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

Abstract

The invention relates to an intelligent question and answer method and device, electronic equipment and a storage medium. The method comprises the steps that a main chat window is displayed, the main chat window is a question and answer interaction window with a question reply party, and the main chat window comprises an intelligent question and answer control. And displaying an auxiliary chat window in response to a trigger operation on the intelligent question and answer control. Wherein the auxiliary chat window is a question and answer interaction window of an artificial intelligence model corresponding to the question reply party; the main chat window and the auxiliary chat window are used for inputting target questions to carry out question-answer dialogues. By adopting the method, the question and answer interaction efficiency is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and particularly to an intelligent question and answer method, device, electronic device, and storage medium. Background Art

[0002] With the increasing complexity of enterprise organizational structures and the diversification of business requirements, cross-departmental collaboration has become a normal working mode in modern enterprise operations. During the process of project promotion, it is often necessary to integrate the professional resources and manpower of multiple departments and achieve the established goals through the close cooperation between teams.

[0003] In traditional technologies, when carrying out cross-departmental projects, information interaction and business docking need to be frequently carried out among members of each department. Specifically, when a certain department encounters problems in the professional field or business process during the project execution, it needs to initiate a consultation request to the professional personnel of the relevant department; at the same time, the requested party also needs to provide professional answers and business guidance in a timely manner 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 costs of employees on both sides of the question and answer, but also, due to the unequal free time among employees, the question and answer efficiency is often restricted by various factors such as communication channels and response speeds. Furthermore, the efficiency of the question and answer process is relatively low. Summary of the Invention

[0005] The present disclosure provides an intelligent question and answer method, device, electronic device, and storage medium to at least solve the problem that in the related technologies, the free time among employees is unequal, the question and answer efficiency is often restricted by various factors such as communication channels and response speeds, and the efficiency of the question and answer process is relatively low. The technical solution of the present disclosure is as follows:

[0006] According to the first aspect of the embodiments of the present disclosure, an intelligent question and answer method is provided. The method includes:

[0007] Display a main chat window, where the main chat window is a question and answer interaction window with the question responder, and the main chat window includes an intelligent question and answer control;

[0008] In response to a trigger operation on the intelligent question and answer control, display an auxiliary chat window; the auxiliary chat window is a question and answer interaction window with the artificial intelligence model corresponding to the question responder; the main chat window and the auxiliary chat window are used to input a target question to carry out a question and answer conversation.

[0009] In one of the embodiments, the intelligent question and answer control includes an intelligent question and answer identifier and an intelligent question and answer card. The displaying of the main chat window includes:

[0010] In response to a first question-and-answer request initiated by a question asker for a problem, display a main chat window, where the main chat window includes an intelligent question-and-answer identifier and / or an intelligent question-and-answer card.

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

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

[0013] In response to a triggering operation on the intelligent question-and-answer card, display an auxiliary chat window.

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

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

[0016] Based on the target question, parse and extract a reply content from the corpus corresponding to the question replier through the artificial intelligence model, and display the reply content in the auxiliary chat window.

[0017] In one embodiment, the displaying of 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, where the auxiliary chat window includes a question-and-answer card, and the question-and-answer card includes candidate questions;

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

[0020] In one embodiment, the auxiliary chat window includes an input control, and the displaying of 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, display an input tool for inputting a target question;

[0022] In response to an operation of inputting a target question through the input tool, display the target question in the auxiliary chat window.

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

[0024] Display a corpus management page, where the corpus management page includes a content addition control;

[0025] In response to a trigger operation for adding a control to the content, a content addition page is displayed, and the content addition page includes content management options;

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

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

[0028] Based on a trigger operation for the classification option in the content management options, the file type and storage form of the target material information to be uploaded are displayed;

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

[0030] Based on the text segmentation form, the material division result of the target material information is 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 question asker, the target question in the interaction process and the corresponding answer content of the target question are obtained, and 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 of previous questions and answers are displayed on the corpus pair configuration page.

[0034] In one embodiment, the corpus pair configuration page includes a configuration management control for the corpus pair, and the configuration management control includes a marking control. The method further includes:

[0035] In response to a trigger operation for the marking control of the target question-and-answer corpus pair in the question-and-answer corpus pairs, a marking configuration page for the target question-and-answer corpus pair is displayed;

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

[0037] According to a second aspect of the embodiments of the present disclosure, an intelligent question-and-answer device is provided, including:

[0038] A first display unit, configured to execute the display of a main chat window, where the main chat window is a question-and-answer interaction window with a question responder, and the main chat window includes an intelligent question-and-answer control.

[0039] A second display unit, configured to execute the display of 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 with an artificial intelligence model corresponding to the question responder; the main chat window and the auxiliary chat window are used to input a target question to conduct a question-and-answer conversation.

[0040] In one embodiment, the intelligent question-and-answer control includes an intelligent question-and-answer identifier and an intelligent question-and-answer card, and the first display unit includes:

[0041] A first display subunit, configured to execute the display of a main chat window in response to a first question-and-answer request initiated by a question asker, where the main chat window includes an intelligent question-and-answer identifier and / or an intelligent question-and-answer card.

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

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

[0044] A third display subunit, configured to execute the display of an auxiliary chat window in response to a trigger operation on the intelligent question-and-answer card.

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

[0046] A third display unit, configured to execute the display of the target question in the auxiliary chat window in response to an input operation on the target question;

[0047] A fourth display unit, configured to execute the parsing and extraction of a reply content from a corpus corresponding to the question responder through the artificial intelligence model based on the target question, and display the reply content in the auxiliary chat window.

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

[0049] A fourth display subunit, configured to execute the display of an auxiliary chat window, where the auxiliary chat window includes a question-and-answer card, and the question-and-answer card includes candidate questions;

[0050] A fifth display subunit, configured to execute the display of the target question in the auxiliary chat window in response to a trigger operation on the target question in the candidate questions.

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

[0052] A sixth display subunit, configured to execute a trigger operation in response to the input control, and display an input tool for inputting a target question;

[0053] A seventh display subunit, configured to execute an operation of inputting a target question through the input tool, and display the target question in the auxiliary chat window.

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

[0055] A fifth display unit, configured to execute a display corpus management page, and the corpus management page includes a content addition control;

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

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

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

[0059] An eighth display subunit, configured to execute a trigger operation based on the classification option in the content management option, and display the file type and storage form of the target material information to be uploaded;

[0060] A ninth display subunit, configured to execute based on the file type and the storage form, obtain the target material information, and display the text segmentation form of the target material information based on a trigger operation on the segmentation option in the content management option;

[0061] A tenth display subunit, configured to execute based on the text segmentation form, and display the material division result of the target material information on the corpus display page.

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

[0063] An acquisition storage unit, configured to execute an answer interaction between the local artificial intelligence model and the question asker, obtain the target question and the corresponding answer content in the interaction process, construct each target question and the answer content into a question-answer corpus pair, and store it in the local corpus;

[0064] The seventh display unit is configured to execute the display of the Q&A corpus pairs of previous Q&A sessions in the corpus pair configuration page.

[0065] In one embodiment, the corpus pair configuration page includes a configuration management control for corpus pairs, and the configuration management control includes a marking control. The apparatus further includes:

[0066] The eighth display unit is configured to execute, in response to a trigger operation on the marking control of the target Q&A corpus pair in the Q&A corpus pairs, the display of a marking configuration page for the target Q&A corpus pair;

[0067] The ninth display unit is configured to execute, in response to a marking operation on the target Q&A corpus pair in the marking configuration page, the display of the marked target Q&A corpus pair.

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

[0069] A processor;

[0070] A memory for storing instructions executable by the processor;

[0071] Wherein, the processor is configured to execute the instructions to implement the intelligent Q&A method described in the first aspect above.

[0072] According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enabling the electronic device to execute the intelligent Q&A method described in the first aspect above.

[0073] According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product, which includes instructions that, when executed by a processor of an electronic device, enable the electronic device to execute the intelligent Q&A method described in the first aspect above.

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

[0075] By setting an intelligent Q&A control in the main chat window, and then triggering the display of an auxiliary chat window through the intelligent Q&A control, so that the question asker can ask questions based on the main chat window and / or the auxiliary chat window, and the artificial intelligence model assists the question responder to answer questions, increasing the Q&A communication channels and improving the Q&A response speed and Q&A efficiency.

[0076] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Description of the Drawings

[0077] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0078] Figure 1 It is a flowchart of an intelligent question and answer method shown according to an exemplary embodiment.

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

[0080] Figure 3 It is a flowchart of a step of displaying an auxiliary chat window through different intelligent question and answer controls shown according to an exemplary embodiment.

[0081] Figure 4 It is a schematic diagram of an interface of a main chat window displaying an intelligent question and answer identifier shown according to an exemplary embodiment.

[0082] Figure 5 It is a flowchart of a step of performing question and answer interaction in an auxiliary chat window shown according to an exemplary embodiment.

[0083] Figure 6 It is a flowchart of a method of displaying a target question in an auxiliary chat window shown according to an exemplary embodiment.

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

[0085] Figure 8 It is a flowchart of another method of displaying a target question in an auxiliary chat window by means of an input tool shown according to an exemplary embodiment.

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

[0087] Figure 10 It is a schematic diagram of an interface of a content addition page shown according to an exemplary embodiment.

[0088] Figure 11 It is a flowchart of a step of uploading and partitioning target material information shown according to an exemplary embodiment.

[0089] Figure 12 It is a schematic diagram of an interface of a file upload management page displaying segmentation options shown according to an exemplary embodiment.

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

[0091] Figure 14 It is a flowchart of steps for displaying question-and-answer corpus pairs of previous questions and answers shown according to an exemplary embodiment.

[0092] Figure 15 It is a schematic diagram of an interface of an auxiliary chat window including a marking control containing a question-and-answer dialogue shown according to an exemplary embodiment.

[0093] Figure 16 It is a schematic diagram of an interface of an auxiliary chat window including a marking input box shown according to an exemplary embodiment.

[0094] Figure 17 It is a schematic diagram of an interface of an auxiliary chat window with a marked identifier conveniently carried below the reply content shown according to an exemplary embodiment.

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

[0096] Figure 19 It is a flowchart of steps for performing similarity marking on a question-and-answer dialogue shown according to an exemplary embodiment.

[0097] Figure 20 It is a schematic diagram of an interface including a marking configuration page shown according to an exemplary embodiment.

[0098] Figure 21 It is a block diagram of an intelligent question-and-answer device shown according to an exemplary embodiment.

[0099] Figure 22 It is a block diagram of an electronic device shown according to an exemplary embodiment. Detailed implementation manners

[0100] To enable those of ordinary skill in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present 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. in the description, claims and the above drawings of the present disclosure are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present 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 for display, data for analysis, etc.) involved in the present disclosure are all information and data authorized by the user or fully authorized by all parties.

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

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

[0105] Among them, the main chat window is a question-and-answer interaction window with the question responder, and the main chat window contains an intelligent question-answering control.

[0106] In practice, in daily work, frequent information interaction and business docking are required among members of different departments and among different members of the same department. When the current user needs to conduct information interaction and business docking with a member of a certain department, the user triggers the main chat window of the target object (i.e., the question responder) integrated in the application or client for information interaction in the terminal, so as to carry out a question-and-answer conversation with the target object (i.e., the question responder). The main chat window also contains an intelligent question-answering control, which is used to trigger the display of an auxiliary chat window. Through the auxiliary chat window where the artificial intelligence model corresponding to the question responder is located, intelligent question-answering interaction with the artificial intelligence model can be carried out to assist the question responder in carrying out information interaction and business docking.

[0107] In step S120, in response to a trigger operation on the intelligent question-answering control, an auxiliary chat window is displayed side by side with the main chat window.

[0108] Among them, 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 a target question to carry out a question-and-answer conversation.

[0109] In implementation, in order to achieve information interaction and business docking among members, each member can pre-train its own exclusive artificial intelligence model, that is, by providing corresponding corpus information, material information, etc. to the artificial intelligence model, enabling the artificial intelligence model to learn the exclusive technical fields, technical content of business projects, professional knowledge, etc. that the member is good at. In this way, the artificial intelligence model can become an auxiliary tool for the member to conduct information interaction and business docking with other members. When other members raise target questions, in addition to the member being able to reply to the questions, the pre-trained artificial intelligence model can also answer questions related to the exclusive technical fields, business projects, etc. for other members.

[0110] Specifically, when the current user is the question asker and needs to conduct information interaction and / or business docking with the target object (i.e., the question responder), for the intelligent question-and-answer control displayed in the main chat window, in addition to the current user being able to directly conduct information interaction with the question responder in the main chat window, the current user can also choose to trigger the intelligent question-and-answer control, thereby displaying an auxiliary chat window based on the intelligent question-and-answer control. In this way, the current user can conduct information interaction or business docking with the artificial intelligence model corresponding to the question responder in the auxiliary chat window. For example, if the question responder being questioned is currently busy and unable to reply to the question in a timely manner, the user can select to trigger the artificial intelligence model of the question responder through the intelligent question-and-answer control in the main chat window, that is, trigger the display of the auxiliary chat window, and conduct a question-and-answer dialogue with the pre-trained artificial intelligence model of the question responder in the auxiliary chat window. Or, the question responder can reply to the question normally and in a timely manner, and the current user can still choose to trigger the artificial intelligence model assistant of the question responder through the intelligent question-and-answer control in the main chat window, that is, trigger the display of the auxiliary chat window, and conduct a question-and-answer dialogue with the question responder and the artificial intelligence model simultaneously through the main chat window and the auxiliary chat window.

[0111] Optionally, the main chat window and the auxiliary chat window are simultaneously displayed on the terminal display interface. The current user can send the same or different questions to the question responder and the pre-trained artificial intelligence model of the question responder respectively, and conduct information interaction dialogues of the same content or different content within the same time period, or can also only ask questions to the question responder or only to the artificial intelligence model, and different questions are carried out in different chat pages. The embodiments of the present application do not limit the question asker of the current user and the number of question askers within the same time period.

[0112] In the above intelligent Q&A method, by setting an intelligent Q&A control in the main chat window, and then triggering the display of an auxiliary chat window through the intelligent Q&A control, so that the question asker can ask questions based on the main chat window and / or the auxiliary chat window, increasing the Q&A communication channels, and using an artificial intelligence model to assist the question responder in answering questions, improving the Q&A response speed and Q&A efficiency.

[0113] In an exemplary embodiment, as Figure 2 shown, the main chat window includes an intelligent Q&A control, and this intelligent Q&A control can include various different display forms. For example, the intelligent Q&A control includes an intelligent Q&A identifier and an intelligent Q&A card. In step S110, the display of the main chat window can be specifically implemented through the following steps:

[0114] In step S211, in response to a first Q&A request initiated by the question asker, the main chat window is displayed.

[0115] Among them, the main chat window includes an intelligent Q&A identifier and / or an intelligent Q&A card.

[0116] In practice, when the current user wants to initiate a Q&A conversation with a certain target object, the current user is the question asker, and this target object is the question responder, answering relevant questions for the current user. Therefore, the current user initiates a first Q&A request, and the terminal responds to this first Q&A request and displays the main chat window. In this main chat window, there are interaction controls for Q&A interaction, and moreover, this main chat window also includes an intelligent Q&A control for opening the auxiliary chat window, and this intelligent Q&A control can be an intelligent Q&A identifier. For example, an intelligent Q&A identifier is displayed at the back end of the question asker identifier in the main chat window, and this intelligent Q&A identifier is used to trigger the display of the auxiliary chat window. Also, for example, an intelligent Q&A card is displayed in the content display area of the main chat window, and this intelligent Q&A card also includes intelligent Q&A options, which can be used to trigger the display of the auxiliary chat window. In this way, the user can trigger the display of the auxiliary chat window through the intelligent Q&A identifier or the intelligent Q&A card, and start the Q&A interaction through the artificial intelligence model.

[0117] In this embodiment, by adding an entry for the Q&A interaction of the artificial intelligence model in the main chat window, that is, the intelligent Q&A identifier and the intelligent Q&A card, triggering the display of the auxiliary chat window by triggering the intelligent Q&A identifier or the intelligent Q&A card, and carrying out Q&A interaction in the auxiliary chat window, so as to increase the user's Q&A communication channels and further improve the Q&A efficiency.

[0118] In an exemplary embodiment, as Figure 3As shown, since the main chat window contains an entry for triggering the auxiliary chat window, which can be embodied in the form of an intelligent Q&A control. The intelligent Q&A control includes an intelligent Q&A identifier and an intelligent Q&A card, etc. In step S120, in response to the triggering operation on the intelligent Q&A control, the specific process of displaying the auxiliary chat window includes:

[0119] In step 301, in response to the triggering operation on the intelligent Q&A identifier, the auxiliary chat window is displayed. Or,

[0120] In implementation, on the display interface of the terminal, there is a main chat window, in which the avatar identifier of the question responder is marked. The question responder in the main chat window is identified through the avatar identifier of the question responder. And in the main chat window, there is also an intelligent Q&A identifier, such as Figure 4 shown. The intelligent Q&A identifier is displayed in the form of a label at the back end of the avatar identifier of the question responder. In Figure 4 it is represented by 411. The intelligent Q&A identifier is one of the intelligent Q&A controls. In this way, the question asker (the current user) can trigger the intelligent Q&A identifier, and the terminal responds to the triggering operation on the intelligent Q&A identifier and displays the auxiliary chat window. The auxiliary chat window is the Q&A interaction window of the artificial intelligence model corresponding to the question responder.

[0121] Optionally, on the display interface of the terminal, the main chat window and the auxiliary chat window can be displayed simultaneously (also called side-by-side display), or only a single chat window can be shown. That is, when the user triggers the intelligent Q&A control in the main chat window, the display interface of the terminal jumps from the main chat window to the auxiliary chat window. Whether the main chat window and the auxiliary chat window are displayed simultaneously, or the main chat window is shown first and then jumps from the main chat window to the auxiliary chat window, the Q&A dialogue between the current user and the question responder in the main chat window can be automatically copied and forwarded to the auxiliary chat window before the next trigger of the auxiliary chat window dialogue, so as to help the artificial intelligence model corresponding to the question responder quickly understand the communication context between the question asker and the question responder.

[0122] In step 302, in response to the triggering operation on the intelligent Q&A card, the auxiliary chat window is displayed.

[0123] In implementation, the intelligent Q&A card can be pre-displayed on the content display page of the main chat window. The intelligent Q&A card contains a trigger option for displaying the auxiliary chat window, and the intelligent Q&A card can also contain guiding information for guiding the user to use the auxiliary chat window where the artificial intelligence model is located for Q&A dialogue. In this way, if the current user triggers the trigger option in the intelligent Q&A card, the terminal responds to the triggering operation on the intelligent 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. Through different types of intelligent question-and-answer controls, it is possible to enter the artificial intelligence model through different paths, enriching the way of starting a question-and-answer dialogue with the artificial intelligence model corresponding to the question responder and improving the efficiency of asking questions.

[0125] In an exemplary embodiment, Figure 5 As shown, since the artificial intelligence model integrated in the auxiliary chat window can assist the question answerer in the main chat window to provide the question asker with the answer or reply content of the target question, the question asker conducting a question-and-answer dialogue in the auxiliary chat window is described as an example. The method further includes:

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

[0127] In implementation, in the auxiliary chat window, the user inputs the target question he wants to ask through preset input controls (for example, input boxes, input cards, candidate input options), etc., and the terminal responds to the triggering 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 reply content from the corpus corresponding to the question responder, and the reply content is displayed in the auxiliary chat window.

[0129] In implementation, a pre-trained AI model corresponding to the question responder is located in the terminal where the question responder resides. The question responder also pre-builds a corpus corresponding to the AI model. The question responder uploads relevant content information (e.g., project documents, management rules, technical manuals, guidelines, etc.) for their target technical fields and target business projects, and stores this information in the corpus as response material for the AI model corresponding to the question responder. There is no need to pre-build the question-and-answer corpus for the AI model. When a user enters a target question, the AI model in the terminal searches the corpus for the response material information uploaded by the question responder based on the target 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 reply content from the corpus, and quickly responds to target questions, significantly shortening the time it takes for users to obtain reply content, thereby improving the user's question-and-answer efficiency.

[0131] In an exemplary embodiment, as Figure 6 shown, there are multiple ways for a user to input a target question in the assisted chat page. In the embodiments of the present disclosure, one way to input the target question is given. Then, in step S501, in response to an input operation of the target question, the specific processing process of the target question displayed in the assisted chat window includes:

[0132] In step S601, display the assisted chat window.

[0133] In practice, in the assisted chat window, there is a Q&A card displayed. The Q&A card contains multiple candidate questions. As Figure 7 shown, in the content display area of the assisted chat window, there is a first Q&A card displayed, which is represented by 711 in Figure 7 . The first Q&A card contains multiple types of candidate questions and question options. These question options also correspond to different types of candidate questions. The candidate questions contained in this question card can be candidate questions refined and summarized by an artificial intelligence model based on the material information pre-uploaded by the question responder, or they can be historical questions or frequently asked questions recorded during the historical Q&A process, etc., for guiding the user to quickly determine the target question based on the candidate questions, thereby realizing a quick query of the target question.

[0134] In step S602, in response to a trigger operation on the target question in the candidate questions, display the target question in the assisted chat window.

[0135] In practice, when the current user selects the target question in the information card through a trigger method such as clicking or dragging, the terminal responds to the trigger operation on the target question in the information card, and the terminal displays the target question in the content display area of the assisted chat window, realizing the input of the target question in one way.

[0136] Optionally, the assisted chat window of the artificial intelligence model provided by the present disclosure supports multi-round information interaction between the user and the artificial intelligence model. Specifically, when one Q&A cannot solve the user's problem, the terminal can analyze and make a decision based on the current Q&A context content in the assisted chat window, and give a new question card. The question card contains a new round of candidate questions. The user can further screen out the target question based on the candidate questions in the new round of Q&A card and input it into the assisted chat window for a new round of Q&A dialogue until the user obtains all the information required to be understood based on the Q&A dialogue and stops the information interaction.

[0137] In this embodiment, by displaying Q&A cards in the auxiliary chat window, candidate questions available for the user to ask are provided. The user can quickly find the target question among the candidate questions without manual input, shortening the question input time, achieving a quick question of the target question, and with the aid of the candidate questions in the question cards, for complex inquiry services, the system supports multi-round interactions to gradually guide the user to obtain a complete answer, improving the Q&A efficiency.

[0138] In one exemplary embodiment, as Figure 8 shown, there are various ways for the user to input the target question in the auxiliary chat page. This disclosure embodiment gives another way to input the target question, that is, the auxiliary chat window includes an input control, then the specific process of displaying the target question in the auxiliary chat window in response to the input operation of the target question in step 501 includes:

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

[0140] In implementation, the terminal pre-includes an input control for inputting the target question. The user triggers this input control, and an input tool for inputting the target question is displayed in the auxiliary chat window. Furthermore, the target question can be input with the aid of the input tool. Specifically, the input control can be a type of input box. As Figure 7 shown, taking the input tool as a soft keyboard as an example for illustration, an input box (input control) for inputting 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 triggering operation of the output box and displays a soft keyboard (input tool) for inputting the target question in the auxiliary chat window, and the target question is input through this soft keyboard.

[0141] Optionally, in addition to the soft keyboard as the input tool, the input tool can also include a voice input tool, a scan input tool, a touchpad input, etc. This disclosure embodiment does not limit the types and quantities of the 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, the user inputs the target question through the input tool. For example, after the user inputs the target question in the soft keyboard, the target question can be sent to the content display area of the auxiliary chat window by triggering the send option in the soft keyboard. In this way, the terminal responds to the operation of the user inputting the target question in 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, and provide instant feedback based on the input of the target question in the auxiliary chat window, enhancing the user's sense of control and participation, and improving the Q&A interaction efficiency.

[0145] In an exemplary embodiment, since each member of the enterprise corresponds to a dedicated artificial intelligence model, each member provides the technical content, professional knowledge, etc. of their own dedicated technical field and business project that they are good at for the dedicated artificial intelligence model. Thus, a corpus belonging to themselves and an artificial intelligence model for intelligent Q&A in related fields are constructed. In this way, when a certain member is the question asker, the member can ask questions to the artificial intelligence models corresponding to other members, and when the member is the question responder, the artificial intelligence model corresponding to the member can also provide reply services for other users. As Figure 9 shown, described with the current user as the role of the question responder, the method further includes:

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

[0147] Among them, the corpus management page contains a content addition control.

[0148] In implementation, an information interaction platform is integrated in the terminal where the current user is located. In this information interaction platform, a corpus corresponding to the artificial intelligence model for the local area (the terminal device where the current user is located) is pre-constructed. A corpus management page is displayed in the terminal display page corresponding to this corpus. As Figure 10 shown, in the corpus management page, according to the preset partition layout rule, the corpus content of each partition during corpus storage is displayed. And, this corpus management page also contains a content addition control, such as Figure 10 the "Add Control" displayed in the upper right corner in [Figure], represented by 1110, and the addition of corpus content is triggered through this content addition control.

[0149] In step S902, in response to the triggering operation on the content addition control, display the content addition page.

[0150] Among them, the content addition page contains content management options.

[0151] In implementation, when the user initially constructs this corpus or updates the corpus daily, the user can trigger the content addition control in this corpus management page, and the terminal responds to the triggering operation of the user on the content addition control and displays the content addition page.

[0152] Optionally, this content addition page can be a pop-up page, a drawer page, etc. displayed on the upper layer of the corpus management page, or an independent content addition page that needs to be jumped from the corpus management page. AsFigure 10 As shown, on the upper layer of the corpus management page, a content addition page is displayed in the form of a pop-up page. The content addition page includes content management options for uploading material information. Through these content management options, there are classification options for classified uploading of files and segmentation options for segmented storage of files.

[0153] Step S903: Based on the classification options 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 classification options and segmentation options. When the user uploads the target material information, the user can, with the help of the classification options, screen candidate files of the target file type and target storage form in the preset storage space. Then, the terminal selects the target file to be uploaded from the candidate files, obtains and uploads the target file as the target material information to be uploaded. Further, the terminal performs segmentation processing on the selected target material information through the segmentation options, and stores the segmented target material area in the target storage area of the local corpus, thereby updating the local corpus.

[0155] In this embodiment, by displaying the corpus management page and providing content addition controls, the user can efficiently manage the corpus content. The classification options and segmentation options in the content addition page can perform structured processing on the target material information according to requirements, ensuring the orderliness and retrievability of the corpus content. And the terminal updates the local corpus in real time, also ensuring the timeliness and integrity of the corpus content.

[0156] In an exemplary embodiment, as Figure 11 shown, the specific processing procedure for obtaining and uploading the target material information based on the classification options and segmentation options in the content management options in step S903 includes:

[0157] In step S1101, based on the trigger operation on the classification options in the content management options, display the file type and storage form of the target material information to be uploaded.

[0158] In implementation, the terminal, based on the trigger operation on the classification options in the content management options, displays the file type and storage form of the target material information to be uploaded. As Figure 12As shown, the classification options included in the content addition page include two types: document type and table type. Different classification options correspond to different file types. Each file type is further divided into different file storage forms. For example, the file storage forms corresponding to the document type include: local file, Docs online document, and Docs knowledge base. The file storage forms corresponding to the table type include: local file and Docs online table. In this way, different file types and different storage forms of files in the content addition page are divided into different upload paths. When a user uploads the target material information, by selecting the target classification option in the classification options, the user can select the target material information in the candidate files based on the file type and storage form corresponding to the target classification option, that is, the file type and storage form of the target material information to be uploaded can be pre-displayed in the terminal display interface.

[0159] In step S1102, based on the file type and storage form, obtain the target material information, and based on the trigger operation on the segmentation option in the content management option, display the text segmentation form of the target material information.

[0160] In implementation, after clarifying the file type and storage form of the target material information to be uploaded, determine the material upload path based on the file type and storage form. And the terminal, based on this material upload path, obtains the target material information in the storage area corresponding to this material upload path. In this way, after uploading the target material information, the content management option is updated to display a segmentation option for selecting the segmentation form of the target material information. As Figure 12 shown, a file upload progress is displayed above the file upload management page, and different segmentation options are shown below the upload progress. Different segmentation options include: an automatic segmentation option (automatically segmented according to the default rules) and a custom segmentation option. Different segmentation options correspond to different text segmentation methods. In this way, the user can select a text segmentation method for the target material information (that is, select the target segmentation option) from different segmentation options according to the text characteristics of the target material information, so as to display the text segmentation form of the target material information.

[0161] In step S1103, based on the text segmentation form, display the material division result of the target material information on the corpus display page.

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

[0163] In this embodiment, by triggering the classification option in the content management option, the file type and storage form 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 form, and segmentation method, the material division result of the target material information is displayed on the corpus display page to ensure the organization and retrievability of the corpus content.

[0164] In an exemplary embodiment, as Figure 14 shown, the method further includes:

[0165] In step S1401, in response to the Q&A interaction between the local artificial intelligence model and the question asker, the target question and the corresponding answer content in the interaction process are obtained, and each target question and answer content are constructed into a Q&A corpus pair and stored in the local corpus.

[0166] In practice, the terminal where the current user is located corresponds to a local artificial intelligence model. When the artificial intelligence model assists the current user in conducting Q&A conversations with other users, the terminal can record and store the Q&A conversations between the artificial intelligence model and other users. Specifically, when the local artificial intelligence model conducts Q&A interaction with the question asker, the terminal responds to the Q&A interaction operation between the artificial intelligence model and the question asker, obtains the target question generated in this Q&A interaction process and the corresponding answer content to the target question. Then, the terminal constructs each target question and the corresponding answer content to the target question into a group of Q&A corpus pairs, and stores the Q&A corpus pairs in the local corpus as well.

[0167] Or, as Figure 15 shown, various Q&A conversations generated during the question interaction between the artificial intelligence model and the question asker are displayed in the assisted chat window. In the Q&A conversation, the answer content below the target question carries a control for annotating the group of Q&A conversations. The current user can trigger the annotation control, and the annotation control is used to add annotation content to the answer content. As Figure 16As shown, when the user triggers the annotation control, the terminal responds to the user's trigger operation on the annotation control and displays an annotation input box. Below the annotation input box, there are a cancel option and a confirm option for modifying and confirming the content in the annotation input box. In this way, after the current user enters the annotation content for the reply content in the annotation input box, the user can confirm the input annotation content through the confirm option below the annotation input box. Thus, the current user completes the annotation of the reply content. Among them, the annotation content input by the current user can be a supplement or correction to the reply content given by the artificial intelligence model, and the present disclosure embodiment does not limit the annotation content input by the current user.

[0168] Therefore, for the Q&A dialogue with added marked content, the terminal automatically constructs a Q&A corpus pair and stores the Q&A corpus pair in the local corpus as a supplement to the reply material information in the local corpus. Optionally, to avoid duplicate data storage, before storing the annotated Q&A corpus pair in the local corpus, a query and retrieval are performed in the local corpus based on the target question in the Q&A corpus pair. When the target question of this type or related type does not exist in the local corpus, the Q&A corpus pair is stored.

[0169] In the content display area of the auxiliary chat window, the reply content in the Q&A dialogue is annotated. As Figure 17 shown, a "annotated" label is carried below the reply content, and the specific annotation content is hidden to save the content display area of the auxiliary chat window. When a question-asking user asks the target question in this Q&A dialogue, since the annotated Q&A dialogue has been constructed as a Q&A corpus pair and stored in the local corpus, the Q&A corpus pair can be used as the basis for the reply content. In the content display area of the auxiliary chat window, the annotated reply content is displayed, and the annotated reply content also carries a "annotated" label. The question-asking user can view the hidden annotation content through the "annotated" label.

[0170] Among them, each Q&A corpus pair can also be divided according to the same question asker or according to the generation time of the Q&A corpus pair. The present disclosure embodiment does not limit the classification and storage rules of each Q&A corpus pair. In this way, the Q&A corpus pairs obtained through previous Q&A processes enrich the reply content resources of the local corpus.

[0171] Optionally, each Q&A corpus pair stored in the local corpus can, in turn, serve as the basis for the AI model to generate response content, supporting the response to new target questions. Specifically, when another user, as the question asker, sends 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 Q&A corpus pair to determine whether the current target question belongs to the same question as the questions in each Q&A corpus pair. When the question in a certain Q&A corpus pair is similar to the current target question, the response content in that Q&A corpus pair can be used to quickly reply to the current target question in the auxiliary chat window.

[0172] In step S1402, the Q&A corpus pairs of previous Q&A sessions are displayed on the corpus pair configuration page.

[0173] In practice, for the Q&A corpus pairs generated during previous Q&A sessions, in addition to storing them in the local corpus, the terminal can also configure the Q&A corpus pairs. Specifically, the full set of Q&A corpus pairs generated from the Q&A interactions between each question asker and the AI model within a preset time period are displayed on the corpus pair configuration page. Optionally, the Q&A corpus pairs can be displayed in a list form or a table form on the corpus pair configuration page.

[0174] As Figure 18 shown, Figure 18 Figure 13 shows a corpus pair configuration page. In the display interface of the terminal, the Q&A corpus pairs are arranged and displayed in a list form according to the generation time of each Q&A corpus pair. Each Q&A corpus pair serves as an item in the list, facilitating the query and search of the Q&A corpus pairs.

[0175] In this embodiment, by automatically extracting the target question and its corresponding response content and constructing them into structured Q&A corpus pairs and storing them in the local corpus, the workload of manually organizing the corpus pairs is reduced, and at the same time, the real-time update and expansion of the corpus are ensured. Moreover, the local corpus can continuously accumulate high-quality Q&A corpus pairs, providing rich corpus support for the iterative training of the AI model and improving the accuracy and generalization ability of the AI model.

[0176] In an exemplary embodiment, as Figure 19 shown, in addition to configuring and annotating the response content in the Q&A corpus pairs in the auxiliary chat window, the Q&A corpus pairs can also be configured and managed on a dedicated corpus pair configuration page. Among them, the corpus pair configuration page includes configuration management controls for the corpus pairs, and the configuration management controls include annotation controls. The method further includes:

[0177] In step S1901, in response to a triggering operation on the annotation control for the target Q&A corpus pair in the Q&A corpus pair, an annotation configuration page for the target Q&A corpus pair is displayed.

[0178] In implementation, Figure 18 the Q&A corpus pairs in the corpus pair configuration page are arranged and displayed in a list form. Each table entry where a Q&A corpus pair is located corresponds to the annotation control for that Q&A corpus pair, and this annotation control includes an editing control, a deletion control, and so on. Also, in each table entry where a Q&A corpus pair is located, the attribute information of each Q&A corpus pair can be included. For example, the creation time, the number of hits, and the belonging tags of this Q&A corpus pair, etc. Therefore, when the current user wants to annotate a certain Q&A corpus pair (i.e., the target Q&A corpus pair) among the Q&A corpus pairs, the current user can trigger the annotation control for this Q&A corpus pair. In this way, the terminal, in response to the triggering operation on the annotation control for the target Q&A corpus pair, displays the annotation configuration page for the target Q&A corpus pair. As Figure 20 shown, this annotation configuration page can be a pop-up page displayed on top of the corpus pair configuration page. In this annotation configuration page, a similarity editor for setting the question matching similarity can be included. The similarity editor contains a movable slider, which is used to determine that the user, by sliding the slider on the similarity editor, determines the similarity between the target question included in the Q&A corpus pair and each target question in the local corpus, 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 Q&A corpus pair in the annotation configuration page, the annotated target Q&A corpus pair is displayed.

[0180] In implementation, after the current user performs an annotation operation on the target Q&A corpus pair through the similarity editor in the annotation configuration page, the terminal, in response to the annotation operation on the target Q&A corpus pair, displays the annotated target Q&A corpus pair in the corpus pair configuration page.

[0181] In this embodiment, by triggering the annotation control for the target Q&A corpus pair, the annotation configuration page is displayed, enabling the user to perform a refined annotation operation on the target Q&A corpus pair. After the annotation operation is completed, the annotated target Q&A corpus pair is displayed, facilitating the verification of the accuracy of the annotation result. The overall performance and scalability of the information interaction platform where the terminal is located are improved.

[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 in sequence according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figures 1 - 3 , Figure 5 , Figure 6 , Figure 8 , Figure 9 , Figure 11 , Figure 14 , Figure 19 at least some of the steps in may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turns with at least some of the steps or stages in other steps or other steps.

[0183] It can be understood that for the same / similar parts among the various embodiments of the above method in this specification, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. For the related parts, reference can be made to the descriptions of other method embodiments.

[0184] Figure 21 is a block diagram of an intelligent question-answering device shown according to an exemplary embodiment. Referring to Figure 21 , the device 2100 includes:

[0185] A first display unit 2101, configured to execute the display of a main chat window, where the main chat window is a question-and-answer interaction window with the question responder, and the main chat window contains intelligent question-answering controls;

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

[0187] In one embodiment, the intelligent question-answering control includes an intelligent question-answering identifier and an intelligent question-answering card. The first display unit 2101 includes:

[0188] A first display subunit, configured to execute the display of the main chat window in response to a first question-and-answer request initiated by the question asker, where the main chat window contains the intelligent question-answering identifier and / or the intelligent question-answering card.

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

[0190] A second display subunit, configured to execute a trigger operation in response to an intelligent Q&A identifier and display an auxiliary chat window; or,

[0191] A third display subunit, configured to execute a trigger operation in response to an intelligent Q&A card and display an auxiliary chat window.

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

[0193] A third display unit, configured to execute an input operation in response to a target question and display the target question in the auxiliary chat window;

[0194] A fourth display unit, configured to execute parsing and extracting a reply content from a corpus corresponding to a question reply party based on the target question through an artificial intelligence model, and display the reply content in the auxiliary chat window.

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

[0196] A fourth display subunit, configured to execute displaying an auxiliary chat window, where the auxiliary chat window includes a Q&A card, and the Q&A card includes candidate questions;

[0197] A fifth display subunit, configured to execute a trigger operation in response to a target question in the candidate questions and display the target question in the auxiliary chat window.

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

[0199] A sixth display subunit, configured to execute a trigger operation in response to the input control and display an input tool for inputting a target question;

[0200] A seventh display subunit, configured to execute an operation of inputting a target question through the input tool and display the target question in the auxiliary chat window.

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

[0202] A fifth display unit, configured to execute displaying a corpus management page, where the corpus management page includes a content adding control;

[0203] A sixth display unit, configured to execute a trigger operation in response to the content adding control and display a content adding page, where the content adding page includes content management options;

[0204] An update unit, configured to execute obtaining and uploading target material information based on classification options and segmentation options in the content management options, and updating a local corpus based on the target material information.

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

[0206] An eighth display subunit, configured to perform a trigger operation based on a classification option in the content management option, and display the file type and storage form of the target material information to be uploaded;

[0207] A ninth display subunit, configured to perform operations based on the file type and storage form to obtain the target material information, and display the text segmentation form of the target material information based on a trigger operation on the segmentation option in the content management option;

[0208] A tenth display subunit, configured to perform operations based on the text segmentation form to display the material division result of the target material information on the corpus display page.

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

[0210] An acquisition storage unit, configured to perform operations in response to a question-and-answer interaction between a local artificial intelligence model and a question asker, acquire the target question and the corresponding answer content during the interaction process, construct each target question and answer content into a question-and-answer corpus pair, and store it in the local corpus;

[0211] A seventh display unit, configured to perform operations to display the question-and-answer corpus pairs of previous questions and answers on the corpus pair configuration page.

[0212] In one embodiment, the corpus pair configuration page includes a configuration management control for the corpus pair, and the configuration management control includes a marking control. The apparatus 2100 further includes:

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

[0214] A ninth display unit, configured to perform operations in response to a marking operation on the target question-and-answer corpus pair on the marking configuration page, and display the marked target question-and-answer corpus pair.

[0215] Regarding the apparatus in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0216] Figure 22 It is a block diagram of an electronic device 2200 for an application intelligent question-and-answer method shown according to an exemplary embodiment. For example, the electronic device 2200 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

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

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

[0219] The memory 2204 is configured to store various types of data to support the operation of the electronic device 2200. Examples of such data include instructions for any application or method operating on the electronic device 2200, contact data, phone book data, messages, pictures, videos, etc. The memory 2204 may 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 memory, flash memory, magnetic disks, optical disks, or graphene memory.

[0220] The power supply component 2206 provides power to various components of the electronic device 2200. The 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 for the electronic device 2200.

[0221] The multimedia component 2208 includes a screen that provides an output interface between the electronic device 2200 and the 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 can be implemented as a touch screen 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 can sense not only the boundaries of touch or swipe actions but also detect the duration and pressure associated with the touch or swipe operation. In some embodiments, the multimedia component 2208 includes a front camera and / or a rear camera. When the electronic device 2200 is in an operation mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have a focal length and optical zoom capabilities.

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

[0223] The I / O interface 2212 provides an interface between the processing component 2202 and a peripheral interface module, and the peripheral interface module can be a keyboard, a click wheel, buttons, etc. These buttons can include but are not limited to: a home button, a volume button, a power button, and a lock button.

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

[0225] The communication component 2216 is configured to facilitate communication between the electronic device 2200 and other devices in a wired or wireless manner. The electronic device 2200 can access a communication standard-based wireless network, such as WiFi, a carrier network (such as 2G, 3G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component 2216 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 2216 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can 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 can 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 for performing the above method.

[0227] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as the memory 2204 including instructions, and the above instructions can be executed by the processor 2220 of the electronic device 2200 to complete the above method. For example, the computer-readable storage medium can 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, and the computer program product includes instructions that can be executed by the processor 2220 of the electronic device 2200 to complete the above method.

[0229] It should be noted that the above-mentioned device, electronic device, computer-readable storage medium, computer program product, etc. may also include other implementation manners according to the description of the method embodiments. The specific implementation manners can refer to the description of the relevant method embodiments and will not be elaborated here one by one.

[0230] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed herein. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

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

Claims

1. An intelligent question-answering method, characterized in that, The method includes: Displaying a main chat window, which is a question-and-answer interaction window with the question responder, and the main chat window contains an intelligent question-and-answer control; In response to a trigger operation on the intelligent question-and-answer control, displaying an auxiliary chat window; the auxiliary chat window is a question-and-answer interaction window with the artificial intelligence model corresponding to the question responder; the main chat window and the auxiliary chat window are used to input a target question to conduct a question-and-answer conversation.

2. The intelligent question-answering method according to claim 1, wherein The intelligent question-and-answer control includes an intelligent question-and-answer identifier and an intelligent question-and-answer card. The displaying of the main chat window includes: In response to a first question-and-answer request initiated by the question asker, displaying the main chat window, and the main chat window contains the intelligent question-and-answer identifier and / or the intelligent question-and-answer card.

3. The intelligent question-answering method according to claim 2, wherein The responding to the trigger operation on the intelligent question-and-answer control and displaying the auxiliary chat window includes: In response to a trigger operation on the intelligent question-and-answer identifier, displaying the auxiliary chat window; or, In response to a trigger operation on the intelligent question-and-answer card, displaying the auxiliary chat window.

4. The intelligent question-answering method according to claim 1, wherein The method further includes: In response to an input operation on the target question, displaying the target question in the auxiliary chat window; Based on the target question, parsing and extracting a reply content from the corpus corresponding to the question responder through the artificial intelligence model, and displaying the reply content in the auxiliary chat window.

5. The intelligent question-answering method according to claim 4, wherein, The responding to the input operation on the target question and displaying the target question in the auxiliary chat window includes: Displaying the auxiliary chat window, which contains a question-and-answer card, and the question-and-answer card contains candidate questions; In response to a trigger operation on the target question among the candidate questions, displaying the target question in the auxiliary chat window.

6. The intelligent question-answering method according to claim 4, characterized in that The auxiliary chat window contains an input control. The responding to the input operation on the target question and displaying the target question in the auxiliary chat window includes: In response to a trigger operation on the input control, displaying an input tool for inputting the target question; In response to an operation of inputting the target question through the input tool, displaying the target question in the auxiliary chat window.

7. The intelligent question and answer method according to claim 1, characterized in that The method further includes: Displaying a corpus management page, which contains a content addition control; In response to a trigger operation on the content addition control, displaying a content addition page, and the content addition page contains content management options; Based on the classification option and the segmentation option in the content management options, obtaining and uploading target material information, and updating the local corpus based on the target material information.

8. The intelligent question-answering method according to claim 7, wherein The obtaining and uploading the target material information based on the classification option and the segmentation option in the content management options includes: Based on a trigger operation on the classification option in the content management options, displaying the file type and the storage form of the target material information to be uploaded; Based on the file type and the storage form, obtaining the target material information, and based on a trigger operation on the segmentation option in the content management options, displaying the text segmentation form of the target material information. Based on the above text segmentation form, display the material division result of the target material information on the corpus display page.

9. The intelligent question-answering method according to claim 7, wherein The method further includes: In response to the Q&A interaction between the local artificial intelligence model and the question asker, obtain the target question and the corresponding answer content during the interaction, construct each target question and the answer content into a Q&A corpus pair, and store it in the local corpus. Display the Q&A corpus pairs of previous Q&A sessions on the corpus pair configuration page.

10. The intelligent question-answering method according to claim 9, characterized in that, The corpus pair configuration page includes a configuration management control for corpus pairs, and the configuration management control includes a marking control. The method further includes: In response to the triggering operation on the marking control of the target Q&A corpus pair in the Q&A corpus pair, display the marking configuration page for the target Q&A corpus pair. In response to the marking operation on the target Q&A corpus pair on the marking configuration page, display the marked target Q&A corpus pair.

11. An intelligent question-answering device, characterized in that, The device includes: A first display unit configured to display the main chat window, where the main chat window is a Q&A interaction window with the question responder, and the main chat window includes an intelligent Q&A control. A second display unit configured to display an auxiliary chat window in response to the triggering operation on the intelligent Q&A control; the auxiliary chat window is a Q&A interaction window with the artificial intelligence model corresponding to the question responder; the main chat window and the auxiliary chat window are used to input target questions to conduct Q&A conversations.

12. An electronic device, characterized in that, It includes: A processor; A memory for storing the executable instructions of the processor; Wherein, the processor is configured to execute the instructions to implement the intelligent Q&A method according to any one of claims 1 to 10.

13. 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 can execute the intelligent Q&A method according to any one of claims 1 to 10.

Images