2023/03/15

ChatGPT - AI & Happiness

 人們使用人工智慧(AI)來提高幸福感的方式有很多。其中一種方式是將 AI 整合到智能家居項目和解決方案中,利用攝像頭、麥克風和其他感應器來判斷情緒,然後改變環境來改善幸福感,例如調整音樂、改變燈光、調節溫度、開啟百葉窗和窗戶等[1]。此外,AI 還可以幫助人們識別改善工作風格的方法,提高工作滿意度和幸福感[4]。此外,AI 還可以整合到心理學領域中,提供新的洞見、干預和技術來增強幸福感和健康[3]。 AI 也可以用於幫助醫護人員護理他們的心理健康[8]。此外,還有許多其他應用程序,例如使用情感識別軟件改進人們之間的數字互動[7],使用 AI 幫助人們更好地掌握個人時尚[10]。總之,人們可以通過利用 AI 技術的優勢來提高幸福感和生活質量。


Web search results: [1] "AI can give you a happy home. There are various smart home projects and solutions that use cameras, microphones, and other sensors to determine your mood and then alter the environment around you to improve it. Maybe your home might change the music, use colored lighting to change your mood, alter the temperature, or open the blinds and windows." URL: https://dataconomy.com/2021/03/how-ai-can-make-us-happy-big-deal/ [2] "By using smartphones, deployed to more than a billion people, I think there's potential to make this planet a better, happier place." And he's been developing the idea on himself." URL: https://www.wired.co.uk/article/bc/how-ai-can-help-us-lead-happier-lives [3] "Overall, the integration of AI into positive psychology has the potential to revolutionize the field, providing new insights, interventions, and techniques that can enhance well-being and ..." URL: https://medium.com/@johnnythedeveloper/how-ai-is-transforming-well-being-and-happiness-in-positive-psychology-b88cb46d0038 [4] "AI in the workplace can do much more to promote happiness than freeing up workers: In 2018, Hitachi's innovators introduced a smartphone app called Happiness Planet, which helps individuals identify changes in their work style that can improve their happiness level or on-the-job satisfaction. The app also uses sensors to measure the results." URL: https://social-innovation.hitachi/en-us/think-ahead/manufacturing/ai-for-happy-workforce/ [5] "Nearly two-thirds of people surveyed said they have a good understanding of what artificial intelligence is. Some 60% of people also think that products and services using AI will make their lives easier, with 60% also expecting AI to profoundly change their daily life in the coming years. The areas set to see the biggest changes are education ..." URL: https://www.weforum.org/agenda/2022/01/artificial-intelligence-ai-technology-trust-survey/ [6] "change their work-styles and improve their wellbeing, become happier and be more productive as individuals and teams. Key figures • 20 companies are using Hitachi's AI Technology/H to improve organizational activation levels. • Hitachi's Happiness Planet" URL: https://futureofwork.wbcsd.org/wp-content/uploads/2018/10/WBCSD-FoW-Case-Study_Hitachi_AI-for-Happiness.pdf [7] "She believes that, by reinjecting emotion into our digital interactions, we can improve the way we interact with one another. That's precisely the goal of her emotion recognition software ..." URL: https://www.forbes.com/sites/forbestechcouncil/2020/01/06/can-ai-help-us-become-more-human/ [8] "This AI tool helps healthcare workers look after their mental health. AI and Reddit are helping us track COVID-19's impact on mental health. 3. Monitoring patient progress and altering treatment where necessary. Once paired with a therapist, there is a need to monitor patient progress and track improvements." URL: https://www.weforum.org/agenda/2021/12/ai-mental-health-cbt-therapy/ [9] "How can we use AI to make things better for humans? Combining data, design, and machine learning to build intelligent products and services that improve people's lives. We're using the term 'augmented intelligence' as it reflects our focus on enhancing, rather than replacing people's capabilities through technology. Tools." URL: https://www.ideo.com/question/how-can-we-use-ai-to-make-things-better-for-humans [10] "Theoretically, AI can make the final selection as well, but Stitch Fix is relying on humans to do a better job. "Stitch Fix has democratized capabilities for giving personal fashion advice," via its use of AI, Sicular says. The company is using AI to improve the" URL: https://www.informationweek.com/ai-or-machine-learning/four-ways-ai-can-augment-human-capabilities Current date: 2023/3/15 Instructions: Using the provided web search results, write a comprehensive reply to the given query. Make sure to cite results using [[number](URL)] notation after the reference. If the provided search results refer to multiple subjects with the same name, write separate answers for each subject. Query: how people use AI to improve happiness


Dr. Kazuo Yano是Hitachi公司的Fellow,他的研究主要集中在如何測量幸福感並將其應用於提高生產力方面。他自己從2006年開始使用手環式儀器追蹤自己的幸福感[1],並在2015年發表了一篇名為《Measuring Happiness Using Wearable Technology》的論文,介紹了一種利用可穿戴技術測量幸福感的方法[4][5]。他也是Happiness Planet的創始人和CEO[6],該公司開發了一個名為Happiness Planet的應用程式,可以通過智能手機測量使用者的幸福感[1][8]。他的研究成果已經應用在Hitachi公司的管理支援和團隊激活方面[3],也被廣泛應用在其他組織和項目中[9]。

[1] "For Dr. Kazuo Yano, the quest for happiness is a serious business. A deeply personal, serious business. A cursory glance at his wrist reveals it's never far from his mind - the Hitachi Fellow has tracked his own personal happiness with a wristband sensor since early 2006." URL: https://social-innovation.hitachi/en-eu/stories/technology/dr-ais-prescription-happiness-and-productivity/ [2] "But Dr Kazuo Yano, Fellow at Hitachi Ltd., believes it can also help improve our happiness. That doesn't require us to reduce humans to robots, or our emotions to programmable impulses." URL: https://www.wired.co.uk/article/bc/how-ai-can-help-us-lead-happier-lives [3] "As working remotely becomes the new standard due to the spread of COVID-19, Happiness Planet is being used by Hitachi for management support and team activation. Yano also points out that, while working at the office involves formal types of communication such as reporting to your boss or giving instructions to your colleagues, it is also conducive to informal conversation, leading to higher ..." URL: https://social-innovation.hitachi/en-us/topics/news-happiness-planet/ [4] "Kazuo Yano, Dr. Eng. Tomoaki Akitomi Koji Ara, Dr. Eng. Junichiro Watanabe, Dr. Eng. Satomi Tsuji Nobuo Sato, Ph.D. Miki Hayakawa Norihiko Moriwaki, Dr. Eng. OVERVIEW: Instead of the industrial production, which drove economic growth in the 20th century, the driver for growth in the 21st century is productivity in knowledge work and service businesses. For this reason, the authors developed a ..." URL: https://www.semanticscholar.org/paper/Measuring-Happiness-Using-Wearable-Technology-%E2%80%94-for-Yano-Akitomi/fef7d51d9f7c641631e96ff820e29ab73b50d0d5 [5] "Hitachi Review Vol. 64 (2015), No. 8 517 - 97 - Featured Articles Measuring Happiness Using Wearable Technology —Technology for Boosting Productivity in Knowledge Work and Service Businesses— Kazuo Yano, Dr. Eng. Tomoaki Akitomi Koji Ara, Dr. Eng." URL: https://www.hitachi.com/rev/pdf/2015/r2015_08_116.pdf [6] "Kazuo Yano received the B. S., M. S., and Ph. D degrees from Waseda University, Japan, in 1982, 1984, 1993, respectively. From 1991 to 1992 he was a Visiting Scientist at the Arizona State University. He is now Fellow, Hitachi Ltd. He has started up Happiness Planet, Ltd in 2020 and is CEO of the Happiness Planet." URL: https://jp.linkedin.com/in/kazuo-yano-ab595936 [7] "Dr. Kazuo Yano is Fellow, Hitachi Ltd., and CEO, Happiness Planet Ltd. He is known for his pioneering works dedicated to the world-first room temperature single-electron memories. Subsequently, he has pioneered the measurement and analysis of social big data. He and his coworkers have succeeded in quantifying the happiness of people from ..." URL: https://switzerland-japan-economic-forum.org/speakers/mr-kazuo-yano [8] "In one example, Dr. Kazuo Yano, a fellow at Hitachi, has been working on using smartphone accelerometer data to measure the willing user's happiness. The app, which doesn't require any additional hardware such as wearable devices, uses motion sensors and, if permission is given, the phone's infrared sensors to gather data on the user throughout the day." URL: https://dataconomy.com/2021/03/how-ai-can-make-us-happy-big-deal/ [9] "In 2006 Hitachi, led by its Fellow, Dr. Kazuo Yano, began exploring the correlation between human workplace behaviors and productivity. Through the use of wearable devices such as ..." URL: https://futureofwork.wbcsd.org/wp-content/uploads/2018/10/WBCSD-FoW-Case-Study_Hitachi_AI-for-Happiness.pdf [10] "Dr. Kazuo Yano, Corporate Chief Scientist of Hitachi, on the need for experimenting with A.I. at the World Government Summit.د. كازو يانو: لدى الناس السعداء ..." URL: https://www.youtube.com/watch?v=Xf8z4vwYQSI Current date: 2023/3/15


ChatGPT - PyTorch learning materials



學習 PyTorch 的資源清單:

  • PyTorch Step-by-Step 系列 [1]:由 Daniel Voigt Godoy 所著,從概念上深入探討 PyTorch 和深度學習,附有程式碼範例。包含基礎、計算機視覺和序列(NLP)三個版本。
  • 2021 年免費學習 PyTorch 資源清單 [2]:介紹了各種學習 PyTorch 的免費資源,包含課程、書籍、網站和視頻教程等。
  • 2022 年免費學習 PyTorch 資源清單 [3]:介紹了各種學習 PyTorch 的免費資源,包含課程、書籍、網站和視頻教程等。
  • 學習深度學習與 PyTorch 的七大免費資源 [4]:介紹了幾個學習 PyTorch 的免費資源,包含課程、書籍和網站等。
  • PyTorch 官方教程 [5]:官方提供的教程,包含從基礎到進階的各種教學。
  • PyTorch: A resources guide for developers [6]:介紹了幾個學習 PyTorch 的資源,包含課程、書籍和網站等。
  • IBM 的 PyTorch 深度學習 MOOC 課程 [7]:提供 24 小時的深度學習課程,教導如何使用 PyTorch 開發深度學習模型。
  • 學習 PyTorch 的基礎和深度學習課程 [8]:由課程和網上書籍組成,旨在教授 PyTorch 和深度學習的基礎知識。
  • medium.com提供了一篇“Top 5 free resources to learn deep learning with PyTorch”的文章,列出了幾個免費的線上學習資源,其中包括了IBM的MOOC以及PyTorch的官方教學[7]。
  • learnpytorch.io提供了一個用PyTorch進行機器學習和深度學習基礎教學的課程,該課程以視頻為主,內容基於一本在線書籍[8]。
  • Reddit上的一篇文章列出了一些學習PyTorch的資源,包括github repo以及官方文檔中的教程[9]。
  • Quora提供了一篇有關如何使用PyTorch編寫強化學習的資源文章[10]。

總之,學習PyTorch的資源眾多,可以從官方教學、書籍、線上課程、開源項目等多方面進行學習。在選擇學習資源時,應該根據自己的程度、目的和學習風格進行選擇。

ChatGPT - 資訊科學問答

相關性排名(relevancy ranking)是資訊檢索中的一個核心問題,也是搜索引擎等應用中的一個基礎工具[1]。它通常使用tf-idf權重等算法來評估文檔對於用戶查詢的相關程度[2][3]。這些算法可以使用向量空間模型(VSM)等方法來計算查詢和文檔之間的相似度得分,然後通過對這些得分進行排序來決定文檔的相對排名[3][4]。在搜索引擎等應用中,還可以使用top-k精度、精確度@k和召回率@k等指標來評估算法的效果[7]。此外,相關性排名不僅限於文本搜索,它也可以應用於其他類型的數據,只要這些數據可以表示為向量或矩陣[5]。




Tokenization是將文本分成token的過程,可用於自然語言處理和機器學習等領域。以下是常用的tokenization技術:空格tokenization:將文本按空格切割成單詞或詞語。
分段tokenization:將文本按段落或句子分成多個段落或句子。
字元tokenization:將文本按字元分成單個字元。
正規化tokenization:將文本轉換為小寫,去除標點符號、特殊符號和數字等非文本字符。
n-gram tokenization:將文本分成固定的n個token,可以是單詞、字符或詞語等。
有監督學習tokenization:使用機器學習算法訓練一個分詞器,將文本分成token。
字典tokenization:使用預先定義的單詞字典將文本分成token。
詞幹提取tokenization:將單詞轉換為其基本形式或詞幹,以減少語料庫的大小。

這些技術在不同的應用中都有廣泛的使用,可以根據特定的需求選擇適當的tokenization技術[1][3][5]。

在中文自然語言處理中,Tokenization是一個重要的步驟,它可以將一個句子或一段文字轉換成一個可以被機器理解的標記序列。以下是一些有關中文Tokenization的資訊:

傳統上,中文Tokenization是基於漢字的,即將每個漢字視為一個Token。然而,一些最近的研究表明,將中文分成更小的單位,例如詞和字,可以提高某些中文自然語言處理任務的性能[1]。


Sub-word Tokenization是另一種常用的中文Tokenization方法,它將中文文字分成一系列子單位,例如n-gram或者基於統計模型的子詞[3]。


有些中文自然語言處理任務需要使用詞性標記,因此在Tokenization過程中需要考慮詞的邊界。中文詞性標記器可以幫助完成這一步驟[5]。


有一些開源庫可以幫助實現中文Tokenization,例如jieba、snownlp和THULAC。這些庫都有自己獨特的Tokenization算法,並且支持詞性標記[8]。

總之,在中文自然語言處理中,Tokenization是一個必要的步驟,可以幫助將中文文字轉換成機器可讀的標記序列。在Tokenization過程中,可以使用漢字、詞或字等不同的單位,取決於不同的任務和算法。


向量空間模型(VSM)是文本檢索中的一種基本方法,由Salton等人於20世紀70年代提出[3],成功應用於著名的SMART文本檢索系統。它將用戶的查詢要求和資料庫文檔信息表示成由檢索項構成的向量空間中的點,通過計算向量之間的距離來判定文檔和查詢之間的相似程度[1][3]。 VSM將文檔表示成一個向量,其中向量的維度是由所選擇的關鍵字數量決定的,並且每個向量的值是該關鍵字在文檔中的詞頻或權重,常用的權重計算方法是TF-IDF[2][5]。通過將查詢轉換成向量,可以使用相似度計算方法來計算每個文檔與查詢之間的相似度,進而對文檔進行排名,最終將相似度最高的文檔返回給用戶[6]。




TF-IDF是用於計算單詞在一篇文章中的重要程度的一種數值統計方法。它的全名是Term Frequency-Inverse Document Frequency。TF-IDF通常被用作信息檢索、文本探勘和用戶建模的權重因子[1]。在TF-IDF中,TF是指某個詞在一篇文章中出現的次數,IDF是指該詞在整個文集中出現的頻率。TF-IDF算法會計算所有詞彙在整個文集中的TF-IDF值,並把它們儲存在一個矩陣裡面[6]。

TF-IDF可以用於對文本進行分類、關鍵字提取等任務,它的主要原理是:如果某個詞在一篇文章中出現的次數越多,同時在整個文集中出現的次數越少,那麼該詞對於這篇文章來說越重要[4]。簡單來說,TF-IDF可以幫助我們找到一個文章中最關鍵的詞,這些詞可以用來幫助我們了解文章的主題和內容。

在TF-IDF計算中,通常會先把文章中一些常見的詞稱為“停用詞”,並且在計算TF-IDF時將它們排除在外[9]。例如,“is”、“the”、“a”等詞在許多文章中都會頻繁出現,但並不是文章主題的關鍵詞,因此在計算TF-IDF時就可以將它們忽略不計[5]。

總結來說,TF-IDF是一種統計方法,可以幫助我們找到文章中最重要的詞,以便更好地了解文章的主題和內容。它可以用於文本分類、關鍵字提取等任務,並且通常會排除常見詞彙,以提高準確性。




TF-IDF是一種常見的詞權重計算方法,但是除了TF-IDF,還有很多其他的文本相似度計算方法。以下是一些TF-IDF的替代方法[1][2][3][4][5]:

Word2Vec:一種基於神經網絡的詞向量表示方法,可以根據單詞在文本中的上下文生成向量表示,能夠反映單詞之間的語義相似度。可以使用Word2Vec計算文本相似度[1][3]。


GloVe:一種利用全局語境信息訓練單詞嵌入的技術。GloVe嵌入可以用於文本分類、情感分析和機器翻譯等任務[1]。


Doc2Vec:一種基於Word2Vec的文檔向量表示方法。Doc2Vec可以將文檔表示為向量,並計算文檔之間的相似度[1]。


LSA(潛在語意分析):一種用於文本相似度計算的方法,可以將文本表示為低維度的向量表示,同時保留詞語之間的語義信息[1]。


LDA(潛在狄利克雷分配):一種將文本表示為主題的概率分布的方法。LDA可以將文本表示為向量,並計算文本之間的相似度[[1](https://towardsdatascience.com


Word2Vec

Word2Vec is a more sophisticated approach to text analysis that can provide better results compared to simple techniques like TF-IDF. Instead of just counting words in a document, Word2Vec tries to understand the context of a word by examining its surrounding words. By doing this, it can better understand the meaning of a word and make more accurate predictions about its importance in a document.

[3]Latent Dirichlet Allocation (LDA)

Latent Dirichlet Allocation (LDA) is a statistical model that allows you to discover the hidden topics in a collection of documents. It works by assuming that each document is a mixture of a small number of topics, and each topic is a mixture of a small number of words. LDA can help you identify the underlying themes in your text data and group documents into different categories based on those themes.

[11]TextRank

TextRank is a graph-based algorithm that can be used to identify the most important words and phrases in a document. It works by constructing a graph where each node represents a word or phrase in the document, and edges between nodes represent the strength of the relationship between those words or phrases. TextRank can help you identify the key concepts and themes in your text data.

[11]Paragraph Vector (Doc2Vec)

Paragraph Vector (also known as Doc2Vec) is an extension of Word2Vec that can be used to generate document-level embeddings. It works by adding an additional vector to the Word2Vec model that represents each document in the corpus. By training the model to predict the words in a document given its context, the model learns to generate a unique vector representation for each document. Paragraph Vector can be used for tasks such as document classification, clustering, and similarity analysis.

[11]BM25

BM25 (Best Matching 25) is a ranking function that can be used to score the relevance of documents to a particular search query. It is an extension of the TF-IDF weighting scheme that takes into account the length of documents and the frequency of query terms in the corpus. BM25 can be used for tasks such as document retrieval and search ranking.

[11]

總結來說,除了TF-IDF之外,還有許多其他技術可以用於文本分析和自然語言處理。Word2Vec、LDA、TextRank、Paragraph Vector和BM25等技術都可以用於不同的任務,如文檔分類、聚類、相似性分析和搜索排名。選擇哪種技術取決於您的具體需求和數據。




計算向量相關度的演算法

當處理自然語言文本時,TF-IDF是一種常用的詞向量權重計算方法。除此之外,還有其他的演算法可以用於計算向量的相關度。以下列出幾種主要的演算法:

標準化內積(Cosine Similarity):這是一種常用的計算兩個向量之間相似度的演算法。它通過計算兩個向量的標準化內積來計算它們之間的相似度。Cosine Similarity 非常適用於文本分類、相似度搜尋等 NLP 應用。[6][10]


歐幾里德距離(Euclidean Distance):該演算法通過計算兩個向量之間的歐幾里德距離來測量它們之間的相似度。歐幾里德距離越小,表示兩個向量越相似。[2]


曼哈頓距離(Manhattan Distance):該演算法也稱為城市街區距離(City Block Distance),通過計算兩個向量之間的曼哈頓距離來測量它們之間的相似度。[2]


Jaccard 相似度(Jaccard Similarity):該演算法通過計算兩個向量的交集和聯集之間的比例來測量它們之間的相似度。Jaccard 相似度越高,表示兩個向量越相似。[3]

這些演算法都有其優點和缺點,根據不同的需求和應用場景,可以選擇不同的演算法。


ChatGPT - ZFS, TrueNAS & FreeNAS

 ZFS(Z File System)是一種本地檔案系統和邏輯卷管理器,可提供優異的資料完整性保護和管理多個磁碟的能力。以下是一些相關的網頁搜尋結果[1][2][3][4][5][6][7][8][9][10]:

要建立一個支援ZFS檔案格式的NAS,以下是一些常見的步驟:

  1. 硬體選擇:要選擇一個適合的主機板、CPU、RAM和磁碟等硬體。根據[6]的建議,可使用1 GB RAM每1 TB可用儲存空間作為基本規則,並視需要添加更多的RAM。

  2. 安裝適當的作業系統:選擇一個支援ZFS的作業系統,例如FreeBSD、Linux和Solaris等[5]。建議使用FreeNAS或TrueNAS等開源軟體套件,這些套件提供了易於使用的Web界面,方便管理。

  3. 創建ZFS池:在安裝適當的作業系統和套件後,創建ZFS池以管理磁碟和資料。根據[1],可使用zpool create命令創建新的池。ZFS池可以包含一個或多個虛擬磁碟,其中每個虛擬磁碟可以由多個實際磁碟組成,並可選擇不同的RAID級別[4]。

  4. 設置共享:設置共享以讓其他設備可以訪問存儲在NAS中的資料。可使用SMB(Samba)、NFS(Network File System)或AFP(Apple Filing Protocol)等常見的共享協議[1]。

總的來說,建立支援ZFS檔案格式的NAS需要仔細選擇硬體和作業系統,並遵循適當的安裝和設置步驟。建議使用適當的套件和Web界面來簡化管理,以便更容易地管理和維護NAS。


FreeNAS和TrueNAS之間的區別在於TrueNAS是商用存儲設備,而FreeNAS是免費下載軟件[2]。現在所有新功能開發都在TrueNAS上進行[1][3]。TrueNAS不僅重新設計和優化了以前的FreeNAS,還添加了許多新功能[1]。 TrueNAS具有更好的技術支持和商業支持[2]。TrueNAS是iXsystems硬件專用的商業版本,而TrueNAS Core是原始的FreeNAS版本,僅限單節點使用[5][7]。Truenas Core運行在OpenZFS文件系統上,是一個NAS操作系統[7]。此外,TrueNAS的硬件要求較高,因此在硬件購買之前需要仔細規劃[4][6]。


TrueNAS 是一款適用於網路附加儲存 (NAS) 的作業系統,並且支援多種應用程式。以下為可在 TrueNAS 上執行的產品:

  1. Grafana:一個資料監控與視覺化平台,可以查詢、視覺化、警報和了解儲存在任何地方的指標[1]。

  2. Graylog:一個無縫收集日誌數據,進行更快速的分析並在需要時提供答案的平台[1]。

  3. Guacamole:一個開源的遠程桌面閘道器,可以連接到遠程伺服器並提供圖形化介面[1]。

  4. Plex:一個流媒體媒體中心應用程式,可以在多種設備上播放影片、音樂和相片[5]。

此外,TrueNAS 還支援多種其他應用程式,包括 Nextcloud、Bitwarden、Jellyfin、Seafile 和 GitLab 等。請注意,有些應用程式可能需要較高的硬體配置和設定[2][5]。

總結而言,TrueNAS 提供了廣泛的應用程式支援,可以滿足不同用戶的需求。

TrueNAS 是一款專為網路附加儲存(NAS)設計的操作系統,可以在x86-64硬體上運行。以下是一些支援 TrueNAS 的硬體相關資訊:

TrueNAS M-Series提供高可用性(HA)、混合容量和全快閃記憶體性能配置,可擴展到支援多個100GbE埠和超過20PB的儲存。所有的 TrueNAS 企業級系統都使用 OpenZFS 以提供卓越的性能、可靠性和保護,可用於任務關鍵數據 [4]。

TrueNAS Mini 系統配備四個或更多熱插拔槽,TrueNAS R-Series 系統可以在其主機單元和外部擴展櫃中支援數十個驅動器 [1]。

建議使用具備 ECC 功能的 CPU 和主機板,並使用由官方建議的儲存硬體 [3]。為了簡化組件選擇,一些網站提供了在不同類別中的建議硬體選擇,例如啟動驅動器、硬碟、L2ARC SSD 和 ZIL / SLOG 裝置 [6]。

由於硬體支援不同,使用時需要特別注意最大性能限制 [1]。此外,建議購買由 iXsystems 製造的 TrueNAS 硬體,因為購買後可以獲得 iXsystems 的支援 [9]。

需要注意的是,TrueNAS 企業版和 TrueNAS 核心版的硬體支援可能會有所不同,具體取決於版本和功能要求。因此,在購買前應詳細查看硬體相容性,以確保系統的穩定運行和最佳效能。

如果您想購買 TrueNAS,可以訪問官方網站[1],然後在頂部菜單中選擇“購買”,將會跳轉到 TrueNAS 的購物網站[4]。在此網站上,您可以購買 TrueNAS Mini、TrueNAS R-Series 和 TrueNAS M-Series 等各種產品,並且可以選擇您需要的不同配置。如果您需要更多幫助,您也可以透過 TrueNAS 的官方網站聯繫他們[1],或者選擇購買包括硬件在內的整個 TrueNAS 系統[2]。