Method and device for generating knowledge graph, equipment, medium and program product

Abstract

The embodiment of the invention provides a method and device for generating a knowledge graph, equipment, a storage medium and a computer program product. The method includes obtaining a user input regarding knowledge content. The method further includes generating a knowledge graph including a plurality of nodes and edges among the plurality of nodes according to the user input using the target model, the plurality of nodes indicating the plurality of knowledge points, the edges indicating association relationships among the plurality of knowledge points, the knowledge graph being visually displayed in the interface. According to the method disclosed by the embodiment of the invention, the knowledge graph can be generated by using the model through one key, the efficiency is relatively high, the user threshold is reduced, and the user experience is improved.

Description

Technical Field

[0001] This disclosure generally relates to the field of data processing, and more specifically to methods, apparatus, devices, computer-readable storage media, and computer program products for generating knowledge graphs. Background Technology

[0002] In today's information-saturated world, people have increasingly diverse ways to acquire knowledge. Traditional learning methods often rely on linear textual materials, such as books and articles, requiring learners to independently sift through large amounts of text to connect concepts. For example, when learning complex subjects like medicine or computer science, learners often feel confused by numerous technical terms and interwoven theories, finding it difficult to clearly construct a complete knowledge framework.

[0003] Knowledge graphs, as a tool for organizing knowledge in a graphical structure, represent knowledge as nodes (representing concepts or entities) and edges (representing relationships between concepts or entities). For existing structured data, they are transformed into triples (object 1-relationship-object 2, or object-attribute-attribute value) of the knowledge graph through mapping rules, helping people to clarify the relationships between concepts. Summary of the Invention

[0004] According to exemplary embodiments of this disclosure, a method, apparatus, device, computer storage medium, and computer program product for generating knowledge graphs are provided.

[0005] In a first aspect of this disclosure, a method for generating a knowledge graph is provided, the method comprising obtaining user input about knowledge content. The method further comprises generating a knowledge graph, comprising multiple nodes and edges between the nodes, based on the user input using a target model, wherein the nodes indicate multiple knowledge points and the edges indicate the relationships between the multiple knowledge points, and the knowledge graph is visualized in an interface.

[0006] In a second aspect of this disclosure, an apparatus for generating a knowledge graph is provided. The apparatus includes a user input acquisition module configured to acquire user input regarding knowledge content. The apparatus also includes a knowledge graph generation module configured to generate a knowledge graph based on the user input using a target model. This knowledge graph includes multiple nodes and edges between the nodes, where the nodes indicate multiple knowledge points and the edges indicate the relationships between the knowledge points. The knowledge graph is then visualized on an interface.

[0007] In a third aspect of this disclosure, an electronic device is provided, comprising: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method described in the first aspect of this disclosure when executed by the at least one processing unit.

[0008] In a fourth aspect of this disclosure, a computer-readable storage medium is provided having machine-executable instructions stored thereon, which, when executed by a device, cause the device to perform the method described in the first aspect of this disclosure.

[0009] In a fifth aspect of this disclosure, a computer program product is provided, including computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method described in the first aspect of this disclosure.

[0010] The summary section is provided to introduce a series of concepts in a simplified form, which will be further described in the detailed description below. The summary section is not intended to identify key or essential features of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

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

[0012] Figure 1B A schematic diagram with a rotated view is shown according to an embodiment of the present disclosure;

[0013] Figure 2 A flowchart of a method for generating a knowledge graph according to an embodiment of the present disclosure is shown;

[0014] Figure 3 A schematic diagram of a mobile node according to an embodiment of the present disclosure is shown;

[0015] Figure 4 A schematic diagram illustrating path exploration according to embodiments of the present disclosure is shown;

[0016] Figure 5 A schematic diagram illustrating the stages of generating a knowledge graph according to an embodiment of the present disclosure is shown;

[0017] Figure 6 A schematic block diagram of an example apparatus according to some embodiments of the present disclosure is shown; and

[0018] Figure 7 A block diagram of an example device that can be used to implement embodiments of the present disclosure is shown.

[0019] In all the accompanying figures, the same or similar reference numerals denote the same or similar elements. Detailed Implementation

[0020] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of these messages or information. It is understood that before using the technical solutions disclosed in the embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0021] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message. As an optional but non-limiting implementation, the prompt message can be sent to the user in the form of a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection component allowing the user to choose whether to "agree" or "disagree" to provide personal information to the electronic device.

[0022] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0023] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0024] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects unless explicitly stated. Other explicit and implicit definitions may also be included below.

[0025] In related technologies, if a user wants to understand a piece of content (such as a piece of physics knowledge), they can only see an abstract summary in text form (such as a knowledge graph). However, text-based abstractions lack visualization and cannot dynamically depict the relationships between objects, making them relatively difficult to understand. For two-dimensional graphs, users typically need to manually code or draw the content, which has a high technical threshold and time cost. Furthermore, two-dimensional diagrams only provide a single-plane view; the positions and relationships of all nodes and edges are fixed on the same plane, and users cannot adjust the viewing angle. When the knowledge system is complex, the fixed perspective inevitably leads to overlapping edges, requiring users to manually sort out the logic amidst the chaotic connections, resulting in high comprehension costs.

[0026] To address this issue, this disclosure proposes a method for generating knowledge graphs. This method acquires user input regarding knowledge content, utilizes a model to generate a knowledge graph including multiple nodes and edges, and then displays the knowledge graph. This method can generate knowledge graphs with a single click using a model, offering high efficiency and lowering the barrier to entry for users. It helps users efficiently understand the input knowledge content and improves the user experience.

[0027] The embodiments of this disclosure will now be described in further detail with reference to the accompanying drawings, wherein... Figure 1A A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. Figure 1A The example environment 100 includes an application 110 on a user device and a server. The server may be deployed with target models (e.g., multimodal models capable of processing multimodal data), which are trained models capable of generating content based on user input. In some embodiments, the user device and the server communicate via a network. The network may include a wired network, a wireless network, or a combination thereof, for providing communication between the user device and the server. In some embodiments, the user device may be connected to the server via a data cable; this disclosure does not limit the method of connection between the user device and the server.

[0028] In some embodiments, application 110 can obtain user input 112 regarding knowledge content on the interface. In some embodiments, application 110 can provide a rich text input box on the interface, where users can enter or copy content. This rich text input box supports a formula editor, allowing users to directly enter content with formulas, copy document fragments, or input content via speech-to-text functionality.

[0029] In some embodiments, application 110 may provide a file upload component 114. Users can click on this file upload component 114 to upload a file containing content, as user input 112. It can automatically recognize semantic information in the file and understand its content (such as concepts), logic, etc. In this embodiment, it is assumed that the user input 112 provided by the user is knowledge about physics, specifically "core formula F". 合 =ma. F 合 : Net external force (unit: Newton, N). m: Mass (unit: kilogram, kg). a: Acceleration (unit: meter / second², m / s²). 2 (Derivation: Acceleration…) Application 110 can also provide a star map generation component 116. Users can generate a 3D star map with one click by clicking the star map generation component 116. In some embodiments, application 110 also provides an image input component, which additionally supports image uploads (such as photos of handwritten notes or screenshots of blackboard writing), and uses OCR technology to recognize the text and formula content in them, converting them into parsable user input 112.

[0030] In some embodiments, application 110 uses a target model to generate a knowledge graph based on user input 112, including multiple nodes and edges between them. The nodes indicate multiple knowledge points, and the edges indicate the relationships between these knowledge points. The knowledge graph is visualized in the interface. In this embodiment, the knowledge graph is shown as a 3D star graph, with nodes represented as 3D stars and edges as the edges between them. This visual representation enhances the user experience. In this embodiment, application 110 can communicate with a server to invoke a multimodal model. This can be achieved, for example, by calling the multimodal model's API. In some embodiments, application 110 constructs prompts for generating the 3D star graph and incorporates user input 112 into them, providing them to the server's multimodal model via an API.

[0031] In other embodiments, the multimodal model not only generates knowledge graph data but also generates code for a 3D star map. In some embodiments, application 110 can provide the code logic for generating the 3D star map and the interaction logic of interactive components as prompts to the multimodal model, and receive the code for generating the 3D star map and the data for the 3D star map from the multimodal model. Of course, the data can also be directly written into the code. Application 110 can run the received code to obtain the 3D star map.

[0032] In some embodiments, if a first interactive operation (e.g., mouse pointer hover) is received for a specific three-dimensional celestial body, a summary of the specific three-dimensional celestial body is displayed. This summary is a summary of the description related to the knowledge point corresponding to the specific three-dimensional celestial body in user input 112. In some embodiments, if a second interactive operation (e.g., a single click or double click) is received for a specific three-dimensional celestial body, a description of the specific three-dimensional celestial body is displayed, wherein the description includes at least one of the name and explanation of the knowledge point corresponding to the specific three-dimensional celestial body. For example, if the user clicks on the three-dimensional celestial body 120, a pop-up window can be provided on the interface displaying the description related to Newton's First Law of Motion from user input 112, including the name and explanation. For example, the name of the three-dimensional celestial body 120 is "Newton's First Law of Motion".

[0033] In some embodiments, application 110 displays the generated three-dimensional star map and a space image 134 matching the three-dimensional star map on the interface. For example... Figure 1A As shown, after the user clicks the star map generation component 116, the generated star map can be displayed in the preview window (right side) of the interface. This three-dimensional star map includes three-dimensional stars 120, 122, 124, 126, 128, 130, and 132, as well as directed edges between these three-dimensional stars, where three-dimensional star 120 is an example. The spatial image 134 matches the three-dimensional star map and also belongs to the galaxy theme. In this embodiment, the spatial image 134 is a cyclical display of multiple star images, which can create a dynamic effect of outer space and enhance the user experience.

[0034] In some embodiments, user input 112 includes multiple application scenarios corresponding to multiple knowledge points, and the 3D star map includes multiple 3D micro-stars. For example, 3D star 122 belongs to 3D micro-stars, and the name of this 3D micro-star is "car acceleration". Figure 1A As can be seen from this, it represents one of the application scenarios of Newton's second law of motion. Figure 1A Other application scenarios were also shown, such as "free fall", "vehicle safety", and "sports".

[0035] As discussed earlier, when the user input "112" is complex, edges may intersect. For example... Figure 1A In this embodiment, the edges between 3D stars 126 and 122, and between 3D stars 132 and 124, intersect. The presence of numerous intersecting edges can easily lead to user misunderstanding. To address this, this embodiment provides a 3D star map that allows the user's viewpoint to be rotated in three dimensions, enabling the user to observe the 3D star map from different perspectives. Figure 1B A schematic diagram with a rotated view is shown according to an embodiment of the present disclosure.

[0036] like Figure 1B As shown, users can rotate the viewing angle of the 3D star chart within the interface. For example, rotating to the right and rear of 3D star 126 can change the display method of 3D stars 122, 124, 126, and 132. Figure 1B As shown on the right, the intersecting edges have disappeared, and the relationships between the three-dimensional celestial bodies are very clear.

[0037] In some embodiments, during the matching and generation of the spatial image 134, prompts can be provided to guide the multimodal model to select an appropriate background theme based on the user-input knowledge domain (such as physics, chemistry, or biology). For example, for knowledge of physics and mechanics, the spatial image can generate a galaxy background containing planetary orbits, with the curvature of the orbits linked to the acceleration parameters in the mechanics formulas. For example, for knowledge of chemical molecular structure, a nebula background of microscopic particle motion can be generated, with the particle density correlated to the molecular bond energy.

[0038] In some embodiments, application 110 also provides rich interactive components to support users in personalizing operations on the 3D star map. For example, users can double-click a star to bring up a property panel to view the detailed definition, formula derivation process, and related examples of that knowledge point. The recorded data of interactive operations will be cached locally by the application, and users can use the "Save Configuration" function to save the current star layout, background theme, and interactive parameters as a file or link for export and sharing.

[0039] In some embodiments, to meet the visualization needs of complex knowledge systems, application 110 supports the layered display of 3D star charts. In some embodiments, multiple 3D stars have multiple levels, and the interface includes a level switching component. If an adjustment operation (i.e., the fifth adjustment) is received based on the level switching component, the corresponding 3D star and the edges between the corresponding 3D stars are displayed according to the adjustment operation. For example, a multimodal model will automatically divide the star levels according to the hierarchical structure of knowledge (such as subject-chapter-knowledge point). Users can select the level to be displayed (i.e., the fifth adjustment) by clicking the level switching component on the interface, and expand or collapse the stars and associated edges of a certain level.

[0040] In this embodiment, multiple methods such as rich text boxes, file uploads, and image OCR recognition are provided to support the input of various content formats, including formulas, voice, and document fragments, adapting to different user habits and reducing input barriers. This embodiment relies on a multimodal model to generate a 3D star map with one click, eliminating the need for manual coding by the user. Combined with domain-adapted dynamic spatial backgrounds (such as physical planetary trajectories), abstract knowledge becomes intuitive and vivid, far surpassing the effect of traditional text or 2D diagrams. The model can be prompted to generate data or directly generate code, adapting to different scenarios and ensuring efficient response. Furthermore, the 3D star map allows users to switch between any perspective (such as from the front, side, top, or bottom) through rotation, translation, and scaling, naturally separating edges at different levels using Z-axis spatial distance. Users can adjust the perspective to "spread" originally intersecting edges in space, achieving a non-overlapping display of edges from a specific angle, intuitively identifying the connection points and relationship types of each edge.

[0041] It should be understood that a server instance can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. Servers can be connected directly or indirectly through wired or wireless communication methods, and this application does not impose any restrictions.

[0042] The user device can be any type of mobile computing device, including mobile computers (e.g., personal digital assistants, laptops, notebooks, tablets, netbooks, etc.), mobile phones (e.g., cellular phones, smartphones, etc.), wearable computing devices (e.g., smartwatches, head-mounted devices, including smart glasses, etc.) or other types of mobile devices. In some embodiments, the user device can also be a fixed computing device, such as a desktop computer, game console, smart TV, etc. It should be understood that, if the user device has sufficient computing power, the user device can perform the above operations on behalf of the server, or the user device and the server can jointly perform the above operations.

[0043] It should be understood that the architecture and functionality in example environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure. Embodiments of this disclosure can also be applied to other environments with different structures and / or functionalities.

[0044] The processes according to embodiments of this disclosure will be described in detail below with reference to other accompanying drawings. For ease of understanding, the specific data mentioned in the following description are exemplary and not intended to limit the scope of this disclosure. It will be understood that the embodiments described below may also include additional actions not shown and / or actions shown may be omitted, and the scope of this disclosure is not limited in this respect.

[0045] Figure 2 A flowchart of a method 200 for generating a knowledge graph according to certain embodiments of the present disclosure is shown. In this embodiment, the method may be performed by an application 110 of a user device. At block 202, user input regarding knowledge content is obtained. The user input is raw information provided by the user for generating the knowledge graph, and can take various forms, such as knowledge content. In some embodiments, the application receives the user input and, upon receiving the user input, can process the format of the user input according to a target markup language, for example, processing it into a format easily understood by the model. In some embodiments, the application provides the processed user input as part of prompt words to a multimodal model. The multimodal model can then generate data for the knowledge graph or code containing data for the knowledge graph based on the prompt words.

[0046] In box 204, the target model is used to generate a knowledge graph based on user input, comprising multiple nodes and edges between them. Multiple nodes represent multiple knowledge points, and edges indicate the relationships between these knowledge points. The knowledge graph is then visualized on the interface. A knowledge graph is a visual graph composed of multiple nodes (representing knowledge points in the user input) and edges between them (representing the relationships between knowledge points), used to intuitively show the connections between the knowledge points in the user input. For example, if the user inputs the physics knowledge "F = ma", the knowledge graph will have three core nodes representing "F", "m", and "a", as well as edges connecting them. Because "F" references both "m" and "a", the edges point from "F" to both "m" and "a".

[0047] According to the method for generating knowledge graphs disclosed herein, user input regarding knowledge content is obtained, a model is used to generate a knowledge graph including multiple nodes and edges, and the knowledge graph is then displayed. This method can generate knowledge graphs with a single click using a model, offering high efficiency and lowering the barrier to entry for users. It helps users efficiently understand the input knowledge content and improves the user experience.

[0048] In some embodiments, a target model is used to identify multiple nominal concepts from user input as multiple nodes, or multiple nodes are determined by performing content reasoning on user input. For example, for Figure 1AThe user input provided in the embodiments includes noun concepts such as net external force, mass, and acceleration. Therefore, these noun concepts can be extracted as individual nodes. In some embodiments, a target model is used to determine the edges between multiple nodes by analyzing the reference relationships between multiple noun concepts. As an example, a target model can be used to analyze formulas in the user input (i.e., knowledge content), where the elements of the formulas can form reference relationships. In some embodiments, a knowledge graph is generated based on multiple nodes and edges. The knowledge graph is obtained by attaching edges to the nodes.

[0049] In the following description, the knowledge graph is shown as a 3D star graph, nodes are shown as 3D stars, and edges are shown as the edges between 3D stars. This visualizes the knowledge graph and improves the user experience. It should be noted that the knowledge graph of this disclosure can also be a two-dimensional knowledge graph, for example, nodes are shown as boxes, and edges are shown as the edges between boxes. The 3D star graph does not limit the embodiments of this disclosure. In some embodiments, a rotation component can be provided on the interface, and if an adjustment operation (i.e., a fourth adjustment) is received based on the rotation component, the perspective of the presented 3D star graph is changed according to the adjustment operation. For example, the user can achieve precise adjustment of the perspective by clicking the direction buttons on the component (such as clockwise rotation, counterclockwise rotation, up / down / left / right flip). Each click of the button will rotate the perspective step by step according to a preset angle (such as 15°), suitable for scenarios requiring precise control of the rotation amplitude. Meanwhile, to improve ease of operation, the application supports direct mouse interaction. For example, when a user holds down the left mouse button and drags the mouse, the viewpoint rotates in real time following the mouse movement. Dragging the mouse left or right rotates the 3D star map horizontally around the vertical axis, allowing for easy viewing of the left and right sides of the stars; dragging the mouse up or down tilts the viewpoint around the horizontal axis, allowing switching between overhead and overhead views to observe the spatial arrangement of the stars. Furthermore, zooming is achieved via the mouse wheel. Scrolling forward gradually zooms in, focusing on the details of the stars in the current field of view (such as attribute labels on the star's surface and the texture features of its edges); scrolling backward gradually zooms out, presenting a broader 3D spatial layout, making it easier for users to grasp the structure of the overall knowledge network. These operation methods work together, supporting both precise step-by-step adjustments and flexible, free control, allowing users to easily explore the 3D star map from any angle and scale, thus separating intersecting edges.

[0050] In some embodiments, if a drag operation is received targeting a three-dimensional celestial body, the target three-dimensional celestial body is moved according to the drag operation. In some embodiments, connected three-dimensional celestial bodies are moved based on the movement of the target three-dimensional celestial body, wherein the movement includes movement speed and movement direction, and the connected three-dimensional celestial bodies include those directly or indirectly connected to the target three-dimensional celestial body. For example Figure 1AIn the diagram, three-dimensional star 120 and three-dimensional star 126 are directly connected, while three-dimensional star 120 and three-dimensional star 130 are indirectly connected.

[0051] In other words, when a user drags a target 3D celestial body, the application can respond in real time and move the target celestial body according to parameters such as the drag trajectory and force. Simultaneously, all 3D celestial bodies directly connected (e.g., via edges) or indirectly connected (e.g., via other celestial bodies) to the target celestial body will also move in tandem with it. Their movement speed is dynamically adjusted based on the closeness of their connection to the target celestial body (e.g., directly connected celestial bodies move faster, while indirectly connected celestial bodies move at progressively slower speeds). Their movement direction coordinates with the drag direction of the target celestial body, creating an overall displacement effect that conforms to spatial logic. This avoids edge intersections or spatial layout chaos caused by the movement of a single celestial body, ensuring that the 3D celestial body map maintains an intuitive and interconnected display throughout the interaction process, thus improving the user experience. Figure 3 A schematic diagram of a moving three-dimensional star according to an embodiment of the present disclosure is shown. (As...) Figure 3 As shown in the upper part, the user can drag the 3D star from position 302 to position 304, so that the 3D star is displayed at position 304. Accordingly, the connected 3D stars include the stars at positions 306 and 310. These two stars are also moved to positions 308 and 312 respectively, as indicated by the dashed arrows.

[0052] In some embodiments, the interface includes a force adjustment component that allows a user to pre-configure or adjust virtual force parameters (such as gravitational coefficients) between three-dimensional celestial bodies in real time. In some embodiments, the direction and speed of movement of connected three-dimensional celestial bodies are determined based on the movement of the target three-dimensional celestial body and the forces between it and the target three-dimensional celestial body, wherein the forces are determined according to the tightness between the celestial bodies. In some embodiments, the connected three-dimensional celestial bodies are moved according to the direction and speed of movement.

[0053] When a user drags a target 3D celestial body to move it, a simplified model based on Newton's law of universal gravitation (the magnitude of gravity is directly proportional to the product of the celestial body's mass and inversely proportional to the square of the distance) is applied. Combined with the target celestial body's movement vector (direction and velocity), the gravitational influence on all connected celestial bodies is dynamically calculated. This makes the entire 3D celestial body map present a linkage effect that conforms to the laws of physics and mechanics during the interaction process. It retains the user's control while maintaining the visual coherence of the relationship between celestial bodies through force simulation, thereby enhancing the naturalness and immersion of the interaction.

[0054] Figure 4A schematic diagram of path exploration according to an embodiment of the present disclosure is shown. In this embodiment, the interface provides components 410 and 412 for path exploration. For example, a user can input a starting point in component 410 and an ending point in component 412. In some embodiments, the application obtains two three-dimensional celestial bodies selected by the user from a plurality of celestial bodies as the starting point and the ending point. As an example, the starting point is a three-dimensional celestial body 402 named "Newton's First Law of Motion," and the ending point is a three-dimensional celestial body 406 named "Net External Force."

[0055] In some embodiments, a knowledge path is determined in a 3D star map based on a start point and an end point, wherein the knowledge path includes the 3D stars and edges traversed from the start point to the end point. Figure 4 As can be seen, the three-dimensional celestial bodies traversed from the starting point to the end point include three-dimensional celestial bodies 402, 404, and 406, as well as the edges between these three-dimensional celestial bodies.

[0056] In some embodiments, the 3D stars and edges included in the knowledge path are highlighted in the 3D star map. For example... Figure 4 As shown, the three-dimensional stars 402, 404, and 406 are highlighted, allowing users to clearly see the path. In this embodiment, users can set a start point and an end point, and generate a path from the start point to the end point with one click. The relationship between the start point and the end point is clearly visible, making it easier for users to understand the content of their input and improving the user experience.

[0057] In some embodiments, the interface includes an adjustment component, and if a size adjustment (i.e., a first adjustment) is received based on the adjustment component, the size of multiple 3D celestial bodies is changed according to the size adjustment. In some embodiments, if a thickness adjustment (i.e., a second adjustment) is received based on the adjustment component, the thickness of the edges is changed according to the thickness adjustment. In some embodiments, if a spacing adjustment (i.e., a third adjustment) is received based on the adjustment component, the spacing between the multiple 3D celestial bodies is changed according to the spacing adjustment. In this embodiment, the adjustment component provided by the interface supports users to perform multi-dimensional personalized optimization of the 3D celestial body diagram, significantly improving the flexibility of interaction and visual adaptability, thereby optimizing the user experience. These adjustment functions allow users to customize the presentation effect of the 3D celestial body diagram according to their own understanding habits and content characteristics, making the visualization of abstract knowledge more in line with personal needs, reducing the understanding cost of information acquisition, and improving the efficiency of users' understanding of knowledge relationships.

[0058] In some embodiments, the interface further includes a filtering component, and if filtering conditions are received based on the filtering component, one or more desired 3D celestial bodies are obtained according to the filtering conditions. For example, the user can select the name of the desired 3D celestial body for filtering. Alternatively, the user can design a regular expression to obtain 3D celestial bodies whose names satisfy the regular expression.

[0059] In some embodiments, the interface displays one or more desired 3D celestial bodies and the edges between them. In some embodiments, the interface may present the filtering results using a combination of highlighted and blurred backgrounds. For example, desired 3D celestial bodies will be highlighted with a more vivid color (e.g., red) and a more striking light effect (e.g., continuous flashing), and their corresponding edges can be thickened and have enhanced glowing effects, while celestial bodies and their edges that do not meet the filtering criteria will become semi-transparent or temporarily hidden to avoid interfering with the user's view.

[0060] Figure 5 A schematic diagram illustrating the stages of generating a three-dimensional star map according to an embodiment of this disclosure is shown. In the user input stage 502, the input and parsing module in the application can provide an input component, upon which the user can provide user input (i.e., content). The input and parsing module can also provide an upload component, allowing the user to upload a file as user input. After the user uploads a file, the input and parsing module can parse the file to extract its content, such as text content, image content, etc. In some cases, calling an API requires providing a key; therefore, the input and parsing module can provide a key management module for encrypting and storing the user's API credentials.

[0061] In the model invocation phase 504, the invocation module in the application can refine the prompts based on built-in prompts, such as incorporating user input into the prompts. These built-in prompts include instructions for generating a 3D star map, such as instructions for generating the module described below. The invocation module can call the API for the multimodal model, send the prompts to the multimodal model, and receive response information from the API. This response information can include data (e.g., JSON data) of the knowledge graph for the 3D star map. The invocation module can extract knowledge points as 3D stars and relationships as edges from this data. Alternatively, the response information can include code that includes the knowledge graph data for the 3D star map.

[0062] In the visualization processing stage 506, the visualization module in the application can create SVG containers to display 3D star maps. Furthermore, the visualization module can simulate the forces between stars based on a simplified gravitational model. The visualization module can apply galaxy-themed styles when displaying 3D star maps. For example, it can display 3D stars as planets of different colors, with edges representing orbits, and provide a spatial image containing stars.

[0063] In the interaction processing phase 508, the application's interaction module can provide various interactive functions, including but not limited to zooming, panning, rotating the viewpoint, and dragging 3D celestial bodies. It also supports hover prompts and clicking to expand details. The interaction module can listen for events, such as user clicks on components. In response to a celestial body being clicked, the interaction module can display the celestial body's details, such as its name and description. The interaction module can provide components to search for specific 3D celestial bodies. Furthermore, the interaction module can provide start-point and end-point components to determine one or more knowledge paths from the start point to the end point and display the determined knowledge paths. The application's analysis module can provide filtering components to display or highlight desired 3D celestial bodies.

[0064] In the custom configuration phase 510, the application's configuration module provides various configuration components for adjusting the configuration of the 3D star chart, such as adjusting the theme, color, and layout of the 3D stars. After configuration is complete, the configuration module can dynamically update the 3D star chart to present the latest configuration effect in real time. The configuration module can also provide visual optimization processing to improve smoothness.

[0065] In the data export stage 512, the application's export module renders the current view of the 3D star chart as an image (e.g., PNG or JPG format), performs serialization and compression on the data, and finally generates a link. Other users do not need to install the application; they can directly click the link to view the 3D star chart image.

[0066] Figure 6 A schematic block diagram of an apparatus 600 for generating a three-dimensional star map according to some embodiments of the present disclosure is shown. The apparatus 600 can be implemented by software, hardware, or a combination of both. Figure 6 As shown, the device 600 includes a user input acquisition module 610 and a knowledge graph generation module 620.

[0067] In some embodiments, the user input acquisition module 610 can be configured to receive user input regarding knowledge content. The knowledge graph generation module 620 can be configured to use a target model to generate a knowledge graph based on the user input, including multiple nodes and edges between the nodes. The nodes indicate multiple knowledge points, and the edges indicate the relationships between the multiple knowledge points. The knowledge graph is then visualized on the interface.

[0068] In some embodiments, the knowledge graph generation module 620 includes a concept recognition module configured to identify multiple noun concepts as multiple nodes from user input using a target model, or to determine multiple nodes by performing content reasoning on user input; a citation relationship analysis module configured to determine edges between multiple nodes by analyzing citation relationships between multiple noun concepts using a target model; and a second generation module configured to generate a knowledge graph based on the multiple nodes and the edges.

[0069] In some embodiments, the plurality of nodes are plurality of three-dimensional celestial bodies, the knowledge graph is a three-dimensional celestial body graph, and the device 600 further includes a first moving module configured to move the target three-dimensional celestial body according to the dragging operation received for the target three-dimensional celestial body; and a second moving module configured to move connected three-dimensional celestial bodies based on the movement of the target three-dimensional celestial body, wherein the movement includes a moving speed and a moving direction, and the connected three-dimensional celestial bodies include three-dimensional celestial bodies that are directly or indirectly connected to the target three-dimensional celestial body.

[0070] In some embodiments, the interface includes a force adjustment component, and the second movement module includes a movement determination module configured to determine the movement direction and movement speed of the connected three-dimensional celestial body based on the movement of the target three-dimensional celestial body and the force between the target three-dimensional celestial body and the target three-dimensional celestial body, wherein the force is determined according to the tightness between the knowledge points; and a third movement module configured to move the connected three-dimensional celestial body according to the movement direction and movement speed.

[0071] In some embodiments, the device 600 further includes a path setting module configured to obtain two nodes selected by the user from multiple nodes as a start point and an end point on the interface; a path determination module configured to determine a knowledge path in the knowledge graph based on the start point and the end point, wherein the knowledge path includes the nodes and edges traversed from the start point to the end point; and a path display module configured to highlight the nodes and edges included in the knowledge path in the knowledge graph.

[0072] In some embodiments, the apparatus 600 further includes a summary display module configured to display a summary of the target node in response to receiving a first interactive operation for the target node; and a description display module configured to display a description of the target node in response to receiving a second interactive operation for the target node, wherein the description includes at least one of the name and explanation of the knowledge point corresponding to the target node.

[0073] In some embodiments, the plurality of nodes are plurality of three-dimensional celestial bodies, the knowledge graph is a three-dimensional celestial body graph, the user input includes plurality of application scenarios corresponding to plurality of knowledge points, the three-dimensional celestial body graph includes plurality of three-dimensional micro-celestial bodies, and the device 600 includes a second display module configured to display on the interface the plurality of three-dimensional celestial bodies and their names, the edges between the plurality of three-dimensional celestial bodies and their directions, the plurality of three-dimensional micro-celestial bodies and their scene names, wherein the names are the names of the corresponding knowledge points, the scene names are the names of the corresponding application scenarios, and the plurality of three-dimensional micro-celestial bodies have different colors and different sizes relative to the three-dimensional celestial bodies.

[0074] In some embodiments, the plurality of nodes are plurality of three-dimensional celestial bodies, the knowledge graph is a three-dimensional celestial body graph, the interface includes an adjustment component, and the device 600 further includes a size adjustment module configured to change the size of the plurality of three-dimensional celestial bodies according to a first adjustment received based on the adjustment component; a thickness adjustment module configured to change the thickness of the edges according to a second adjustment received based on the adjustment component; and a spacing adjustment module configured to change the spacing between the plurality of three-dimensional celestial bodies according to a third adjustment received based on the adjustment component.

[0075] In some embodiments, the interface further includes a filtering component, and the device 600 further includes a filtering module configured to obtain one or more desired nodes based on filtering conditions received from the filtering component; and a desired node display module configured to display one or more desired nodes and edges between one or more desired nodes on the interface.

[0076] In some embodiments, the user input acquisition module 610 includes a receiving module configured to receive user input; a processing module configured to process the format of the user input according to a target markup language; and a providing module configured to provide the processed user input as part of a prompt word to a target model.

[0077] In some embodiments, the plurality of nodes are three-dimensional celestial bodies, the knowledge graph is a three-dimensional celestial body graph, the interface includes a rotation component, and the device 600 further includes a viewpoint adjustment component configured to change the viewpoint of the three-dimensional celestial body graph presented according to a fourth adjustment received based on the rotation component.

[0078] The division of modules or units in the embodiments of this disclosure is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. Furthermore, the functional units in the disclosed embodiments may be integrated into one unit, exist as separate physical entities, or two or more units may be integrated into one unit. The integrated unit described above can be implemented in hardware or as a software functional unit.

[0079] Figure 7 A block diagram of an example device 700 that can be used to implement embodiments of the present disclosure is shown. It should be understood that... Figure 7 The device 700 shown is merely an example and should not be construed as limiting the functionality and scope of the implementation described herein. For example, device 700 may correspond to the implementation described herein. Figures 1A-1B The user equipment described above can be used to perform the functions described above. Figures 1A to 5 The process. For example, device 700 may correspond to the electronic device of the third aspect of the invention.

[0080] like Figure 7 As shown, device 700 is in the form of a general-purpose computing device. Components of device 700 may include, but are not limited to, one or more processors or processing units 710, memory 720, storage devices 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. Processing unit 710 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 720. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of device 700.

[0081] Device 700 typically includes multiple computer storage media. Such media can be any available media accessible to device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 720 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof). Storage device 730 can be removable or non-removable media and may include machine-readable media, such as flash drives, disks, or any other media capable of storing information and / or data (e.g., training data for training) and accessible within device 700.

[0082] Device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not specified in the original text... Figure 7As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 720 may include computer program product 725 having one or more program modules configured to perform various methods or actions of various implementations of this disclosure.

[0083] The communication unit 740 enables communication with other computing devices via a communication medium. Additionally, the functionality of the components of device 700 can be implemented as a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, device 700 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0084] Input device 750 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 760 can be one or more output devices, such as a monitor, speaker, printer, etc. Device 700 can also communicate as needed with one or more external devices (not shown) via communication unit 740. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with device 700, or with any device that enables device 700 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).

[0085] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is provided that stores a computer program thereon, which, when executed by a processor, implements the methods described above.

[0086] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0087] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0088] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0089] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0090] Various implementations of this disclosure have been described above. The foregoing description is exemplary and not exhaustive, nor is it limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for generating knowledge graphs, comprising: Obtain user input regarding knowledge content; as well as The target model is used to generate a knowledge graph based on the user input, which includes multiple nodes and edges between the multiple nodes. The multiple nodes indicate multiple knowledge points, and the edges indicate the relationships between the multiple knowledge points. The knowledge graph is then visualized in the interface.

2. The method of claim 1, wherein generating a knowledge graph comprising multiple nodes and edges between the multiple nodes based on the user input using a target model comprises: The target model is used to identify multiple noun concepts from the user input as the multiple nodes, or the multiple nodes are determined by performing content reasoning on the user input; The target model is used to determine the edges between the multiple nodes by analyzing the reference relationships between the multiple nominal concepts; as well as The knowledge graph is generated based on the plurality of nodes and the edges.

3. The method according to claim 1, wherein the plurality of nodes are plurality of three-dimensional celestial bodies, the knowledge graph is a three-dimensional celestial body graph, and the method further comprises: In response to receiving a drag operation for a target three-dimensional celestial body, the target three-dimensional celestial body is moved according to the drag operation; as well as Based on the movement of the target three-dimensional celestial body, a connected three-dimensional celestial body is moved, wherein the movement includes a movement speed and a movement direction, and the connected three-dimensional celestial body includes a three-dimensional celestial body that is directly or indirectly connected to the target three-dimensional celestial body.

4. The method of claim 3, wherein the interface includes a force adjustment component, and moving the connected three-dimensional celestial body based on the movement of the target three-dimensional celestial body comprises: Based on the movement of the target three-dimensional celestial body and the interaction force between the target three-dimensional celestial body, the movement direction and speed of the connected three-dimensional celestial body are determined, wherein the interaction force is determined according to the closeness between the knowledge points; as well as The connected three-dimensional celestial body is moved according to the direction and speed of movement.

5. The method according to claim 1, further comprising: The interface retrieves two nodes selected by the user from the plurality of nodes, serving as the start and end points; A knowledge path is determined in the knowledge graph based on the starting point and the ending point, wherein the knowledge path includes the nodes and edges traversed from the starting point to the ending point; as well as The nodes and edges included in the knowledge path are highlighted in the knowledge graph.

6. The method according to claim 1, further comprising: In response to receiving a first interactive operation for a target node, a summary of the target node is displayed; as well as In response to receiving a second interactive operation for a target node, a description of the target node is displayed, wherein the description includes at least one of the name and explanation of a knowledge point corresponding to the target node.

7. The method according to claim 6, wherein the plurality of nodes are plurality of three-dimensional celestial bodies, the knowledge graph is a three-dimensional celestial body graph, the user input includes plurality of application scenarios corresponding to the plurality of knowledge points, the three-dimensional celestial body graph includes plurality of three-dimensional microcelestial bodies, and the method further includes: The interface displays the multiple three-dimensional celestial bodies and their names, the edges between the multiple three-dimensional celestial bodies and their directions, and the multiple three-dimensional micro-celestial bodies and their scene names. The names are the names of the corresponding knowledge points, and the scene names are the names of the corresponding application scenarios. The multiple three-dimensional micro-celestial bodies have different colors and different sizes relative to the three-dimensional celestial bodies.

8. The method according to claim 1, wherein the plurality of nodes are a plurality of three-dimensional celestial bodies, the knowledge graph is a three-dimensional celestial body graph, the interface includes an adjustment component, and the method further includes: In response to receiving a first adjustment based on the adjustment component, the size of the plurality of three-dimensional celestial bodies is changed according to the first adjustment; In response to receiving a second adjustment based on the adjustment component, the thickness of the edge is changed according to the second adjustment; as well as In response to receiving a third adjustment based on the adjustment component, the spacing between the plurality of three-dimensional celestial bodies is changed according to the third adjustment.

9. The method of claim 1, wherein the interface further includes a filtering component, and the method further includes: In response to receiving filtering conditions based on the filtering component, one or more desired nodes are obtained according to the filtering conditions; as well as The interface displays one or more desired nodes and the edges between them.

10. The method of claim 1, wherein obtaining user input regarding knowledge content comprises: Receive the user input; The format of the user input is processed according to the target markup language; as well as The processed user input is provided to the target model as part of the prompt words.

11. The method of claim 1, wherein the plurality of nodes are three-dimensional celestial bodies, the knowledge graph is a three-dimensional celestial body graph, the interface includes a rotation component, and the method further comprises: In response to receiving a fourth adjustment based on the rotating component, the viewpoint from which the three-dimensional star map is presented is changed according to the fourth adjustment.

12. An apparatus for generating knowledge graphs, comprising: The user input acquisition module is configured to acquire user input about knowledge content. The knowledge graph generation module is configured to use a target model to generate a knowledge graph based on the user input, which includes multiple nodes and edges between the multiple nodes. The multiple nodes indicate multiple knowledge points, and the edges indicate the relationships between the multiple knowledge points. The knowledge graph is visualized and displayed on the interface.

13. An electronic device, comprising: At least one processing unit; At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 11 when executed by the at least one processing unit.

14. A computer program product having a computer program stored thereon, which, when executed by a processor, implements the method according to any one of claims 1 to 11.

Images