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 the content of the reading document in the reading area; obtaining first prompt information in the dialogue area, wherein the first prompt information is used for generating a mind map of at least one part of content of the read document; and in response to first prompt information obtained in the dialogue area, generating and displaying a mind map for at least one part of content in the read document in the dialogue area.

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 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 the content of the reading document in the reading area; obtaining first prompt information in the dialogue area, the first prompt information being used to generate a mind map of at least a portion of the content of the reading document; and generating and displaying a mind map for at least a portion of the content in the reading document in the dialogue area in response to the first prompt information obtained in the dialogue area.

[0006] The method according to an embodiment of the present disclosure further includes: in response to a selection operation on a component element in the mind map in the conversation area, displaying content corresponding to the selected component element in the reading document in the reading area.

[0007] According to the method of an embodiment of the present disclosure, it also includes: in response to a selection operation on a component element of the mind map in the conversation area, scrolling the content of the reading document in the reading area and jumping to the content corresponding to the selected component element in the reading document.

[0008] According to the method of an embodiment of the present disclosure, it also includes: in response to a selection operation on a component element of the mind map in the conversation area, the content corresponding to the selected component element in the reading document and other content of the reading document in the reading area are displayed differentially in the reading area.

[0009] According to the method of an embodiment of the present disclosure, the method further includes: in response to entering the first mode, displaying one or more recommendation prompt information for the reading document in a first sub-area of ​​the conversation area, wherein the one or more recommendation prompt information include the first prompt information.

[0010] According to the method of an embodiment of the present disclosure, obtaining the first prompt information in the dialogue area specifically includes: receiving the first prompt information in a user input area of ​​the dialogue area.

[0011] According to the method of an embodiment of the present disclosure, displaying a mind map for at least a portion of the content in the reading document in the conversation area includes displaying the mind map in a mind map window, wherein the size of the mind map is related to the size of the mind map window, and the mind map is completely displayed in the mind map window, and wherein the mind map window includes a title area and a function area.

[0012] According to the method of an embodiment of the present disclosure, the title area includes the content of the root node of the mind map, and the function area includes one or more of a download indicator, a copy indicator, and a zoom-in view indicator.

[0013] According to the method of an embodiment of the present disclosure, wherein the size of the mind map window is related to the size of the conversation area, the method further comprises: in response to the size of the conversation area being adjusted, adjusting the size of the mind map window and the size of the mind map.

[0014] According to a method of an embodiment of the present disclosure, wherein the human-computer dialogue program runs on a first device, the method further includes: in response to selecting a zoom view indicator, enlarging the mind map window, wherein the enlarged mind map window covers at least a portion of at least one of the reading area and the dialogue area, or wherein the human-computer dialogue program runs on a second device, and the mind map window is displayed in the dialogue area in a first direction, the method further includes: in response to selecting a zoom view indicator, enlarging the mind map window, wherein the enlarged mind map window occupies the entire interface of the human-computer dialogue program and the enlarged mind map window is displayed on the interface of the human-computer dialogue program in a second direction.

[0015] According to the method of an embodiment of the present disclosure, the method further includes scaling the mind map in the mind map window and maintaining the scaled state of the mind map in the mind map window.

[0016] According to the method of an embodiment of the present disclosure, it also includes clearing the zoom state in response to one or more of the following: selecting the zoom viewing indicator and closing the enlarged mind map window, sharing the current human-computer dialogue content, the human-computer dialogue program entering the second mode from the first mode, switching from the current human-computer dialogue to another human-computer dialogue, and answering the content with the mind map again.

[0017] The method according to an embodiment of the present disclosure further includes sharing the mind map in the form of a poster or a web page developed based on HTML5 technology.

[0018] The method according to an embodiment of the present disclosure further includes: in response to selecting to copy the mind map, copying the text in the Markdown format corresponding to the mind map.

[0019] According to the method of an embodiment of the present disclosure, the method further includes editing the mind map in the interface of the human-computer dialogue program in response to an editing trigger operation on the mind map.

[0020] According to the method of an embodiment of the present disclosure, editing the mind map in the interface of the human-computer dialogue program includes: adjusting the hierarchical structure of the mind map, adjusting the sequential relationship of the constituent elements in the hierarchy of the mind map, and editing at least one of the text contents in the constituent elements of the mind map.

[0021] According to the method of an embodiment of the present disclosure, it also includes: in response to an editing trigger operation on the mind map, displaying the text in the Markdown format corresponding to the mind map in the interface of the human-computer dialogue program, and editing the mind map by modifying the text in the Markdown format corresponding to the mind map in the interface of the human-computer dialogue program.

[0022] An embodiment of the present disclosure provides a human-computer dialogue method, which is applied to a human-computer dialogue program based on a large language model. The method includes: receiving a reading document in a dialogue area in an interface of the human-computer dialogue program; in response to receiving the reading document, displaying one or more recommendation prompt information for the reading document in the dialogue area, wherein the one or more recommendation prompt information include first prompt information, and the first prompt information is used to generate a mind map of at least a portion of the content of the reading document; in response to selecting the first prompt information in the one or more recommendation prompt information, displaying a mind map for at least a portion of the content in the reading document in the dialogue area.

[0023] 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, configured to select a reading 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, configured to display the content of the reading document in the reading area in the first mode of the human-computer dialogue program; and a dialogue module, configured to obtain first prompt information in the dialogue area in the first mode of the human-computer dialogue program, the first prompt information being used to generate a mind map of at least a portion of the content of the reading document; and wherein, in response to the first prompt information obtained by the dialogue module in the dialogue area, the dialogue module is configured to generate and display a mind map for at least a portion of the content in the reading document in the dialogue area.

[0024] An embodiment of the present disclosure provides a human-computer dialogue device, including one or more processors; and one or more memories, in which a computer executable program is stored. When the computer executable program is executed by the processor, the above method is executed.

[0025] 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.

[0026] The human-computer dialogue method provided by the embodiment of the present disclosure can collaborate with users and artificial intelligence, and promote users to immerse themselves in reading documents by providing users with mind maps for reading documents. The method according to the present disclosure can enter the immersive reading mode based on the user's choice, and in the immersive reading mode, ask and answer questions with the user about the reading document, generate a mind map for the content of the reading document, and locate the content in the reading document in response to the user's selection of the unit text content in the mind map. In addition, the method according to 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

[0027] 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.

[0028] Figure 1A is a schematic diagram showing a scenario of a human-computer dialogue according to an embodiment of the present disclosure;

[0029] Figure 1B is a schematic diagram showing a dialog interface at a user terminal according to an embodiment of the present disclosure;

[0030] Figure 2A-2B is a schematic diagram of a human-computer dialogue interface in a dialogue mode according to an embodiment of the present disclosure;

[0031] 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;

[0032] Figure 3E It is a schematic diagram of the principle of generating a mind map through a human-computer dialogue program according to an embodiment of the present disclosure;

[0033] Figure 4A-4B is a flow chart showing a human-computer dialogue method according to an embodiment of the present disclosure;

[0034] Figure 5 is a schematic diagram of a human-machine dialogue device according to an embodiment of the present disclosure;

[0035] Figure 6 A schematic diagram showing a human-machine dialogue device according to an embodiment of the present disclosure; and

[0036] Figure 7 A schematic diagram illustrating the architecture of an exemplary computing device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] To facilitate description of the present disclosure, concepts related to the present disclosure are introduced below.

[0042] 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.

[0043] 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.

[0044] 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 can 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 user experience. Traditional information retrieval models are usually based on keyword matching and indexing technology, and the limitation of this method is that it cannot understand the semantic information and context of the text. The large language model can understand the deep semantic information of the text, and can better match the user's query intent, thereby improving the accuracy and efficiency of information retrieval.

[0045] "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.

[0046] Mind Map is an effective graphic thinking tool for expressing divergent thinking. It is simple, efficient and a practical thinking tool. Mind Map uses the technique of giving equal importance to pictures and texts to express the relationship between themes at all levels with mutually subordinate and related hierarchical diagrams, and establish memory links between theme keywords and images, colors, etc. Mind Map makes full use of the functions of the left and right brains, and uses the laws of memory, reading and thinking to help people develop a balanced development between science and art, logic and imagination, thereby unlocking the infinite potential of the human brain. Mind Map therefore has the powerful function of human thinking. Mind Map is also called Brain Map, Mind Map, Brainstorming Map, Inspiration Triggering Map, Concept Map, Tree Map, Branch Map or Thinking Map. Mind Map can include various components. For example, the components can include text, graphics (e.g., lines, boxes, etc.) and other elements that make up the mind map.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] The above-mentioned 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.

[0053] However, in Figure 1B In the interactive process with the reading assistant, after the user uploads a document and inputs prompt information for the document, such as "What is the main content of reading document 1?", the user only receives the reading assistant's answer to the prompt information for the reading document, but cannot understand the basis of the reading assistant's answer in the reading document. This causes the user to be unable to trust the reading assistant's answer, greatly reducing 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 by referring 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. In addition, in the case of Figure 1B In the above-mentioned interaction process with the reading assistant, the reading assistant's answers are pure text content, which cannot provide the user with a graphical representation of thinking, such as a mind map, thereby reducing the user's satisfaction with the immersive reading experience.

[0054] Therefore, in the present disclosure, it is hoped to provide a more accurate and convenient reading experience, wherein a mind map of the content of the reading document can be provided when the user desires immersive reading, which will enable the user to easily and quickly understand the reading document and make more full use of the answers to the human-computer dialogue.

[0055] 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 the content of the reading document in the reading area; obtaining first prompt information in the dialogue area, the first prompt information being used to generate a mind map of at least a portion of the content of the reading document; and generating and displaying a mind map for at least a portion of the content in the reading document in the dialogue area in response to the first prompt information obtained in the dialogue area.

[0056] Figure 2A is a schematic diagram of a human-computer dialogue interface in a dialogue mode according to an embodiment of the present disclosure.

[0057] The human-computer dialogue program may include a first mode and a second mode. The first mode may correspond to an immersive reading mode, and the second mode may correspond to a dialogue mode. The human-computer dialogue program may switch between the first mode and the second mode.

[0058] like Figure 2A As shown, Figure 2A The human-computer dialogue interface in the second mode 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. In the second mode, the human-computer dialogue interface may include a dialogue area. The dialogue area may include an input area 201 and a dialogue display area 210. 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 dialogue display area 210 may display the human-computer dialogue history.

[0059] like Figure 2A As shown, the user can upload "Read Document 1" in the input area 201. Accordingly, in response to receiving the reading document, the reading assistant can display one or more recommended prompt information 203 for "Read Document 1" in the input area 201. For example, one or more recommended prompt information 203 may include prompt information for generating a mind map of at least a portion of the content of the reading document, and prompt information for translating at least a portion of the content of the reading document. In response to the user selecting the prompt information for generating a mind map, the reading assistant can display a mind map for at least a portion of the content in the reading document in the dialogue area, such as in the dialogue display area 210. In response to the user selecting the prompt information for translation, the reading assistant can display a translation for at least a portion of the content in the reading document in the dialogue area, such as in the dialogue display area 210. Although Figure 2A The one or more recommended prompt information 203 is shown as including two prompt information, but the one or more recommended prompt information 203 can include more or less prompt information according to user needs. In addition, the user can also input prompt information for generating a mind map in the input area 201 .

[0060] Figure 2B is a schematic diagram of another human-computer dialogue interface in a dialogue mode according to an embodiment of the present disclosure.

[0061] like Figure 2BAs shown, the reading document 1 uploaded by the user can be displayed below the user dialog box 207. Those skilled in the art should understand that this is only an example, and the reading document 1 can also be displayed at other locations of the user dialog box 207, for example, above the user dialog box 207. In one embodiment, the reading document 2 and the reading document 3 can be uploaded at the same time. In another embodiment, the reading document 2 and the reading document 3 can be uploaded separately. In the reading assistant dialog box 204, the reading assistant can answer the prompt information in the user dialog box 207.

[0062] exist Figure 2A In the example, the user can select one or more of the recommended prompt information 203, namely, "generate a mind map". Figure 2B As shown, the selected prompt information of "generate mind map" can be displayed in the user dialog box 207 in the dialogue display area 210. In response to the prompt information of the user selecting to generate a mind map, the reading assistant can display a mind map for at least a part of the content in "read document 1" in the reading assistant dialog box 204 in the dialogue display area 210. By generating and displaying a mind map, the reading assistant can convey the idea of ​​reading the document more quickly and clearly, making it easier for the user to understand the content to be conveyed by the reading document.

[0063] In addition, 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 previously uploaded by the user (for example, in Figure 2A ), and the reading document 2 and reading document 3 uploaded this time. In the reading assistant dialog box 206, the reading assistant can answer the prompt information 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.

[0064] like Figure 2B 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 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, as shown below the user dialog box 205 in Figure 2, 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.

[0065] A first mode may be entered for reading a document. The first mode may correspond to an immersive reading mode. The specific details of the immersive reading mode will be referred to later. Figure 3A-3D Further description.

[0066] 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 2B As shown, the entry to the first mode can be displayed for reading document 1 and reading document 3 ( Figure 2B , a box for entering the first mode), the entrance to the first mode may not be displayed for reading document 2. FIG. 2 shows an embodiment of displaying the entrance to the first mode in a permanent display. In another embodiment, the entrance to the first mode may be displayed by hovering display. Hover display may 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 may be displayed. When the user hovers the cursor over reading document 2, the file name may be displayed but the entrance to the first mode may not be displayed. Alternatively or additionally, when the user hovers the cursor over reading document 2, the file name and other text content may be displayed, such as "Open reader preview".

[0067] 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.

[0068] 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.

[0069] 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.

[0070] Figure 3AThe interface of the human-computer dialogue program in the first mode is shown. The first mode may correspond to 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 FIG. 2 may be presented after the user selects to read the document 3 in the second mode to enter the first mode.

[0071] The reading area 310 may display the content of the reading document. For example, the reading area 310 may display the entire content of the reading document or 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 3A In 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.

[0072] 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.

[0073] 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.

[0074] When the length of the 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.

[0075] Can be in Figure 2A and Figure 2B 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 2B The reading document 1 in the user dialog box 207 may be sent together with the prompt information in the user dialog box 207. The reading document 1 may be the reading document received by the reading assistant for the first time. When the user enters the first mode for reading document 3, all human-machine dialogue histories from the user dialog box 207 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 2B The conversation history in .

[0076] Users can trigger the reading assistant to generate a mind map by selecting recommended reading document prompts or entering prompts in the input area.

[0077] like Figure 3A As shown, when the user enters the first mode for reading the document, or when the user creates a new conversation for reading the document in the first mode, reading document recommendation prompt information for reading the document 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 reading assistant's answer to the prompt information can be displayed in the conversation area 320, and the recommendation bubble 321 can be eliminated. The recommendation bubble 321 can include general reading document recommendation prompt information, such as "generate a mind map", "summarize an outline", "summarize the core ideas", etc., but the present disclosure is not limited to this. Figure 3A The reading document recommendation prompt information "Generate mind map" shown in FIG. 3 may indicate generating a mind map for the entire reading document 3. In another embodiment, Figure 3A The document reading recommendation prompt information shown in may indicate generating a mind map of a portion of the content of the document being read.

[0078] The recommendation bubble 321 may also include reading document recommendation prompt information for the reading document, for example, "What is the ending of the little match girl?" and "Where was the ugly duckling born?", but the present disclosure is not limited thereto. When the user selects one of the reading document recommendation prompt information, the reading document recommendation prompt information may be sent to the dialogue display area 323 in the form of a user dialog box. The reading assistant may answer the selected reading document recommendation prompt information. The answer may be displayed 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.

[0079] In addition, if Figure 3A As shown, a prompt message including "generate a mind map" can be input in the input area 322, and the prompt message can be sent to the dialogue display area 323. In immersive mode, the reading assistant can detect whether the information input by the user through the input area 322 hits the keyword that triggers the generation of a mind map. If the keyword is hit, the reading assistant can generate and display a mind map. Exemplarily, keywords may include "mind map", "generate outline", "brain map" and the like, but the present disclosure is not limited thereto. In addition, it is possible to identify whether the user intends to generate a mind map or to identify whether providing a mind map is more helpful for the user to understand the reading document based on algorithms such as semantic recognition or intent recognition.

[0080] 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.

[0081] like Figure 3A As shown, the user can input prompt information including "generate a mind map" in the input area 322 and send the prompt information. Alternatively, the user can select the reading document recommendation prompt information of "generate a mind map". In response to the user selecting or sending the prompt information in the dialogue area 320 to generate the prompt information of the mind map of the reading document, the interface of the human-computer dialogue program can be as follows: Figure 3B shown.

[0082] like Figure 3B As shown, in response to the prompt information of obtaining the mind map of the reading document in the dialogue area 320, the reading assistant can generate and display the mind map for at least a part of the content in the reading document in the dialogue area 320, such as in the mind map window 324. When generating and displaying the mind map, it can be presented in the mind map window 324 in stages and streams, and can be accompanied by corresponding positioning prompts in the process of outputting the mind map. For example, when generating and displaying the mind map, a progressive visual effect of fading in and out can be adopted to increase the overall sense of flow. The size of the mind map can be related to the size of the mind map window 324, and the mind map can be fully displayed in the mind map window 324. For example, after the streaming output is completed, the mind map can be re-rendered to adapt the size of the mind map window 324. The mind map can be appropriately scaled to fill the mind map field of view 324 as much as possible, and the mind map can be displayed in the center of the mind map field of view 324.

[0083] The size of the mind map window 324 may be related to the size of the conversation area 320. For example, the size of the mind map window 324 may be adapted to the size of the conversation display area 323 of the conversation area 320. In response to the size of the conversation area 320 being adjusted, the size of the mind map window 324 and the size of the mind map may be adjusted accordingly. For example, when the user adjusts the size of the conversation area 320 by dragging, the mind map window 324 may be dynamically adjusted in combination with the width of the adjusted conversation area 320, and the content of the mind map may be scaled in real time to adapt to the width of the adjusted mind map window 324.

[0084] The mind map window 324 may include a title area 327 and a function area 326. The title area 327 may include the content of the root node of the mind map. For example, the title area 327 may include the content of "Andersen's Fairy Tales" included in the root node of the mind map.

[0085] Function area 326 may include one or more of a copy indicator, a download indicator, and an enlarged view indicator arranged sequentially from left to right. Those skilled in the art will appreciate that function area 326 may include more or fewer indicators, and these indicators may be arranged in different orders.

[0086] For example, the function area 326 may also include a share indicator ( Figure 3B (not shown). In one embodiment, in response to the sharing indicator being selected, the reading assistant can share the mind map in the form of a poster. By reading the poster, the user who shared the poster can view the restored mind map. In another embodiment, in response to the sharing indicator being selected, the reading assistant can share the mind map in the form of a web page developed based on HTML5 technology. The sharing method of web pages developed based on HTML5 technology can also be called h5 method. When viewing a mind map shared in h5 mode through a mobile terminal (for example, a mobile phone), a conversation area 320 including a mind map window 324 can be viewed, and the zoom viewing identifier in the function area 326 is shielded, and the copy identifier and download identifier can be viewed and selected. The user can zoom in and out (for example, through a two-finger operation) on the screen of the mobile terminal, and drag to view the mind map. When viewing a mind map shared in h5 mode through a personal computer (e.g., a desktop computer, a laptop computer, a tablet computer, etc.), a conversation area 320 including a mind map window 324 can be viewed, and the zoom viewing identifier in the function area 326 is shielded, and the copy identifier and the download identifier can be viewed and selected. The user can zoom in and out to view the mind map on the screen of the personal computer. Interaction with the reading assistant can be performed in the conversation area 320 obtained by viewing the shared mind map on the personal computer.

[0087] For example, the function area 326 may also include an edit indicator. The user can edit the mind map by selecting the edit indicator. It should be understood by those skilled in the art that the edit trigger operation that triggers the editing of the mind map is not limited to this, for example, the edit operation can be triggered by quickly double-clicking the mind map, etc. In one embodiment, in response to the edit trigger operation of the mind map, the user can edit the mind map in the interface of the man-machine dialogue program. For example, the hierarchical structure of the mind map can be adjusted by operating the constituent elements of the mind map in the dialogue area or in other areas of the interface of the man-machine dialogue program, the sequential relationship of the constituent elements in the hierarchy of the mind map can be adjusted, and at least one of the text content in the constituent elements of the mind map can be edited. In another embodiment, in response to the edit trigger operation of the mind map, the user can display the text in the Markdown format corresponding to the mind map in the interface of the man-machine dialogue program, and edit the mind map by modifying the text in the Markdown format corresponding to the mind map in the interface of the man-machine dialogue program. The text in the Markdown format can be displayed and edited in the dialogue area or in a separate edit window.

[0088] The user can use the mouse and keyboard or other peripheral components to Figure 3B The mind map window 324 of the present invention can be used to zoom the mind map. For example, the zoom ratio of zooming the mind map in the mind map window 324 can be between 10% and 500%. When the zoom ratio exceeds the minimum value or the maximum value (for example, less than the minimum value or greater than the maximum value), it can no longer be further zoomed in response to the user operation. A threshold zoom value can be set to display a scroll bar. When the zoomed mind map is greater than the threshold zoom value, a scroll bar can be displayed on the right and bottom of the mind map window 324. The user can view different parts of the mind map in the mind map window 324 by dragging and sliding the mind map.

[0089] In a dialogue with the reading assistant, the zoom state of the last zoom in the mind map window 324 will be maintained. The maintained zoom state can be cleared in response to the following operations: select the zoom view indicator and close the enlarged mind map window (refer to Figure 3C further described); sharing the current human-computer dialogue content; the human-computer dialogue program enters the second mode from the first mode (for example, the human-computer dialogue program exits the immersive reading mode); switching from the current human-computer dialogue to another human-computer dialogue and switching from another human-computer dialogue back to the current human-computer dialogue; and the reading assistant answers the content with the mind map again.

[0090] When the mind map is not completely output, all indicators in the functional area 326 may not be selected. For example, all indicators in the functional area 326 may be set to gray to prompt the user that they cannot be selected. After the mind map is completely output, the indicators in the functional area 326 may be selected. For example, all indicators in the functional area 326 may be canceled and set to gray to prompt the user that they can make a selection. When the mind map is not completely generated and displayed, and the user chooses to stop the answer operation of the reading assistant, the generated part may be displayed in the mind map window 324, and the indicator in the functional area 326 may not be selected. When the mind map is completely generated and displayed, and the user chooses to stop the answer operation of the reading assistant, the generated mind map may be completely displayed in the mind map window 324, and the indicator in the functional area 326 may be selected. When the reading assistant fails to generate a mind map, the mind map and the mind map window 324 may not be displayed, and the answer in text form may be output.

[0091] In response to the user copying the mind map by selecting the copy indicator, the reading assistant can copy the text in Markdown format corresponding to the mind map. Markdown is a lightweight markup language that allows people to write documents in a plain text format that is easy to read and write. Through simple tag syntax, Markdown can give ordinary text content a formatted appearance without complex typesetting operations. In this way, the user can be allowed to apply the mind map generated by the reading assistant to other applications that use the Markdown format language. In response to the user downloading the mind map by selecting the download indicator, the reading assistant can download the image including the mind map to the user's local. In response to the user enlarging the mind map by selecting the zoom view indicator, the reading assistant can present the enlarged mind map to the user.

[0092] For example, in response to a user Figure 3B By selecting the zoom view indicator, you can zoom in on the mind map. Figure 3C As shown, an enlarged mind map window 328 is presented to the user. 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 3C Zhongyu Figure 3B Similar elements will not be described repeatedly.

[0093] Figure 3CThe human-computer dialogue program in can be run on the first device. The first device can be a personal computer terminal including, for example, a desktop computer, a laptop computer, a tablet computer, etc. The enlarged mind map window 328 can cover at least a portion of at least one of the reading area 310 and the dialogue area 320. The upper right corner of the enlarged mind map window 328 may include an exit identifier indicating that the enlarged mind map window 328 can be exited by selecting it. When switching to displaying the mind map through the enlarged mind map window 328, a loading effect (for example, a progressive visual effect) can be added. The mind map can adapt to the size of the enlarged mind map window 328, and the mind map can be displayed in the center of the enlarged mind map window 328.

[0094] The enlarged mind map window 328 may include a zoom function area 329. The zoom ratio of the mind map may be adjusted by operating the indicator in the zoom function area 329. For example, the mind map may be enlarged by selecting the "+" indicator, the mind map may be reduced by selecting the "-" indicator, and the mind map may be enlarged by inputting a specific zoom ratio. A threshold zoom value may be set to display a scroll bar. When the zoomed mind map is greater than the threshold zoom value, a scroll bar may be displayed on the right and bottom of the enlarged mind map window 328. The user may view different parts of the mind map in the enlarged mind map window 328 by dragging and sliding the mind map.

[0095] The enlarged mind map window 328 may also include an adapt window indicator ( Figure 3C For example, by selecting the adapt window indicator, the zoom ratio of the mind map can be adaptively adjusted according to the screen parameters (e.g., screen model and screen size). In the process of adaptively adjusting the zoom ratio of the mind map, the collapsed or expanded state of the branches in the mind map does not change.

[0096] exist Figure 3C In an embodiment not shown in the figure, the mind map can be synchronized or shared to a second device. The second device can be a mobile terminal including, for example, a mobile phone. The interface of the human-computer dialogue program running on the second device can only include a dialogue area including a mind map window. The mind map window in the dialogue area can be displayed in the dialogue area in a first direction. For example, the dialogue area and the mind map window can be displayed in a vertical screen manner, and the human-computer dialogue interface presented in the vertical screen can be similar to Figure 2BIn response to selecting the zoom view indicator, the reading assistant can zoom in on the mind map window. The enlarged mind map window can occupy the entire interface of the human-computer dialogue program and the enlarged mind map window can be displayed on the interface of the human-computer dialogue program in a second direction. The first direction can be perpendicular to the second direction. That is, when the human-computer dialogue program running on the second device displays the enlarged mind map window, the mind map window can be displayed in a horizontal and full-screen manner. The operation method of the functional area in the mind map window can be similar to that described above.

[0097] Return to reference Figure 3B The user can select a component element in the mind map by using the cursor 325. The component elements in the mind map may include text, graphics (such as lines, boxes, etc.) and other elements that constitute the mind map. Figure 3B As shown, the user can select the text "The Daughter of the Sea" in the mind map through the cursor 325. In response to selecting the component element "The Daughter of the Sea" in the mind map in the dialogue area 320, the reading assistant can display the content corresponding to the selected component element "The Daughter of the Sea" in the reading document in the reading area 310. Those skilled in the art should understand that, depending on the specific implementation, in response to the user's selection operation on the graphics (such as lines, boxes, etc.) in the component element, the reading assistant can also display the content corresponding to the selected component element in the reading document in the reading area 310.

[0098] Figure 3D 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 Zhongyu Figure 3B Similar elements will not be described repeatedly.

[0099] In response to the selection operation of the component element "The Daughter of the Sea" in the mind map in the dialogue area 320, the reading assistant can scroll the content of the reading document in the reading area 310 and jump to the content corresponding to the selected component element "The Daughter of the Sea" in the reading document. Figure 3D As shown, the reading area 310 can display the content corresponding to the selected component element "The Daughter of the Sea" in the reading document. In addition, in response to selecting a component element in the mind map in the conversation area, the content corresponding to the selected component element in the reading document and other content of the reading document in the reading area can be displayed differentially in the reading area. For example, Figure 3D The content corresponding to the selected component element is highlighted as shown. When the editing trigger operation of the mind map as described above occurs, the user can also edit the corresponding relationship between the component element and the content in the reading document.

[0100] In one embodiment, Figure 3BAs shown in the scene, the reading area 310 does not display the content corresponding to the selected component element "The Daughter of the Sea". In response to selecting the component element "The Daughter of the Sea" in the mind map in the dialogue area 320, the content of the document can be scrolled and jumped in the reading area 310 to Figure 3D As shown, the content corresponding to the selected component element “The Daughter of the Sea” is displayed in the reading area 310 .

[0101] exist Figure 3B In another embodiment not shown, before the user selects the component element "The Daughter of the Sea" in the mind map, a portion of the content corresponding to the selected component element "The Daughter of the Sea" may be displayed in the reading area and the reading document content that does not belong to the content corresponding to the selected component element "The Daughter of the Sea" is displayed. In response to the user selecting the component element "The Daughter of the Sea" in the mind map, the content of the reading document can be scrolled in the reading area and jumped to display more content corresponding to the selected component element "The Daughter of the Sea" in the reading area.

[0102] exist Figure 3B In another embodiment not shown, before the user selects the component element "The Daughter of the Sea" in the mind map, the reading area may display all parts of the content corresponding to the selected component element "The Daughter of the Sea" and display the reading document content that does not belong to the content corresponding to the selected component element "The Daughter of the Sea". In response to the user selecting the component element "The Daughter of the Sea" in the mind map, scrolling and jumping may not be performed in the reading area, because the entire content corresponding to the selected component element "The Daughter of the Sea" has been displayed in the reading area. In this case, jumping and scrolling cannot display more of the first part of the content.

[0103] exist Figure 3BIn another embodiment not shown, before the user selects the component element "Daughter of the Sea" in the mind map, a part of the content corresponding to the selected component element "Daughter of the Sea" may be displayed in the reading area, and the reading document content that does not belong to the content corresponding to the selected component element "Daughter of the Sea" is not displayed. That is to say, the length of the content corresponding to the selected component element "Daughter of the Sea" can be very long, and the reading area has displayed the most content corresponding to the selected component element "Daughter of the Sea" under the current zoom ratio. In response to the user selecting the component element "Daughter of the Sea" in the mind map, scrolling and jumping can not be performed in the reading area. In this case, jumping and scrolling cannot display more of the first part of the content. In this case, the content corresponding to the selected component element in the reading document and other content of the reading document in the reading area can be displayed differentially in the reading area. For example, the content corresponding to the selected component element can be highlighted. In this way, the position of the content corresponding to the selected component element can be conveyed to the user in a clearer way.

[0104] Figure 3E FIG. 1 is a schematic diagram of the principle of generating a mind map through a human-computer dialogue program according to an embodiment of the present disclosure. Figure 3E As shown, the front end, back end, and large language model of the human-computer dialogue program can interact with each other to generate and present a mind map to the user.

[0105] like Figure 3E As shown, the front end of the human-computer dialogue program can receive the user's human-computer dialogue content at box 331. The user's human-computer dialogue content may include the user's selection of Figure 2A The one or more recommendation prompt information 203 shown, the prompt information input by the user through the input area 201, and the user's selection Figure 3A The illustrated recommendation bubble 321 includes prompt information and the user inputs prompt information through the input area 322 .

[0106] The back end of the human-computer dialogue program can determine whether the user's human-computer dialogue content hits the mind map prompt information matching rule in box 332. In one embodiment, when the user selects Figure 2A The one or more recommended prompt information 203 shown in FIG. 2 may be prompt information for generating a mind map (eg, Figure 2A The prompt "Generate Mind Map" shown in the figure) or the user selects Figure 3A The recommendation bubble 321 includes prompt information for generating a mind map (for example, Figure 3AIn another embodiment, when the prompt information input by the user through the input area 201 or the prompt information input by the user through the input area 322 hits the keyword that triggers the generation of a mind map, the back end of the human-computer dialogue program can determine that the human-computer dialogue content hits the mind map prompt information matching rule. Exemplarily, the keywords may include "mind map", "generate outline", "mind map" and the like, but the present disclosure is not limited thereto.

[0107] The back end of the human-computer dialogue program may add implicit prompt information of the mind map in box 333. For example, in response to determining that the mind map prompt information matches the rule hit, the back end of the human-computer dialogue program may generate implicit prompt information of the mind map to be sent to the large language model in box 333. The implicit prompt information of the mind map may be invisible to the user. The implicit prompt information of the mind map may be more accurately parsed and understood by the large language model to instruct the large language model to generate a mind map.

[0108] The large language model can request or call the long window model to process the mind map implicit prompt information in box 334. The long window model can be a part of the large language model or independent of the large language model. The long window model can be a model that can support, understand and process longer reading documents (for example, reading documents of 350,000 Chinese characters and above).

[0109] The large language model can return content in a format corresponding to the mind map through the long window model in box 335. For example, the structured data of the reading document used to generate the mind map can be returned through the long window model, and the structured data can be converted into text content in Markdown format for generating the mind map.

[0110] The front end of the human-computer dialogue program can render the content in the format corresponding to the mind map as a mind map in block 336. For example, the front end of the human-computer dialogue program can generate and display a mind map to the user based on the text content in the Markdown format.

[0111] Alternatively or additionally, the large language model may call or request a model capable of directly generating a mind map in block 335 , thereby directly generating a mind map for display to the user at the front end of the human-computer dialogue program.

[0112] Figure 4A is a flow chart showing a human-computer dialogue method according to an embodiment of the present disclosure.

[0113] In S411, you can choose to read the document to enter the first mode, where the interface of the human-computer dialogue program in the first mode includes a reading area and a dialogue area.

[0114] At S412, the content of the reading document may be displayed in the reading area.

[0115] In S413, first prompt information may be obtained in the dialog area, where the first prompt information is used to generate a mind map for reading at least a portion of the content of the document.

[0116] In S414, in response to the first prompt information obtained in the conversation area, a mind map for reading at least a portion of the content in the document may be generated and displayed in the conversation area.

[0117] Figure 4B is a flow chart illustrating another human-computer dialogue method according to an embodiment of the present disclosure. Figure 4B The method in may be a method executed by the human-computer dialogue program in the second mode.

[0118] At S421, a document reading may be received in a dialogue area in an interface of the human-computer dialogue program.

[0119] In S422, in response to receiving a reading document, one or more recommendation prompt information for reading the document may be displayed in the conversation area, wherein the one or more recommendation prompt information includes first prompt information, and the first prompt information is used to generate a mind map of at least a portion of the content of the reading document.

[0120] In S423, in response to selecting the first prompt information among the one or more recommended prompt information, a mind map for at least a portion of the content in the reading document may be displayed in the conversation area.

[0121] Figure 5 is a schematic diagram of a human-machine dialogue device according to an embodiment of the present disclosure.

[0122] 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 .

[0123] 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.

[0124] The reading module 520 may be configured to display the content of the reading document in the reading area in the first mode of the human-computer dialogue program.

[0125] The dialogue module 530 may be configured to obtain and generate first prompt information in the dialogue area in the first mode of the human-computer dialogue program, where the first prompt information is used to generate a mind map for reading at least a portion of the content of the document.

[0126] In response to the dialogue module 530 obtaining the first prompt information in the dialogue area, the dialogue module 530 may be configured to generate and display a mind map for reading at least a portion of the content in the document in the dialogue area.

[0127] According to yet another aspect of the present disclosure, a human-computer dialogue device is provided. Figure 6 A schematic diagram of a human-machine dialogue device 600 according to an embodiment of the present disclosure is shown.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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 7As 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 7 The 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.

[0132] 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.

[0133] 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.

[0134] Embodiments of the present disclosure provide a human-computer dialogue method, apparatus, device, and computer-readable storage medium.

[0135] The human-computer dialogue method provided by the embodiment of the present disclosure can collaborate with users and artificial intelligence, and promote users to immerse themselves in reading documents by providing users with mind maps for reading documents. The method according to the present disclosure can enter the immersive reading mode based on the user's choice, and in the immersive reading mode, ask and answer questions with the user about the reading document, generate a mind map for the content of the reading document, and locate the content in the reading document in response to the user's selection of the unit text content in the mind map. In addition, the method according to the present disclosure can save user usage records and further form a knowledge flywheel for reading documents, thereby greatly improving the user experience.

[0136] 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.

[0137] 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.

[0138] 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 comprising: 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 the content of the reading document in the reading area; Obtaining first prompt information in the conversation area, where the first prompt information is used to generate a mind map of at least a portion of the content of the reading document; and In response to the first prompt information obtained in the conversation area, a mind map for at least a portion of the content in the reading document is generated and displayed in the conversation area.

2. The method according to claim 1, further comprising: In response to a selection operation on a component element of the mind map in the conversation area, content corresponding to the selected component element in the reading document is displayed in the reading area.

3. The method according to claim 2, further comprising: In response to a selection operation on a component element in the mind map in the conversation area, the content of the reading document is scrolled in the reading area and jumps to the content corresponding to the selected component element in the reading document.

4. The method according to claim 2, further comprising: In response to a selection operation on a component element of the mind map in the conversation area, the content corresponding to the selected component element in the reading document and other content of the reading document in the reading area are displayed differentially in the reading area.

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

6. The method according to claim 1, wherein: Obtaining the first prompt information in the dialog area specifically includes: The first prompt information is received in a user input area of ​​the dialog area.

7. The method according to claim 1, wherein: Displaying a mind map for at least a portion of the content in the reading document in the conversation area includes displaying the mind map in a mind map window, The size of the mind map is related to the size of the mind map window, and the mind map is completely displayed in the mind map window, and Wherein, the mind map window includes a title area and a function area.

8. The method according to claim 7, wherein: The title area includes content of a root node of the mind map, and the function area includes one or more of a download indicator, a copy indicator, and an enlarged view indicator.

9. The method according to claim 7, wherein: The size of the mind map window is related to the size of the conversation area, and the method further includes: In response to the size of the conversation area being adjusted, the size of the mind map window and the size of the mind map are adjusted.

10. The method according to claim 8, in, The human-computer dialogue program is run on the first device, and the method further includes: in response to selecting a zoom view indicator, enlarging the mind map window, wherein the enlarged mind map window covers at least a portion of at least one of the reading area and the dialogue area, or Wherein, the human-computer dialogue program runs on a second device, and the mind map window is displayed in a first direction in the dialogue area, and the method further comprises: in response to selecting a zoom view indicator, enlarging the mind map window, wherein the enlarged mind map window occupies the entire interface of the human-computer dialogue program and the enlarged mind map window is displayed in a second direction on the interface of the human-computer dialogue program. 11 . The method according to claim 10 , further comprising zooming the mind map in the mind map window and maintaining the zoomed state of the mind map in the mind map window.

12. The method of claim 10, further comprising clearing the zoom state in response to one or more of: Select the enlarged view indicator and close the enlarged mind map window. Share the current human-computer dialogue content, The human-computer dialogue program enters the second mode from the first mode, Switch from the current human-computer dialogue to another human-computer dialogue, and Answer again with the content of the mind map.

13. The method according to claim 1, further comprising sharing the mind map in the form of a poster or a web page developed based on HTML5 technology.

14. The method according to claim 1, further comprising: In response to selecting to copy the mind map, the text in the Markdown format corresponding to the mind map is copied.

15. The method according to claim 1, further comprising editing the mind map in an interface of the human-computer dialogue program in response to an editing trigger operation on the mind map.

16. The method according to claim 15, wherein editing the mind map in the interface of the human-computer dialogue program comprises: At least one of adjusting the hierarchical structure of the mind map, adjusting the order relationship of the constituent elements in the hierarchy of the mind map, and editing the text content in the constituent elements of the mind map.

17. The method according to claim 15, further comprising: In response to an editing trigger operation on the mind map, a text in Markdown format corresponding to the mind map is displayed in the interface of the human-computer dialogue program, The mind map is edited by modifying the text in the Markdown format corresponding to the mind map in the interface of the human-computer dialogue program.

18. A human-computer dialogue method, applied to a human-computer dialogue program, the method comprising: receiving a reading document in a dialog area in the interface of the human-computer dialog program, In response to receiving the reading document, displaying one or more recommendation prompt information for the reading document in the conversation area, wherein the one or more recommendation prompt information includes first prompt information, and the first prompt information is used to generate a mind map of at least a portion of the content of the reading document, In response to selecting a first prompt information among the one or more recommended prompt information, a mind map for at least a portion of the content in the reading document is displayed in the conversation area.

19. A human-computer dialogue device, configured to execute a human-computer dialogue program, the device comprising: A mode selection module, configured to select reading 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 the content of the reading document in the reading area in a first mode of the human-computer dialogue program; and a dialogue module, configured to obtain first prompt information in the dialogue area in a first mode of the human-computer dialogue program, wherein the first prompt information is used to generate a mind map of at least a portion of the content of the reading document; and In response to the first prompt information obtained by the dialogue module in the dialogue area, the dialogue module is configured to generate and display a mind map for at least a portion of the content in the reading document in the dialogue area.

20. A human-computer dialogue device, comprising: 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 1-18 is performed.

21. 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 18 when executed by a processor.

Images