Man-machine conversation method, device and equipment and computer readable storage medium

Abstract

The embodiment of the invention provides a man-machine conversation method, device and equipment and a computer readable storage medium. The method provided by the embodiment of the invention comprises the steps that a reading document is selected to enter a first mode, and an interface of a man-machine conversation program in the first mode comprises a reading area and a conversation area; displaying a part of the content of the reading document through the reading area; obtaining prompt information through the dialogue area; and in response to the prompt information obtained in the dialogue area, displaying a first part of content in the content associated with the prompt information in the reading document in the reading area. According to the method disclosed by the invention, the immersive reading of the reading document can be realized, and the knowledge flywheel of the reading document is constructed, so that the user experience is greatly improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and more specifically, to a human-computer dialogue method, apparatus, device, and computer-readable storage medium. Background Art

[0002] As an important branch of computer science, human-computer dialogue interaction is used to realize natural language communication between humans and computers. Human-computer dialogue is an important challenge for artificial intelligence technology. With the rapid development of artificial intelligence, the research on human-computer dialogue is becoming more and more popular. The main goal of human-computer dialogue interaction technology is to enable computers to understand and generate human language and have natural conversations with humans. This requires computers to have multiple capabilities such as natural language processing, machine learning, and knowledge representation. In recent years, with the breakthrough of deep learning technology, human-computer dialogue interaction technology has made great progress. Deep learning models can learn language patterns and semantic knowledge from massive text data, thereby improving the computer's ability to understand and generate natural language.

[0003] At present, human-computer dialogue interaction technology has become the core technology of various intelligent dialogue applications, greatly affecting the efficiency and convenience of human-computer interaction. For example, in the field of reading, the deep reading method based on human-computer dialogue is a new type of reading tool that can provide users with convenient and efficient reading services. Therefore, an effective human-computer dialogue interaction method is needed to achieve better document reading functions. Summary of the invention

[0004] Embodiments of the present disclosure provide a human-computer dialogue method, apparatus, device, and computer-readable storage medium.

[0005] An embodiment of the present disclosure provides a human-computer dialogue method, which is applied to a human-computer dialogue program, and the method includes: selecting a reading document to enter a first mode, wherein in the first mode the interface of the human-computer dialogue program includes a reading area and a dialogue area; displaying a portion of the content of the reading document through the reading area; obtaining prompt information through the dialogue area; and in response to obtaining the prompt information in the dialogue area, displaying a first portion of the content in the reading document associated with the prompt information in the reading area.

[0006] According to the method of an embodiment of the present disclosure, it also includes: in response to obtaining prompt information in the conversation area, when at least a part of the first part of the content is not displayed in the reading area and at least a part of the reading area displays the content of the reading document other than the first part of the content, scrolling the content of the reading document in the reading area and jumping to the first part of the content to display more of the first part of the content in the reading area.

[0007] The method according to an embodiment of the present disclosure further includes: in response to obtaining prompt information in the dialogue area, displaying an answer to the prompt information in the dialogue area.

[0008] According to the method of an embodiment of the present disclosure, it also includes: in response to obtaining prompt information in the conversation area, displaying the distribution of content associated with the prompt information in the reading document in a bar-shaped sub-area in the reading area, and using a positioning identifier to indicate the position of the first part of the content in the reading document, wherein, among the content associated with the prompt information, the first part of the content is most associated with the prompt information.

[0009] According to the method of an embodiment of the present disclosure, it also includes: in response to a second part of the content of the reading document in the reading area being cited, displaying the second part of the content in a first sub-area of ​​the conversation area, displaying one or more recommendation prompt information for the second part of the content in the conversation area, and in response to one of the one or more recommendation prompt information being selected, displaying the second part of the content, the selected recommendation prompt information, and an answer to the recommendation prompt information in a second sub-area of ​​the conversation area.

[0010] According to the method of an embodiment of the present disclosure, it also includes: receiving prompt information for the second part of the content in a third sub-area of ​​the conversation area, and in response to selecting to send the second part of the content and the prompt information for the second part of the content to the second sub-area, displaying the second part of the content, the prompt information and an answer to the prompt information in the second sub-area of ​​the conversation area.

[0011] According to the method of an embodiment of the present disclosure, it also includes: in response to selecting the second part of the content in the second sub-area of ​​the conversation area, scrolling the content of the reading document in the reading area and jumping to the second part of the content when at least a part of the second part of the content is not displayed in the reading area.

[0012] According to the method of an embodiment of the present disclosure, scrolling the content of the reading document in the reading area and jumping to the second part of the content includes: displaying the second part of the content in the center of the reading area.

[0013] According to the method of an embodiment of the present disclosure, it also includes: conducting a human-computer dialogue in the second mode, and receiving one or more documents including the reading document, and in response to entering the first mode for the reading document, synchronously displaying the first reception of the reading document in the second mode and the human-computer dialogue history after the first reception of the reading document in the dialogue area in the first mode.

[0014] According to the method of an embodiment of the present disclosure, receiving the reading document in the second mode includes receiving one or more reading documents, and in response to receiving the one or more reading documents, the received one or more reading documents are displayed in the form of an array in the second mode, and an entry prompt to enter the first mode is displayed for at least a part of the one or more reading documents in the second mode.

[0015] According to the method of an embodiment of the present disclosure, it also includes: in response to the cursor lingering on the table of contents area in the reading document, differentially displaying the table of contents area where the cursor lingers, and in response to selecting the table of contents area in the reading document, jumping the reading area to the main text content corresponding to the table of contents area in the reading document.

[0016] According to the method of an embodiment of the present disclosure, jumping the reading area to the main text content corresponding to the directory area in the reading document includes: displaying the title corresponding to the directory area in the main text content at the top of the reading area.

[0017] The method according to an embodiment of the present disclosure further includes: in response to selecting the directory area in the reading document, displaying recommendation prompt information for the directory area and the text content corresponding to the directory area in the conversation area.

[0018] The method according to an embodiment of the present disclosure further includes: in response to entering the first mode, displaying one or more recommendation prompt information for the reading document in a fourth sub-area of ​​the conversation area.

[0019] According to the method of an embodiment of the present disclosure, it also includes: in response to selecting one of the one or more recommendation prompt information for the reading document, displaying the selected recommendation prompt information and an answer to the selected recommendation prompt information in the conversation area, and eliminating the fourth sub-area displaying the one or more recommendation prompt information for the reading document.

[0020] According to the method of an embodiment of the present disclosure, it also includes: in response to receiving prompt information in the third sub-area of ​​the conversation area and sending the prompt information in the second sub-area of ​​the conversation area, displaying the prompt information and an answer to the prompt information in the conversation area, and eliminating the fourth sub-area displaying one or more recommended prompt information for the reading document.

[0021] The method according to an embodiment of the present disclosure further includes: in response to returning from the first mode to the second mode, displaying in the second mode the content displayed in the conversation area in the first mode.

[0022] An embodiment of the present disclosure provides a human-computer dialogue device, which is configured to execute a human-computer dialogue program, and the device includes: a mode selection module, which selects reading a document to enter a first mode, wherein the interface of the human-computer dialogue program in the first mode includes a reading area and a dialogue area; a reading module, which is configured to display a part of the content of the reading document through the reading area in the first mode of the human-computer dialogue program; and a dialogue module, which is configured to receive prompt information through the dialogue area in the first mode of the human-computer dialogue program, wherein the prompt information is used to determine the content in the reading document associated with the prompt information; and wherein, in response to the dialogue module receiving the prompt information in the dialogue area, the reading module is configured to display the first part of the content in the reading document associated with the prompt information in the reading area.

[0023] An embodiment of the present disclosure provides a human-computer dialogue device, including: one or more processors; and one or more memories, wherein a computer executable program is stored, and when the computer executable program is executed by the processor, the above method is executed.

[0024] An embodiment of the present disclosure provides a computer-readable storage medium on which computer-executable instructions are stored. When the instructions are executed by a processor, the above method is implemented.

[0025] The human-computer dialogue method provided by the embodiment of the present disclosure can coordinate users and artificial intelligence to promote users to read documents immersively. According to the method of the present disclosure, it is possible to enter the immersive reading mode based on the user's choice, and in the immersive reading mode, the user can ask and answer questions about the reading document, summarize the reading document, locate the content in the reading document based on the user's prompt information, and other operations. In addition, the method of the present disclosure can save user usage records and further form a knowledge flywheel for reading documents, thereby greatly improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some exemplary embodiments of the present disclosure, and a person of ordinary skill in the art can obtain other drawings based on these drawings without creative work.

[0027] Figure 1A is a schematic diagram showing a scenario of a human-computer dialogue according to an embodiment of the present disclosure;

[0028] Figure 1B is a schematic diagram showing a dialog interface at a user terminal according to an embodiment of the present disclosure;

[0029] Figure 2 is a schematic diagram of a human-computer dialogue interface in a dialogue mode according to an embodiment of the present disclosure;

[0030] Figure 3A-3D is a schematic diagram of a human-computer dialogue interface in an immersive reading mode according to an embodiment of the present disclosure;

[0031] Figure 4 is a flow chart showing a human-computer dialogue method according to an embodiment of the present disclosure;

[0032] Figure 5 is a schematic diagram of a human-machine dialogue device according to an embodiment of the present disclosure;

[0033] Figure 6 A schematic diagram showing a human-machine dialogue device according to an embodiment of the present disclosure; and

[0034] Figure 7 A schematic diagram illustrating the architecture of an exemplary computing device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present disclosure more obvious, the exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described here.

[0036] In this specification and the accompanying drawings, substantially the same or similar steps and elements are represented by the same or similar reference numerals, and repeated descriptions of these steps and elements will be omitted. At the same time, in the description of the present disclosure, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance or ranking.

[0037] In the embodiments of the present disclosure, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present disclosure pertains. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0039] To facilitate description of the present disclosure, concepts related to the present disclosure are introduced below.

[0040] The human-computer interaction method disclosed in the present invention may be based on artificial intelligence (AI). Artificial intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. By studying the design principles and implementation methods of various intelligent machines, artificial intelligence enables the human-computer dialogue method disclosed in the present invention to have the functions of asking and answering questions with users for reading documents, summarizing reading documents, locating the content in reading documents based on user prompt information, and saving user usage records to form a knowledge flywheel for reading documents.

[0041] The human-computer dialogue method disclosed in the present invention may be based on natural language processing (Natural Language Processing, NLP). Natural language processing is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that can achieve effective communication between humans and computers using natural language. Natural language processing is a science that integrates linguistics, computer science, and mathematics. Therefore, research in this field will involve natural language, that is, the language used by people in daily life, so it is closely related to the study of linguistics. Natural language processing technology generally includes text processing, semantic understanding, machine translation, robot question answering, knowledge graphs and other technologies.

[0042] The human-computer dialogue method disclosed in the present invention may be based on a large language model (LLM). A large language model is a language model in the field of NLP that is trained on a large amount of language corpus using an autoregressive method for analyzing and processing language texts, and is intended to understand and generate human language. The large language model is trained on a large amount of text data and can perform a wide range of tasks, including text summarization, translation, sentiment analysis, and the like. The large language model is characterized by its large scale, which may contain billions of parameters to help it learn complex patterns in language text data. Therefore, in the human-computer dialogue method disclosed in the present invention, the trained large language model can be applied to interactive information processing in human-computer dialogue interaction to provide efficient and accurate dialogue services, thereby improving the user experience.

[0043] "Knowledge flywheel" can refer to an efficient knowledge management system. Through this system, knowledge can be collected, organized, classified, shared and applied to promote knowledge innovation and value-added. This system helps users to quickly call relevant knowledge resources when facing complex problems, improve decision-making efficiency and problem-solving ability. According to the method disclosed in the present invention, user usage records can be saved, and a knowledge flywheel for reading documents can be further formed, which is convenient for users to review, search and summarize reading records.

[0044] In summary, the solutions provided by the embodiments of the present disclosure involve technologies such as artificial intelligence, natural language processing, and large language models. The embodiments of the present disclosure will be further described below in conjunction with the accompanying drawings.

[0045] Figure 1A It is a schematic diagram showing a scenario of human-computer dialogue according to an embodiment of the present disclosure. Figure 1B is a schematic diagram showing a dialog interface at a user terminal according to an embodiment of the present disclosure.

[0046] like Figure 1AAs shown, the user can send user input (for example, a request for obtaining information from the server, or a question from the user to the server) or upload a reading document to the server through the user terminal, so that the server can answer the user input. Subsequently, the server can return the generated machine answer information to the user terminal through the network. Optionally, the user terminal may specifically include a smart phone, a tablet computer, a laptop, a desktop computer, a vehicle terminal, a wearable device, etc., but is not limited to this. The user terminal can also be a client that installs a browser or various applications (including system applications and third-party applications). Optionally, the network can be an Internet of Things based on the Internet and / or telecommunications network, which can be a wired network or a wireless network. For example, it can be a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a cellular data communication network, etc., which can realize an electronic network that can realize an information exchange function. The user terminal and the server can be directly or indirectly connected by wired or wireless communication, and this application is not limited here. Optionally, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. Figure 1A In addition to the interactive scenarios shown, human-computer interaction can be implemented only on the user terminal side, and the present disclosure does not limit this. For example, a functional module for human-computer interaction can be deployed on the user terminal side, so that the user terminal can independently implement human-computer interaction without relying on the server.

[0047] The construction of intelligent assistants based on LLM is one of the important research directions in the field of AI and NLP. As an NLP model based on deep learning, LLM has a wide range of applications, including language generation, text classification, information retrieval, etc. At present, the intelligent assistant construction scheme based on LLM mainly involves inputting relevant knowledge during the LLM training process, training LLM through autoregressive tasks, so that it has the ability of intelligent question answering. In this scheme, LLM is regarded as a general intelligent model that can learn and simulate human language ability to achieve natural language understanding and generation. Therefore, the intelligent assistant construction scheme based on LLM has important research and application value, especially for intelligent assistants in specific fields (for example, document reading comprehension, law, medical care, customer service, etc.), which is currently a very promising application scheme.

[0048] As an example, in the field of document reading, AI-collaborative reading assistants, as a new type of reading tool, can assist users in reading through human-computer dialogue, thereby providing users with convenient and efficient reading services.

[0049] The above reading assistant has become a technology that has attracted much attention in the reading field. It can be used to understand the user's query and extract relevant reading document information, and output the corresponding answer. Figure 1B As shown, the user and the reading assistant can interact through text dialogue, and the reading assistant can answer the user's prompt information based on the prompt information extracted from the question-and-answer dialogue and the document information obtained from reading the document.

[0050] However, in Figure 1B During the interactive process of the reading assistant, after the user uploads a document and inputs prompt information such as "What is the main content of reading document 1?" for the document, only the reading assistant's answer to the prompt information for the reading document is received, and the basis of the reading assistant's answer in the reading document cannot be understood. This causes the user to be unable to trust the reading assistant's answer, which greatly reduces the user's willingness to continue the conversation or reading. In addition, during the conversation process of these reading assistants, it is often impossible to understand the original content of the reading document at the same time. This means that when the user receives the answer to the prompt information, the user cannot understand the reading assistant's answer with reference to the original content of the reading document and cannot provide further prompt information based on the original content, which greatly reduces the user's understanding of the reading assistant's answer and the user's willingness to continue the conversation or reading.

[0051] Therefore, in the present disclosure, it is hoped to provide a more accurate and convenient reading experience, wherein, when the user desires immersive reading, both human-computer dialogue and reading the original content of the document can be provided simultaneously, which will enable the user to easily and quickly understand the reading document, and more fully understand the answers to the human-computer dialogue.

[0052] Based on this, the present disclosure provides a human-computer dialogue method, which is applied to a human-computer dialogue program, and the method includes: selecting to read a document to enter a first mode, wherein in the first mode, the interface of the human-computer dialogue program includes a reading area and a dialogue area; displaying a portion of the content of the reading document through the reading area; obtaining prompt information through the dialogue area; and in response to obtaining the prompt information in the dialogue area, displaying a first portion of the content in the reading document associated with the prompt information in the reading area.

[0053] Figure 2 is a schematic diagram of a human-computer dialogue interface in a dialogue mode according to an embodiment of the present disclosure.

[0054] like Figure 2 As shown, Figure 2The human-computer dialogue interface in the embodiment may correspond to the second mode of the human-computer dialogue program. In the present disclosure, the human-computer dialogue program may also be referred to as a reading assistant. The second mode may be a dialogue mode. In the second mode, the user may input prompt information and upload a reading document in the input area 201. The input area 201 includes a sending identifier 202 for sending the prompt information or the reading document. The human-computer dialogue history may be displayed in the dialogue display area 210. Figure 2 As shown, the prompt message "What is the main content of Reading Document 1?" sent by the user is displayed in the user dialog box 203. In addition, Reading Document 1 and Reading Document 2 uploaded by the user may be displayed below the user dialog box 203. Those skilled in the art should understand that this is only an example, and Reading Documents 1-2 may also be displayed at other locations of the user dialog box 203, for example, above the user dialog box 203. In one embodiment, Reading Documents 1-2 may be uploaded at the same time. In another embodiment, Reading Document 1 may be uploaded this time, and Reading Document 2 may be uploaded previously. In the reading assistant dialog box 204, the reading assistant may answer the prompt message in the user dialog box 203.

[0055] The prompt message "What is the main content of reading document 3?" sent by the user is displayed in the user dialog box 205. In addition, the reading document 1, reading document 2, and reading document 3 uploaded by the user previously can be displayed below the user dialog box 205. In the reading assistant dialog box 206, the reading assistant can answer the prompt message in the user dialog box 205. Interactive options for the reading assistant's answer can be displayed below the reading assistant dialog boxes 204 and 206, such as but not limited to: copy, like, dislike, share, and regenerate.

[0056] like Figure 2 As shown, the human-computer dialogue program can receive one or more reading documents including reading documents 1-3 in the second mode. In response to receiving the reading documents 1-3, the received reading documents 1-3 can be displayed in the second mode in the form of an array. For example, Figure 2 As shown below the user dialog box 205, the icons of reading documents 1-3 can be displayed in a horizontal array. In addition, the user can upload more reading documents. In one embodiment, depending on the user operation, the icons of a portion of the uploaded reading documents can be folded and expanded. In another embodiment, depending on the user operation, the uploaded reading documents can be partially displayed, and the icons of other uploaded reading documents can be slid horizontally to browse.

[0057] A first mode may be entered for reading a document. The first mode may be an immersive reading mode. The specific details of the immersive reading mode will be described later. Figure 3A-3D Further description.

[0058] As a way to enter the first mode, an entry prompt to enter the first mode may be displayed for at least a portion of the one or more reading documents in the second mode. For example, depending on factors such as the format and content of the reading documents, among the uploaded reading documents 1-3, reading document 1 and reading document 3 may be reading documents that can enter the first mode, and reading document 2 may be a reading document that cannot enter the first mode. Figure 2 As shown, the entry to the first mode can be displayed for reading document 1 and reading document 3 ( Figure 2 In the box for entering the first mode), the entrance to the first mode may not be displayed for reading document 2. Figure 2 An embodiment of displaying the entrance to the first mode in a permanent display manner is shown in . In another embodiment, the entrance to the first mode can be displayed in a hover display manner. Hover display can mean that when a user hovers the cursor over an element (such as a button, link, icon, etc.), the element will give feedback in some way (such as changing color, displaying additional information, popping up a prompt box, etc.). For example, when the user hovers the cursor over reading documents 1 and 3, the file name and the entrance to the first mode can be displayed. When the user hovers the cursor over reading document 2, the file name can be displayed but the entrance to the first mode is not displayed. Alternatively or additionally, when the user hovers the cursor over reading document 2, the file name and other text content, such as "Open reader preview", etc., can be displayed.

[0059] As another way to enter the first mode, the first mode is entered through a reading document library of the human-computer dialogue program. For example, the reading document library may include reading documents imported by a user or searched on the Internet.

[0060] When the reading assistant is outputting answers to the prompt information sent by the user in the second mode, when the user chooses to enter the first mode, the reading assistant may not interrupt the output of the answers. In other words, the reading assistant may continue to stream the answers to the prompt information.

[0061] When the reading document is being uploaded, the user selects the reading document to enter the first mode, and can be prompted that the file is being uploaded. For example, the user can be prompted in the form of text "The file is being uploaded, please wait", and those skilled in the art can understand that other forms of prompting are also possible, and the present disclosure is not limited thereto.

[0062] The uploaded reading document may be very long. In this case, only a portion of the reading document may be parsed. For example, only the first 50% of the reading document may be parsed, and the user may be prompted in the form of text that "the file is a bit long, I only read the first 50%". When the human-computer dialogue program enters the first mode from the second mode, the text prompt may be retained.

[0063] The first time the reading document is received in the second mode and the human-computer dialogue history after the first time the reading document is received can be synchronously displayed in the first mode. Figure 3A-3D The process is further described.

[0064] The human-computer dialogue program can create a dialogue history for reading documents. For example, a user can upload one or more reading documents for the first time, and the human-computer dialogue program can create a dialogue history in response to the first uploaded reading document and generate a dialogue history icon including the uploaded reading document icon. When the user continues to upload reading documents in the dialogue history, the dialogue history icon can be updated based on the subsequently uploaded reading document icons. For example, the subsequently uploaded reading document icons can be added to the dialogue history icon. When the number of reading document icons included in the dialogue history icon exceeds a threshold number, a portion of the reading document icons in the dialogue history can be collapsed and expanded depending on the user operation; alternatively, a portion of the reading document icons in the dialogue history can be partially displayed depending on the user operation, and other reading document icons in the dialogue history can be swiped horizontally to browse. The user can delete one or more dialogue histories for reading documents. In addition, if the user creates a new dialogue in the first mode, a new dialogue history will be created.

[0065] Figure 3A It is a schematic diagram of a human-computer dialogue interface in an immersive reading mode according to an embodiment of the present disclosure.

[0066] Figure 3A The interface of the human-computer dialogue program in the first mode is shown. The first mode may be an immersive reading mode. The interface of the human-computer dialogue program in the first mode may include a reading area 310 and a dialogue area 320. The dialogue area 320 may include a dialogue display area 323 and an input area 322. Figure 3A The human-computer dialogue program interface shown in the figure can be used by users in Figure 2 Select Read Document 3 in the second mode and enter the first mode.

[0067] The reading area 310 may display a portion of the content of the reading document. Figure 3A As shown, the reading area 310 may include a title bar area 301 and a document content area 302. The title bar area 301 may display the name of the reading document and an identifier indicating exiting the immersive reading mode. Figure 3AIn the example, the name of the document is fully displayed. When the name of the reading document is too long, the title bar area 301 can display the first part of the name of the reading document and replace the last part of the name of the reading document with an ellipsis to indicate that the name of the reading document is omitted. Figure 3A In the figure, the identifier indicating exiting the immersive reading mode is a cross, but those skilled in the art will appreciate that other identifiers are also possible. The document content area 302 displays the title and table of contents of the reading document. In one embodiment, after the human-computer dialogue program enters the first mode for a reading document, the first page of the reading document can be displayed by default in the document content area 302, but the present disclosure is not limited to this. The alignment of the document can be an alignment such as left alignment and top alignment. When there are multiple pages in the document, there can be a fixed gap between pages.

[0068] The bottom of the reading area 310 can display the page number area 303. The page number area 303 can display the current page number page 1 and the total number of pages of the reading document 200 pages. In one embodiment, the page number area 303 can further display a button for turning pages up and a button for turning pages down. When the reading document is at the first page, the corresponding "previous page" button will be displayed differently (for example, set to gray), indicating that the current position does not support further turning pages up. When the reading document is at the last page, the corresponding "next page" button will be displayed differently (for example, set to gray), indicating that the current position does not support further turning pages down. In this way, users can be prevented from performing invalid operations. In addition, the page number can also be entered by the user to jump.

[0069] In one embodiment, the reading area 310 also includes a zoom area ( Figure 3A (not shown in the figure). In one embodiment, the page number area 303 may further display "zoom in" and "zoom out" buttons to allow the user to zoom in or out on the document page as needed. In one embodiment, a default zoom value may be set. For example, when entering a page, the system will automatically match the default zoom value for display, and the default zoom value is usually determined based on the document content and the screen size. When the user clicks the zoom in or zoom out button each time, the content of the reading text can be zoomed in or out in increments of 10% with the upper left corner of the current page as a fixed point. The zoom range may be limited to between 10% and 1000%, and those skilled in the art will appreciate that this value is only an example. When the maximum or minimum value of this interval is reached, the corresponding zoom in or zoom out button will be displayed differently (for example, set to gray), indicating that the current zoom level has reached the limit and cannot be further zoomed in or out. In this way, users can be prevented from performing invalid operations. After performing a zoom operation, when turning pages, the page can be displayed by aligning the upper left corner of the currently zoomed page to the upper left corner of the window by default.

[0070] When the length of a document exceeds the size of the document's reading area, a roller can be displayed on the left or right side of the document's text. Figure 3A As shown, a roller 305 can be displayed on the right side of the reading document text, and a positioning identifier 306 indicating the position of the current page in the document can be displayed. Similarly, when the width of the document exceeds the reading area size of the document, a roller can be displayed on the upper or lower side of the reading document text.

[0071] The zooming and page turning operations may be independent of other operations. For example, the zooming and page turning operations may not affect the use of other interactive functions, such as underlining and quoting of document content (described further below). For example, the marking operations such as underlining performed by the user before zooming or page turning will be retained and will not be lost due to the zooming or page turning operations. In addition, the zooming and page turning operations may not affect the interactive state of the dialogue area 320.

[0072] Can be in Figure 2 The reading document is received for the first time in the second mode and the human-computer dialogue history after the reading document is received for the first time is synchronously displayed in the first mode. For example, Figure 2 The reading document 1 and the reading document 2 in the user dialog box 203 may be sent together with the prompt information in the user dialog box 203. The reading document 1 and the reading document 2 may be the reading documents received by the reading assistant for the first time. When the user enters the first mode for reading 3, all the human-machine dialogue histories from the user dialog box 203 to the reading assistant dialog box 206 may be synchronized to Figure 3A In the first mode, the human-computer dialogue program interface is in the dialogue area 320. If the human-computer dialogue history is long, the human-computer dialogue history can be scrolled in the dialogue area 320 to display the bottom dialogue. If the reading assistant is outputting answers when entering the first mode, the output state can be maintained and synchronized to the first mode. For simplicity, Figure 3A The dialog area 320 is not displayed. Figure 2 The conversation history in .

[0073] like Figure 3AAs shown, when the user enters the first mode for reading documents, or when the user creates a new dialogue for reading documents in the first mode, reading document recommendation prompt information for reading documents can be displayed. For example, a recommendation bubble 321 including reading document recommendation prompt information can be displayed. After the user sends the prompt information for the first time through the input area 322 or selects the reading document recommendation prompt information in the recommendation bubble 321, the sent or selected prompt information and the answer of the reading assistant to the prompt information can be displayed in the dialogue area 320, and the recommendation bubble 321 can be eliminated. The recommendation bubble 321 can include general reading document recommendation prompt information, such as "sorting out keywords", "summarizing the outline", "summarizing the core ideas", etc., but the present disclosure is not limited to this. The recommendation bubble 321 can also include reading document recommendation prompt information for reading documents, such as "What is the ending of the little match girl?" and "Where was the ugly duckling born?", but the present disclosure is not limited to this. When the user selects one of the reading document recommendation prompt information, the reading document recommendation prompt information can be sent to the dialogue display area 323 in the form of a user dialog box. The reading assistant can answer the selected reading document recommendation prompt information. In the reading assistant dialog box ( Figure 3A (not shown in the figure) below, interactive options for the reading assistant's answers are displayed, such as but not limited to: copy, like, dislike, share, and regenerate.

[0074] like Figure 3A As shown, the reading assistant can identify the contents of the reading document including the directory, and execute the target link jump function. The target link jump function can mean that when the user selects (e.g., clicks) a directory area of ​​the reading document, the document content area 302 of the reading assistant can jump to the content corresponding to the directory area in the body of the reading document. In addition, the target link jump function can be independent of other operations. For example, the target link jump function may not affect the use of other interactive functions, such as underlining, quoting, etc. of the document content (described further below).

[0075] Specifically, in response to the cursor staying in the directory area in the reading document, the directory area where the cursor stays can be displayed differentially. For example, when the cursor 307 stays in the directory area including the content of "The Emperor's New Clothes", the directory area 308 can be highlighted to indicate that the area is the directory area.

[0076] In response to selecting the table of contents area in the reading document, the reading area can be jumped to the main text content corresponding to the table of contents area in the reading document. For example, in response to the user clicking the highlighted area 308 with the cursor, the reading document content displayed in the document content area 302 can be jumped to the chapter corresponding to "The Emperor's New Clothes". For example, the title of the chapter corresponding to "The Emperor's New Clothes" in the main text content can be displayed at the top of the reading area. If the title of the chapter corresponding to the table of contents area is on the last page, the document content area 302 can display the content of the last page of the reading document.

[0077] Additionally or alternatively, in response to selecting the table of contents area 308 in the reading document, recommendation prompt information for the table of contents area and the text content corresponding to the table of contents area may be displayed in the dialogue area 320. The recommendation prompt information may also appear in the form of a recommendation bubble, but the present disclosure is not limited thereto.

[0078] Figure 3B is a schematic diagram of another human-computer dialogue interface in the immersive reading mode according to an embodiment of the present disclosure.

[0079] like Figure 3A As shown in FIG. 3 , a prompt message including “What is the main content of The Little Mermaid?” can be input in the input area 322 and sent. In response to sending the prompt message, the interface of the human-computer dialogue program can be as follows: Figure 3B As shown. Figure 3B As shown, in response to obtaining the prompt information in the dialogue area 320 , the reading assistant's answer to the prompt information can be displayed in the dialogue area 320 .

[0080] Some of the prompt information input by the user through the input area 322 can be used to determine the content associated with the prompt information in the reading document. For example, in response to obtaining the prompt information in the dialogue area, the first part of the content associated with the prompt information in the reading document can be displayed in the reading area. For example, in response to obtaining the prompt information of "What is the main content of the daughter of the sea?" through the input area 322, the content associated with the prompt information in the reading document can be determined. For example, the content associated with the prompt information can include the content of "The daughter of the sea" in the directory area and the chapters of "The daughter of the sea" in the text area. Among the content associated with the prompt information, the first part of the content associated with the prompt information can be the highest degree of association with the prompt information. As an example only, among the content associated with the prompt information of "What is the main content of the daughter of the sea?", the content of the chapters of "The daughter of the sea" in the text area has a higher relevance than the content of "The daughter of the sea" in the directory area, so the content of the chapters of "The daughter of the sea" in the text area corresponds to the first part of the content. Others of the prompt information input by the user through the input area 322 may not be used to determine the content associated with the prompt information in the reading document.

[0081] In response to obtaining prompt information in the conversation area 320, when at least a portion of the first part of the content is not displayed in the reading area 310 and at least a portion of the reading area 310 displays content in the reading document other than the first part of the content, the content of the reading document is scrolled in the reading area 310 and a jump is made to the first part of the content to display more of the first part of the content in the reading area.

[0082] In one embodiment, Figure 3A As shown in the scenario, the content of the chapter "The Daughter of the Sea" in the body area as the first part of the content is not displayed in the reading area 310. In response to obtaining the prompt information "What is the main content of The Daughter of the Sea?" in the dialogue area 320, for example, the prompt information sent through the input area 322 can be scrolled in the reading area 310 to read the content of the document and jump to the first part of the content to Figure 3B As shown, the first portion of content is displayed in the reading area 310 .

[0083] exist Figure 3A In another embodiment not shown, before the user sends the prompt information through the input area, a part of the first part of the content may be displayed in the reading area and the reading document content that does not belong to the first part of the content may be displayed. In response to obtaining the prompt information in the dialogue area, the content of the reading document can be scrolled in the reading area and the first part of the content can be jumped to display more of the first part of the content in the reading area.

[0084] exist Figure 3AIn another embodiment not shown, before the user sends the prompt information through the input area, the reading area may display all of the first part of the content and display the reading document content that does not belong to the first part of the content. In response to obtaining the prompt information in the dialogue area, scrolling and jumping in the reading area may not be performed because the first part of the content has been displayed in its entirety in the reading area. In this case, jumping and scrolling cannot display more of the first part of the content.

[0085] exist Figure 3A In another embodiment not shown, before the user sends the prompt information through the input area, a portion of the first part of the content may be displayed in the reading area, and the reading document content that does not belong to the first part of the content is not displayed. In other words, the length of the first part of the content can be very long, and the reading area has already displayed the most of the first part of the content under the current zoom. In response to obtaining the prompt information in the dialogue area, scrolling and jumping in the reading area may not be performed. In this case, jumping and scrolling cannot display more of the first part of the content.

[0086] like Figure 3B As shown, in response to obtaining the prompt information in the dialogue area 320, the roller 305 in the reading area 310 includes a shaded area 309. The shaded area 309 shows the distribution of the content associated with the prompt information in the reading document. Figure 3B As shown, the current position of the document can be indicated by a positioning identifier. That is, the positioning identifier shows the position of the first part of the content in the reading document. In one embodiment, the first part of the content can be displayed differentially so that the user can distinguish the first part of the content from other contents of the reading document. In this way, the user can be encouraged to quickly browse the first part of the content.

[0087] Figure 3C is a schematic diagram of another human-computer dialogue interface in the immersive reading mode according to an embodiment of the present disclosure. Figure 3D A schematic diagram of another human-computer dialogue interface in the immersive reading mode according to an embodiment of the present disclosure.

[0088] like Figure 3C As shown, the user can perform manual underline selection. Specifically, the user can select the text content of the reading document by clicking the cursor and sliding. For example, the user can select the text "cornflower" by clicking the cursor and sliding from the "arrow" character of "cornflower" to the "chrysanthemum" character, and the reading assistant can display the "cornflower" text differentially. When the user clicks on other locations in the reading document content, the manually underlined selection of the text "cornflower" can be canceled. When the user clicks the cursor and slides to select another text in the reading document, the previously manually underlined selection of the text can be canceled.

[0089] In response to manually selecting text such as "cornflower", function area 311 may be further displayed. Function area 311 may include functions such as "quote", "summary", "translation", "copy", etc. After selecting any function in function area 311, the manual selection of text may be canceled. In one embodiment, multiple content types may be manually selected by stroke, such as text, tables, formulas, etc. In one embodiment, text may be manually selected by stroke across pages. For example, after selecting the bottom of document content area 302, the screen may be automatically scrolled downward to manually select continuous text of multiple pages at a time. In one embodiment, when manually selecting by stroke, unsupported content such as pictures may be automatically skipped. In one embodiment, when the manual stroke selection stops in the middle, the selected text may be displayed differentially and more text may be stopped from being selected.

[0090] exist Figure 3C In an embodiment not shown, when the cursor moves to the text content of the reading document, the reading assistant can automatically identify the smallest paragraph where the cursor is located and display the paragraphs differently. The reading assistant can identify the smallest paragraph unit by identifying elements such as line breaks, paragraph gaps, pictures, formulas, etc. in the text, but the present disclosure is not limited to this. When the user's cursor stays on the paragraph and clicks it, the paragraph can be selected and displayed similar to Figure 3C The function area 311 shown in FIG. When the cursor moves to another paragraph, the differential display state of the previous paragraph can be automatically exited, and the new paragraph can be differentially displayed. In addition, when the user performs a manual line selection operation in the current paragraph or other position, the differential display state of the current entire paragraph can be exited. After selecting any function in the function area, the differential display state of the text can be canceled.

[0091] Functions such as "reference", "summary", "translation", and "copy" that may be included in the function area 311 may be buttons. In one embodiment, when the user selects the "summary" function, the selected text and the prompt information "summary" may be directly displayed in the dialogue display area 323, and the answer of the reading assistant to the prompt information may be displayed. In one embodiment, when the user hovers the cursor over the "translation" function, the "Chinese to English" and "English to Chinese" buttons may be further displayed. In one embodiment, when the user selects the "Chinese to English" function, the selected text and the prompt information "Chinese to English" may be directly displayed in the dialogue display area 323, and the answer of the reading assistant to the prompt information may be displayed. When the selected text is very long, the selected text displayed in the dialogue area 320 may briefly display the selected text. For example, only a part of the selected text may be displayed, and the selected content that is not displayed may be replaced by an ellipsis to indicate omission. When the cursor hovers over the briefly displayed selected text, the complete selected content may be hovered to display. When the user selects the "copy" function, the selected text content may be copied to the clipboard.

[0092] When the reading assistant is outputting answers in the dialogue area 320, if a function such as "summary" or "translation" is selected, the selected text and the prompt information "summary" or "Chinese to English translation" and the answer of the reading assistant to the prompt information may not be directly displayed in the dialogue area 320. In this case, the user may be prompted that the above content cannot be directly displayed at present. For example, the text "dialogue in progress, please wait" may be displayed to the user.

[0093] like Figure 3C As shown, in response to selecting the "Quote" function for the manually marked "Cornflower" text, the "Cornflower" text can be displayed in the quote area 324 in the conversation area 320. As shown in FIG. 3 , the user can eliminate the quote area 324 in the conversation area 320 by clicking an identifier 325 indicating an exit from the quote state. In one embodiment, when a new conversation is created in the first mode, the quote area 324 in the conversation area 320 can be eliminated. In another embodiment, the quote area 324 in the conversation area 320 can be eliminated after the user deletes all the contents in the input area 323. In response to quoting new text, the text in the quote area 324 can be replaced with the newly quoted text.

[0094] In one embodiment, in response to the user selecting a text and selecting the "summary" function for the text, the selected text may be displayed in the reference area 324 and prompt information about the "summary" may be displayed in the input area 323. The prompt information may exemplarily include "summarize the above content in written form in detailed, specific, and popular language". In response to the user sending the above prompt information and the content in the reference area 324 to the dialogue display area 323, the reading assistant may answer both.

[0095] In one embodiment, in response to the user selecting a text and selecting the "Chinese to English" function for the text, the selected text may be displayed in the reference area 324 and prompt information about the "Chinese to English" translation may be displayed in the input area 323. In response to the user sending the prompt information and the content in the reference area 324 to the dialogue display area 323, the reading assistant may answer both.

[0096] Figure 3C In the example of FIG. 320 , a shorter text is quoted in the text “cornflower”, and the quoted text “cornflower” can be fully displayed in the quoted area 324. When quoting text exceeding a threshold length, the quoted text can be briefly displayed, for example, only a part of the quoted text can be displayed, and the undisplayed quoted content can be replaced with an ellipsis to indicate omission. When the cursor hovers over the briefly displayed quoted text, the complete quoted content can be hovered to display. Here, the length of the text can be measured in terms of the number of words or lines, but the present disclosure is not limited thereto.

[0097] like Figure 3C As shown, one or more reference text recommendation prompt information 326 for the referenced text "cornflower" can be displayed in the dialogue area 320. In one embodiment, in response to one of the one or more recommendation prompt information being selected, the referenced text, the selected recommendation prompt information, and the reading assistant's answer to the recommendation prompt information can be displayed in the dialogue display area 323, and the reference text recommendation prompt information 326 can continue to be displayed in the reference area 324.

[0098] like Figure 3C As shown, the user can enter prompt information for the quoted text in the input area 322. In one embodiment, as Figure 3D As shown, in response to the user sending the quoted text and prompt information for the quoted text to the dialog display area 323 by clicking the send identifier 327, the quoted text 328 and the prompt information 329 for the quoted text and the reading assistant's answer to the prompt information can be displayed in the dialog display area 323, and the prompt information entered in the quoted areas 324 and 322 can be removed.

[0099] Figure 3DIn the example, a shorter text is quoted in the text 328 "Cornflower", the quoted text 328 "Cornflower" can be fully displayed. When quoting text exceeding a threshold length, the quoted text can be briefly displayed, for example, only a portion of the quoted text can be displayed, and the undisplayed quoted content can be replaced with ellipsis to indicate omission. When the cursor hovers over the briefly displayed quoted text, the complete quoted content can be hovered and displayed. Here, the length of the text can be measured in terms of the number of words or lines, but the present disclosure is not limited thereto.

[0100] like Figure 3D After sending the quoted text and the prompt information for the quoted text, the user may browse other parts of the document in the reading area 310. In response to selecting the quoted text 328 in the conversation display area 323 in the conversation area, if at least a part of the quoted text 328 is not displayed in the reading area 310, the content of the document can be scrolled in the reading area 310 and jumped to the quoted content. For example, the reading area 310 can scroll and jump to display the quoted text "cornflower". In one embodiment, Figure 3D The reading area 310 in the image can be scrolled and jumped back to Figure 3B In another embodiment, the reading area 310 can scroll and jump to display the content corresponding to the reference content 328 in the center of the reading area 310.

[0101] When returning to the second mode from the first mode, the reading assistant can display the content displayed in the dialogue area in the first mode in the second mode. For example, the reading assistant can synchronize the content displayed in the dialogue area in the first mode to the dialogue display area in the second mode. In the first mode, the user can manually stop the reading assistant's answer while the reading assistant is outputting the answer. In response to the user manually stopping the reading assistant's answer, information that the user manually stopped answering can be displayed in the dialogue area in the first mode. When returning to the second mode from the first mode, the information that stopped answering can be synchronized to the dialogue display area in the second mode.

[0102] If no conversation was conducted in the first mode, after returning to the second mode from the first mode, the conversation display area may be displayed at the location of the conversation history before entering the first mode. If a conversation was conducted in the first mode, after returning to the second mode from the first mode, the conversation display area may scroll to the bottom of the conversation history in the first mode. If the user returns to the second mode from the first mode while the reading assistant is outputting answers in the first mode, the reading assistant may continue outputting and synchronize the output state to the second mode.

[0103] When entering the first mode from the second mode, other text input information in the input box in the second mode except for uploaded attachments such as reading documents or pictures can be synchronized to the first mode. When returning to the second mode from the first mode, the text information entered in the input box in the first mode can be synchronized to the second mode. Attachments such as reading documents or pictures can be uploaded in the input box in the second mode, and the first mode can be entered in this state. If no conversation is conducted in the first mode, the previously uploaded attachments in the input box are retained when returning to the second mode. If a conversation is conducted in the first mode, the previously uploaded attachments are cleared when returning to the second mode.

[0104] Figure 4 is a flow chart showing a human-computer dialogue method according to an embodiment of the present disclosure.

[0105] In S401, you can choose to read a document to enter a first mode, where the interface of the human-computer dialogue program in the first mode includes a reading area and a dialogue area.

[0106] At S402, a portion of the content of the reading document may be displayed in a reading area.

[0107] In S403, prompt information may be obtained through the dialog area.

[0108] In S404, in response to obtaining the prompt information in the conversation area, a first portion of the content associated with the prompt information in the reading document may be displayed in the reading area.

[0109] Figure 5 is a schematic diagram of a human-machine dialogue device according to an embodiment of the present disclosure.

[0110] like Figure 5 As shown, the human-machine dialogue device 500 may include a mode selection module 510 , a reading module 520 and a dialogue module 530 .

[0111] The mode selection module 510 may be configured to select reading a document to enter a first mode, wherein the interface of the human-computer dialogue program in the first mode includes a reading area and a dialogue area.

[0112] The reading module 520 may be configured to display a portion of the content of the reading document through the reading area in the first mode of the human-computer dialogue program.

[0113] The dialogue module 530 may be configured to receive prompt information through the dialogue area in the first mode of the human-machine dialogue program.

[0114] In response to the dialog module receiving the prompt information in the dialog area, the reading module is configured to display the first part of the content associated with the prompt information in the reading document in the reading area.

[0115] According to yet another aspect of the present disclosure, a human-computer dialogue device is also provided. Figure 6 A schematic diagram of a human-machine dialogue device 600 according to an embodiment of the present disclosure is shown.

[0116] like Figure 6 As shown, the human-machine dialogue device 600 may include one or more processors 610 and one or more memories 620. The memory 620 stores computer-readable codes, which, when executed by the one or more processors 610, may execute the human-machine dialogue method described above.

[0117] The processor in the embodiments of the present disclosure may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc., and may be an X86 architecture or an ARM architecture.

[0118] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0119] For example, the method or device according to the embodiment of the present disclosure may also be implemented by Figure 7 The architecture of the computing device 700 shown in FIG. Figure 7 As shown, the computing device 700 may include a bus 710, one or more CPUs 720, a read-only memory (ROM) 730, a random access memory (RAM) 740, a communication port 750 connected to a network, an input / output component 760, a hard disk 770, etc. The storage device in the computing device 700, such as the ROM 770 or the hard disk 770, may store various data or files used for processing and / or communication of the human-computer dialogue method provided by the present disclosure and program instructions executed by the CPU. The computing device 700 may also include a user interface 780. Of course, Figure 7The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 7 One or more components of a computing device are shown.

[0120] According to another aspect of the present disclosure, a computer-readable storage medium is also provided. Computer-readable instructions are stored on the computer storage medium. When the computer-readable instructions are executed by the processor, the human-computer dialogue method according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer-readable storage medium in the embodiment of the present disclosure can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of exemplary but not limiting description, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous connection dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM). It should be noted that memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory. It should be noted that memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0121] The embodiments of the present disclosure also provide a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the human-computer dialogue method according to the embodiments of the present disclosure.

[0122] Embodiments of the present disclosure provide a human-computer dialogue method, apparatus, device, and computer-readable storage medium.

[0123] The human-computer dialogue method provided by the embodiment of the present disclosure can coordinate users and artificial intelligence to promote users to read documents immersively. According to the method of the present disclosure, it is possible to enter the immersive reading mode based on the user's choice, and in the immersive reading mode, the user can ask and answer questions about the reading document, summarize the reading document, locate the content in the reading document based on the user's prompt information, and other operations. In addition, the method of the present disclosure can save user usage records and further form a knowledge flywheel for reading documents, thereby greatly improving the user experience.

[0124] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of the code contains at least one executable instruction for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0125] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0126] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. It should be understood by those skilled in the art that various modifications and combinations may be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. A human-computer dialogue method, applied to a human-computer dialogue program, the method include: Selecting to read the document to enter the first mode, wherein in the first mode the interface of the human-computer dialogue program includes a reading area and a dialogue area; Displaying a portion of the content of the reading document through the reading area; Obtaining prompt information through the dialogue area; and In response to obtaining the prompt information in the conversation area, a first portion of the content associated with the prompt information in the reading document is displayed in the reading area.

2. The method according to claim 1, further comprising: include: In response to obtaining prompt information in the conversation area, when at least a portion of the first part of the content is not displayed in the reading area and at least a portion of the reading area displays content in the reading document other than the first part of the content, the content of the reading document is scrolled in the reading area and a jump is made to the first part of the content to display more of the first part of the content in the reading area.

3. The method according to claim 1, further comprising: include: In response to obtaining prompt information in the dialog area, a response to the prompt information is displayed in the dialog area.

4. The method according to claim 1, further comprising: include: In response to obtaining the prompt information in the dialog area, displaying the distribution of the content associated with the prompt information in the reading document in the strip-shaped sub-area in the reading area, and using a positioning identifier to indicate the position of the first part of the content in the reading document, Among the contents associated with the prompt information, the first part of the contents has the highest degree of association with the prompt information.

5. The method according to claim 1, further comprising: include: In response to a second portion of the content of the reading document in the reading area being quoted, displaying the second portion of the content in the first sub-area in the conversation area, displaying one or more recommendation prompt information for the second part of content in the conversation area, In response to one of the one or more recommendation prompt information being selected, the second portion of content, the selected recommendation prompt information, and an answer to the recommendation prompt information are displayed in a second sub-area in the conversation area.

6. The method according to claim 5, further comprising: include: receiving prompt information for the second part of the content in a third sub-area of ​​the conversation area, In response to selecting to send the second portion of the content and the prompt information for the second portion of the content to the second sub-area, the second portion of the content, the prompt information, and an answer to the prompt information are displayed in the second sub-area of ​​the dialog area.

7. The method according to claim 5 or 6, further comprising: include: In response to selecting the second portion of content in the second sub-area of ​​the conversation area, if at least a portion of the second portion of content is not displayed in the reading area, scrolling the content of the reading document in the reading area and jumping to the second portion of content.

8. The method according to claim 7, in, Scrolling the content of the reading document in the reading area and jumping to the second part of the content includes: The second part of content is displayed in the center of the reading area.

9. The method according to claim 1, further comprising: include: Conducting a human-computer dialogue in the second mode and receiving one or more documents including the reading document, In response to the click on the reading document to enter the first mode, the first reception of the reading document in the second mode and the human-computer dialogue history after the first reception of the reading document are synchronously displayed in the dialogue area in the first mode.

10. The method according to claim 9, in, Receiving the reading document in the second mode includes receiving one or more reading documents, In response to receiving one or more reading documents, displaying the received one or more reading documents in the form of an array in the second mode, In the second mode, an entry prompt for entering the first mode is displayed for at least a portion of the one or more reading documents.

11. The method according to claim 1, further comprising: include: In response to a cursor being placed in a directory area in the reading document, differentially displaying the directory area where the cursor is placed, In response to selecting the directory area in the reading document, the reading area is jumped to the main text content corresponding to the directory area in the reading document.

12. The method according to claim 11, in, Jumping the reading area to the text content corresponding to the directory area in the reading document includes: The title corresponding to the directory area in the main text content is displayed at the top of the reading area.

13. The method according to claim 11, further comprising: include: In response to selecting the table of contents area in the reading document, recommendation prompt information for the table of contents area and the main text content corresponding to the table of contents area is displayed in the dialog area.

14. The method according to claim 1, further comprising: include: In response to entering the first mode, one or more recommendation prompt information for the reading document is displayed in a fourth sub-area of ​​the conversation area.

15. The method according to claim 14, further comprising: include: In response to selecting one of the one or more recommendation prompt information for the reading document, the selected recommendation prompt information and an answer to the selected recommendation prompt information are displayed in the dialogue area, and a fourth sub-area displaying the one or more recommendation prompt information for the reading document is eliminated.

16. The method according to claim 14, further comprising: include: In response to receiving prompt information in the third sub-area of ​​the conversation area and sending the prompt information to the second sub-area of ​​the conversation area, the prompt information and an answer to the prompt information are displayed in the conversation area, and the fourth sub-area displaying one or more recommended prompt information for the reading document is eliminated.

17. The method according to claim 9, further comprising: include: In response to returning from the first mode to the second mode, the content displayed in the conversation area in the first mode is displayed in the second mode.

18. A human-computer dialogue device, configured to execute a human-computer dialogue program, the device include: A mode selection module, which selects to read a document to enter a first mode, wherein in the first mode the interface of the human-computer dialogue program includes a reading area and a dialogue area; a reading module configured to display a portion of the content of the reading document through the reading area in the first mode of the human-computer dialogue program; and a dialogue module configured to receive prompt information through the dialogue area in a first mode of the human-computer dialogue program, wherein the prompt information is used to determine content associated with the prompt information in the reading document; and In response to the dialogue module receiving the prompt information in the dialogue area, the reading module is configured to display a first portion of the content associated with the prompt information in the reading document in the reading area.

19. A human-computer dialogue device, include: one or more processors; as well as One or more memories, wherein a computer executable program is stored, and when the computer executable program is executed by the processor, the method of any one of claims 1-17 is performed.

20. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the instructions are used to implement the method according to any one of claims 1 to 17 when executed by a processor.

Images