answer card.

[0189] In one embodiment, the second display unit 2102 includes:

[0190] The second display subunit is configured to perform an operation in response to a smart question-and-answer flag, displaying an auxiliary chat window; or,

[0191] The third display subunit is configured to display an auxiliary chat window in response to a triggering action on a smart question-and-answer card.

[0192] In one embodiment, the device 2100 further includes:

[0193] The third display unit is configured to display the target question in an auxiliary chat window in response to input to the target question.

[0194] The fourth display unit is configured to perform tasks based on the target question, using an artificial intelligence model to parse and extract the response content from the corpus corresponding to the question responder, and then display the response content in the auxiliary chat window.

[0195] In one embodiment, the second display unit 2102 includes:

[0196] The fourth display subunit is configured to display an auxiliary chat window containing question and answer cards, which in turn contain candidate questions.

[0197] The fifth display subunit is configured to perform a triggering action on the target question among the candidate questions, displaying the target question in the auxiliary chat window.

[0198] In one embodiment, the auxiliary chat window includes input controls, and the second display unit 2102 includes:

[0199] The sixth display subunit is configured to perform an input tool for entering the target question in response to a triggering operation on the input control;

[0200] The seventh display subunit is configured to perform an operation in response to the input of the target question via the input tool, displaying the target question in the auxiliary chat window.

[0201] In one embodiment, the device 2100 further includes:

[0202] The fifth display unit is configured to display the corpus management page, which contains content addition controls;

[0203] The sixth display unit is configured to perform a response to a triggering operation on the content addition control, displaying a content addition page containing content management options;

[0204] The update unit is configured to execute the category and segmentation options in the content management options, obtain and upload target material information, and update the local corpus based on the target material information.

[0205] In one embodiment, the updating unit includes:

[0206] The eighth display sub-unit is configured to perform a trigger operation based on the category option in the content management options, and display the file type and storage format of the target material information to be uploaded;

[0207] The ninth display subunit is configured to retrieve target material information based on file type and storage format, and display the target material information in text segmentation format based on the trigger operation of the segmentation option in the content management options;

[0208] The tenth display subunit is configured to perform text segmentation based on text segments and display the target material information as a result on the corpus display page.

[0209] In one embodiment, the device 2100 further includes:

[0210] The storage unit is configured to perform a question-and-answer interaction between the local artificial intelligence model and the questioner, acquire the target question and the corresponding answer content during the interaction, construct each target question and answer content into a question-and-answer corpus pair, and store it in the local corpus.

[0211] The seventh display unit is configured to display question-and-answer corpus pairs from previous question-and-answer sessions in the corpus configuration page.

[0212] In one embodiment, the corpus configuration page includes a configuration management control for corpus pairs, and the configuration management control includes annotation controls. The device 2100 also includes:

[0213] The eighth display unit is configured to perform a trigger operation in response to the annotation control of the target question-answer corpus pair in the question-answer corpus pair, and display the annotation configuration page for the target question-answer corpus pair;

[0214] The ninth display unit is configured to perform the annotation operation on the target question-answer corpus pair in response to the annotation operation on the annotation configuration page, and display the annotated target question-answer corpus pair.

[0215] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0216] Figure 22 This is a block diagram illustrating an electronic device 2200 for applying an intelligent question-answering method according to an exemplary embodiment. For example, the electronic device 2200 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0217] Reference Figure 22 The electronic device 2200 may include one or more of the following components: processing component 2202, memory 2204, power supply component 2206, multimedia component 2208, audio component 2210, input / output (I / O) interface 2212, sensor component 2214, and communication component 2216.

[0218] Processing component 2202 typically controls the overall operation of electronic device 2200, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 2202 may include one or more processors 2220 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 2202 may include one or more modules to facilitate interaction between processing component 2202 and other components. For example, processing component 2202 may include a multimedia module to facilitate interaction between multimedia component 2208 and processing component 2202.

[0219] Memory 2204 is configured to store various types of data to support the operation of electronic device 2200. Examples of such data include instructions for any application or method operating on electronic device 2200, contact data, phonebook data, messages, pictures, videos, etc. Memory 2204 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, optical disk, or graphene storage.

[0220] Power supply component 2206 provides power to various components of electronic device 2200. Power supply component 2206 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 2200.

[0221] Multimedia component 2208 includes a screen that provides an output interface between electronic device 2200 and user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 2208 includes a front-facing camera and / or a rear-facing camera. When electronic device 2200 is in an operating mode, such as a shooting mode or video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0222] Audio component 2210 is configured to output and / or input audio signals. For example, audio component 2210 includes a microphone (MIC) configured to receive external audio signals when electronic device 2200 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 2204 or transmitted via communication component 2216. In some embodiments, audio component 2210 also includes a speaker for outputting audio signals.

[0223] I / O interface 2212 provides an interface between processing component 2202 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0224] Sensor assembly 2214 includes one or more sensors for providing state assessments of various aspects of electronic device 2200. For example, sensor assembly 2214 can detect the on / off state of electronic device 2200, the relative positioning of components such as the display and keypad of electronic device 2200, changes in position of electronic device 2200 or its components, the presence or absence of user contact with electronic device 2200, orientation or acceleration / deceleration of device 2200, and temperature changes of electronic device 2200. Sensor assembly 2214 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 2214 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 2214 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0225] Communication component 2216 is configured to facilitate wired or wireless communication between electronic device 2200 and other devices. Electronic device 2200 can access wireless networks based on communication standards, such as WiFi, carrier networks (such as 2G, 3G, 4G, or 5G), or combinations thereof. In one exemplary embodiment, communication component 2216 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 2216 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0226] In an exemplary embodiment, the electronic device 2200 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0227] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 2204 including instructions, which can be executed by a processor 2220 of an electronic device 2200 to perform the above-described method. For example, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0228] In an exemplary embodiment, a computer program product is also provided, which includes instructions that can be executed by the processor 2220 of the electronic device 2200 to perform the above-described method.

[0229] It should be noted that the above-mentioned apparatus, electronic equipment, computer-readable storage medium, computer program product, etc., may also include other implementation methods according to the description of the method embodiments. For specific implementation methods, please refer to the description of the relevant method embodiments, which will not be elaborated here.

[0230] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0231] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. An intelligent question-answering method, characterized in that, The method includes: In response to the first question-and-answer request, the main chat window is displayed. The main chat window is a question-and-answer interaction window with the question responder, and the main chat window contains intelligent question-and-answer controls. In response to the triggering operation of the intelligent question-and-answer control, an auxiliary chat window is displayed side by side with the main chat window; the question-and-answer dialogue between the question responder and the main chat window is automatically copied and forwarded to the auxiliary chat window before the next triggering of the dialogue in the auxiliary chat window; the auxiliary chat window is a question-and-answer interaction window of the artificial intelligence model corresponding to the question responder; the main chat window and the auxiliary chat window are used to input the target question and conduct a question-and-answer dialogue; The method further includes: The terminal display page simultaneously displays the main chat window and the auxiliary chat window. When the same or different questions are sent to the question responder and the corresponding artificial intelligence model, information interaction dialogue with the same or different content is carried out at the same time. The method further includes: Display the corpus management page, which includes content addition controls; In response to a triggering operation on the content addition control, a content addition page is displayed, which includes content management options; Based on the category and segmentation options in the content management options, the target material information is obtained and uploaded, and the local corpus is updated based on the target material information.

2. The intelligent question-answering method according to claim 1, characterized in that, The intelligent question-and-answer control includes an intelligent question-and-answer icon and an intelligent question-and-answer card. The step of displaying the main chat window in response to a first question-and-answer request includes: In response to the first question-and-answer request initiated by the questioner, a main chat window is displayed, which includes a smart question-and-answer icon and / or a smart question-and-answer card.

3. The intelligent question-answering method according to claim 2, characterized in that, The step of displaying an auxiliary chat window alongside the main chat window in response to a trigger operation on the intelligent question-and-answer control includes: In response to a trigger operation on the intelligent question-and-answer icon, an auxiliary chat window is displayed alongside the main chat window; or, In response to the triggering operation of the smart question and answer card, an auxiliary chat window is displayed side by side with the main chat window.

4. The intelligent question-answering method according to claim 1, characterized in that, The method further includes: In response to an input operation on the target question, the target question is displayed in the auxiliary chat window; Based on the target question, the artificial intelligence model parses and extracts the response content from the corpus corresponding to the question responder, and displays the response content in the auxiliary chat window.

5. The intelligent question-answering method according to claim 4, characterized in that, The step of displaying the target question in the auxiliary chat window in response to an input operation on the target question includes: Display an auxiliary chat window, which contains question and answer cards, and the question and answer cards contain candidate questions; In response to a triggering action on the target question among the candidate questions, the target question is displayed in the auxiliary chat window.

6. The intelligent question-answering method according to claim 4, characterized in that, The auxiliary chat window includes input controls, and the step of displaying the target question in the auxiliary chat window in response to an input operation on the target question includes: In response to a triggering operation on the input control, an input tool for entering the target question is displayed; In response to the input of a target question through the input tool, the target question is displayed in the auxiliary chat window.

7. The intelligent question-answering method according to claim 1, characterized in that, The process of obtaining and uploading target material information based on the category and segmentation options in the content management options includes: Based on the trigger operation of the category option in the content management options, the file type and storage format of the target material information to be uploaded are displayed; Based on the file type and storage format, the target material information is obtained, and based on the triggering operation of the segmentation option in the content management options, the text segmentation format of the target material information is displayed; Based on the aforementioned text segmentation format, the material segmentation results of the target material information are displayed on the corpus display page.

8. The intelligent question-answering method according to claim 1, characterized in that, The method further includes: In response to the question-and-answer interaction between the local artificial intelligence model and the questioner, the target question and the corresponding answer content are obtained during the interaction process. Each target question and the answer content are constructed into a question-and-answer corpus pair and stored in the local corpus. The question-and-answer corpus pairs from each question-and-answer session are displayed on the corpus configuration page.

9. The intelligent question-answering method according to claim 8, characterized in that, The corpus configuration page includes a configuration management control for corpus pairs, and the configuration management control includes a labeling control. The method further includes: In response to the triggering operation of the annotation control of the target question-answer corpus pair in the question-answer corpus pair, the annotation configuration page for the target question-answer corpus pair is displayed; In response to the annotation operation on the target question-and-answer corpus pair on the annotation configuration page, the annotated target question-and-answer corpus pair is displayed.

10. An intelligent question-and-answer device, characterized in that, The device includes: The first display unit is configured to respond to the first question-and-answer request by displaying a main chat window, which is a question-and-answer interaction window with the question responder, and the main chat window includes intelligent question-and-answer controls; The second display unit is configured to perform a response to a trigger operation on the intelligent question-and-answer control, and to display an auxiliary chat window alongside the main chat window; the question-and-answer dialogue between the respondent and the questioner in the main chat window is automatically copied and forwarded to the auxiliary chat window before the next trigger of the dialogue in the auxiliary chat window; the auxiliary chat window is a question-and-answer interaction window of the artificial intelligence model corresponding to the respondent; the main chat window and the auxiliary chat window are used to input target questions and conduct question-and-answer dialogues; The device further includes: The third display unit is configured to simultaneously display the main chat window and the auxiliary chat window on the terminal display page. When the same or different questions are sent to the question responder and the artificial intelligence model corresponding to the question responder, the same or different information interaction dialogues with the same or different content are carried out at the same time. The device further includes: The fifth display unit is configured to display the corpus management page, which includes content addition controls; The sixth display unit is configured to perform a trigger operation in response to the content addition control, and display a content addition page, which includes content management options; The update unit is configured to execute the classification and segmentation options in the content management options, obtain and upload target material information, and update the local corpus based on the target material information.

11. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the intelligent question-answering method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is enabled to perform the intelligent question-answering method as described in any one of claims 1 to 9.

Images