TW202127364A - System and method for innovation, creativity, and learning as a service - Google Patents
System and method for innovation, creativity, and learning as a service Download PDFInfo
- Publication number
- TW202127364A TW202127364A TW109134881A TW109134881A TW202127364A TW 202127364 A TW202127364 A TW 202127364A TW 109134881 A TW109134881 A TW 109134881A TW 109134881 A TW109134881 A TW 109134881A TW 202127364 A TW202127364 A TW 202127364A
- Authority
- TW
- Taiwan
- Prior art keywords
- attribute
- tag
- user
- historical
- label
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3322—Query formulation using system suggestions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
Description
本公開總體上涉及人工智能認識論系統及方法的領域,尤其是用於提供創新、創意和學習即服務的系統及方法。The present disclosure generally relates to the field of artificial intelligence epistemological systems and methods, especially systems and methods for providing innovation, creativity, and learning as a service.
從認識論的角度來看,如果人們(包括個人以及由個人組成的團隊)有更好的知識框架,便可以潛在地改善他們的任務表現。然而,實際上,許多人在首次開始執行任務之前可能需要獲取關聯的知識框架。其他一些人可能會從自身的經驗中得到關聯的知識框架的概念,但仍不停地尋找並根據語境構建更好的框架以改善其任務表現。鑑於知識工作的這種性質的複雜性,根據獲取語境及構建該改進的知識框架,滿足了針對相關人員的學習、創新和創意的一定要求。From an epistemological perspective, if people (including individuals and teams of individuals) have a better knowledge framework, they can potentially improve their task performance. However, in reality, many people may need to acquire an associated knowledge framework before starting a task for the first time. Some other people may get the concept of the related knowledge framework from their own experience, but they are still constantly looking for and constructing a better framework based on the context to improve their task performance. In view of the complexity of this nature of knowledge work, according to the acquisition context and the construction of the improved knowledge framework, certain requirements for learning, innovation and creativity of relevant personnel are met.
在一方面,本公開描述了一種系統,該系統用於基於從一或多個源對象導出的資訊,在創新和創意方面進行自學習,以提高用戶的任務表現。該系統包括:包含指令的非臨時性計算機可讀存儲介質;以及耦接至該存儲介質的系統伺服器。該系統被配置為執行用於方法的指令,該指令包括:提供用戶界面,該用戶界面被配置為接收用戶輸入;及構建與該任務相關的知識框架。知識框架由多個歷史第一屬性標籤界定,該多個歷史第一屬性標籤中的每一個與至少一個相對應的歷史語境元素相關聯。該方法進一步包括提供基於語境元素和知識框架的自動建議,該自動建議包括響應於在用戶界面處所選擇的語境元素且由系統生成的一或多個候選屬性標籤,其中該一或多個候選屬性標籤中的每一個對應於以下之一:與任務關聯的目標、與任務相關的問題、該問題的答案,以及與該答案不同的見解。In one aspect, the present disclosure describes a system for self-learning in innovation and creativity based on information derived from one or more source objects to improve user task performance. The system includes: a non-transitory computer-readable storage medium containing instructions; and a system server coupled to the storage medium. The system is configured to execute instructions for the method, the instructions including: providing a user interface configured to receive user input; and constructing a knowledge framework related to the task. The knowledge framework is defined by a plurality of historical first attribute tags, and each of the plurality of historical first attribute tags is associated with at least one corresponding historical context element. The method further includes providing an automatic suggestion based on the context element and the knowledge frame, the automatic suggestion including one or more candidate attribute tags generated by the system in response to the selected context element at the user interface, wherein the one or more Each of the candidate attribute tags corresponds to one of the following: a goal associated with the task, a question related to the task, an answer to the question, and an insight different from the answer.
可選地,提供自動建議包括:響應於在用戶界面處所選擇的語境元素,確定第一屬性標籤,第一屬性標籤與該語境元素相關聯,從而相對於知識框架界定第一屬性標籤,語境元素基於一或多個源對象;提供一或多個候選屬性標籤作為自動建議;及響應於作為用戶輸入而接收的該自動建議,使用戶能夠輸入一或多個其他屬性標籤,以使得語境元素與標籤相關聯。該標籤至少由第一屬性標籤、第二屬性標籤、第三屬性標籤和第四屬性標籤界定,其中第一屬性標籤對應於與任務關聯的目標,第二屬性標籤對應於與任務相關的問題,第三屬性標籤對應於問題的答案,第四屬性標籤對應於與答案不同的見解。系統可以被配置為使得自動建議包括對應於第二屬性標籤和第三屬性標籤的候選屬性標籤。系統可以被配置為使得自動建議包括對應於第一屬性標籤、第二屬性標籤和第三屬性標籤的候選屬性標籤。系統可以被配置為使得自動建議包括對應於第二屬性標籤、第三屬性標籤和第四屬性標籤的候選屬性標籤。系統可以被配置為使得自動建議包括對應於第一屬性標籤、第二屬性標籤、第三屬性標籤和第四屬性標籤的候選屬性標籤。該系統可以被配置為使得自動建議包括候選屬性標籤,該候選屬性標籤對應於以下一或多個的任意組合:第一屬性標籤、第二屬性標籤、第三屬性標籤和第四屬性標籤。Optionally, providing automatic suggestions includes: in response to the selected context element in the user interface, determining a first attribute tag, the first attribute tag is associated with the context element, thereby defining the first attribute tag with respect to the knowledge framework, The context element is based on one or more source objects; provides one or more candidate attribute tags as automatic suggestions; and in response to the automatic suggestions received as user input, enables the user to input one or more other attribute tags so that The context element is associated with the label. The label is defined by at least a first attribute label, a second attribute label, a third attribute label, and a fourth attribute label, where the first attribute label corresponds to a target associated with the task, and the second attribute label corresponds to a problem related to the task, The third attribute label corresponds to the answer to the question, and the fourth attribute label corresponds to an opinion different from the answer. The system may be configured such that the automatic suggestion includes candidate attribute tags corresponding to the second attribute tag and the third attribute tag. The system may be configured such that the automatic suggestion includes candidate attribute tags corresponding to the first attribute tag, the second attribute tag, and the third attribute tag. The system may be configured such that the automatic suggestion includes candidate attribute tags corresponding to the second attribute tag, the third attribute tag, and the fourth attribute tag. The system may be configured such that the automatic suggestion includes candidate attribute tags corresponding to the first attribute tag, the second attribute tag, the third attribute tag, and the fourth attribute tag. The system may be configured such that the automatic suggestion includes candidate attribute tags, the candidate attribute tags corresponding to any combination of one or more of the following: a first attribute tag, a second attribute tag, a third attribute tag, and a fourth attribute tag.
可選地,該系統進一步包括:提供具有新興標籤工具的用戶界面,該新興標籤工具被配置為響應於所選擇的語境元素而接收用戶輸入,其中該用戶輸入包括屬性標籤,及其中屬性標籤為以下之一:第一屬性標籤、第二屬性標籤、第三屬性標籤、第四屬性標籤及/或一或多個定制標籤。Optionally, the system further includes: providing a user interface with an emerging tag tool configured to receive user input in response to the selected context element, wherein the user input includes an attribute tag, and the attribute tag therein It is one of the following: a first attribute label, a second attribute label, a third attribute label, a fourth attribute label and/or one or more custom labels.
可選地,為候選第二屬性標籤提供自動建議包括:基於各個相關聯的語境元素之間的相似度,從多個第一歷史屬性標籤中識別歷史第一屬性標籤;及用與歷史語境元素相關聯的歷史第二屬性標籤作為自動建議的候選第二屬性標籤。可選地,知識框架包括來自至少第一用戶作為用戶輸入所接收的歷史第一屬性標籤,及其中自動建議被提供給第二用戶。Optionally, providing automatic suggestions for candidate second attribute tags includes: identifying historical first attribute tags from a plurality of first historical attribute tags based on the similarity between each associated context element; and using historical language The historical second attribute tag associated with the context element is used as the candidate second attribute tag for automatic suggestion. Optionally, the knowledge framework includes historical first attribute tags received as user input from at least the first user, and automatic suggestions therein are provided to the second user.
可選地,用於候選第二屬性標籤的自動建議基於以下之一或兩者:歷史第二屬性標籤及生成式第二屬性標籤。歷史第二屬性標籤與具有與語境元素的相似度的歷史語境元素相關聯,該歷史語境元素與為知識框架的一部分的歷史第一屬性標籤相關聯。生成式第二屬性由一種方法生成,該方法包括:基於為輸入的語境元素,從自然語言處理模塊獲得輸出;及用生成式對抗網絡將該輸出與歷史第二屬性標籤進行迭代比較,其中基於第一屬性標籤和知識框架選擇歷史第二屬性標籤。可選地,知識框架包括從至少第一用戶作為用戶輸入所接收的歷史第一屬性標籤,及其中自動建議被提供給第二用戶。Optionally, the automatic suggestion for candidate second attribute tags is based on one or both of the following: historical second attribute tags and generative second attribute tags. The historical second attribute tag is associated with a historical context element having a similarity with the context element, and the historical context element is associated with a historical first attribute tag that is part of the knowledge framework. The generative second attribute is generated by a method that includes: obtaining an output from a natural language processing module based on the context element as the input; and using a generative adversarial network to iteratively compare the output with the historical second attribute tag, where Select the historical second attribute label based on the first attribute label and the knowledge frame. Optionally, the knowledge framework includes historical first attribute tags received as user input from at least the first user, and automatic suggestions therein are provided to the second user.
可選地,該系統還被配置為基於訓練後的機器學習模型的加權集合生成標籤,其中相對於分配給歷史第一屬性標籤、歷史第二屬性標籤和歷史第三屬性標籤中的任意一個模型的各個權重,將較大的權重分配給歷史第四屬性標籤的模型。Optionally, the system is further configured to generate a label based on a weighted set of the trained machine learning model, which is relative to the model assigned to any one of the historical first attribute label, the historical second attribute label, and the historical third attribute label For each weight of, the larger weight is assigned to the model of the historical fourth attribute label.
可選地,新興標籤工具還包括:被配置為接收手動用戶輸入的手動交互面板;以及被配置為提供自動建議的自動建議交互面板。Optionally, the emerging label tool further includes: a manual interactive panel configured to receive manual user input; and an automatic suggestion interactive panel configured to provide automatic suggestions.
可選地,用戶界面還包括被配置為知識可視化工具,該知識可視化工具提供一或多個自動建議,其中響應於由鏈接至任務的一或多個社交媒體渠道訂閱提供的新的源對象,提供一或多個自動建議。Optionally, the user interface further includes a knowledge visualization tool configured to provide one or more automatic suggestions, wherein in response to a new source object provided by one or more social media channel subscriptions linked to the task, Provide one or more automatic suggestions.
根據另一方面,本公開包括根據上述任何實施例的用於將軟體作為服務部署的方法。According to another aspect, the present disclosure includes a method for deploying software as a service according to any of the embodiments described above.
將容易理解,除了所描述的實例實施例之外,如本文附圖中總體描述和示出的實施例的組件可以以各種不同的配置來佈置和設計。如此,結合附圖所表示的實例實施例的以下描述並非旨在限制所要求保護的實施例的範圍,而僅是實例實施例的代表。It will be readily understood that, in addition to the described example embodiments, the components of the embodiments as generally described and illustrated in the drawings herein may be arranged and designed in various different configurations. As such, the following description of the example embodiments shown in the accompanying drawings is not intended to limit the scope of the claimed embodiments, but is merely representative of the example embodiments.
在本公開中,對“一個實施例”、“另一實施例”或“實施例”(或諸如此類)的引用意味著結合該實施例描述的特定特點、結構或特徵包括在至少一個實施例中。如此,在整個說明書中各處出現的短語“在一個實施例中”或“在實施例中”等不一定都指同一實施例。In the present disclosure, reference to "one embodiment", "another embodiment" or "an embodiment" (or the like) means that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least one embodiment . As such, the phrases "in one embodiment" or "in an embodiment" appearing in various places throughout the specification do not necessarily all refer to the same embodiment.
此外,在一或多個實施例中,所描述的特點、結構或特徵可以以任何合適的方式組合。在以下描述中,提供許多具體細節以提供對實施例的透徹理解。然而,相關領域的技術人員將意識到,可以在沒有一或多個特定細節的情況下,或者在利用其他方法、組件、材料等的情況下實踐各種實施例。在其他情況下,為了清楚起見,一些或所有已知的結構、材料、操作,將不詳細示出或描述。In addition, in one or more embodiments, the described features, structures, or characteristics can be combined in any suitable manner. In the following description, many specific details are provided to provide a thorough understanding of the embodiments. However, those skilled in the relevant art will realize that various embodiments may be practiced without one or more specific details, or using other methods, components, materials, and the like. In other cases, for clarity, some or all known structures, materials, and operations will not be shown or described in detail.
僅出於幫助理解的目的,以下將參考工作環境描述用於在創新、創意和學習即服務中提供自學習的系統及方法的實施例。可以理解,本公開的實施例還可以應用於各種不同的應用場景,例如學習、工作、個人及/或社交場合。在一個實例性場景中,第一用戶(例如,設計師)被指派創建用於新產品的產品包裝的設計。新產品是一項新的創新,因此第一用戶沒有產品相關的包裝要求的先驗知識或經驗。公司中的第二用戶被指派執行新產品的數位營銷活動。第二用戶是數位營銷過程的新手。第二用戶在數位營銷或新產品的主題上也沒有先驗知識或經驗。這種場景為潔淨案例的一個實例,其中學習者缺乏具有關聯性的認知系統。可以理解,個人和團隊需要大量的學習、創新和創意,以使公司啟動數位營銷活動並在市場上推出新產品。如此,迫切需要改進獲取與任務關聯的知識的傳統方式。Only for the purpose of helping understanding, embodiments of the system and method for providing self-learning in innovation, creativity, and learning as a service will be described below with reference to the working environment. It can be understood that the embodiments of the present disclosure can also be applied to various different application scenarios, such as learning, work, personal and/or social occasions. In an example scenario, a first user (eg, designer) is assigned to create a design for product packaging for a new product. The new product is a new innovation, so the first user does not have prior knowledge or experience in product-related packaging requirements. The second user in the company is assigned to execute a digital marketing campaign for the new product. The second user is a newbie in the digital marketing process. The second user also has no prior knowledge or experience on the subject of digital marketing or new products. This scenario is an example of a clean case, where the learner lacks a relevant cognitive system. Understandably, individuals and teams need a lot of learning, innovation and creativity to enable companies to launch digital marketing activities and launch new products on the market. As such, there is an urgent need to improve traditional methods of acquiring knowledge associated with tasks.
根據一個方面,根據本公開的實施例的系統100提供了用於創建更好的知識框架300的工具200,該工具進而可用於加速學習並改善任務表現。系統100被配置為使得它可以提供用於促進自學習及/或改善任務表現的服務。According to one aspect, the
根據一個實施例,如圖1顯示,用於創意、創新和學習即服務的系統100可以由具有至少一個處理器的系統伺服器110實施,該至少一個處理器被配置為執行存儲在計算機可讀存儲介質112上的指令。系統100被配置為可由用戶通過用戶設備130(諸如移動電話、平板電腦、膝上型電腦,或計算或智能設備)且經由網絡120訪問以提供服務。該系統可以被配置為將數據存儲在數據庫140中,諸如在客戶端數據庫中。用戶在用戶的學習歷程中可以查詢第三方資訊源150,諸如網站。為避免疑義,在本文中提及用戶對此類第三方資源的訪問是指對此類資源的授權訪問。According to one embodiment, as shown in FIG. 1, the
圖2示出了由系統100提供的用戶界面200的實例。用戶界面200可以是被配置為在計算設備上使用的軟體應用程式的形式。用戶界面200可以是插件、附件、實用程序的形式。用戶界面可以作為在線平台、基於雲端的應用程式、可下載程序等的一部分提供。用戶界面200可以配置為適於與瀏覽器、電子書閱讀器或其他應用程式一起使用,諸如社交媒體應用程式、學習平台、新聞應用程式等。這些可能的形式僅作為實例提供。FIG. 2 shows an example of a
用戶界面200包括新興標籤工具210。在該實施例中,新興標籤工具210提供文本框220供用戶輸入標籤300。當第一用戶在線閱讀有關產品包裝的資訊時(在此實例中,使用網絡瀏覽器),新興標籤工具被配置為使得第一用戶能夠從源對象240(於此實例中為網絡文章)的表示中選擇(諸如通過突出顯示)一或多個語境元素230(在該實例中,短語“您正在為理想的客戶策劃理念而不是為自己策劃理念”)。新興標籤工具210在此處顯示為彈出菜單,但它也可以為插件、附件或實用程序等形式。The
源對象可以對應於電子書、PDF文檔、視頻、音頻記錄、多媒體文件、網站、部落格(blog)、影像部落格(vlog)、應用程式、社交媒體發布或任何電子實體。可以通過呈現、存儲或傳達資訊的電子手段以用戶可以讀取、聽到或以其他方式感知的形式來訪問源對象。用戶界面200可與其他應用程式一起操作,以使得用戶可以訪問源對象或其中的資訊,而不會侵越電子文件的版權擁有者所許可的權利。舉例言之,將用戶界面200配置為用戶可以通過通常所許可的場所訪問電子文件,例如,網際網路瀏覽器、電子書閱讀器、電子圖書館會員帳戶、社交媒體應用程式等。如此,源對象可以是本地駐留在用戶的計算設備130中的一個源對象,也可以是駐留在網絡120的另一部分中的一個源對象。網絡120可以通過無線、有線或另一種形式的連接來訪問。網絡120的實例包括局域網、廣域網、外部網、內部網等。該源不必是電子文件。舉例言之,該源可以是可識別的印刷出版物。於一些實施例中,用戶界面200可以提供參考工具,以使得用戶可以諸如通過參考國際標準書號(ISBN)或期刊文章等來識別非電子資源。The source object can correspond to e-books, PDF documents, videos, audio records, multimedia files, websites, blogs, video blogs (vlog), applications, social media publishing, or any electronic entity. The source object can be accessed through electronic means of presenting, storing, or conveying information in a form that the user can read, hear, or perceive in other ways. The
響應於語境元素230的選擇,系統100被配置為將語境元素與至少一個標籤300/310相關聯。該系統被配置為接收、建議及/或生成至少一個標籤300/310。該系統類似地能夠從第二用戶接收輸入,例如,第二用戶可以使用新興標籤工具210來創建與數位營銷活動相關的語境元素,其中每一個語境元素230與至少一個相對應的標籤300/310相關聯。In response to the selection of the
每一個標籤300可以根據一或多個屬性標籤310而界定。在本文中,術語“標籤”(或“多個標籤”)可以指代屬性標籤,或者該術語可以指代由一或多個屬性標籤界定的標籤。系統100被配置為將標籤300/310作為標籤的集合存儲在數據庫140中,其中每一個標籤300包括一或多個屬性標籤310。系統100被配置為使得每一個屬性標籤310可以與相對應的語境元素230相關聯。Each
於此實例中,標籤300可以根據以下屬性標籤310中的一或多個而界定:目標屬性標籤312(也稱為第一屬性標籤)、問題屬性標籤314(也稱為第二屬性標籤)、答案屬性標籤316(也稱為第三屬性標籤)和見解屬性標籤318(也稱為第四屬性標籤)。舉例言之,關於所選擇的語境元素230,第一用戶可以使用新興標籤工具210以輸入標籤300,其中標籤300根據以下屬性標籤310而界定:
標籤=(目標、問題、答案、見解)
目標=初步.設計
問題=誰是我的理想客戶?
答案=澳大利亞國際學校
見解=無尾熊In this example, the
新興標籤工具210可以進一步被配置為使得用戶可以用一或多個標籤300標記一或多個語境元素230,其中該標籤包括答案屬性標籤316。每一個答案屬性標籤316指向或對應於一答案。答案屬性標籤316對應於特定的問題屬性標籤314。系統100被配置為使得用戶(學習者)能夠構想設計答案屬性標籤316,並將該答案標籤與所選擇的語境元素230形成相關。每一個答案屬性標籤316和相對應的問題屬性標籤314與至少一個語境元素230相關。The emerging
新興標籤工具210可以進一步被配置為使得用戶可以用一或多個見解屬性標籤318標記一或多個語境元素230。每一個見解屬性標籤點318指向或對應於一見解。見解可被描述為當用戶經歷“啊哈!”或“尤里卡(Eureka)!”時刻時的認知事件。輸入或選擇見解屬性標籤318的用戶是學習者,即,正在經歷學習歷程的人。系統100被配置為使得用戶(學習者)能夠構想設計見解屬性標籤318,並向所選擇的語境元素230輸入或選擇見解屬性標籤318。於一方面,見解屬性標籤318可以被使用為擷取創意或創新思想。於一方面,見解屬性標籤318 “無尾熊”與一對標籤相關聯,其中該對標籤包括問題屬性標籤314標“誰是我的理想客戶?”及答案屬性標籤316“澳大利亞國際學校”。於另一方面,見解屬性標籤318與至少一個第一屬性標籤及至少一個其他標籤相關聯。於該實例中,目標屬性標籤312被配置為第一屬性標籤410。問題屬性標籤是該至少一個其他標籤310。The emerging
如圖3顯示,系統100被配置為使得可以基於各種類型的屬性標籤310中的一者來組織節點410的框架400。於本文中,這種標籤也被稱為第一屬性標籤312。第一屬性標籤312被配置為可以基於各個框架標籤410之間的關係在階級式框架400中形成節點410。於此實例中,目標屬性標籤312被配置為第一屬性標籤410。框架400可以被界定為節點410的網絡,其中每一個節點對應於第一屬性標籤312。每一個目標屬性標籤312可以被配置為負載關於其在框架400中的相對位置的資訊。框架400可以被逐步地或迭代地組織。基於第一屬性標籤/節點312/410的關聯度,第一屬性標籤/節點312/410之間可以形成關係。該系統被配置為,響應於將標籤300添加到標籤的集合中及作為在各個框架標籤/節點312/410之間形成關係的結果,使得該系統能夠構建及/或修改框架400。各個框架標籤/節點312/410之間的關係可用於代表用戶的知識框架400。於該實例中,基於第一用戶輸入的標籤的知識框架400可用於幫助第一用戶加速他的學習,其目的為設計新產品的包裝。As shown in FIG. 3, the
同時,當第二用戶搜索關於計劃數位營銷活動的技巧時,他可以基於不同的源對象240識別不同的語境元素230,並將它們與不同的標籤300相關聯。舉例言之,當第二用戶閱讀有關消費者行為分析在市場營銷中使用的資訊時,他可能對消費者行為分析與他的特定任務的相關性有所疑問,該特定任務即推出新產品的數位市場營銷活動。系統100使得第二用戶能夠以標籤300的形式輸入此類問題,其中標籤300具有與語境元素230相關聯的至少一個問題屬性標籤314,且其中該語境元素基於第二用戶的閱讀材料。於此種情況下,第二用戶可以從數個標籤開始,每一個標籤僅具有一個屬性標籤310,例如:
問題=何時推出營銷活動?
問題=社交媒體是否與此產品關聯?
問題=誰是目標市場?At the same time, when the second user searches for tips on planning digital marketing activities, he can identify different
由第二用戶選擇的每一個語境元素將與包括一或多個空白屬性標籤的標籤相關聯,例如: 標籤=(空白、何時推出營銷活動、空白、空白)Each context element selected by the second user will be associated with a tag that includes one or more blank attribute tags, for example: Label = (blank, when to launch the marketing campaign, blank, blank)
系統100被配置為使得用戶可以繼續修飾現有標籤300。舉例言之,第二用戶可以取回他先前所輸入至系統的關於語境元素的問題。第二用戶可以進一步修飾標籤300,以使標籤300現在由更多屬性標籤310界定,例如:
問題=何時推出營銷活動?
答案=節日The
如該實例中顯示,問題(用於問題屬性標籤314的輸入)由第一用戶和第二用戶自己提出。換言之,當用戶處於學習者的角色(正在經歷學習歷程以獲取知識的用戶)時,問題輸入由用戶提供。輸入、建議或生成的每個問題屬性標籤314是與相對應的語境元素230相對應或相關聯的一個標籤。As shown in this example, the question (input for the question attribute tag 314) is posed by the first user and the second user themselves. In other words, when the user is in the role of a learner (a user who is going through a learning process to acquire knowledge), the question input is provided by the user. Each question attribute label 314 input, suggestion, or generated is a label corresponding to or associated with the
當第二用戶在一段時間內繼續學習該主題時,他可以繼續向其標籤集合添加新標籤。系統100被配置為存儲源自第二用戶的標籤的第二標籤集合,以使得第二用戶可以擁有他自己的個人知識框架。該知識框架400可以用於表示與第二用戶相關聯的個人知識的當前狀態。系統100還可以被配置使得第一用戶和第二用戶均可貢獻於標籤的共享標籤集合。所得知識框架400可以用於表示用戶團隊的集體知識的當前狀態。When the second user continues to learn the topic for a period of time, he can continue to add new tags to his tag collection. The
根據一方面,系統100被配置為向不同的客戶端提供服務。客戶(諸如公司)可以擁有作為學習者使用系統100的多個僱員。客戶可以任命其一名僱員為協調員或管理員。協調員或管理員也可以是學習者。管理員是指操持學習的管理方面(例如,跟踪出勤、提供對資源的訪問等)的一或多人。協調員是指設計課程提綱及/或交付教學內容的一或多人。用戶界面200被配置為除非必要,否則將不突出協調員/管理員的角色。舉例言之,協調員向學習者提供預定的課程提綱是可選的。如此,系統100有益地適合於現實生活或連續學習,在現實生活或連續學習中可能要求學習者從沒有先驗知識及沒有先驗課程提綱或框架以幫助學習者系統地學習的狀態下開始,以達到目標。學習者也可能被要求在沒有導師或手冊的指導的情況下“在工作中學習”。於實施例中,用戶(包括學習者)可以定制或設置其他定制屬性標籤310及/或框架標籤410,諸如“重要”、“注意”等。換言之,雖然不排除將教育和培訓行業中的組織作為系統100所提供的服務的用戶,實際上,系統100適用於更廣泛的多種應用場景。According to one aspect, the
根據另一方面,系統100使學習者能夠創建自己的動態“教科書”或資訊資源庫150。於第一用戶的實例中,第一用戶可以在網際網路上爬取用於類似產品的產品包裝的圖像。第一用戶可以訪問網站及將關聯標準識別為第一語境元素。新興標籤工具210使得第一用戶能夠通過識別其位置,諸如網址(URL: Uniform Resource Locator)及/或其他標識符,來識別語境元素230。新興標籤工具210可以使得第一用戶能夠用快照工具來識別語境元素。新興標籤工具210還可以進一步被配置為使得用戶能夠將資源的一部分複制為語境元素230,其中可以根據所許可的或由訂閱該系統的版權所有者所允許的內容來控制或預定可複制部分的最大尺寸。According to another aspect, the
根據另一方面,第一用戶可以創建新的問題屬性標籤314並將問題屬性標籤314應用於所識別/選擇的語境元素230。系統100將問題屬性標籤314作為標籤集合的一部分存儲於數據庫140中。如果在使用了系統100之後,第一用戶已經開發了由多個問題屬性標籤314組成的數據庫140,則第一用戶隨後可以從標籤集合中選擇問題屬性標籤314,並將所選擇的問題屬性標籤314與另一語境元素230形成相關。根據一方面,由于用戶必須以問題的形式進行思考,則用戶被“強制”以學習者的身分思考,即為知識的尋求者。通過成為制定問題的人(而不是專注於答案或多條資訊的人),學習者對自己的知識差距的意識較為敏感。此外,系統100意識到可以從問題而不是從答案中獲得更多的學習。系統100被配置為從問題中提取一拼圖,而其與其他拼圖組裝時則產生至少一部分知識框架400。According to another aspect, the first user can create a new question attribute label 314 and apply the question attribute label 314 to the identified/selected
上述各方面不同於傳統的學習系統,在傳統的學習系統中,協調員(在主題方面具有先驗知識)設計課程提綱(要教授的多個知識、多個知識的教授順序、所教授的多個知識的學習者吸收或習得的評估),而根據本實施例的系統100則提供與自指導、自定進度和自實現學習的精神更一致的學習。系統100被配置為使學習者驅動他/她自己的學習,而不是用由協調員所選擇的資訊過量的強塞給學習者。具體地,系統100被配置為實現知識框架400的動態演化。將根據學習者的至少一個目標組或任務來配置此類知識框架400。此類知識框架400被配置為幫助學習者執行任務或改善執行任務的效果。根據該實施例,系統100被配置為使得知識框架400是基於與問題屬性標籤314相關聯的框架標籤410。The above-mentioned aspects are different from the traditional learning system. In the traditional learning system, the coordinator (with prior knowledge of the subject) designs the syllabus (multiple knowledge to be taught, the order in which multiple knowledge is taught, and the number of lessons to be taught). Learners of individual knowledge are absorbed or acquired), while the
系統100被配置為基於其他標籤300/310構造知識框架400,諸如答案屬性標籤、見解屬性標籤、目標屬性標籤,其他標籤300/310包括由這些屬性標籤中的任何一或多個標籤所界定的標籤。知識框架400還可以基於定制標籤300/310,即由用戶定制標籤的類型。知識框架400可以基於除上述屬性標籤之外的其他屬性標籤310,諸如視覺相關屬性標籤、目的相關屬性標籤等。標籤300可以相對應地由一或多個屬性標籤310界定。標籤300可以由任意數量的屬性標籤310組成。The
根據本公開的另一方面,利用人工智能/機器學習算法520來施行該系統及方法。圖4示意性地例示說明了系統100的另一方面。系統100還被配置有機器學習模塊500。該系統配置有一或多個數據庫140,該一或多個數據庫140存儲與一或多個標籤集合中的各個標籤300/310相關聯的語境元素230以及相關的知識框架400。機器學習算法520被配置為利用數據庫140中存儲的數據。一個實例是自然語言處理(NLP: Natural Language Processing)引擎,該自然語言處理引擎被配置為從已識別/選擇的語境元素230和所應用的標籤300/310中提取數據。作為另一實例,第一用戶還可以使用用戶界面(諸如圖2中顯示的界面)以兩個標籤“高效”或“有效”來標記他所認為的文本/視頻/圖像/音頻文件(源)的重要部分。語境元素和標籤的含義可以由自然語言處理(NLP: Natural Language Processing)引擎提取,並饋送至機器學習模塊500,以進行有監督甚至無監督的學習,如圖5中顯示。According to another aspect of the present disclosure, an artificial intelligence/machine learning algorithm 520 is used to implement the system and method. FIG. 4 schematically illustrates another aspect of the
如圖5中顯示,系統100的機器學習模塊500可以被配置為包括處於監督學習或無監督學習的一或多個子模塊。機器學習模塊500可以被配置為包括一或多個子模塊,其中子模塊可以被配置為組合施行以下一或多個:人工神經網絡模型、深度學習算法、降維法、特徵提取法、嵌入生成法、集成法、基於實例的方法、貝葉斯法、聚類和其他合適的方法。機器學習模塊可以包括被配置為施行一或多人工神經網絡模型的子模塊。人工神經網絡模型的實例包括但不限於:反向傳播法、Hopfield網絡法、自組織映射法和學習矢量量化法等。機器學習模塊可以包括配置為施行一或多種深度學習算法的子模塊。深度學習算法的實例包括但不限於:變換器、長短期記憶(LSTM: Long short-term memory)、自動編碼器和解碼器、生成式對抗網絡、深度信念網絡法、卷積神經網絡、遞歸神經網絡、堆疊式自動編碼器等。機器學習模塊可以包括被配置為施行一或多種降維法的子模塊。降維法的實例包括但不限於:主成分分析、偏最小二乘回歸、Sammon映射、多維縮放、投影追踪等。機器學習模塊可以包括被配置為施行一或多種特徵提取法的子模塊。機器學習模塊可以包括被配置為施行一或多種嵌入生成法的子模塊。特徵提取法及/或嵌入生成法的實例包括但不限於:連續詞袋(CBOW)、跳过语法(Skip-gram)方法等。機器學習模塊可以包括被配置為施行一或多種集成法的子模塊。集成法的實例包括但不限於:增強、堆疊概括、梯度增強機器法、隨機森林法等。機器學習模塊可以包括被配置為施行一或多種基於實例的方法的子模塊。基於實例的方法的實例包括但不限於:k最近鄰、自組織映射等。機器學習模塊可以包括被配置為施行一或多種貝葉斯法的子模塊。貝葉斯法的實例包括但不限於:樸素貝葉斯、貝葉斯信念網絡等。機器學習模塊可以包括被配置為施行一或多種聚類方法的子模塊。聚類方法的實例包括但不限於:k均值聚類、期望最大化等。As shown in FIG. 5, the
圖5中的機器學習模塊可以被配置為從語境元素和標籤中學習,以修飾或豐富知識框架。具體言之,系統100可以被配置為建議與被獲取或建造的框架400的各方面有關的關聯標籤300/310。系統100可以被配置為建議各種類型的標籤(自動建議)。下面將描述兩種類型的自動建議(歷史式及生成式)的實例。The machine learning module in Figure 5 can be configured to learn from contextual elements and tags to modify or enrich the knowledge framework. Specifically, the
參照圖6,此時,基於來自第一用戶的輸入,數據庫140已經累積了標籤集合及已經生成了知識框架400。系統100被配置為自動地建議候選標籤及/或候選屬性標籤。可以通過新興標籤工具210或用戶界面200向用戶呈現候選標籤及/或候選屬性標籤。自動建議的呈現可以響應於語境元素被選擇。在本文中,術語“候選標籤”和“候選屬性標籤”可以依據語境的理解而互換使用,及指代由系統向用戶自動建議的標籤/屬性標籤。如果用戶接受自動建議,則將候選標籤或候選屬性標籤作為用戶輸入而接收,並用作相對應的標籤/屬性標籤。Referring to FIG. 6, at this time, based on the input from the first user, the
根據一實施例,新興標籤工具600被配置為建議候選標籤610(或一或多個候選屬性標籤610)。由系統100建議的候選標籤610可以包括從數據庫140所取回的歷史標籤300/310。候選標籤610可以從在同一認知項目中使用的歷史標籤300/310中選擇,或者候選標籤610可以是另一現有或較早的項目中的歷史標籤300/310。系統100可以被配置為基於由第二用戶選擇的語境元素630與歷史語境元素230(圖3)之間的相似度來選擇歷史標籤300/310。歷史語境元素230可以包括第一用戶用於與至少一個標籤關聯的語境元素。歷史語境元素230還可以指代存儲在數據庫中的語境元素。歷史語境元素230還可以指代鏈接至知識框架400的語境元素。於該實例中,第二用戶選擇包含“數位營銷始於描述您的理想客戶”的語境元素。作為響應,系統100確定該語境元素630具有與歷史語境元素“為理想客戶……蒐集設計構思……”(圖3)某種程度的相似度。系統100基於與歷史語境元素230相關聯的歷史標籤300/310,將以下內容作為候選標籤610呈現:
目標=初步.設計
問題=誰是我的理想客戶?
答案=澳大利亞國際學校
見解=無尾熊According to an embodiment, the emerging
以此方式,第二用戶可以受益於第一用戶的學習。配置有自動建議600的新興標籤工具可以被配置為允許第二用戶確認候選標籤610的使用。新興標籤工具600還可以被配置為允許第二用戶修改或替換候選標籤610。關於相似的語境元素,第二用戶可以擁有與他的角色或任務的性質更關聯的不同標籤。系統100被配置為擷取這些變化,以使得所得知識框架400被進一步豐富。In this way, the second user can benefit from the learning of the first user. The emerging tag tool configured with the
參照圖7,根據另一實施例,響應於第二用戶選擇語境元素630“數位營銷始於描述您的理想客戶”並提供目標屬性標籤“焦點”,系統100被配置為通知第二用戶這可能與知識框架400的現有節點410有關。知識框架400可以是由第一用戶及第二用戶共享的知識框架,因為他們在同一團隊中或執行相同或相關的任務。如果第二用戶選擇相似的語境元素,系統100則可以建議歷史目標屬性標籤和問題屬性標籤。系統100可以被配置為基於如上所述的機器學習模塊500來提供此類自動建議。基於知識框架400,系統100可以向第二用戶建議歷史目標屬性標籤“初步.設計”可能與目標屬性標籤“焦點”有關。系統100被配置為允許第二用戶將目標屬性標籤從“焦點”更改為“初步.設計.焦點”612。該屬性標籤612還被配置為框架標籤410,及可以添加新標籤至關聯框架400。系統100實際上幫助第二用戶快速了解新獲得的知識如何與較早獲得的知識相關,以及使得第二用戶能夠快速地繼續獲得其他知識,特別是在知識框架400中與此標籤612緊密相關的知識。7, according to another embodiment, in response to the second user selecting the
響應於被突顯的語境元素,系統100還可被配置為建議在數據庫中找不到的標籤。圖8顯示了新興標籤工具800的另一實施例,其提供用於手動用戶輸入標籤的第一交互面板810、用於基於歷史標籤的自動建議的第二交互面板820以及用於基於生成引擎的自動建議的第三交互面板830。響應於所選擇的語境元素,用戶可以使用文本框815來輸入標籤300/310。第一交互面板810被配置為使得用戶能夠輸入不同類型的標籤300/310,諸如目標屬性標籤811、問題屬性標籤812、答案屬性標籤813、見解屬性標籤814及/或其組合。於一些實施例中,新興標籤工具800包括用於標籤的手動用戶輸入的手動輸入交互面板810,以及用於提供自動建議的自動建議交互面板820/830。提供自動建議的不同方法的實例如下所述。In response to the contextual elements being highlighted, the
第二交互面板820被配置為基於所選擇的語境元素來呈現自動建議。自動建議可以包括目標屬性標籤821、問題屬性標籤822、答案屬性標籤823、見解屬性標籤824及/或其組合。新興標籤工具800被配置為使得用戶能夠為每一個屬性標籤821/822/823/824採用自動建議、拒絕建議或修改自動建議。新興標籤工具800還被配置為在系統不為任何或所有屬性標籤提供自動建議的情況下,則讓用戶能夠手動輸入標籤。當用戶接受自動建議時,所接受的自動建議被視為用戶輸入至系統。當用戶修改自動建議時,所修改的自動建議被視為用戶輸入至系統。The second
第三交互面板830被配置為呈現由機器學習模塊500提供的生成引擎所生成的自動建議。在本公開中,生成引擎可以包括基於訓練後的機器模型的加權集合的標籤生成器,該機器模型通過將機器學習應用於上述歷史屬性而獲得;或不同地,使用生成式對抗網絡(Generative Adversarial Networks)。使用生成式對抗網絡的生成引擎將在此作為實例進行描述。於一些實施例中,響應於第二用戶選擇語境元素,諸如“數位營銷始於描述您的理想客戶”,系統生成候選生成式問題並將其呈現給用戶。機器學習模塊500內的自然語言處理/自然語言處理器(NLP)模塊可以被配置為使得,基於作為輸入的語境元素,NLP模塊輸出可能的問題。基於目標屬性標籤在相關知識框架中的相對位置,所生成的問題可以與歷史問題進行比較,其中歷史問題根據知識框架基於其相關性來選擇。如果系統將可能的問題確定為“假”問題,則該結果將反饋給生成引擎。迭代執行此比較和反饋後,系統將呈現不會產生“假”結果的候選問題。於此實例中,系統提供候選問題(候選第二屬性標籤)作為自動建議。即,生成式第二屬性標籤“誰是您的忠實客戶?”作為候選第二屬性標籤被提供給第二用戶。當系統如此配置時,系統將為用戶提供更多 “非一般” 的標籤建議。這允許在獲取和建造新知識框架期間出現新理念。於此實例中,所生成的問題促使用戶採用略微不同的觀點,並基於歷史標籤從建議中得出不同的答案。當與相關的目標和問題共同考慮時,不同的答案“悉尼國際學校”可以幫助用戶與新的見解“沙袋鼠”建立認知聯繫。The third
上面僅是用於一個屬性標籤的自動建議之一的實例。於一些其他實施例中,一或多個標籤/屬性標籤(諸如目標屬性標籤、問題屬性標籤、答案屬性標籤、見解屬性標籤和任何定制標籤)可以由系統基於所選擇的語境元素及/或其他標籤/屬性標籤的一自動建議。如此,當用戶接受由系統提供的建議時(無論是歷史的還是生成的),由於該過程擴展了知識框架400,因此可以說產生了創新類型的服務。當用戶接受任何其他歷史類型或生成類型的建議時,可以說是產生了創意類型的服務,因為其潛在地為正在執行任務但不直接為知識框架本身的修飾做出貢獻的用戶打開了新的視角。The above is only an example of one of the automatic suggestions for an attribute tag. In some other embodiments, one or more tags/attribute tags (such as target attribute tags, question attribute tags, answer attribute tags, insights attribute tags, and any custom tags) can be determined by the system based on the selected context elements and/or An automatic suggestion of other tags/attribute tags. In this way, when the user accepts the suggestion provided by the system (whether historical or generated), since the process expands the
根據另一實施例,於已被指派執行數位營銷活動的第二用戶的實例中,第二用戶可以使用系統100來獲取關於數位營銷的知識。於閱讀有關數位營銷的主題的過程中,用戶能夠標記數位營銷中可能遇到的問題的類型。一段時間後,系統100可以學到在主題的語境中什麼是重要的及什麼是不重要的,或者什麼是更關聯的及什麼是較無關聯的。如此,一段時間後,及隨著由與標籤相關聯的語境元素所表示的源(參考源)的庫140/150不斷的增長,系統100可以進一步為用戶扮演協調員的角色。舉例言之,時不時地,系統100可以向用戶提出問題,諸如“您對數位營銷更清楚的是什麼?”或更籠統的問題諸如“最重要的方面是什麼?”、“您的問題是否已得到解答?”、“您現在能夠將其置於項目階段中嗎?”或“您認為您將面對哪些議題?”等。According to another embodiment, in the instance of a second user who has been assigned to perform a digital marketing campaign, the second user may use the
為了進一步幫助組織學習並更好地修飾正在構建的各種知識框架,系統100可以被配置為執行(於後端)將已被標記為諸如“重要”的東西拼湊在一起的過程,或諸如“高效”或“有效”的其他任何有意義的標籤。此類標籤也可以加權。於前述實例中,系統100可以被配置為採用已由第一用戶標記為“重要”的東西(例如,使用可持續包裝)以豐富或補充第二用戶的學習歷程。因此,第二用戶可以受益於由第一用戶所建造的知識框架400,及更重要的,不疏忽對用於產品營銷的重要特徵的學習。In order to further help the organization learn and better modify the various knowledge frameworks being built, the
根據另一方面,系統被配置為對用戶呈現其“發現結果”,諸如通過圖形用戶界面格式。此類“發現結果”可以被配置為包括來自先前構建的知識框架中未來學習者要關注的領域。圖9顯示知識可視化工具900的一示意例。“重要”或“關聯”資訊可以在工作台環境中呈現給用戶,該工作台環境被配置為給用戶相對於時間線930或一系列里程碑940重新安排(選擇)910里程碑、任務、項目階段、議題、問題等920。以此種方式,系統100可以通過將“重要”資訊納入時間線而更好地幫助用戶從知識框架獲取過渡至應用。舉例言之,第二用戶可以使用由系統100所提供的用戶界面200來佈置數位營銷活動項目的各步驟。系統100可以被配置為向用戶呈現問題和答案之間的鏈接,並將這些鏈接至項目的各個關聯步驟/階段/里程碑。如此,該系統是一 “實時”環境。於一實施例中,例如,一項任務被鏈接至一或多個社交媒體頻道訂閱。系統100可以被配置為每當從此類訂閱服務中提取新文章時,向用戶呈現自動建議。換言之,用戶界面被配置為使得知識可視化工具可以響應於由鏈接至任務的一或多個社交媒體頻道訂閱所提供的新源對象而提供一或多個自動建議。According to another aspect, the system is configured to present its "discovery results" to the user, such as through a graphical user interface format. Such "discovery results" can be configured to include areas that future learners will focus on from a previously constructed knowledge framework. FIG. 9 shows a schematic example of the
如果第三用戶(例如,在世界的另一地區)也對學習數位營銷活動感興趣,則系統100可以加速第三用戶的學習。即使沒有使第三用戶得知第二用戶所設計的問題標籤,系統100通过其結構被配置為幫助重要語境元素230的識別的自動化,以及幫助將問題314和答案316的建議自動化以幫助學習。舉例言之,一段時間後,系統100可以收集足夠的數據以預測更可能導致用戶得出見解的問題314的類型。如此,系統可以“推動”後續用戶更早或更頻繁地達到見解318(“啊哈!”時刻)。一段時間後,系統100能夠獲取此類“高價值”問題314的集合,以用於促進進一步的創意和學習。If the third user (for example, in another region of the world) is also interested in learning digital marketing activities, the
系統100可以被配置為提供新興標記過程的分析。系統100可以被配置為確定各個類型的標籤300/310的數量。系統100可以被配置為發覺標籤300/310的時間順序,以幫助學習歷程的可視化。舉例言之,於數位營銷實例中,系統100可以識別用戶獲取見解318所花費的時長。如一實例,第二用戶花費12天來獲得見解318,見解318為數位營銷的關鍵是轉化。系統100可以跟踪其他人達到相似見解所需的天數。一段時間後,由於系統100提供了加速的學習,借助系統100,後續學習者可以在更短的時間內達到相似的見解318。一段時間後,隨著越來越多的用戶使用該系統100,其目的為縮短從首次學習至見解318的時間。The
系統100被配置為跟踪學習成果。換言之,當給定任務時,系統100可以跟踪用戶開發適當的知識框架400所需的迭代量。於此實例中,學習成果是新的知識框架400,及系統100能夠衡量此類框架成組織構建所需的時間。於該實例中,這可以採取向第二用戶提供用戶界面200的形式,以根據與項目的階段和子階段相對應的時間線來計劃營銷活動。系統100還可用於識別數位營銷中可能遇到的議題和問題,其中可能遇到的議題是基於第二用戶學習時動態演變的事物。當第二用戶準備就緒時,第二用戶可以轉至執行活動的下一步。系統100可以繼續被第二用戶或另一用戶用以監視數位營銷活動。數位營銷活動本身可以充當用於進一步標記的附加語境元素320的源240,以便可以完善、改進或以其他方式更新知識框架400。如此,可以繼續使用新興標籤工具210。The
為幫助理解,以下的一實例描述系統100如何可以具有更廣泛的應用以使其可以應用於一組用戶。系統100可以附加地被配置為使得多個用戶可以參與一個學習歷程。來自團隊的各個成員的輸入可以用顏色編碼或以其他方式與團隊的各個成員識別/相關聯。團隊成員可以檢查同一團隊中其他團隊成員的標籤,及用戶界面200可以被配置為使得用戶能進行討論,而無需考慮源240、語境元素230及/或標籤300/310。用戶界面200也可以被配置為使得用戶可以回答由團隊的其他成員提出的問題314。新興標籤工具210可以進一步被配置為允許用戶將文本/視頻/圖像/語音240鏈接至那些問題314。To help understanding, the following example describes how the
上文描述了系統的各種實施例,該系統用於在創新和創意方面進行自學習以基於從一或多個源對象導出的資訊來改善用戶的任務表現。該系統包括包含指令的非暫時性計算機可讀存儲介質以及耦接至該存儲介質及用戶界面的系統伺服器。該系統被配置為執行用於如圖10中例示說明的方法(1000)的指令。該方法包括提供(1010)用戶界面,該用戶界面被配置為接收用戶輸入。該方法包括構建(1020)關於任務的知識框架,該知識框架由多個歷史第一屬性標籤界定,該多個歷史第一屬性標籤中的每一個與至少一個相對應的歷史語境元素相關聯。該方法進一步包括基於語境元素和知識框架提供(1030)自動建議,該自動建議包括由系統響應於在用戶界面處所選擇的語境元素而生成的一或多個候選屬性標籤,其中該一或多個候選屬性標籤中的每一個對應於以下之一:與任務關聯的目標、與任務相關的問題、問題的答案以及與答案不同的見解。The foregoing describes various embodiments of the system for self-learning in terms of innovation and creativity to improve the user's task performance based on information derived from one or more source objects. The system includes a non-transitory computer-readable storage medium containing instructions and a system server coupled to the storage medium and a user interface. The system is configured to execute instructions for the method (1000) as illustrated in FIG. 10. The method includes providing (1010) a user interface configured to receive user input. The method includes constructing (1020) a knowledge frame about the task, the knowledge frame being defined by a plurality of historical first attribute tags, each of the plurality of historical first attribute tags being associated with at least one corresponding historical context element . The method further includes providing (1030) automatic suggestions based on the context elements and the knowledge framework, the automatic suggestions including one or more candidate attribute tags generated by the system in response to the selected context elements at the user interface, wherein the one or Each of the plurality of candidate attribute tags corresponds to one of the following: a goal associated with the task, a question related to the task, an answer to the question, and insights different from the answer.
系統可以被配置為執行用於如圖11中例示說明的方法(1100)的指令。該方法包括構建(1020)與任務有關的知識框架,該知識框架由多個歷史第一屬性標籤界定,該多個歷史第一屬性標籤中的每一個與至少一個相對應的歷史語境元素相關聯。該方法包括,響應於在用戶界面處所選擇的語境元素,確定(1130)第一屬性標籤,第一屬性標籤與語境元素相關聯以便相對於知識框架界定第一屬性標籤。語境元素基於一或多個源對象。該方法包括基於語境元素和知識框架提供(1140)一或多個候選屬性標籤作為自動建議。及該方法包括,響應於被接收為用戶輸入的自動建議,使得(1150)用戶能夠輸入一或多個其他屬性標籤以使得語境元素與標籤相關聯,該標籤由至少第一屬性標籤、第二屬性標籤、第三屬性標籤及第四屬性標籤界定,其中第一屬性標籤對應於與任務關聯的目標,第二屬性標籤對應於與任務相關的問題,第三屬性標籤對應於問題的答案,及第四屬性標籤對應於與答案不同的見解。如此,該系統可以以軟體即服務的形式部署。The system may be configured to execute instructions for the method (1100) as illustrated in FIG. 11. The method includes constructing (1020) a task-related knowledge frame, the knowledge frame being defined by a plurality of historical first attribute tags, each of the plurality of historical first attribute tags being related to at least one corresponding historical context element United. The method includes, in response to the selected context element at the user interface, determining (1130) a first attribute tag, the first attribute tag being associated with the context element so as to define the first attribute tag with respect to the knowledge framework. Context elements are based on one or more source objects. The method includes providing (1140) one or more candidate attribute tags as automatic suggestions based on the context element and the knowledge framework. And the method includes, in response to an automatic suggestion received as a user input, enabling (1150) the user to input one or more other attribute tags to associate the context element with the tag, the tag consisting of at least the first attribute tag, the first attribute tag, and the first attribute tag. The second attribute label, the third attribute label and the fourth attribute label are defined, where the first attribute label corresponds to the target associated with the task, the second attribute label corresponds to the task-related question, and the third attribute label corresponds to the answer to the question. And the fourth attribute tag corresponds to an opinion different from the answer. In this way, the system can be deployed in the form of software as a service.
如此,如本公開中所描述的知識框架是非常具體的且是具有語境的,可以採取許多形式及可以在其上不斷地改進。在本公開中,創新、創意和學習即服務被視為一種促使人們更加有創意地和創新地改善這些知識框架的系統及方法,從而組織表現的所有方面都可以進入一個新的水平等等。於此情況下,無論是個人還是團隊,都可以說已經促成了學習或人類潛能的發展。從認識論的角度來看,該系統及方法使用戶能夠更系統地及更快速地獲取與任何特定任務關聯的知識框架。此外,所獲得的知識框架的形式將多次經歷演變和轉化,從更抽象的形式變為更具體的形式,直至學習者滿意於所得知識框架關聯於語境。新興標籤工具可以使更好的知識框架被擷取以促進未來的學習歷程。從認識論的角度來看,如此獲得的數據呈現了學習發生的歷史軌跡,及可供未來的學習者參考。In this way, the knowledge framework as described in this disclosure is very specific and contextual, can take many forms and can be continuously improved on it. In this disclosure, innovation, creativity, and learning as a service are regarded as a system and method that encourages people to improve these knowledge frameworks more creatively and innovatively, so that all aspects of organizational performance can enter a new level and so on. In this case, whether it is an individual or a team, it can be said that it has contributed to the development of learning or human potential. From an epistemological point of view, the system and method enable users to acquire the knowledge framework associated with any specific task more systematically and faster. In addition, the form of the acquired knowledge framework will undergo many changes and transformations, from a more abstract form to a more concrete form, until the learner is satisfied that the acquired knowledge framework is related to the context. Emerging tagging tools can enable better knowledge frameworks to be captured to facilitate future learning journeys. From an epistemological point of view, the data obtained in this way presents the historical trajectory of learning and can be used as a reference for future learners.
從另一認識論的角度來看,正是見解驅動了創新和創意。具體言之,以上實施例使得不同的用戶能夠受益於其他用戶的關聯學習,其中該關聯學習由系統自動地策劃。這等同於不同的用戶共同進行“頭腦風暴”以尋求新的創新的場景,這種創新可能需要生成大量新的見解,但是具有使不同的用戶能夠在不同時間從不同位置在線參與的優勢。From another epistemological perspective, it is insights that drive innovation and creativity. Specifically, the above embodiments enable different users to benefit from the associated learning of other users, wherein the associated learning is automatically planned by the system. This is equivalent to a scenario where different users jointly "brainstorm" to find new innovations. This innovation may require the generation of a large number of new insights, but has the advantage of enabling different users to participate online from different locations at different times.
除非另外明確指出,在本文使用的單數的“一個”和“一”可以被解釋為包括複數的“一或多個”。Unless expressly stated otherwise, the singular "a" and "an" used herein can be construed as including the plural "one or more".
已經出於說明和描述的目的呈現了本公開,但是並不意圖是窮舉的或限制性的。對於本領域普通技術人員而言,許多修改和變化將是顯而易見的。已經選擇並描述了實例實施例,以便解釋原理和實際應用,並使本領域的其他普通技術人員能夠理解具有各種修改的各種實施例的公開內容,這些修改適合於預期的特定用途。The present disclosure has been presented for purposes of illustration and description, but is not intended to be exhaustive or limiting. Many modifications and changes will be obvious to those of ordinary skill in the art. The example embodiments have been selected and described in order to explain the principles and practical applications, and to enable others of ordinary skill in the art to understand the disclosure of the various embodiments with various modifications, which are suitable for the specific intended use.
如此,儘管這裡已經參考附圖描述了說明性的實例實施例,但是應當理解,該描述不是限制性的,及本領域的技術人員可以在其中進行各種其他改變和修改而不背離本公開的範圍。As such, although illustrative example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the description is not restrictive, and those skilled in the art can make various other changes and modifications therein without departing from the scope of the present disclosure .
100:系統 110:系統伺服器 112:計算機可讀存儲介質 120:網絡 130:設備 140:數據庫 150:資訊資源庫 200:知識框架的工具/用戶界面 210:新興標籤工具 220:文本框 230:語境元素 240:源對象/源 300:知識框架/標籤 310:標籤 312:目標屬性標籤 314:問題屬性標籤 316:答案屬性標籤 318:見解屬性標籤 400:框架 410:框架標籤/節點 500:機器學習模塊 520:機器學習算法 600:新興標籤工具 610:候選標籤 612:標籤 630:語境元素 640:源對象 714:標籤 800:新興標籤工具 810:第一交互面板/手動輸入交互面板 811:目標屬性標籤 812:問題屬性標籤 813:答案屬性標籤 814:見解屬性標籤 815:文本框 820:第二交互面板/自動建議交互面板 821:自動建議所包括的目標屬性標籤 822:自動建議所包括的問題屬性標籤 823:自動建議所包括的答案屬性標籤 824:自動建議所包括的見解屬性標籤 830:第三交互面板/自動建議交互面板 831:生成式目標屬性標籤 832:生成式問題屬性標籤 833:生成式答案屬性標籤 834:生成式見解屬性標籤 900:知識可視化工具 910:重新安排(選擇) 920:里程碑、任務、項目階段、議題、問題等 930:時間線 940:里程碑 1000:方法 1010:提供被配置為接收用戶輸入的用戶界面 1020:基於歷史第一屬性標籤構建知識框架 1030:提供包括由系統生成的一或多個候選屬性標籤的自動建議 1100:方法 1130:確定與語境元素相關聯的第一屬性標籤 1140:基於語境元素和知識框架提供一或多個候選屬性標籤作為自動建議 1150:使得能夠輸入一或多個屬性標籤以使得語境元素與標籤相關聯100: System 110: system server 112: Computer readable storage medium 120: Network 130: Equipment 140: database 150: Information Resource Library 200: Tools/User Interface of Knowledge Framework 210: Emerging Label Tool 220: text box 230: Contextual Elements 240: source object/source 300: knowledge framework/label 310: label 312: target attribute label 314: problem attribute label 316: Answer attribute label 318: Insights attribute tag 400: Frame 410: frame label/node 500: Machine Learning Module 520: machine learning algorithm 600: Emerging Label Tool 610: Candidate label 612: Label 630: Contextual Elements 640: Source Object 714: label 800: Emerging Label Tool 810: The first interactive panel/manual input interactive panel 811: target attribute label 812: problem attribute label 813: Answer attribute label 814: Insights attribute tag 815: text box 820: The second interactive panel / automatic suggestion interactive panel 821: Target attribute tags included in automatic suggestions 822: Problem attribute tags included in automatic suggestions 823: Answer attribute tags included in automatic suggestions 824: Insight attribute tags included in automatic suggestions 830: The third interactive panel / automatic suggestion interactive panel 831: generative target attribute label 832: generative question attribute label 833: generative answer attribute label 834: Generative insights attribute tags 900: knowledge visualization tool 910: rearrangement (selection) 920: Milestones, tasks, project phases, issues, problems, etc. 930: Timeline 940: Milestone 1000: method 1010: Provide a user interface configured to receive user input 1020: Building a knowledge framework based on historical first attribute tags 1030: Provide automatic suggestions including one or more candidate attribute tags generated by the system 1100: Method 1130: Determine the first attribute tag associated with the context element 1140: Provide one or more candidate attribute tags as automatic suggestions based on contextual elements and knowledge frameworks 1150: Enable the input of one or more attribute tags to associate contextual elements with tags
圖1是用於創新、創意和學習即服務的系統的示意圖。Figure 1 is a schematic diagram of a system for innovation, creativity, and learning as a service.
圖2是根據系統的一個實施例的具有新興標籤工具的用戶界面的示意圖。Fig. 2 is a schematic diagram of a user interface with an emerging label tool according to an embodiment of the system.
圖3顯示基於目標屬性標籤的知識框架。Figure 3 shows the knowledge framework based on target attribute tags.
圖4是根據一個實施例的系統的示意性框圖。Fig. 4 is a schematic block diagram of a system according to an embodiment.
圖5是系統的機器學習模塊的示意性流程圖。Fig. 5 is a schematic flow chart of the machine learning module of the system.
圖6是根據另一實施例的新興標籤工具的示意圖。Fig. 6 is a schematic diagram of an emerging label tool according to another embodiment.
圖7是根據另一實施例的新興標籤工具的示意圖。Fig. 7 is a schematic diagram of an emerging label tool according to another embodiment.
圖8是根據另一實施例的新興標籤工具的示意圖。Fig. 8 is a schematic diagram of an emerging label tool according to another embodiment.
圖9是由系統提供的知識可視化工具的示意圖。Figure 9 is a schematic diagram of the knowledge visualization tool provided by the system.
圖10是根據本公開的實施例的方法的示意性流程圖。Fig. 10 is a schematic flowchart of a method according to an embodiment of the present disclosure.
圖11是根據其他實施例的方法的示意性流程圖。Fig. 11 is a schematic flowchart of a method according to other embodiments.
100:系統 100: System
110:系統伺服器 110: system server
112:計算機可讀存儲介質 112: Computer readable storage medium
120:網絡 120: Network
130:設備 130: Equipment
140:數據庫 140: database
150:資訊資源庫 150: Information Resource Library
Claims (11)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
SG10201909407W | 2019-10-09 | ||
SG10201909407W | 2019-10-09 |
Publications (1)
Publication Number | Publication Date |
---|---|
TW202127364A true TW202127364A (en) | 2021-07-16 |
Family
ID=75438329
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW109134881A TW202127364A (en) | 2019-10-09 | 2020-10-08 | System and method for innovation, creativity, and learning as a service |
Country Status (2)
Country | Link |
---|---|
TW (1) | TW202127364A (en) |
WO (1) | WO2021071428A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023156995A1 (en) * | 2022-02-15 | 2023-08-24 | Marktrix Ltd. | Computer implemented methods for generation of documents with personalized content, and/or strategy, and/or action plan |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2016218970B2 (en) * | 2015-02-13 | 2018-06-28 | Thomson Reuters Enterprise Centre Gmbh | Systems and methods for natural language question answering and analysis |
US10033714B2 (en) * | 2015-06-16 | 2018-07-24 | Business Objects Software, Ltd | Contextual navigation facets panel |
US20170097984A1 (en) * | 2015-10-05 | 2017-04-06 | Yahoo! Inc. | Method and system for generating a knowledge representation |
US10606952B2 (en) * | 2016-06-24 | 2020-03-31 | Elemental Cognition Llc | Architecture and processes for computer learning and understanding |
CN107122399A (en) * | 2017-03-16 | 2017-09-01 | 中国科学院自动化研究所 | Combined recommendation system based on Public Culture knowledge mapping platform |
-
2020
- 2020-10-08 WO PCT/SG2020/050570 patent/WO2021071428A1/en active Application Filing
- 2020-10-08 TW TW109134881A patent/TW202127364A/en unknown
Also Published As
Publication number | Publication date |
---|---|
WO2021071428A1 (en) | 2021-04-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kotsiantis | Use of machine learning techniques for educational proposes: a decision support system for forecasting students’ grades | |
Minichiello et al. | Bringing user experience design to bear on STEM education: A narrative literature review | |
Truong | Integrating learning styles and adaptive e-learning system: Current developments, problems and opportunities | |
CN108121785A (en) | A kind of analysis method based on education big data | |
Omeihe et al. | The role of the entrepreneurial leader: a study of Nigerian SMEs | |
Bozo et al. | Recommending learning objects according to a teachers’ contex model | |
Sekkal et al. | Knowledge management and reuse in virtual learning communities | |
Juškevičienė et al. | On recommending Web 2.0 tools to personalise learning | |
Lau et al. | A folksonomy-based lightweight resource annotation metadata schema for personalized hypermedia learning resource delivery | |
Semertzaki | Knowledge Management Skills Applicable to Information Management–Information Management Skills Applicable to Knowledge Management in an Organization☆ | |
Kushwaha et al. | Integrating the linkages between learning systems and knowledge process: an exploration of learning outcomes | |
Ranjan et al. | The six faces of value co-creation: A field guide for executives | |
Kwok et al. | Designing individualisation of eco information: A conceptual framework and design toolkit | |
Hanington et al. | The Pocket Universal Methods of Design, Revised and Expanded: 125 Ways to Research Complex Problems, Develop Innovative Ideas, and Design Effective Solutions | |
TW202127364A (en) | System and method for innovation, creativity, and learning as a service | |
Al-Rasheed et al. | Knowledge management of best practices in a collaborative environment | |
Radenković et al. | Creating adaptive environment for e-learning courses | |
Nashed et al. | Educational resources recommender system for teachers: why and how? | |
Sloep | Design for networked learning | |
Shahbani et al. | Improving entrepreneurial opportunity recognition through web content analytics | |
Wanapu et al. | An investigation on the correlation of learner styles and learning objects characteristics in a proposed Learning Objects Management Model (LOMM) | |
Kunneman et al. | Data science for service design: An introductory overview of methods and opportunities | |
Pereira et al. | Application of a management and storage system for knowledge generated from simulation projects as a teaching and assessment tool | |
Wang et al. | Adaptive Education System for Drama Education in College Education System Based on Human-Computer | |
McKenna et al. | Exploring a creativity assessment technique for use in 21st century learning, library, and instructional collaborations |