跳转到主要内容

热门内容

今日:


总体:


最近浏览:


Chinese, Simplified

在我之前的关于将Mermaid.js与ChatGPT一起使用以构建系统图的系列文章(第1部分和第2部分)中,我们研究了ChatGPT构建序列、活动、状态和C4模型的能力。

我有兴趣进一步探索这一点,下面是我关于使用PlantUML使用ChatGPT构建更复杂的图的下一个系列

PlantUML允许您根据文本描述创建广泛的图表。在目前的状态下,除了所有UML图之外,它还可以支持甘特图、思维导图、概念图等

我对构建思维导图特别感兴趣,所以这是我关于PlantUML系列的第一篇文章。我与ChatGPT的交互,并使用它与PlantUML创建思维导图

SA

思维导图简介

Prompt: What's a mindmap

ChatGPT: A mind map represents ideas or information organized around a central concept or key idea. Mind maps are often used to visually organize information and create a clear structure for thoughts and concepts. The nodes in a mind map can branch out to show relationships between ideas. They can be colour-coded, labelled with icons, or annotated with text to clarify the relationships further. Mind maps are commonly used in note-taking, brainstorming, problem-solving, and decision-making, as they help to capture and organize thoughts visually and intuitively.

基本思维导图

Prompt: Okay, Let's start by creating a simple MindMap on the topic of Artificial Intelligence

Can you give the mindmap in PlantUML format. Keep it structured from the core central topic branching out to other domains and sub-domains. Let's go to 4 levels to begin with. Add the start and end mindmap tags and keep it expanding on one side for now

ChatGPT: Sure, here's a simple mind map of the topic "Artificial Intelligence" in PlantUML format, with four levels

@startmindmap
* Artificial Intelligence
** AI Technologies
*** Machine Learning
**** Supervised Learning
**** Unsupervised Learning
**** Reinforcement Learning
*** Natural Language Processing (NLP)
**** Sentiment Analysis
**** Part-of-Speech Tagging
**** Named Entity Recognition
@endmindmap

为了将其可视化,让我们打开draw.io或diagrams.net,然后转到

排列->插入->高级->PlantUML

并粘贴上面的片段

SA

opening plantUML diagrams in draw.io

下面是可视化

basic MindMap in plantUML

凉的我们有思维导图!!

让我们试着调整一些设置。

提高级别

Prompt: Can you increase it by two more levels and add further domains

ChatGPT: Sure, here's the expanded mind map of the topic "Artificial Intelligence" in PlantUML format, with six levels:

@startmindmap
* Artificial Intelligence
** AI Technologies
*** Machine Learning
**** Supervised Learning
***** Regression
***** Classification
**** Unsupervised Learning
***** Clustering
***** Association Rules
**** Reinforcement Learning
*** Natural Language Processing (NLP)
**** Sentiment Analysis
***** Polarity Analysis
***** Emotion Analysis
**** Part-of-Speech Tagging
**** Named Entity Recognition
** AI Applications
*** Computer Vision
**** Object Recognition
**** Image Segmentation
*** Robotics
**** Navigation
**** Manipulation
*** Speech Recognition
**** Speaker Verification
**** Speech Synthesis
@endmindmap

Representation of six levels of mindmap

添加颜色代码

接下来,让我们为我们的思维导图添加颜色代码。

注意:我必须提供提供颜色代码的语法,因为ChatGPT可能使用了一个旧的语法,该语法在预处理时破坏了plantUML代码

Prompt: Can you add colour codes to the above mind map? Use the format *[#FFFF00] Artificial Intelligence. The above is just an example; use your colour codes for each node based on the complexity of each node in terms of the time it takes to learn that topic for a beginner

ChatGPT: Here's an updated version of the mindmap, with colour codes indicating the complexity of each topic

@startmindmap

*[#red] Artificial Intelligence

**[#red] AI Technologies

***[#orange] Machine Learning

****[#orange] Supervised Learning

*****[#yellow] Regression

*****[#yellow] Classification

****[#orange] Unsupervised Learning

*****[#yellow] Clustering

*****[#yellow] Association Rules

****[#orange] Reinforcement Learning

***[#orange] Natural Language Processing (NLP)

****[#yellow] Sentiment Analysis

*****[#green] Polarity Analysis

*****[#green] Emotion Analysis

****[#yellow] Part-of-Speech Tagging

****[#yellow] Named Entity Recognition

**[#red] AI Applications

***[#orange] Computer Vision

****[#yellow] Object Recognition

****[#yellow] Image Segmentation

***[#orange] Robotics

****[#yellow] Navigation

****[#red] Manipulation

***[#orange] Speech Recognition

****[#yellow] Speaker Verification

****[#yellow] Speech Synthesis

@endmindmap

和表示

colour coded mindmap

但是这些颜色是什么意思?让我试着找到一个传奇

Prompt: can you create a PlantUML legend for the colour codes above? Mark them against the time duration based on which the colours were selected

ChatGPT: Here is a PlantUML legend for the colour codes, indicating the time duration for a beginner to learn each topic:

legend
- Green: Topics that can be learned in less than a week (around 10-20 hours of study)
- Yellow: Topics that take a few weeks to a month to learn (around 30-50 hours of study)
- Orange: Topics that take a few months to learn (around 100-150 hours of study)
- Red: Topics that require substantial effort and time to learn (around 200-300 hours or more of study)
endlegend

和在draw.io中导入

legend

太好了,我们有一个带有颜色代码的思维导图和一个相应的图例,其中包含每个颜色代码的描述。

添加图标

接下来,让我们尝试将图标添加到我们的思维导图中

注意:我必须提供提供图标的语法,因为ChatGPT可能使用了一种旧的语法,它在预处理时破坏了plantUML代码

Prompt: Can you add icons to the above MindMap using plantUML-supported icons from the open iconic library? The format for usage is as *[#red] <&star> Manipulation. The above is an example of a red colour node and start icon from the open iconic library. Keep the same colour codes as above but use relevant icons as appropriate

ChatGPT:

@startmindmap
*[#red] <&home> Artificial Intelligence
**[#red] <&aperture> AI Technologies
***[#orange] <&puzzle-piece> Machine Learning
****[#orange] <&tag> Supervised Learning
*****[#yellow] <&code> Regression
*****[#yellow] <&circle-check> Classification
****[#orange] <&dashboard> Unsupervised Learning
*****[#yellow] <&list> Clustering
*****[#yellow] <&tag> Association Rules
****[#orange] <&pulse> Reinforcement Learning
***[#orange] <&cog> Natural Language Processing (NLP)
****[#yellow] <&pulse> Sentiment Analysis
*****[#green] <&arrow-top> Polarity Analysis
*****[#green] <&eye> Emotion Analysis
****[#yellow] <&tag> Part-of-Speech Tagging
****[#yellow] <&bookmark> Named Entity Recognition
**[#red] <&aperture> AI Applications
***[#orange] <&image> Computer Vision
****[#yellow] <&target> Object Recognition
****[#yellow] <&crop> Image Segmentation
***[#orange] <&code> Robotics
****[#yellow] <&map-marker> Navigation
****[#red] <&star> Manipulation
***[#orange] <&microphone> Speech Recognition
****[#yellow] <&person> Speaker Verification
****[#yellow] <&audio> Speech Synthesis
@endmindmap

和代表

icons from the open iconic library in plantUML

这些图标看起来并不都合适,但至少是ChatGPT根据主题映射关闭图标的一次非常好的尝试。

进入下一步

添加说明

Prompt: Can you add a definition to only the leaf nodes? These definitions should be word-wrapped using PlantUML format and not have a surrounding box. Keep the Icons and Colors of the nodes as-is, and add additional description nodes to all leaf nodes. The format for adding leaf nodes is ****_ description

ChatGPT:

@startmindmap
*[#red] <&home> Artificial Intelligence
**[#red] <&aperture> AI Technologies
***[#orange] <&puzzle-piece> Machine Learning
****[#orange] <&tag> Supervised Learning
*****[#yellow] <&code> Regression
******_ A statistical approach to finding the relationship between a dependent and one or more independent variables.
*****[#yellow] <&circle-check> Classification
******_ The task of categorizing a set of data into classes based on their features.
****[#orange] <&dashboard> Unsupervised Learning
*****[#yellow] <&list> Clustering
******_ A method of organizing a set of data into groups (clusters) based on their similarities.
*****[#yellow] <&tag> Association Rules
******_ A statistical approach for finding relationships between variables in large datasets.
****[#orange] <&pulse> Reinforcement Learning
*****_ An area of machine learning that focuses on training an agent to make a sequence of decisions by maximizing a reward.
***[#orange] <&cog> Natural Language Processing (NLP)
****[#yellow] <&pulse> Sentiment Analysis
*****[#green] <&arrow-top> Polarity Analysis
******_ A method of identifying the sentiment expressed in a text as positive, negative, or neutral.
*****[#green] <&eye> Emotion Analysis
******_ The task of detecting and classifying emotions in text or speech.
****[#yellow] <&tag> Part-of-Speech Tagging
*****_ The task of marking each word in a sentence with its corresponding part of speech, such as noun, verb, adjective, etc.
****[#yellow] <&bookmark> Named Entity Recognition
*****_ A NLP technique that identifies named entities in a text, such as organizations, people, locations, etc.
**[#red] <&aperture> AI Applications
***[#orange] <&image> Computer Vision
****[#yellow] <&target> Object Recognition
*****_ The task of recognizing objects in images or videos based on their features and attributes.
****[#yellow] <&crop> Image Segmentation
*****_ The process of dividing an image into multiple segments or regions, each of which corresponds to a different object or part of the image.
***[#orange] <&code> Robotics
****[#yellow] <&map-marker> Navigation
*****_ The task of guiding a robot from one place to another.
****[#red] <&star> Manipulation
*****_ The task of manipulating objects in the environment using a robot.
***[#orange] <&microphone> Speech Recognition
****[#yellow] <&person> Speaker Verification
*****_ The task of verifying the identity of a speaker based on their speech.
****[#yellow] <&audio> Speech Synthesis
*****_ The task of generating speech from text.
@endmindmap

and the representation

leaf nodes with descriptions (no boxes)

就在这里。用ChatGPT制作的复杂思维导图,用图例、图标和描述性进行颜色编码。

感谢阅读!

本文地址
最后修改
星期一, 五月 29, 2023 - 22:09
Article