Mind mapping construction method and device, equipment and medium

Abstract

The invention provides a mind map construction method and device, equipment and a medium, and the method comprises the steps: generating a first father node through a preset language model based on the input content of a user; in response to a first confirmation operation of the user, generating a corresponding first child node based on the first father node by using the language model, and confirming a first node operation of the user on the first child node; when the first node operation is a second confirmation operation, taking the first child node as a second father node, and generating a corresponding second child node based on the second father node by using the language model; and when the first node operation is an end operation, responding to the end operation, and constructing a target mind map based on all the generated nodes. Compared with the scheme of generating the mind map by one key in the prior art, the method has the advantages that the user can confirm the nodes of each level in sequence, so that the modification operation of the user is reduced, and the mind map generation efficiency can be effectively improved.

Description

Technical Field

[0001] The present invention application relates to the field of artificial intelligence, and particularly to a method, device, equipment and medium for constructing a mind map. Background Art

[0002] The English name of the mind map is The Mind Map, also known as the mental map. It is a graphical thinking tool for expressing divergent thinking, with the characteristics of simplicity, efficiency and practicality. By using the technique of combining pictures and texts, it shows the relationships of various levels of themes with a hierarchical diagram of mutual subordination and correlation, and establishes memory links between the theme keywords and images, colors, etc., which can make full use of the functions of the left and right brains of people and activate the potential of the brain.

[0003] With the development of science and technology, artificial intelligence has gradually been applied to various technical fields. At present, the method for generating a mind map based on artificial intelligence mainly generates all the contents of the mind map at one time, including all the interconnected nodes and the contents of each node. Therefore, when the mind map does not match the content required by the user, the user needs to manually modify the structure and content of the mind map, resulting in the problem of low efficiency in generating the mind map. Summary of the Invention

[0004] The present invention application provides a method, device, equipment and medium for constructing a mind map to solve the technical problem of how to improve the efficiency of generating a mind map.

[0005] To solve the above technical problem, the present invention application provides a method for constructing a mind map, including:

[0006] Based on the input content of the user, use a preset language model to generate a first parent node;

[0007] In response to the user's first confirmation operation, use the language model to generate corresponding first child nodes based on the first parent node, and confirm the user's first node operation on the first child nodes;

[0008] When the first node operation is a second confirmation operation, use the first child node as a second parent node, and use the language model to generate corresponding second child nodes based on the second parent node;

[0009] When the first node operation is an end operation, in response to the end operation, construct a target mind map based on all the generated nodes.

[0010] As a preferred solution, the method for constructing the mind map further includes:

[0011] Confirm the user's second node operation on the second child nodes;

[0012] When the operation of the second node is the third confirmation operation, in response to the third confirmation operation, the second child node is used as the third parent node, and based on the third parent node and all the superior nodes of the third parent node by using the language model, the third child node corresponding to the third parent node is generated.

[0013] As a preferred solution, after generating the first parent node by using the preset language model, the method for constructing the mind map further includes:

[0014] In response to the first editing operation of the user, the content of the first parent node is modified to obtain the updated first parent node.

[0015] As a preferred solution, the operation of the first node further includes a second editing operation; after generating the first child node corresponding to the first parent node, the method for constructing the mind map further includes:

[0016] In response to the second editing operation, the content of the first child node and all the superior nodes of the first child node are updated, and the updated first child node is used as the second parent node.

[0017] As a preferred solution, the target mind map adopts a theme list in Markdown format.

[0018] Correspondingly, the present invention application further provides a device for constructing a mind map, including a first generation module, a first confirmation module, a second generation module and a construction module; wherein,

[0019] The first generation module is configured to generate a first parent node based on the input content of the user by using a preset language model;

[0020] The first confirmation module is configured to, in response to the first confirmation operation of the user, generate a first child node corresponding to the first parent node by using the language model, and confirm the first node operation of the user on the first child node;

[0021] The second generation module is configured to, when the operation of the first node is the second confirmation operation, use the first child node as the second parent node and generate a second child node corresponding to the second parent node by using the language model;

[0022] The construction module is configured to, when the operation of the first node is the end operation, in response to the end operation, construct a target mind map based on all the generated nodes.

[0023] As a preferred solution, the construction device further includes a third generation module; the third generation module is configured to:

[0024] Confirm the user's second node operation on the second child node;

[0025] When the second node operation is a third confirmation operation, in response to the third confirmation operation, use the second child node as the third parent node, and based on the third parent node and all its superior nodes, generate the third child node corresponding to the third parent node using the language model.

[0026] As a preferred solution, the construction device further includes a first update module, which is configured to, after generating the first parent node using the preset language model: in response to the user's first editing operation, modify the content of the first parent node to obtain the updated first parent node.

[0027] As a preferred solution, the construction device further includes a second update module, which is configured to, after generating the corresponding first child node based on the first parent node: in response to the second editing operation, update the content of the first child node and all its superior nodes, and use the updated first child node as the second parent node.

[0028] As a preferred solution, the target mind map adopts a theme list in Markdown format.

[0029] Correspondingly, the present invention application also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the construction method of the mind map is implemented.

[0030] Correspondingly, the present invention application also provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the construction method of the mind map.

[0031] Compared with the prior art, the present invention application has the following beneficial effects:

[0032] The present invention provides a method, apparatus, device, and medium for constructing a mind map. Based on the user input content, a first parent node is generated using a preset language model. After the user's confirmation operation, corresponding first child nodes are further generated. Further, when the user confirms the first child nodes, second child nodes are generated, or when the user finishes confirmation, a target mind map is obtained in response to the end operation. Compared with the prior art one-button mind map generation solution, there is no need for the user to modify each node of the mind map one by one. The user can confirm each level of nodes in sequence, reducing the user's modification operations and avoiding the need to regenerate from scratch when the generated target mind map does not match the user's requirements, which can effectively improve the mind map generation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 : A flowchart of an embodiment of the method for constructing a mind map provided by the present invention application.

[0034] Figure 2 : A schematic diagram of the principle of an embodiment of the method for constructing a mind map provided by the present invention application.

[0035] Figure 3 : A schematic structural diagram of an embodiment of the apparatus for constructing a mind map provided by the present invention application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0037] Embodiment 1

[0038] Please refer to Figure 1 , Figure 1 A method for constructing a mind map provided by the present invention application, including steps S101 to S104. Each step is described in detail as follows:

[0039] Step S101, based on the user input content, generate a first parent node using a preset language model.

[0040] The method for constructing a mind map in this embodiment can be applied to a computer device, which includes but is not limited to a smart phone, a notebook computer, a tablet computer, a desktop computer, and physical servers and cloud servers connected with a display unit, etc.

[0041] In this step, the above computer device can receive the user's input content through an external device; use the user's input content as the central theme or question, and as the prompt of the above preset language model, and generate the first parent node of the target mind map according to the output of the language model, which is also the initial node A (or can also be called the first-level node), as Figure 2 shown.

[0042] Specifically, the language model can be a Large Language Model (LLM for short), which specifically refers to a deep learning model trained with a large amount of text data. This model can generate natural language text or understand the meaning of language text. Its core idea is to learn the patterns and structures of natural language through large-scale unsupervised training, and to simulate the human language cognition and generation process to a certain extent.

[0043] Step S102, in response to the user's first confirmation operation, use the language model to generate corresponding first child nodes based on the first parent node, and confirm the user's first node operation on the first child nodes.

[0044] In this embodiment, the user confirms the content of the first parent node. For example, after the first parent node is generated in step S101, an interaction window is displayed on the application interface, and the content of the interaction window includes text prompting the user to perform a confirmation operation. The user presses the Enter key on the keyboard or clicks "Yes" with the mouse to perform the first confirmation operation.

[0045] In one implementation of this step, the computer device responds to the user's first confirmation operation, uses the above language model, and generates corresponding first child nodes based on the first parent node (such as Figure 2 B1, B2 and / or B3 shown), generates an initial mind map, the initial mind map includes the first parent node and the first child nodes, and the first parent node is connected to the first child nodes. This initial mind map is presented through a Markdown format theme list.

[0046] Exemplarily, the basic structure of Markdown includes elements such as headings, paragraphs, emphasis, lists, quotes, and / or code blocks, etc. Using # represents a first-level heading, ## represents a second-level heading, and so on.

[0047] In this application, # can represent the user input content or the first parent node. When # represents the user input content, ## represents the first parent node, and represents the first child node; when # represents the first parent node, ## represents the first child node.

[0048] Any child node generated in this step is an expansion and extension of the user input content and its parent node or all upper-level nodes to ensure that the generated results are closely centered around the subject requirements of the user input.

[0049] In another implementation of this step, the computer device responds to the user's first editing operation and modifies or proofreads the content of the first parent node to obtain an updated first parent node, so that the updated first parent node can be used to generate the corresponding first child node.

[0050] In this step, the user can not only edit or modify the first parent node, but also edit or modify the initial input content to ensure flexible adjustment of the mind map content.

[0051] Furthermore, the first node operation includes a second confirmation operation, a first end operation, and a second edit operation. The user can make a selection through an external device, such as a keyboard or a mouse.

[0052] Step S103: when the first node operation is a second confirmation operation, the first child node is used as a second parent node, and a corresponding second child node is generated based on the second parent node using the language model.

[0053] Specifically, Figure 2 As shown, when the first node operation is the second confirmation operation, the first child node is used as the second parent node, and the language model is used to generate corresponding second child nodes C1, C2 and / or C3 based on the second parent node.

[0054] In another embodiment, when the first node operation is the second editing operation, the computer device responds to the second editing operation, updates the content of the first child node and all parent nodes of the first child node, and uses the updated first child node as the second parent node; and can generate a corresponding second child node through the updated first child node or second parent node.

[0055] By analogy with the above content, when the user edits or modifies the first child node, and the second child node, third child node, ..., nth child node that may be generated subsequently, any upper-level node corresponding to these child nodes can also be edited, and the user can choose to manually modify and update the lower-level nodes or have the language model update them, so that the system considers the latest content of all levels when generating next time.

[0056] Step S104, when the first node operation is an end operation, in response to the end operation, a target mind map is constructed based on all generated nodes.

[0057] As described above, the method for constructing the mind map further includes: confirming a second node operation of the user on the second child node; when the second node operation is a third confirmation operation, in response to the third confirmation operation, taking the second child node as a third parent node, and using the language model to generate third child nodes corresponding to the third parent node based on the third parent node and all the superior nodes of the third parent node.

[0058] Similarly, the second node operation further includes a third editing operation or the above-mentioned end operation. The third editing operation can update the content of the second child node and all the superior nodes of the second child node, and take the updated second child node as the third parent node.

[0059] When the end operations of all the nodes of the initial mind map are completed, a target mind map is constructed based on all the generated nodes.

[0060] It should be noted that for any node, the node content at the current level can be expanded and generated based on the content of the previous level plus the comprehensive information of all the previous levels. The system can separately mark the node content of the previous level to ensure the relevance of the newly generated node to the content of the previous level, and at the same time help the user to more clearly understand the logical relationship between the child node and the corresponding parent node.

[0061] In this embodiment, the input of the large model can be the above-mentioned Markdown structure as context information to help generate the next-level nodes and construct the logical association of the nodes in the same branch, avoiding phenomena such as logical contradictions or logical irrelevance between node A and node C2.

[0062] The way of model expansion can adopt the prompt of Function Call. Function Call is a function that allows developers to describe functions when calling a large model and enables the model to intelligently output a JSON object containing the parameters required to call these functions.

[0063] This function can more reliably connect the capabilities of the large model with external tools and application programming interfaces (Application Programming Interface, abbreviated as API), thus realizing richer application scenarios. Using Function Call can make the large language model output JSON structured text in a specified format to ensure that the generated content conforms to the predefined format.

[0064] When the user modifies or edits the content of nodes in the previous level, the system will replace the text information previously generated by the large model with the content edited by the user as the basis for subsequent generation. The system will dynamically update the context information and reconstruct the Prompt content, which is then passed to the large model for generation. This process ensures that the subsequent generated topic content can be closely combined with the information modified by the user and is consistent with the user's requirements.

[0065] When all node contents meet the user's requirements, the target mind map is displayed. In addition, in this implementation, through the Stream parameter, the large language model is allowed to output the generated content verbatim, thereby reducing the user's waiting time and improving the user experience.

[0066] In some examples, by analyzing the first half of the model output, the missing JSON structure is automatically completed to ensure that the output JSON string can be correctly parsed; open-source tools are used to repair the JSON structure to ensure that even if the output is incomplete during the Streaming process, a parsable JSON string can be obtained.

[0067] The method for constructing a mind map according to any implementation manner of this embodiment can be widely applied to fields such as education, business planning, and / or personal development, supporting users to gradually generate and correct a mind map during the construction process of a complex knowledge structure, and improving the organization and readability of information.

[0068] Correspondingly, as Figure 3 shown, the present invention application also provides a mind map construction device 300, including a first generation module 301, a first confirmation module 302, a second generation module 303, and a construction module 304; wherein,

[0069] The first generation module 301 is configured to generate a first parent node based on the input content of the user by using a preset language model;

[0070] The first confirmation module 302 is configured to, in response to the user's first confirmation operation, use the language model to generate corresponding first child nodes based on the first parent node and confirm the user's first node operation on the first child nodes;

[0071] The second generation module 303 is configured to, when the first node operation is a second confirmation operation, use the first child node as a second parent node and generate corresponding second child nodes based on the second parent node by using the language model;

[0072] The construction module 304 is configured to, when the first node operation is an end operation, in response to the end operation, construct a target mind map based on all the generated nodes.

[0073] As a preferred solution, the construction device 300 further includes a third generation module; the third generation module is used to:

[0074] Confirm the user's second node operation on the second child node;

[0075] When the second node operation is a third confirmation operation, respond to the third confirmation operation, use the second child node as the third parent node, and use the language model to generate the third child node corresponding to the third parent node based on the third parent node and all its superior nodes.

[0076] As a preferred solution, the construction device 300 further includes a first update module, and the first update module is used to, after generating the first parent node using the preset language model: respond to the user's first editing operation, modify the content of the first parent node, and obtain the updated first parent node.

[0077] As a preferred solution, the construction device 300 further includes a second update module, and the second update module is used to, after generating the corresponding first child node based on the first parent node: respond to the second editing operation, update the content of the first child node and all its superior nodes, and use the updated first child node as the second parent node.

[0078] As a preferred solution, the target mind map adopts a Markdown format topic list.

[0079] Correspondingly, the present invention application further provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the mind map construction method described above is implemented.

[0080] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc. The processor is the control center of the terminal and connects various parts of the entire terminal through various interfaces and lines.

[0081] The memory can be used to store the computer program. By running or executing the computer program stored in the memory and calling the data stored in the memory, the processor realizes various functions of the terminal. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0082] Correspondingly, the present invention application also provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the method for constructing the mind map described above.

[0083] Among them, if the module integrated in the mind map construction device / terminal is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0084] Compared with the prior art, the present invention application has the following beneficial effects:

[0085] The present invention application provides a method, apparatus, device and medium for constructing a mind map. Based on the user input content, a first parent node is generated using a preset language model. After the user's confirmation operation, corresponding first child nodes are further generated. Further, when the user performs a confirmation operation on the first child nodes, second child nodes are generated, or when the user finishes the confirmation, a target mind map is obtained in response to the end operation. Compared with the one-key generation scheme of the mind map in the prior art, there is no need for the user to modify each node of the mind map one by one. The user can confirm each level of nodes in turn, reducing the user's modification operations and avoiding the need to regenerate from scratch when the generated target mind map does not match the user's requirements, which can effectively improve the efficiency of mind map generation.

[0086] In the specific embodiments described above, the purpose, technical solution and beneficial effects of the present invention have been further described in detail. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. In particular, it is pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for constructing a mind map, characterized in that: include: Based on the user's input content, a first parent node is generated using a preset language model; In response to a first confirmation operation by the user, using the language model, generating a corresponding first child node based on the first parent node, and confirming a first node operation of the user on the first child node; When the first node operation is a second confirmation operation, taking the first child node as a second parent node, and using the language model to generate a corresponding second child node based on the second parent node; When the first node operation is an end operation, in response to the end operation, a target mind map is constructed based on all generated nodes.

2. A method for constructing a mind map as claimed in claim 1, characterized in that: The method for constructing the mind map also includes: confirming a user's second node operation on the second sub-node; When the second node operation is a third confirmation operation, in response to the third confirmation operation, the second child node is used as a third parent node, and the language model is used to generate a third child node corresponding to the third parent node based on the third parent node and all upper nodes of the third parent node.

3. A method for constructing a mind map as claimed in claim 1, characterized in that: After the first parent node is generated by using the preset language model, the mind map construction method further includes: In response to a first editing operation by the user, the content of the first parent node is modified to obtain an updated first parent node.

4. A method for constructing a mind map as claimed in claim 1 or 2, characterized in that: The first node operation further includes a second editing operation; after generating the corresponding first child node based on the first parent node, the mind map construction method further includes: In response to the second editing operation, the content of the first child node and all parent nodes of the first child node are updated, and the updated first child node is used as the second parent node.

5. A method for constructing a mind map as claimed in claim 1, characterized in that: The target mind map uses a list of topics in Markdown format.

6. A mind map construction device, characterized in that: It includes a first generation module, a first confirmation module, a second generation module and a construction module; wherein, The first generating module is used to generate a first parent node based on the user's input content using a preset language model; The first confirmation module is used to, in response to a first confirmation operation of the user, generate a corresponding first child node based on the first parent node using the language model, and confirm the first node operation of the user on the first child node; The second generating module is used to use the first child node as a second parent node and generate a corresponding second child node based on the second parent node by using the language model when the first node operation is a second confirmation operation; The construction module is used to respond to the end operation when the first node operation is an end operation, and to construct a target mind map based on all generated nodes.

7. A mind map construction device as claimed in claim 6, characterized in that: The construction device further includes a third generation module; the third generation module is used to: confirming a user's second node operation on the second sub-node; When the second node operation is a third confirmation operation, in response to the third confirmation operation, the second child node is used as a third parent node, and the language model is used to generate a third child node corresponding to the third parent node based on the third parent node and all upper nodes of the third parent node.

8. A mind map construction device as claimed in claim 6, characterized in that: The construction device also includes a first updating module, which is used to respond to a first editing operation of a user to modify the content of the first parent node and obtain an updated first parent node after the first parent node is generated by using a preset language model.

9. A mind map construction device as claimed in claim 6 or 8, characterized in that: The construction device also includes a second updating module, which is used to respond to the second editing operation, after the corresponding first child node is generated based on the first parent node, to update the content of the first child node and all upper-level nodes of the first child node, and use the updated first child node as the second parent node.

10. A mind map construction device as claimed in claim 6, characterized in that: The target mind map uses a list of topics in Markdown format.

11. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for constructing a mind map as claimed in any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for constructing a mind map as claimed in any one of claims 1 to 5.

Images