TW201317954A - Method and system for learning diagnosis and dynamic recommendation of learning resource - Google Patents
Method and system for learning diagnosis and dynamic recommendation of learning resource Download PDFInfo
- Publication number
- TW201317954A TW201317954A TW100138801A TW100138801A TW201317954A TW 201317954 A TW201317954 A TW 201317954A TW 100138801 A TW100138801 A TW 100138801A TW 100138801 A TW100138801 A TW 100138801A TW 201317954 A TW201317954 A TW 201317954A
- Authority
- TW
- Taiwan
- Prior art keywords
- problem solving
- solving
- strategy
- knowledge
- behavior
- Prior art date
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
本發明係有關於數位學習，且特別有關於學習評估與學習資源推薦的技術。The present invention relates to digital learning, and in particular to techniques for learning assessment and learning resource recommendation.
傳統上，老師藉由閱改學生的作業或考卷來評量學生的學習情況，並根據學生的學習情況選擇適合的教材。隨著科技的發展，現在學習者可藉由電腦與網路進行線上評量，並針對錯誤的題目取得多媒體形式的解答。Traditionally, the teacher evaluates the student's learning by reading the student's homework or exam papers, and selects the appropriate textbook according to the student's learning situation. With the development of technology, learners can now conduct online assessments through computers and the Internet, and get multimedia solutions to the wrong topics.
然而現今的數位學習系統大多藉由附上對應解答的方式讓學習者自行閱讀解答以修正答錯的題目，此種方式欠缺對學習者答題過程的分析，由於在答題過程中通常需要運用不只一種知識概念，因此現今的數位學習系統無法具體得知學習者真正不會的知識概念是何者。舉例而言，若有兩位學生算錯相同的題目，這兩位學生不懂的知識概念也不一定相同，更甚者，學生可能因為先備知識的不足而無法理解附上的解答。除此之外，現有數位學習系統的解答機制是針對每題題目設計其對應的解答，但是一個知識概念可能會同時出現在不同的解答中，若學生僅是對應題目去理解解答可能無法真正融會貫通其中的知識概念，也無法將該知識概念運用至其他題目，容易產生孤島知識。因此，老師無法經由現今的數位學習系統具體得知學生真正不會的知識概念，也無法針對不會的知識概念提供更適性的補充資源。However, most of today's digital learning systems allow learners to read the answers themselves to correct the wrong answers by attaching corresponding answers. This method lacks the analysis of the learner's answering process, because it usually needs to use more than one kind in the answering process. The concept of knowledge, so today's digital learning system can't specifically know what the knowledge concept that learners really don't. For example, if two students miscalculate the same problem, the knowledge concepts that the two students do not understand are not necessarily the same. Moreover, the students may not be able to understand the attached answers because of the lack of prior knowledge. In addition, the solution mechanism of the existing digital learning system is to design corresponding answers for each topic, but a knowledge concept may appear in different solutions at the same time. If the students only understand the answers, they may not be able to truly integrate. The concept of knowledge cannot apply this knowledge concept to other topics, and it is easy to generate island knowledge. Therefore, teachers can't know the concept of knowledge that students really don't know through the current digital learning system, and they can't provide more appropriate supplementary resources for the concept of knowledge that they don't.
有鑑於此，本發明提供一種學習診斷與動態學習資源推薦的方法，其記錄解題行為並從中分析解題策略來推論錯誤的知識概念，並基於所推論的錯誤知識概念整理線上教學資源，以適性地提供學習補救資源。In view of this, the present invention provides a method for learning diagnosis and dynamic learning resource recommendation, which records the problem-solving behavior and analyzes the problem solving strategy to infer the wrong knowledge concept, and organizes the online teaching resource based on the inferred wrong knowledge concept to appropriately Provide learning remediation resources.
本發明一實施例揭露一種學習診斷與動態學習資源推薦的方法，包括：藉由一使用者介面提供一題目；藉由該使用者介面記錄對應該題目的一解題行為；根據該解題行為判斷對應該解題行為的一解題策略；比對該解題行為與對應該解題策略的一正確解題行為，以判斷錯誤的至少一知識概念；根據該至少一知識概念與該解題行為，判斷至少一錯誤類型，其中每個知識概念對應至複數個錯誤類型；根據該至少一知識概念，從複數個教學資源庫中擷取與該至少一知識概念相關的複數個相關教學資源；以及根據該等相關教學資源提供一推薦教學資源。An embodiment of the present invention discloses a method for learning diagnosis and dynamic learning resource recommendation, including: providing a topic through a user interface; recording a problem-solving behavior corresponding to the topic through the user interface; and determining a pair according to the problem-solving behavior a problem solving strategy that should solve the problem; a correct problem solving behavior corresponding to the problem solving behavior and the corresponding problem solving strategy to judge at least one knowledge concept of the error; according to the at least one knowledge concept and the problem solving behavior, determining at least one error type, Each knowledge concept corresponds to a plurality of error types; according to the at least one knowledge concept, a plurality of related teaching resources related to the at least one knowledge concept are extracted from a plurality of teaching resource pools; and provided according to the related teaching resources A recommended teaching resource.
本發明另一實施例揭露一種學習診斷與動態學習資源推薦系統，包括：一使用者介面，提供一題目；一行為記錄模組，透過該使用者介面記錄對應該題目的一解題行為；一策略分析模組，根據該解題行為判斷對應該解題行為的一解題策略；一錯誤推論模組，比對該解題行為與對應該解題策略的一正確解題行為，以判斷錯誤的至少一知識概念，並根據該至少一知識概念與該解題行為，判斷至少一錯誤類型，其中每個知識概念對應至複數個錯誤類型；以及一動態資源推薦模組，根據該至少一知識概念從複數個教學資源庫中擷取與該至少一知識概念相關的複數個相關教學資源，並且根據該等相關教學資源提供薦一推薦教學資源。Another embodiment of the present invention discloses a learning diagnosis and dynamic learning resource recommendation system, including: a user interface for providing a topic; and a behavior recording module for recording a problem solving problem corresponding to the topic through the user interface; The analysis module determines a problem solving strategy corresponding to the problem solving behavior according to the problem solving behavior; an error inference module compares the correct problem solving behavior with the solving problem and the corresponding problem solving strategy to judge at least one knowledge concept of the error, and Determining at least one error type according to the at least one knowledge concept and the problem solving behavior, wherein each knowledge concept corresponds to a plurality of error types; and a dynamic resource recommendation module, according to the at least one knowledge concept, from the plurality of teaching resource pools A plurality of related teaching resources related to the at least one knowledge concept are extracted, and a recommended teaching resource is provided according to the related teaching resources.
以下說明為本發明的實施例。其目的是要舉例說明本發明一般性的原則，不應視為本發明之限制，本發明之範圍當以申請專利範圍所界定者為準。The following description is an embodiment of the present invention. The intent is to exemplify the general principles of the invention and should not be construed as limiting the scope of the invention, which is defined by the scope of the claims.
本發明之核心技術為操作行為記錄技術、解題策略分析技術、多變量錯誤類型推論技術以及動態資源推薦技術。以下以數學題目為例，分別說明學習診斷與動態學習資源推薦的核心技術。The core technologies of the present invention are operational behavior recording technology, problem solving strategy analysis technology, multivariate error type inference technology, and dynamic resource recommendation technology. The following is a mathematical topic as an example to illustrate the core technologies of learning diagnosis and dynamic learning resource recommendation.
[操作行為記錄技術][Operational Behavior Recording Technology]
第1圖所示為依據本發明實施例之使用者介面100的示意圖。該使用者介面100包括顯示題目的題目區110、答題輸入區120、運算符號區130以及答題呈現區140。如第1圖所示，使用者介面100將可能的運算式與操作行為做成按鈕，使學習者可以在電腦上透過使用者介面100以及滑鼠、鍵盤等輸入裝置輸入完整的解題行為，且操作行為記錄技術可透過使用者介面的按鈕與輸入裝置記錄所輸入的解題行為。1 is a schematic diagram of a user interface 100 in accordance with an embodiment of the present invention. The user interface 100 includes a title area 110 for displaying a title, an answer input area 120, an arithmetic symbol area 130, and a question presentation area 140. As shown in FIG. 1, the user interface 100 makes possible calculations and operation behaviors as buttons, so that the learner can input complete problem-solving behaviors on the computer through the user interface 100 and input devices such as a mouse and a keyboard. The operational behavior recording technique records the input problem-solving behavior through a user interface button and an input device.
[解題策略分析技術][Solution Strategy Analysis Technology]
解題策略分析技術將解題行為拆解為複數個解題步驟，並比對該等解題步驟與對應題目的解題策略集合，以從該解題策略集合中判斷出與解題行為相符的解題策略。以第2圖為例，第2圖所示為依據本發明實施例之解題策略集合200的示意圖。如第2圖所示，解題策略集合200包括5種解題策略A1~A5。以解題策略A2為例，其包括解題策略步驟S210、S230、S231、S232、S233以及S234。舉例而言，解題行為EB(Equation Behavior)為，解題策略分析技術藉由等號將解題行為EB分解為五個解題步驟，並根據每個解題步驟中的運算符號及數字，判斷每個解題步驟對應至解題策略集合200的解題策略步驟S210~S261其中的哪個步驟，以判斷出解題行為EB屬於哪個解題策略。例如上述解題行為EB係對應至解題策略A3。解題策略集合200係對應至題目，每個題目有其對應的解題策略集合，解題策略集合可在設計題目時對應題目建立。The problem-solving strategy analysis technology disassembles the problem-solving behavior into a plurality of problem-solving steps, and compares the problem-solving steps with the problem-solving strategies of the corresponding problem-solving steps to determine a solution-solving strategy consistent with the problem-solving behavior. Taking Figure 2 as an example, Figure 2 is a schematic diagram of a problem solving policy set 200 in accordance with an embodiment of the present invention. As shown in FIG. 2, the problem solving strategy set 200 includes five problem solving strategies A1 to A5. Taking the problem solving strategy A2 as an example, it includes problem solving strategies steps S210, S230, S231, S232, S233, and S234. For example, the EB (Equation Behavior) is The problem solving strategy analysis technique decomposes the problem solving behavior EB into five problem solving steps by equal sign, and judges each problem solving step corresponding to the problem solving strategy set 200 problem solving step S210~ according to the operation symbols and numbers in each problem solving step. Which step of S261 is used to determine which problem-solving strategy EB belongs to. For example, the above problem solving behavior EB corresponds to the problem solving strategy A3. The problem solving strategy set 200 corresponds to the title, each topic has its corresponding problem solving strategy set, and the problem solving strategy set can be established corresponding to the title when designing the topic.
[多變量錯誤類型推論技術][Multivariate error type inference technique]
多變量錯誤類型推論技術藉由比對解題行為與對應解題策略的正確解題行為，分析學習者運算發生錯誤的地方，以確定錯誤類型與學習者不會的知識概念。The multivariate error type inference technique analyzes the place where the learner's operation is erroneous by comparing the problem-solving behavior with the correct problem-solving behavior of the corresponding problem-solving strategy to determine the type of error and the knowledge concept that the learner does not.
第3圖所示為依據本發明實施例之多變量錯誤類型推論技術的示意圖。如上所述，解題行為EB對應至解題策略A3，而解題策略集合200所對應的題目依照解題策略A3進行解題的正確解題行為稱為REB(Right Equation Behavior)。多變量錯誤類型推論技術比對解題行為EB的每個解題步驟，以及正確解題行為REB的每個正確解題步驟，來判斷出解題行為EB中哪個解題步驟算錯了。以解題行為EB為例，經過與正確解題行為REB的比對之後，可以得知解題行為EB從解題步驟處便開始運算錯誤。由於錯誤的解題步驟對應至解題策略步驟S241，而解題策略步驟S241所對應的知識概念為「分數加減」，因此可以從解題行為EB推論出學習者很有可能在「分數加減」方面有不會的地方。Figure 3 is a diagram showing a multivariate error type inference technique in accordance with an embodiment of the present invention. As described above, the problem solving behavior EB corresponds to the problem solving strategy A3, and the correct problem solving behavior of the problem corresponding to the problem solving strategy set A3 according to the problem solving strategy set A3 is called REB (Right Equation Behavior). The multivariate error type inference technique compares each problem solving step of the problem solving behavior EB and each correct problem solving step of the correct problem solving behavior REB to determine which problem solving step in the problem solving behavior EB is wrong. Taking the problem-solving behavior EB as an example, after comparing with the correct problem-solving behavior REB, you can know the problem-solving behavior EB from the problem-solving step. The operation error started. Due to wrong problem solving steps Corresponding to the problem solving strategy step S241, the knowledge concept corresponding to the problem solving strategy step S241 is "score addition and subtraction", so it is possible to infer from the problem solving behavior EB that the learner is likely to have a place in the "score addition and subtraction".
第4圖所示為依據本發明實施例之知識概念與錯誤類型之間的對應關係400的示意圖。如上所述，已推論出不會的知識概念為「分數加減」，根據第4圖，在知識概念S01「分數加減」中可能的錯誤類型有錯誤類型B1「通分、約分的錯誤」、錯誤類型B2「加法運算時，分母乘分母，分子乘分子」、錯誤類型B3「帶分數與假分數轉換的錯誤」以及錯誤類型B12「計算錯誤或粗心」。也就是說，在運用知識概念S01「分數加減」時若運算錯誤，則運算錯誤的可能原因為錯誤類型B1~B3、B12。由於錯誤的解題步驟對應至解題策略步驟S241，解題策略步驟S241所對應的知識概念為S01「分數加減」，知識概念S01對應至錯誤類型B1~B3、B12，藉由比對錯誤的解題步驟以及正確解題行為可以判斷出，錯誤類型為知識概念S01所對應的錯誤類型B1~B3、B12中的錯誤類型B3。藉由多變量錯誤類型推論技術，本發明可以有效分析學習者的解題行為，進而推論出學習者不會的知識概念。Figure 4 is a diagram showing the correspondence 400 between the knowledge concept and the type of error in accordance with an embodiment of the present invention. As described above, it has been inferred that the concept of knowledge that is not possible is "score addition and subtraction". According to Fig. 4, the possible error types in the knowledge concept S01 "score addition and subtraction" are error type B1 "passpoint, error of the score", Error type B2 "when adding, denominator multiplier, numerator multiply", error type B3 "error with fractional and false fraction conversion", and error type B12 "calculation error or carelessness". In other words, if the operation is incorrect when applying the knowledge concept S01 "Score Addition and Subtraction", the possible causes of the operation error are error types B1 to B3 and B12. Due to wrong problem solving steps Corresponding to the problem solving strategy step S241, the knowledge concept corresponding to the problem solving strategy step S241 is S01 "score addition and subtraction", and the knowledge concept S01 corresponds to the error types B1~B3, B12, and the problem solving steps by comparing errors And the correct problem solving behavior can be judged that the error type is the error type B1~B3 corresponding to the knowledge concept S01, and the error type B3 in B12. With the multivariate error type inference technique, the present invention can effectively analyze the learner's problem-solving behavior, and then infer the knowledge concept that the learner does not.
[動態資源推薦技術][Dynamic Resource Recommendation Technology]
第5圖所示為依據本發明實施例之動態資源推薦技術的示意圖。在經由多變量錯誤類型推論技術推論出學習者不會的知識概念後，利用動態資源推薦技術找出對應學習者不會的知識概念的學習補充資源。舉例而言，若學習者不會的知識概念為「分數加法」，則動態資源推薦技術以「分數加法」為關鍵字，從複數個教學資源庫D1-D8中擷取出與該關鍵字相關的複數個相關教學資源。例如以「分數加法」為關鍵字，從教學資源庫D1中擷取出與「分數加法」之關鍵字相關的複數個相關教學資源S1。第5圖中的教學資源庫D1-D8皆為線上資源，例如教學資源庫D1-D8可以為***的數位教學資源網、維基百科以及YouTube等，但教學資源庫D1-D8也可以為實體的教學資源庫，而教學資源可以是一段教學影片、動畫或是互動式操作軟體等。由於知識概念之間會有共通的部份，例如在做分數乘法運算時會需要利用到假分數轉換的概念，因此以「分數加法」為關鍵字所檢索到的教學資源有可能是分屬不同知識概念的教學資源，例如「假分數」與「分數乘法」知識概念下的教學資源有可能會與「分數加法」之關鍵字相關，接下來再根據知識概念的不同，把相關教學資源分類至複數個知識目錄，其中每個知識目錄對應至一知識概念。以第5圖為例，將分別從各教學資源庫D1-D8檢索到的相關教學資源S1-S8，依照知識概念分為「假分數」、「分數加法」以及「分數乘法」三個類別。FIG. 5 is a schematic diagram showing a dynamic resource recommendation technique according to an embodiment of the present invention. After inferring the knowledge concept that the learner does not learn through the multivariate error type inference technique, the dynamic resource recommendation technique is used to find the learning supplementary resource corresponding to the knowledge concept that the learner does not. For example, if the learner does not have the concept of knowledge as "score addition", the dynamic resource recommendation technique uses "score addition" as a key to extract the keywords associated with the keyword from the plurality of teaching resource pools D1-D8. A number of related teaching resources. For example, using "score addition" as a key, a plurality of related teaching resources S1 related to the keyword of "score addition" are extracted from the teaching resource library D1. The teaching resource pools D1-D8 in Figure 5 are all online resources. For example, the teaching resource library D1-D8 can be the digital teaching resource network of the Ministry of Education, Wikipedia. And YouTube Etc., but the teaching resource library D1-D8 can also be a physical teaching resource library, and the teaching resources can be a teaching film, animation or interactive operating software. Since there is a common part between knowledge concepts, for example, the concept of false fractional conversion is needed when doing fractional multiplication. Therefore, the teaching resources retrieved by using "score addition" as keywords may be different. Teaching resources of knowledge concepts, such as "fake scores" and "score multiplication" knowledge, may be related to the keywords of "score addition", and then classify relevant teaching resources according to different knowledge concepts. A plurality of knowledge directories, each of which corresponds to a knowledge concept. Taking Figure 5 as an example, the related teaching resources S1-S8 retrieved from the respective teaching resource pools D1-D8 are classified into three categories: "false points", "score addition", and "score multiplication" according to the concept of knowledge.
需注意的是，一個相關教學資源可以同時屬於不只一個知識概念。接下來再分別將「假分數」、「分數加法」以及「分數乘法」三個知識目錄中的相關教學資源依照例如難易程度或學習先後順序等歸納成對應知識目錄(知識概念)的教知識概念教學資源，最後整合各知識概念教學資源為推薦教學資源，並推薦給學習者。It should be noted that a related teaching resource can belong to more than one knowledge concept at the same time. Then, the related teaching resources in the three knowledge directories of "false score", "score addition" and "score multiplication" are respectively classified into the knowledge knowledge concept corresponding to the knowledge list (knowledge concept) according to the difficulty level or the learning order. Teaching resources, and finally integrate the teaching resources of various knowledge concepts as recommended teaching resources, and recommend them to learners.
藉由上述操作行為記錄技術、解題策略分析技術、多變量錯誤類型推論技術以及動態資源推薦技術，本發明可以有效分析學習者的解題行為以歸納錯誤類型，並根據錯誤類型即時分析大量的教學資源，將與錯誤類型相關的教學資源整合成適性化的推薦教學資源以使學習者可藉由該推薦教學資源補強不會的知識概念。Through the above operation behavior recording technology, problem solving strategy analysis technology, multivariate error type inference technology and dynamic resource recommendation technology, the present invention can effectively analyze the learner's problem solving behavior to summarize the error types, and analyze a large number of teaching resources according to the error type. The teaching resources related to the error type are integrated into the appropriate recommended teaching resources so that the learner can reinforce the knowledge concept that is not possible by the recommended teaching resources.
第6圖所示為依據本發明實施例之學習診斷與動態學習資源推薦的方法600的流程圖。FIG. 6 is a flow chart showing a method 600 of learning diagnosis and dynamic learning resource recommendation in accordance with an embodiment of the present invention.
在步驟S600中，藉由使用者介面提供一題目，例如第1圖的使用者介面100。In step S600, a topic, such as the user interface 100 of FIG. 1, is provided by the user interface.
在步驟S610中，藉由使用者介面記錄對應題目的解題行為。In step S610, the problem solving behavior of the corresponding topic is recorded by the user interface.
在步驟S620中，如上列解題策略分析技術所述，根據解題行為判斷對應解題行為的解題策略。其中解題策略包含於對應題目之解題策略集合中，例如第2圖的解題策略集合200，解題策略集合包括複數個解題策略，每個解題策略包括複數個解題策略步驟，每個解題策略步驟對應至一知識概念，因此在比對解題行為與正確解題行為時，首先將解題行為拆解為複數個解題步驟，然後比對解題步驟與解題策略步驟，以從解題策略集合中判斷出與解題行為相符的解題策略。In step S620, as described in the problem solving strategy analysis technique, the problem solving strategy corresponding to the problem solving behavior is judged according to the problem solving behavior. The problem solving strategy is included in the problem solving strategy set of the corresponding topic, for example, the problem solving strategy set 200 of FIG. 2, the problem solving strategy set includes a plurality of problem solving strategies, each problem solving strategy includes a plurality of problem solving strategy steps, and each problem solving strategy step corresponds to A knowledge concept, therefore, in the comparison of the problem-solving behavior and the correct problem-solving behavior, firstly, the problem-solving behavior is disassembled into a plurality of problem-solving steps, and then the problem-solving step and the problem-solving strategy step are compared to determine that the problem-solving behavior is consistent with the problem solving strategy set. Problem solving strategy.
在步驟S630中，如上列解題策略分析技術所述，比對解題行為與對應解題策略的正確解題行為，以判斷解題行為中發生錯誤的知識概念。In step S630, as described in the problem solving strategy analysis technique, the correct problem solving behavior of the problem solving behavior and the corresponding problem solving strategy is compared to determine the knowledge concept of the error occurring in the problem solving behavior.
在步驟S640中根據錯誤的知識概念與解題行為，判斷至少一個錯誤類型，其中每個知識概念對應至複數個錯誤類型，如第4圖所示。正確解題行為包括複數個正確解題步驟，而正確解題步驟對應至解題策略的解題策略步驟，如第3圖所示，正確解題行為REB的各正確解題步驟係對應至解題策略A3的各解題策略步驟。在比對解題行為與正確解題行為以判斷解題行為中發生錯誤的知識概念時，首先比對解題步驟與正確解題步驟以判斷錯誤發生在哪個解題步驟，並得知對應於錯誤的解題步驟的解題策略步驟，然後再根據對應該解題策略步驟的知識概念以及錯誤的解題步驟判斷錯誤類型。At least one error type is determined according to the erroneous knowledge concept and the problem solving behavior in step S640, wherein each knowledge concept corresponds to a plurality of error types, as shown in FIG. The correct problem solving behavior includes a plurality of correct problem solving steps, and the correct problem solving step corresponds to the problem solving strategy step of the problem solving strategy. As shown in FIG. 3, the correct problem solving steps of the correct problem solving behavior REB correspond to the problem solving strategy steps of the problem solving strategy A3. . When comparing the problem-solving behavior with the correct problem-solving behavior to judge the knowledge concept of the error in the problem-solving behavior, first compare the problem-solving step with the correct problem-solving step to determine which problem-solving step the error occurred in, and to know the problem-solving step corresponding to the wrong problem-solving step. The strategy step, and then judge the type of error according to the knowledge concept corresponding to the problem solving strategy step and the wrong problem solving step.
在步驟S650中，如上列動態資源推薦技術所述，根據發生錯誤的知識概念，從複數個教學資源庫中擷取與發生錯誤的知識概念相關的複數個相關教學資源。In step S650, as described in the dynamic resource recommendation technique, the plurality of related teaching resources related to the knowledge concept in which the error occurred are extracted from the plurality of teaching resource pools according to the knowledge concept of the error occurrence.
最後於步驟S660中，根據該等相關教學資源提供一推薦教學資源。關於提供一推薦教學資源部份，首先利用與發生錯誤的知識概念相關之關鍵字檢索複數個教學資源庫，例如直接以發生錯誤的知識概念為關鍵字檢索該等教學資源庫，以從該等教學資源庫中擷取與關鍵字相關的複數個相關教學資源。然後根據該等相關教學資源分別所屬的知識概念，將該等相關教學資源依據知識概念分類至複數個知識目錄，其中該等知識目錄分別對應至一知識概念。接著根據相關教學資源的難易程度或學習先後順序，將這些知識目錄下的相關教學資源歸納為對應於每個該等知識目錄的知識概念教學資源，並將該等知識概念教學資源整合為推薦教學資源。Finally, in step S660, a recommended teaching resource is provided according to the related teaching resources. Regarding the provision of a recommended teaching resource, firstly, a plurality of teaching resource pools are searched by using keywords related to the knowledge concept in which the error occurred, for example, directly searching for the teaching resource pools by using the knowledge concept of the error as a key to The teaching resource library draws a plurality of related teaching resources related to keywords. Then, according to the knowledge concepts respectively belonged to the related teaching resources, the related teaching resources are classified into a plurality of knowledge directories according to the knowledge concept, wherein the knowledge directories respectively correspond to a knowledge concept. Then, according to the difficulty level of the relevant teaching resources or the order of learning, the relevant teaching resources under these knowledge directories are summarized into the knowledge concept teaching resources corresponding to each of the knowledge directories, and the knowledge concept teaching resources are integrated into the recommended teaching. Resources.
第7圖所示為依據本發明實施例之學習診斷與動態學習資源推薦系統700的示意圖。學習診斷與動態學習資源推薦系統700包括使用者介面模組710、行為記錄模組720、策略分析模組730、錯誤推論模組740以及動態資源推薦模組750。FIG. 7 is a schematic diagram of a learning diagnostic and dynamic learning resource recommendation system 700 in accordance with an embodiment of the present invention. The learning diagnosis and dynamic learning resource recommendation system 700 includes a user interface module 710, a behavior recording module 720, a policy analysis module 730, an error inference module 740, and a dynamic resource recommendation module 750.
使用者介面模組710提供一題目。行為記錄模組720，透過使用者介面模組710記錄對應該題目的一解題行為。策略分析模組730根據解題行為，判斷對應解題行為的一解題策略。其中解題策略包含於對應該題目之解題策略集合中，解題策略集合包括複數個解題策略，每個解題策略包括複數個解題策略步驟，每個解題策略步驟對應至一知識概念。舉例而言，如上列解題策略分析技術所述，策略分析模組730將解題行為拆解為複數個解題步驟，比對各解題步驟與各解題策略步驟，以從解題策略集合中判斷出與解題行為相符的解題策略。The user interface module 710 provides a topic. The behavior record module 720 records a problem-solving behavior corresponding to the topic through the user interface module 710. The strategy analysis module 730 determines a problem solving strategy corresponding to the problem solving behavior according to the problem solving behavior. The problem solving strategy is included in the problem solving strategy set corresponding to the topic, and the problem solving strategy set includes a plurality of problem solving strategies, each of which includes a plurality of problem solving strategy steps, and each problem solving strategy step corresponds to a knowledge concept. For example, as described in the problem-solving strategy analysis technique, the strategy analysis module 730 disassembles the problem-solving behavior into a plurality of problem-solving steps, and compares each problem-solving step with each problem-solving strategy step to determine and solve the problem-solving strategy set. A behavioral problem-solving strategy.
錯誤推論模組740比對解題行為與對應解題策略的正確解題行為，以判斷發生錯誤的知識概念，並根據發生錯誤的知識概念與解題行為判斷錯誤類型，其中每個知識概念對應至複數個錯誤類型，如第4圖所示。正確解題行為包括複數個正確解題步驟，正確解題步驟對應至解題策略步驟。如上述多變量錯誤類型推論技術，錯誤推論模組740比對解題步驟與正確解題步驟以判斷哪個解題步驟發生錯誤，並得知對應於錯誤的解題步驟的解題策略步驟，然後再根據對應該解題策略步驟的知識概念以及錯誤的解題步驟判斷錯誤類型。The error inference module 740 compares the correct problem solving behavior of the problem solving behavior and the corresponding problem solving strategy to judge the knowledge concept of the error, and judges the error type according to the knowledge concept and the problem solving behavior in which the error occurs, wherein each knowledge concept corresponds to a plurality of errors. Type, as shown in Figure 4. The correct problem solving behavior includes a plurality of correct problem solving steps, and the correct problem solving steps correspond to the problem solving strategy steps. As described above, the multivariate error type inference technique, the error inference module 740 compares the problem solving step with the correct problem solving step to determine which problem solving step has an error, and knows the problem solving strategy step corresponding to the wrong problem solving step, and then solves the problem according to the corresponding problem. The knowledge concept of the strategy step and the wrong problem solving step determine the type of error.
動態資源推薦模組750根據發生錯誤的知識概念從複數個教學資源庫760中，擷取與該知識概念相關的複數個相關教學資源，並且根據該等相關教學資源提供一推薦教學資源。動態資源推薦模組750利用與發生錯誤的知識概念相關之關鍵字檢索該等教學資源庫760，以從該等教學資源庫760中擷取與該關鍵字相關的複數個相關教學資源，根據該等相關教學資源之每一者所屬的知識概念，將該等相關教學資源分類至複數個知識目錄，其中該等知識目錄分別對應至一知識概念，接著根據相關教學資源的難易程度或學習先後順序，將每個該等知識目錄下的相關教學資源歸納為對應於每個該等知識目錄的知識概念教學資源，並將該等知識概念教學資源整合為推薦教學資源。The dynamic resource recommendation module 750 retrieves a plurality of related teaching resources related to the knowledge concept from the plurality of teaching resource pools 760 according to the knowledge concept of the error, and provides a recommended teaching resource according to the related teaching resources. The dynamic resource recommendation module 750 retrieves the teaching resource pools 760 using keywords related to the knowledge concept in which the errors occurred, to retrieve a plurality of related teaching resources related to the keywords from the teaching resource pool 760, according to the And the knowledge concept of each of the related teaching resources, the related teaching resources are classified into a plurality of knowledge directories, wherein the knowledge directories respectively correspond to a knowledge concept, and then according to the difficulty level or the learning order of the related teaching resources The relevant teaching resources under each of the knowledge directories are summarized into knowledge concept teaching resources corresponding to each of the knowledge directories, and the knowledge concept teaching resources are integrated into the recommended teaching resources.
以上實施例雖以數學題目舉例說明，但本發明並不局限於數學題目，例如本發明也可運用至物理與化學題目等，因物理與化學題目的運算常運用到數學領域的知識概念。除此之外，對於未能以數字或符號表示解題行為的題目而言，本發明可藉由提供複數個思考步驟或邏輯供學習者選用以記錄並分析學習者在解題時的邏輯，並藉此分析學習者所使用的解題策略。Although the above embodiments are exemplified by mathematical problems, the present invention is not limited to mathematical problems. For example, the present invention can also be applied to physical and chemical problems, and the calculation of physical and chemical topics is often applied to the knowledge concept in the field of mathematics. In addition, for the subject that fails to represent the problem solving function by number or symbol, the present invention can provide a plurality of thinking steps or logic for the learner to select and analyze the logic of the learner in solving the problem, and borrow This analyzes the problem-solving strategies used by learners.
本發明之方法，或特定型態或其部份，可以以程式碼的型態存在。程式碼可以包含於實體媒體，如軟碟、光碟片、硬碟、或是任何其他電子設備或機器可讀取(如電腦可讀取)儲存媒體，亦或不限於外在形式之電腦程式產品，其中，當程式碼被機器，如電腦載入且執行時，此機器變成用以參與本發明之裝置或系統，且可執行本發明之方法步驟。程式碼也可以透過一些傳送媒體，如電線或電纜、光纖、或是任何傳輸型態進行傳送，其中，當程式碼被電子設備或機器，如電腦接收、載入且執行時，此機器變成用以參與本發明之系統或裝置。當在一般用途處理單元實作時，程式碼結合處理單元提供一操作類似於應用特定邏輯電路之獨特裝置。The method of the invention, or a particular type or portion thereof, may exist in the form of a code. The code may be embodied in a physical medium such as a floppy disk, a compact disc, a hard disk, or any other electronic device or machine readable (eg computer readable) storage medium, or is not limited to an external form of computer program product. Wherein, when the code is loaded and executed by a machine, such as a computer, the machine becomes a device or system for participating in the present invention and the method steps of the present invention can be performed. The code can also be transmitted over some transmission medium, such as wire or cable, fiber optics, or any transmission type, where the machine becomes available when the code is received, loaded, and executed by an electronic device or machine, such as a computer. To participate in the system or device of the present invention. When implemented in a general purpose processing unit, the code combination processing unit provides a unique means of operation similar to application specific logic.
以上所述為實施例的概述特徵。所屬技術領域中具有通常知識者應可以輕而易舉地利用本發明為基礎設計或調整以實行相同的目的和/或達成此處介紹的實施例的相同優點。所屬技術領域中具有通常知識者也應了解相同的配置不應背離本創作的精神與範圍，在不背離本創作的精神與範圍下他們可做出各種改變、取代和交替。說明性的方法僅表示示範性的步驟，但這些步驟並不一定要以所表示的順序執行，可另外加入、取代、改變順序和/或消除步驟以視情況而作調整，並與所揭露的實施例精神和範圍一致。The above is an overview feature of the embodiment. Those having ordinary skill in the art should be able to use the present invention as a basis for design or adaptation to achieve the same objectives and/or achieve the same advantages of the embodiments described herein. It should be understood by those of ordinary skill in the art that the same configuration should not depart from the spirit and scope of the present invention, and various changes, substitutions and substitutions can be made without departing from the spirit and scope of the present invention. The illustrative methods are merely illustrative of the steps, but are not necessarily performed in the order indicated, and may be added, substituted, changed, and/or eliminated, adjusted as appropriate, and disclosed. The spirit and scope of the examples are consistent.
100．．．使用者介面100. . . user interface
110．．．題目區110. . . Topic area
120．．．答題輸入區120. . . Answer input area
130．．．運算符號區130. . . Operator symbol area
140．．．答題呈現區140. . . Answer presentation area
200．．．解題策略集合200. . . Problem solving strategy set
400．．．知識概念與錯誤類型之間的對應關係400. . . Correspondence between knowledge concepts and error types
600．．．學習診斷與動態學習資源推薦的方法600. . . Learning diagnosis and dynamic learning resource recommendation method
700．．．學習診斷與動態學習資源推薦系統700. . . Learning diagnosis and dynamic learning resource recommendation system
710．．．使用者介面模組710. . . User interface module
720．．．行為記錄模組720. . . Behavior record module
730．．．策略分析模組730. . . Strategy analysis module
740．．．錯誤推論模組740. . . Error inference module
750．．．動態資源推薦模組750. . . Dynamic resource recommendation module
A1、A2、A3、A4、A5．．．解題策略A1, A2, A3, A4, A5. . . Problem solving strategy
B1、B2、B3...、B13．．．錯誤類型B1, B2, B3..., B13. . . Error type
D1、D2、D3...、D8、760．．．教學資源庫D1, D2, D3..., D8, 760. . . Teaching resource library
EB．．．解題行為EB. . . Problem solving behavior
REB．．．正確解題行為REB. . . Correct problem solving behavior
S01、S02、S03...、S09．．．知識概念S01, S02, S03..., S09. . . Knowledge concept
S1、S2、S3...、S8．．．相關教學資源S1, S2, S3..., S8. . . Related teaching resources
S210、S230、S231、...、S261．．．解題策略步驟S210, S230, S231, ..., S261. . . Problem solving strategy step
S600、S610、S620...S660．．．步驟S600, S610, S620...S660. . . step
第1圖所示為依據本發明實施例之使用者介面的示意圖；1 is a schematic diagram of a user interface in accordance with an embodiment of the present invention;
第2圖所示為依據本發明實施例之解題策略集合的示意圖；2 is a schematic diagram showing a set of problem solving strategies according to an embodiment of the present invention;
第3圖所示為依據本發明實施例之多變量錯誤類型推論技術的示意圖；3 is a schematic diagram showing a multivariate error type inference technique according to an embodiment of the present invention;
第4圖所示為依據本發明實施例之知識概念與錯誤類型之間的對應關係的示意圖；FIG. 4 is a schematic diagram showing a correspondence between a knowledge concept and an error type according to an embodiment of the present invention;
第5圖所示為依據本發明實施例之動態資源推薦技術的示意圖；FIG. 5 is a schematic diagram showing a dynamic resource recommendation technique according to an embodiment of the present invention;
第6圖所示為依據本發明實施例之學習診斷與動態學習資源推薦的方法的流程圖；6 is a flow chart showing a method for learning diagnosis and dynamic learning resource recommendation according to an embodiment of the present invention;
第7圖所示為依據本發明實施例之學習診斷與動態學習資源推薦系統的示意圖。FIG. 7 is a schematic diagram showing a learning diagnosis and dynamic learning resource recommendation system according to an embodiment of the present invention.
S600、S610、S620...S660．．．步驟S600, S610, S620...S660. . . step
Claims (8)
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW100138801A TW201317954A (en) | 2011-10-26 | 2011-10-26 | Method and system for learning diagnosis and dynamic recommendation of learning resource |
| CN201210324624XA CN103077178A (en) | 2011-10-26 | 2012-09-05 | Learning diagnosis and dynamic learning resource recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW100138801A TW201317954A (en) | 2011-10-26 | 2011-10-26 | Method and system for learning diagnosis and dynamic recommendation of learning resource |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| TW201317954A true TW201317954A (en) | 2013-05-01 |
Family
ID=48153709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW100138801A TW201317954A (en) | 2011-10-26 | 2011-10-26 | Method and system for learning diagnosis and dynamic recommendation of learning resource |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN103077178A (en) |
| TW (1) | TW201317954A (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104732826A (en) * | 2015-03-27 | 2015-06-24 | 宋晓宇 | Augmented reality (AR) interactive teaching material and teaching resource cloud platform |
| CN105022828A (en) * | 2015-07-31 | 2015-11-04 | 阔地教育科技有限公司 | Resource pushing method and device |
| CN105787839A (en) * | 2016-03-23 | 2016-07-20 | 成都准星云学科技有限公司 | Method and device for pushing learning resources |
| TWI606432B (en) * | 2016-11-10 | 2017-11-21 | 淡江大學 | Assessment system for structrual concept learning |
| CN106781782A (en) * | 2016-11-23 | 2017-05-31 | 阔地教育科技有限公司 | A kind of information feedback method and device |
| CN106651701A (en) * | 2016-12-29 | 2017-05-10 | 山东科技大学 | Learning resource constructing method and device |
| CN107784069B (en) * | 2017-09-14 | 2020-08-18 | 深圳市赛达教育咨询有限公司 | Method for intelligently diagnosing knowledge ability of students |
| CN107741978A (en) * | 2017-10-13 | 2018-02-27 | 北京中教在线科技有限公司 | A kind of Pushing personality study resource method and its system |
| CN108172047B (en) * | 2018-01-19 | 2019-11-01 | 上海理工大学 | A kind of network on-line study individualized resource real-time recommendation method |
| CN108897879B (en) * | 2018-07-04 | 2020-11-10 | 北京希子教育科技有限公司 | Method for realizing personalized teaching through man-machine interaction |
| CN109035947B (en) * | 2018-08-06 | 2020-11-06 | 孙文武 | Working method of education system based on step analysis simulation |
| CN110263259A (en) * | 2019-07-08 | 2019-09-20 | 上海乂学教育科技有限公司 | Online teaching video push management system |
| CN117557426B (en) * | 2023-12-08 | 2024-05-07 | 广州市小马知学技术有限公司 | Work data feedback method and learning evaluation system based on intelligent question bank |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1635486A (en) * | 2003-12-25 | 2005-07-06 | 英业达股份有限公司 | Quick learning system and method capable of improving achievement |
| KR100877583B1 (en) * | 2006-07-19 | 2009-01-07 | 성균관대학교산학협력단 | Diagnosis System of Learning Style and Method Thereof |
| CN101582101A (en) * | 2008-05-15 | 2009-11-18 | 梁昌年 | Method and device thereof for providing individualized learning for user by using computer system |
| US8366449B2 (en) * | 2008-08-13 | 2013-02-05 | Chi Wang | Method and system for knowledge diagnosis and tutoring |
-
2011
- 2011-10-26 TW TW100138801A patent/TW201317954A/en unknown
-
2012
- 2012-09-05 CN CN201210324624XA patent/CN103077178A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| CN103077178A (en) | 2013-05-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TW201317954A (en) | Method and system for learning diagnosis and dynamic recommendation of learning resource | |
| Bosch et al. | The affective experience of novice computer programmers | |
| US10467919B2 (en) | Systems and methods for AI-based student tutoring | |
| Vie et al. | A review of recent advances in adaptive assessment | |
| CN111475627B (en) | Method and device for checking solution deduction questions, electronic equipment and storage medium | |
| Francois et al. | Big-data literacy as a new vocation for statistical literacy | |
| US10373512B2 (en) | Mathematical language processing: automatic grading and feedback for open response mathematical questions | |
| US20140038160A1 (en) | Providing computer aided speech and language therapy | |
| Olney et al. | Assessing Computer Literacy of Adults with Low Literacy Skills. | |
| Huang et al. | Behavioral intention to continuously use learning apps: A comparative study from Taiwan universities | |
| Bisanz et al. | On “understanding” children's developing use of inversion | |
| Chang et al. | Yet another adaptive learning management system based on Felder and Silverman’s learning styles and Mashup | |
| Yang et al. | How to assess the contributions of processing fluency and beliefs to the formation of judgments of learning: Methods and pitfalls | |
| Pinnell et al. | Curricular and learning analytics: a big data perspective | |
| Malmi et al. | Development and use of domain-specific learning theories, models, and instruments in computing education | |
| Singh et al. | Acceptance of open learning resources: Perspectives of higher education students in India | |
| Abdullahi et al. | Learning to make rare and complex diagnoses with generative AI assistance: qualitative study of popular large language models | |
| Taskiran et al. | Contribution of automated feedback to the English writing competence of distance foreign language learners | |
| Krauss et al. | Teaching advanced web technologies with a mobile learning companion application | |
| Zhang et al. | Sequential pattern mining in educational data: The application context, potential, strengths, and limitations | |
| TW201348988A (en) | Self-assessment feedback audio and video learning method and system thereof | |
| JP6530967B2 (en) | Auxiliary analysis system using expert information and its method | |
| Rudzewitz | Learning analytics in intelligent computer-assisted language learning | |
| Bojic et al. | Empowering Health Care Education Through Learning Analytics: In-depth Scoping Review | |
| Fergusson | Towards an integration of statistical and computational thinking: Development of a task design framework for introducing code-driven tools through statistical modelling |