201237764 六、發明說明： c發明戶斤屬之技術領域3 發明領域 本發明之實施例一般係有關資訊處理。更特別是，本 發明之實施例係有關用於重疊手寫法之方法、裝置與電腦 程式產品。 【先前技術3 發明背景 眾所週知，手寫法對使用者而言是一自然且便利的機 構來將資訊輸入至一電子設備，諸如一桌上型電腦、平板 電腦、膝上型電腦、個人數位助理(PDA)、或一行動電話。 特別是，手寫法結合適當的字元辨識引擎，可於電子設備 ' 中用來輸入可用於諸如編輯或文字處理之各種不同目的的 - 文字。 於手寫法輸入操作中，使用者可使用一寫入工具，諸 如一光筆、鉛筆、或僅是他/她的手指，來於該目標設備之 一特定區（例如，一寫入板、一觸控螢幕、或一鄰近區螢幕）， 如同於一普通紙張上寫入。該寫入區上之工具的軌跡（下文 中參照為“筆跡”)可被記錄，而一或更多字元辨識引擎之後 執行適當的辨識演算法來將該等記錄之筆跡轉換成字元。 目前已有若干可用的字元辨識之辨識演算法或產品，例 如，根據架構辨識、如隱藏性markov模型之統計模型、神 經網路、等等。由於其自然性與便利性，手寫法已日漸增 加使用於更多計算設備中，特別是行動端子。 201237764 近來，已有一種稱為重疊手寫法之技術被提出，其允 許使用者於一單一寫入區中連續寫入超過一個字元，如第1 圖所示，輸入之每一字元重疊於先前字元之上。藉由使用 重疊手寫法，使用者可連續寫入而不需等待辨識每一字元 之逾時。此方式中，多個字元可一次平順地寫入而不中斷， 因此可改善操作效能。此外，相較於提供多個寫入區來支 援連續寫入之其他手寫法解決方案，重疊寫入法之解決方 案對具有有限大小之設備僅需要相當小的寫入區是相當重 要的。 參照第1圖，其顯示一繪示重疊手寫法之一般程序的高 階示意圖。如圖所示，於重疊手寫法中，由至少一字元之 筆劃所組成的該筆跡102需分為至少一部段104。該程序可 參照為分段。該辨識引擎之後將該一或更多部段轉換成可 辨識字元106來作為輸出。於習知技術中，該分段程序可於 背景執行。換言之，從該初始重疊手寫法取得之該等部段 將不顯示至使用者，但直接受辨識。通常，該分段與辨識 可同時執行，並支援特定的語言模型。此方式中，可期待 該辨識引擎根據該等輸入筆跡與對應分段結果來公佈該最 有意義之字串。很明顯地，該最後辨識準確性相當依賴分 段程序之品質。 理想情況是，該辨識字串應實質為使用者初始欲輸入 的字串。但不巧地，雖已提出若干解決方案來改善重疊手 寫法之辨識準確性，但某些誤差仍無法避免。該分段與辨 識兩者皆可能有誤差問題。實際上，分段正確但辨識字串 201237764 不正確時，如候選者清單或重新寫入一單一字元之若干現 有的誤差修正方法皆可正常運作。然而，該分段程序中出 現誤差而因此造成輸出的辨識字串誤差的情況中，傳統修 正方法(例如，一候選者清單）通常會失敗。 例如，分段中有一共同的誤差類型是所謂的一筆劃誤 差，其中一分段具有一額外的筆劃、或缺少一筆劃。根據 統計，所有可能的分段誤差中，一筆劃誤差具有支配性。 也有其他類型的分段誤差將說明如下。分段中出現誤差的 事件中，最後的辨識結果可能不正確。該類情況中，習知 技術無法讓使用者有效修正該辨識結果，因此使用者必須 重新寫入一個或多個字元，其帶來操作效率與因而使用者 經驗之負面效應。 ' 【發明内容】 發明概要 鑑於上述用於重疊手寫法之現存方法中的問題，該技 術有一需求是提供用以修正重疊手寫法辨識中由錯誤分段 造成之誤差，以克服上述缺點的一方法、裝置、與電腦程 式產品。 於一觀點中，本發明之實施例提供一種用於重疊手寫 法之方法。該方法包含下列步驟：形成由一重疊手寫法之 部段取得的至少一部段之顯示；接收用於修正該部段之一 要求；以及用以響應該接收之要求，來修改該至少一部段 以取得至少一新的部段。 另一觀點中，本發明之實施例提供用於重疊手寫法之 201237764 裝置。該裝置包含：至少一處理器，以及至少—個儲存電 腦可執行碼之程式的記憶體。該至少一記憶體與該電腦可 執行碼以該至少一處理器來組配，以使該裝置來至少執行 下列步驟：形成由一重疊手寫法之部段取得的至少一部段 之顯示；接收用於修正該部段之一要求；以及用以響應該 接收之要求，來修改該至少一部段以取得至少—新的部段。 尚有另一觀點中，本發明之實施例提供一種電腦程式 產品，其包含具有儲存於此之一電腦可讀程式碼部分的至 少一電腦可讀儲存媒體。該電腦可執行碼部分包含：用於 形成由一重疊手寫法之部段取得的至少一部段之顯示的編 碼；用於接收修正該部段之一要求的編碼；以及用於用以 響應該接收之要求，來修改該至少一部段以取得至少—新 部段的編碼。 還有另一觀點中，本發明之實施例提供用於重疊手寫 法之一裝置。該裝置包含：用於形成由一重疊手寫法之部 段取得的至少一部段之顯示的裝置；用於接收修正該分段 之一要求的裝置；以及用於用以響應該接收之要求，來修 改該至少一部段以取得至少—新部段的裝置。 由於本發明之實施例，例如，該辨識字串中有任何誤 差時’分段結果（亦即，至少-部段)可以-可修改或可編輯 的方式來呈現至使用者。就本身而言，若有的話使用者 直覺上可找出分段中之衫。之後他/她可以有效且容易的 方法例> 干動作來要求修正分段誤差。根據 本發明之某#•實&例’可使該使用者藉由使用—組預定筆 6 201237764 諸如h、點擊、或搖動來啟動分段結果之修正或修 :求=該等分段結果之修改或修― 如業界熟於此技者所體認，本發明之實施例可提供使 用者交互修正料分段縣之—便，構以修正錯誤部 段造成之_縣。此料I其提供錢用者可修正錯 誤分段造成之_誤差的—有效解決方案，關此使用者 、二驗可顯著改善。替代或額外地，執行辨識之前亦可使該 使用者檢查與修正該等分段結果。此方式中，其可確認待 辨識之部段為無誤差。此外，根據本發明之某些實施例， 該使用者亦可藉由，例如，將一或更多筆劃加入現存部段 來改變其本身啟始之輸入。 本發明之實施例的其他特徵與優點亦可從下列特定實 施例之說明，連同該等附圖來讀取以獲得了解，其藉由範 例來繪示本發明之實施例的原理。 圖式簡單說明 本發明之實施例以範例概念來呈現，而其優點將參照 該等附圖於下文中更詳細説明，其中： 第1圖是一顯示繪示-···重疊手寫法之一般程序的高階 不意圖， 第2圖顯示一根據本發明之實施例，用於重疊手寫法之 一方法的流程圖； 第3A圖至第3F圖顯示根據本發明之實施例，可用來要 求修正部段及其個別修改之若干筆勢的範例； 201237764 第4A圖至第4B圖顯示根據本發明之實施例，使操作中 之部分或部段以醒目提示的範例； 第5圖顯示一適合用於實作本發明之實施例的—圖形 使用者介面（GUI)之示意圖； 第6圖顯示一根據本發明之實施例，用於重疊手寫法之 一裝置的簡化方塊圖；以及 第7圖顯示一適合用於實作本發明之實施例的—裝置 之簡化方塊圖。 I：實施方式3 較佳實施例之詳細說明 本發明之實施例提供一種用於重疊手寫法，特別是， 讓使用者能夠交互修改分段誤差之方法、裝置與電腦程式 產品。根據本發明之實施例，由—重疊手寫法之分段取得 的部段可以-可修改或可編輯的方式顯示至使用者。特別 是’針對包含在每-部段之每一部分(亦即，一或更多筆劃） 的位置與時間資訊可被取得，此，該使用者能夠選擇3任 何部段之任何部分，並，例如’使用财筆勢來如所 需修改該部分。結果是，該使用者能夠有效修正任何分段 誤差，因而可修正該最終辨識結果。替代或額外地執^ 辨識之前較帛者亦㈣檢t與紅該分段結果。此方式 中，可確認該等待辨識部段為無誤差，使得該最終辨鮮 確性可得以增加。 下文將參照圖形來說明本發明之實施例。可體認雖然 下文中主要參照中文字元來說明本發明之特定實施例，但 201237764 本發明之糾並不侷限於此方面。本發明之實施例可相同 應用在適合重疊手寫法之任何語言的字元 如上所述’第ι_示-繪示重疊手寫法之—般程序的 尚階示意圖。該習知技術中，分段之中間結果不顯示給使 用者。相反地，根據本發明之實施例，該類分段結果，亦 即’由該初始重疊手寫法之分段取得的—或更多部段，^ 呈現至該使用者並由該使用者修改，其將詳細說明如下。 第2圖顯示-根據本發明之實施例，•重疊手寫法之 -方法麵餘圖。如圖所示’該方法2⑽於步驟_開 始’其中由一重疊手寫法之分段取得的至少一部段顯示至 使用者。該至少-部段可，例如，從—分段模組取得，該 模組可在該重疊手寫法中執行分段程序以產生一或更多部 段。應了解該等部段可根據該使用者要求，例如，该使用 者欲修改辨識字串中之誤差時來顯示，外或替代地，該 等部段可連同該最終辨識㈣來自動顯示。某&實施例 中，該等部段可經由諸如第5圖所示之_圖形使用者介面來 顯示，其將詳細說明如下。 一部段可用來作為隨後字元辨識之—基本單元，而因 此如上所述’理想情況中可符合-單—與整個字元。一部 段可由或更多筆劃所組成。如本文所使用，術語“筆劃” 參照為〆字元或—部段之基本與不可分離之元体 應了解’步驟娜中，該至少一部段可=可修改或 可編輯的方式來顯示。亦即，該使用者能夠選擇並之後調 處一部段、或-整體部段之一或更多筆劃。為此目的需 201237764 要该等部段筆劃之位置資訊。義資til可從先前的分段程 序來取得。如業界所熟知，於該使用者重疊手寫法執行分 段時，針對每一結果部段，可決定包含於該部段中之每一 筆劃的位置資訊’而不管所使用之特定演算法為何。換言 之，根據該分段程序，可取得每一筆劃之位置資訊供未來 使用，例如，如下所述一筆劃之選擇或挑選。於是，針對 該筆跡之每—點’可蚊該闕屬之部段與（多個）筆劃。 此外，亦可取得每一筆劃之時間資訊。例如，筆劃之 時間資訊可藉由手寫期間記錄使用者之寫入順序來取得。 實際上，使用者可能很難僅根據位置資訊，例如，—部段 之結構报複雜時，來從一部段選擇一特定筆劃。此時，可 單獨使用筆劃之時間資訊，或結合該位置資訊來選擇一筆 劃。例如，於一較佳實施例中，每一部段下方可晝出該等 筆劃之一時間線，使得該使用者能選擇時間線之一部分而 之後可選擇該部段中之對應一或更多筆劃。亦可有根據該 位置與/或時間資訊來選擇一筆劃或一部分之其他選擇。 應了解任何目前存在或未來開發的方法可用來執行重 疊手寫法之分段，而因此筆劃之位置與/或時間資訊可以不 同方式來取得。本發明之範疇並不侷限於此方面。 接著，步驟S210中，可接收用於修正該分段之—要求。 如步驟S205中所示，該使用者發現該等部段中之—或更多 誤差的情況中’他/她可以若干方式來啟動修正要求。之 後’步驟S215中，用以響應步驟S210中接收之要求，該至 少一部段可被修改以取得至少一新的部段。現將詳細說明 201237764 步驟S210與步驟S215之操作。 本發明之較佳實施例中，步驟咖中，該要求可經由 讀用者之-級預定筆勢來接收，而該部段之修改可因此 於步驟S210中完成。如第3A圖至第3ρ圖所示，某些典 勢可用來要求修正分段。 一。參，3A圖’某些情況中，該分段程序可能不適合將 -單-字元之筆跡來分開作為超過一個分開的部段。例 如’如第3A®所示，使用者欲由重疊手寫法輸人之中文字 元為“明”。然而，該分段中，此單—字元之筆跡可分為兩 個分開的部段，一帛一部段31〇“日，，與一第二部段 312“月’、為修正該類誤差，根據本發明之某些實施例，方 法_之步驟議中，該使用者可以下列方式來要求修改該 分段。 ~ ★首先，該使用者可，例如，藉由使用一指向設備(諸如 筆、光筆、手指、或滑鼠)於該第一部段31〇之定界框内或 其鄰近區點擊、或藉由按下一特定按鈕來選擇或挑選該第 一部段310。之後可允許該使用者將該選擇之第一部段31〇 牽曳至該第二部段312之一預定鄰近區，亦即，至該第—與 第二部段31〇與312間之距離小於一預定臨界距離的—位 置。回應上，如第3A圖中所示，可執行該等第一與第二部 段31〇與315組合為一部段314“明”的修改。應了解上述筆勢 僅為舉例解說’而亦可有其他筆勢。 另一方面，分段誤差之另一類型為相關第3A圖中所示 之情況相反，其中分段期間兩個或更多分開字元的筆跡會 201237764 不正確地組合為一單一部段。第3B圖顯示該類範例。該範 例中，使用者欲輸入兩個中文字元“日”與“月”，但該分段 引擎產生一單一部段320“明，，。根據本發明之實施例’該類 誤差可藉由於該提及部段執行重新分段來修正。該使用者 可藉由於該部段作一預定筆勢來要求重新分段。某些實施 例中，該預定筆勢可為，例如，雙點擊、長時間按下、或 任何其他適當的筆勢。如第3B圖所示，該使用者可在該部 段320“明”上作該預定筆勢(例如，雙點擊）。之後，藉由使 用該相關筆劃之位置與時間資訊，可響應執行一重新分 段’使得該部段320分割為若干部段（第3B圖所示範例中之 兩個部段322與324)。應了解雙點擊僅為用來要求一重新分 段之該預定筆勢的一舉例解說範例，而亦可有其他筆勢。 第3C圖顯示類似第3B圖的一情況，其中分段期間兩個 或更多部段會不正確地組合為一單一部段。然而，不像第 3B圖，某些該等部段會相當簡單，其每一部段由若干筆劃 (例如，僅一或兩筆劃）所組成。根據本發明之實施例，此時， 反而不呼叫該分段模組來執行重新分段，減用者可選擇 僅藉由將4部分牽$至—預定區域，例如…空白區來 刀開一描繪部分與一部段。 —本文所使用，術語“部分，，參照為由-或更多筆劃組 筆，來°卩刀°應了解~部分之選擇可藉由選擇其 該分段程序取得之擇可藉由使用如以述’可從 擊—整章丨 、置與/或時間資訊來完成^例如，點 任何部分時，可選擇該筆劃。 12 201237764 繼續第3C圖之範例，根據選擇並牽曳至一預定區，該 操作部分可從該初始部段移動，而一新的部段將根據該部 分來取得。就本身而言，一部段可分割為二，而此程序可 重覆直到結果皆正確。特別是，如第3C圖所示，中文字元 “人”之筆跡與中文句號“。”由誤差而組合為一部段330。此 時，該使用者首先可選擇該句號的筆劃，而之後將該選擇 的筆劃牵曳至一空白區。回應上，該筆劃“。”可從該組合 部段330移除，而僅留下“人’’。此外，可產生由該牽曳部分 組成之一新部段334。結果是，可取得兩個分開部段332“人” 與334“。”。應了解雖然第3C圖所示之描繪部分僅包含一筆 劃，但本發明之實施例亦可應用在由多個筆劃組成的一部分。 分段誤差之另一類型包括兩個或更多部段之順序。不 像該單一字元手寫法，使用重疊手寫法時，一使用者通常 欲同時輸入多個字元，例如，一片語或甚至一句子。因此， 該等辨識結果不僅可確認各自與每個字元之正確性，而且 還可確認該字元序列之適當順序。例如參照第3D圖，該使 用者初始欲輸入一中文片語“清明节”。然而，由於使用者 書寫的誤差或一分段誤差，該等部段342“明”與340“节”之 順序會顛倒。根據本發明之實施例，該使用者可藉由，例 如，選擇一部段並將其牽曳至該部段序列中之一位置來要 求修正該等部段的順序。之後該序列中此部段的順序可根 據該目標位置來改變。特別是，如第3D圖所示，該使用者 選擇該部段340“节”並將其牽曳至該部段342“明”之後的一 位置。回應上，該等部段340與342之順序可改變。某些其 13 201237764 他實施例中，將一部段牵曳至，例如，一空白區中之一位 置亦可使該部段序列重新排列。 現參照第3E圖，其顯示分段修正的另一範例。此範例 中，一部段352“国”之一筆劃（一垂直筆劃或“豎”)會不正確 地指派至一第二部段350“中”。亦即，如上述一個一筆劃誤 差會出現在該分段中。結果是，該部段350“中”具有多一筆 劃而該部段352“国”缺少一筆劃，其非常容易造成兩部段之 辨識誤差。根據本發明之實施例，該使用者可以下列方式 來要求修正以處理該類分段誤差。 該使用者可被允許選擇該不正確的指派部分，其可包 含一第一部段之一或更多筆劃。之後，該第一部段之該選 擇部分可被牽良至該部分將所屬之一第二部段的一預定鄰 近區。用以響應該類筆勢，該等第一與第二部段之修改可 被實現，使得該選擇部分可根據，例如，該等相關筆劃之 位置與時間資訊來從該第一部段移除、而加至該第二部 段。特別是，如第3E圖所示，該使用者可選擇該部段350 中之垂直筆劃，並將其牽曳至該部段352之一預定鄰近區。 此方式中，可取得兩個修改的新部段354與356。 實際上，可找出該最易出錯筆劃為兩相鄰字元之“邊界 區”的筆劃，因為在分段期間該類筆劃最容易不正確地指派 至另一部段。例如，一部段之該第一或更多筆劃可指派至 立即位於該部段之前的部段（例如，第3E圖）。同樣地，一 部段之該最後一個或更多筆劃通常指派至立即位於該提及 部段之後的部段。根據本發明之實施例，為了更適當處理 .-.Ά 、·^- 14 201237764 該類共同情況，可提供特定筆勢使該使用者能夠更簡易與 精確地選擇一字元之該（等）第一或最後筆劃。該類筆勢之一 範例是搖動。例如，可藉由在該部段之定界框中點擊之後 快速向左移動來選擇一部段之該第一或更多筆劃，而可藉 由在該定界框中點擊並快速向右移動來選擇該最後一個或 更多筆劃。如上所述，給定一部段，由於各自與每個筆劃 之時間資訊（亦即，該寫入順序）的可用性，可能選擇第一或 最後一個或更多筆劃。當然，亦可有選擇一部段之該第一/ 或最後一個筆劃之其他筆勢。但本發明之範疇並不侷限於 此方面。 請注意，雖然第3E圖中顯示一筆劃誤差，但本發明之 實施例可應用於一部段中超過一筆劃不正確地指派至另一 部段的情況中。 參照第3F圖，根據本發明之實施例，亦可允許該使用 者將一或更多筆劃加入一現存部段中。有時由於該使用者 書寫的誤差或一分段誤差，會遺漏一字元之一或更多筆 劃。因此，相較於該使用者初始欲輸入之字元，該部段會 缺少一或更多筆劃。另一事件中，該使用者可能想改變他/ 她本身啟始之輸入。每一情況中，該使用者可直接將一部 分（亦即，一或更多筆劃）加入任何現存部段中，而非刪去重 新鍵入。回應上，可根據該提及的部段與部分來產生一新 部段。如第3F圖所示，藉由將一筆劃加入一部段360“人”， 可產生由該部段360“人”與該加入部分“一”所組成之另一 部段362“大”。 15 201237764 從上述說明中，可看出要求分段修正時，可使一使用 者來選擇包含—或更多筆劃、或_整體分段之一特定部 7刀。爲此目的，針對部分選擇與部段選擇之筆勢應可被足 二清楚區別。根據本發明之某些實施例，該區別可由按下 3擊的持續期間來達成。例如，一短暫按下或點擊可對 應筆劃之選擇，而一長久按下或點擊可對應一整個部段之 選擇。如另—範例中，其可提供該使用者可設定之一選項 或7旗標。若該選項或旗標設定為一第一狀態，則該筆勢 Z轉為部分選擇。另-方面，若該選項或旗標設定為- =狀態，則該筆勢將用於部段選擇。該等僅為某些舉例 =說的範例。亦可使用用於區別—部分或_整個部段之區 段選擇的任何其他機構。 她的L了Γ上述筆勢可受組配。亦即’一使用者可根據他， 偏I、/或該設備之狀態來加入新筆勢、移除筆勢、鱼 /或修改現存筆勢。替代或額外地，有關該等筆勢之各種^ 同參數，諸如上述預定鄰近區（該臨界轉）、預定區 '與/ 或預定位置’亦可由該使用者來組配。 、 此外，如業界熟於此技者所體認，第3a圖至第 顯示根據本發明之實施例，用於分段修正之筆勢與對 作的某些舉例解說與非限制範例。給定上述教示後，= 熟於此技者可輕易想像其他㈣以要求分郷正。此外| 交互作=法而非筆勢可用來要求修正分段。例如單 獨或組t使用如触、軟鍵、與下拉清單的控制，來輸I 修正要求。如另一範例中’該使用者可直接鍵入特定的預 16 201237764 定指令來啟動該要求。但本發 回到細，步购2〇中，体料並不偈限於此方面。 段以醒目提示。藉由將該操作期間场作之部分或部 改期間該使用者可-直意識醒目提示的方式，修 清。該醒目提…咐㈣可避免受混 工、水70成。例如，續蓝从 二件之顏色、外觀、陰影、字型與/或大小可加以改變。' 代或額外地’動晝效果可_在_作之部分與 參照第至第4B圖，其顯示根據本發明I 範例，其中該操作之部分或部段以-魚眼透鏡作醒目^ 不。該等顯不fe例中，該使用者啟動一特定部分(第4侧 或-部段（第侧）上之操作時，該操作之部分或部段將以 一魚眼來顯示。該魚眼可，例如，根據該操作部分或部段 之動作來於祕改期間移動。除了触置之外’該*眼中 顯示之該等内容亦可於調處期間動態更新。例如，第_ 所示之範例中’該使用者首次選擇部段35〇之-筆割時，該 部段350與該選擇筆劃包括於該魚眼中，而可能《擇筆則 之顏色改變。該選擇筆劃牽复至該部段352時，其可於該魚 眼中醒目提示。最後’該筆劃與該部段352組合時，該所生 結果的部段將於該魚眼中_心應了解該魚眼僅為一舉例 解說的油，並可連同-或更多其他醒目提示效果(例如， 如第4A圖至第4B圖所示之顏色改變）來使用。 亦應注意該步驟S220為任選的，因該使用者可選擇將 該操作元件之醒目提不賦能/停用。此外，該等醒目提示效 果可受組配。亦即，該使用者可根據他/她的偏好或該設備 17 201237764 之狀態來加入新效果、移除現有效果、與/或組配各種不同 的相關參數。 接著，步驟S225中，可辨識步驟S215中取得之至少一 新部段’以輸出一或更多字元。該方法2〇〇之後終止。如上 所述’任何目前現存或之後開發的辨識方法可用來將該等 部段轉換為字元，而本發明之範疇並不侷限於此方面。再 者，步驟S225為任選的，因為某些應用中，代表該使用者 之初始葦跡的部段可被儲存並直接使用而不需辨識。該類 應用之一範例為寫入練習的應用。 第5圖顯示一適合用於實作本發明之實施例的一圖形 使用者介面（GUI)500。根據本發明之某些實施例，該gui 5〇〇可與該方法200共同使用，並可，例如，由以下將參照 第6圖與第7圖說明之裝置來產生與呈現。 如圖所示，該GUI 500包括一編輯器區5〇5、一候選字 元區510、一分段結果區515、一寫入區52〇、以及一控制區 525。操作上，該使用者可在該寫入區52〇中以一重疊方法 來寫入多個字元。之後可執行該使用者之手寫法的分段與 辨識。該等最後字元可顯示於該編輯器區5〇5中，而一候選 子/月單可顯示於§玄候選字元區51〇中。特別是，根據本發明 之實施例，該結果之一或更多部段可顯示於該分段結果區 515中。例如，該使用者發現由錯誤分段造成之一辨識誤差 時，他/她可以上述方式與該分段結果區515互動，以修正 s玄分段之誤差（若有的話）。修正之後，該使用者可確認該分 段無誤差，該等部段可受到辨識。之後該編輯器區5〇5與該 18 201237764 候選子元區510可因此更新。替代或額外地，執行辨識之 刚，亦可使6亥使用者來檢查與修正如該分段結果區515中顯 不之該等分段結果。該控制區525中，可提供該使用者可控 制重疊手寫法之程序的如按纽、軟鍵之一或更多控制、或 者任何其他適當的控制。 應了解第5圖所示之該GUI 500僅為一舉例解說的範 例。適合用於實作本發明之實施例的該GUI可包含較少、額 外、與/或不同的構件。替代或額外地，其他實施例中之該 等GUI上的構件布局或安排亦可加以改變。 第6圖顯示一根據本發明之實施例，用於重疊手寫法之 一裝置600的簡化方塊圖。如上所述，該裝置6〇〇可產生ϋ 呈現如第5圖所示之該GUI 500的一GUI。如第6圖所示，該 裝置600可包括分段顯示裝置605、修正要求裝置61〇、分段 修改裝置615、修改醒目提示裝置620(任選的）、字元辨識裝 置625(任選的）。 該分段顯示裝置605可組配來使由一重疊手寫法之分 段取得的至少一部段顯示。該修正要求裝置61〇可組配來接 收用以修正該分段之一要求。該分段修改襄置615可組配來 用以響應該接收要求而修改該至少一部段以取得至少-·*·個 新部段。 特別是’該分段修改裝置615可組配來執行下列/或更 多步驟：用以響應將一第一部段拖曳至一第二部段之〆預 定鄰近區，而將該等第一與第二部段組合成為一部段；用 以響應一第一部段之一部分上的一預定筆勢，而執行該第 19 201237764 一部段之一重新分段以取得兩個或更多部段；用以響應將 一第一部段之一部分拖曳至一預定區，而從該第一部段移 除該部分、以及根據該部分來建立一新的部段；用以響應 將一第一部段拖曳至部段序列中之一位置，而改變該序列 中該第一部段之順序；用以響應將一第一部段拖曳至一第 二部段之一預定鄰近區，而從該第一部段移除該部分、以 及將該部分加入該第二部段；以及用以響應將一部分加入 一第一部段，而產生由該第一部段與該加入部分所組成之 一新的部段以取代該第一部段。 該分段修改裝置615操作期間，修改醒目提示裝置620 可組配來使操作之部分或部段以醒目提示。該字元辨識裝 置625可組配來與該分段修改裝置615合作執行辨識，以便 將該等修正部段轉換為可編輯字元。 應了解該裝置600可以硬體或專用電路、軟體、邏輯或 其任何組合來具體化。因此，該裝置600之各種不同裝置 可作為軟體模組、與/或硬體方塊、單元、或構件來予以 具體化。 上述程序或方法（例如，如第2圖所示之方法200)之實施 例可由任何適當裝置來執行。第7圖顯示一適合用於實作本 發明之實施例的一裝置700之簡化方塊圖。某些實施例中， 該裝置700可作為一行動端子來予以具體化。然而，應了解 一行動端子僅為可從本發明之實施例獲益之一種裝置類型 的舉例解說，而因此，其不應視為限制本發明之實施例的 範疇。201237764 VI. INSTRUCTIONS: C TECHNICAL FIELD OF THE INVENTION The invention is generally related to information processing. More particularly, embodiments of the present invention relate to methods, apparatus, and computer program products for overlapping handwriting. [Prior Art 3 BACKGROUND OF THE INVENTION It is well known that handwriting is a natural and convenient mechanism for a user to input information to an electronic device such as a desktop computer, tablet computer, laptop computer, personal digital assistant ( PDA), or a mobile phone. In particular, handwriting combined with an appropriate character recognition engine can be used in electronic devices to input text that can be used for various purposes such as editing or word processing. In the handwriting input operation, the user can use a writing tool, such as a light pen, a pencil, or just his/her finger, to a specific area of the target device (for example, a writing board, a touch Control screen, or a neighboring screen), as if written on a plain paper. The trajectory of the tool on the write zone (hereinafter referred to as "handwriting") can be recorded, and one or more character recognition engines then perform an appropriate recognition algorithm to convert the recorded handwriting into characters. There are currently a number of available character recognition recognition algorithms or products, for example, based on architectural identification, statistical models such as the hidden markov model, neural networks, and the like. Due to its naturalness and convenience, handwriting has been increasingly used in more computing devices, especially mobile terminals. 201237764 Recently, a technique called overlap handwriting has been proposed which allows a user to continuously write more than one character in a single write area. As shown in Fig. 1, each character of the input is overlaid on Above the previous character. By using overlapping handwriting, the user can write continuously without waiting to recognize the timeout of each character. In this manner, multiple characters can be written smoothly without interruption at one time, thereby improving operational efficiency. In addition, the overlapped write solution is quite important for devices of limited size that require relatively small write regions as compared to other handwriting solutions that provide multiple write regions to support continuous writes. Referring to Fig. 1, there is shown a high level schematic diagram showing the general procedure of overlapping handwriting. As shown, in the overlay handwriting method, the handwriting 102 consisting of at least one character stroke is divided into at least one segment 104. This program can be referred to as segmentation. The recognition engine then converts the one or more segments into recognizable characters 106 as an output. In the prior art, the segmentation procedure can be performed in the background. In other words, the segments obtained from the initial overlap handwriting will not be displayed to the user, but will be directly recognized. Typically, this segmentation and recognition can be performed simultaneously and support a specific language model. In this manner, the recognition engine can be expected to publish the most meaningful string based on the input handwriting and the corresponding segmentation result. Obviously, this final identification accuracy is quite dependent on the quality of the segmentation process. Ideally, the identification string should be essentially the string that the user initially wants to enter. Unfortunately, although several solutions have been proposed to improve the identification accuracy of overlapping handwriting methods, some errors are still unavoidable. Both the segmentation and the recognition may have errors. In fact, when the segmentation is correct but the identification string 201237764 is incorrect, some existing error correction methods such as the candidate list or rewriting a single character can work normally. However, in the case where an error occurs in the segmentation procedure and thus causes an identified string error of the output, conventional correction methods (e.g., a candidate list) typically fail. For example, a common type of error in a segment is the so-called one-stroke error, where a segment has an extra stroke or a missing stroke. According to statistics, among all possible segmentation errors, one stroke error is dominant. There are other types of segmentation errors that will be explained below. In the event of an error in the segment, the final identification result may be incorrect. In such cases, the prior art does not allow the user to effectively correct the identification result, so the user must rewrite one or more characters, which brings about operational effects and thus the negative effects of user experience. SUMMARY OF THE INVENTION In view of the above problems in the existing method for overlapping handwriting, there is a need in the art to provide a method for correcting errors caused by erroneous segmentation in overlapping handwriting recognition to overcome the above disadvantages. , devices, and computer programs. In one aspect, embodiments of the present invention provide a method for overlapping handwriting. The method comprises the steps of: forming a display of at least one segment taken by a portion of an overlapping handwriting; receiving a request to correct one of the segments; and modifying the at least one portion in response to the request for the receiving Segment to get at least a new section. In another aspect, embodiments of the present invention provide a 201237764 device for overlapping handwriting. The apparatus includes: at least one processor, and at least one memory that stores a program of the computer executable code. The at least one memory and the computer executable code are assembled by the at least one processor to cause the apparatus to perform at least the steps of: forming a display of at least one segment obtained by a portion of an overlapping handwriting; receiving Used to modify one of the requirements of the segment; and to modify the at least one segment to obtain at least a new segment in response to the request for the receipt. In still another aspect, embodiments of the present invention provide a computer program product comprising at least one computer readable storage medium having a portion of a computer readable code stored thereon. The computer executable code portion includes: an encoding for forming a display of at least one segment taken by a portion of an overlapping handwriting; for receiving a code to modify a requirement of the segment; and for responding to the Receiving the request to modify the at least one segment to obtain at least a code for the new segment. In still another aspect, embodiments of the present invention provide an apparatus for overlapping handwriting. The apparatus includes: means for forming a display of at least one segment taken by a portion of an overlapping handwriting; means for receiving a request to modify one of the segments; and for responding to the request for the receiving, To modify the at least one segment to obtain at least a new segment of the device. Due to embodiments of the present invention, for example, if there is any error in the identification string, the segmentation result (i.e., at least - the segment) can be presented to the user in a modifiable or editable manner. For its part, the user can intuitively find the shirt in the segment if there is one. Then he/she can make an effective and easy method example > dry action to request correction of the segmentation error. According to the present invention, the #•实&example can enable the user to initiate the correction or repair of the segmentation result by using the group predetermined pen 6 201237764 such as h, click, or shake: seeking = the segmentation result Modifications or repairs - As is well known in the art, embodiments of the present invention can provide a user-interactive correction material segmentation county, which is constructed to correct the error section. This material I can provide a cost-effective solution to correct the error caused by the error segmentation, and the user and the second test can be significantly improved. Alternatively or additionally, the user may be caused to check and correct the segmentation results prior to performing the identification. In this way, it can confirm that the section to be identified is error-free. Moreover, in accordance with certain embodiments of the present invention, the user can also change their own initiated input by, for example, adding one or more strokes to an existing section. Other features and advantages of the embodiments of the present invention can be understood from the following description of the specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS The embodiments of the present invention are presented by way of example, and the advantages thereof will be described in more detail hereinafter with reference to the accompanying drawings, in which: FIG. 1 is a diagram showing a general description of overlapping handwriting The high-order of the program is not intended, and FIG. 2 shows a flow chart of a method for overlapping handwriting according to an embodiment of the present invention; FIGS. 3A to 3F show that the correction portion can be used according to an embodiment of the present invention. Examples of segments and their individual modifications; 201237764 Figures 4A-4B show examples of making a portion or section of an operation a bold reminder in accordance with an embodiment of the present invention; Figure 5 shows a suitable for use in real A schematic diagram of a graphical user interface (GUI) as an embodiment of the present invention; FIG. 6 shows a simplified block diagram of an apparatus for overlapping handwriting according to an embodiment of the present invention; and FIG. 7 shows a suitable A simplified block diagram of a device for implementing an embodiment of the invention. I. Embodiment 3 DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments of the present invention provide a method, apparatus, and computer program product for overlapping handwriting, and in particular, for enabling a user to interactively modify segmentation errors. In accordance with an embodiment of the present invention, the segments obtained by the segmentation of the overlay handwriting can be displayed to the user in a modifiable or editable manner. In particular, 'location and time information for each part (ie, one or more strokes) included in each section can be obtained, whereby the user can select any part of any section, and, for example, 'Use the financial pen to modify this part as needed. As a result, the user can effectively correct any segmentation errors and thus correct the final identification. Substitute or additionally to identify the previous ones (4) check t and red the segmentation results. In this manner, it can be confirmed that the waiting recognition section is error-free, so that the final discrimination can be increased. Embodiments of the present invention will be described below with reference to the drawings. It is to be understood that the specific embodiments of the present invention are described below primarily with reference to Chinese characters, but the limitations of the present invention are not limited in this respect. Embodiments of the present invention can be equally applied to characters in any language suitable for overlapping handwriting as described above, and the first embodiment of the general procedure of the overlapping handwriting method is shown. In this prior art, the intermediate results of the segments are not displayed to the user. Conversely, in accordance with an embodiment of the present invention, the segmentation result, i.e., the segment obtained by the segmentation of the initial overlap handwriting, or more segments, is presented to and modified by the user. It will be explained in detail as follows. Figure 2 shows a method of overlaying a handwritten method in accordance with an embodiment of the present invention. As shown in the figure, the method 2 (10) is at step _ start where at least a segment obtained by a segment of an overlapping handwriting is displayed to the user. The at least section can be obtained, for example, from a segmentation module that can perform a segmentation process in the overlay handwriting to generate one or more segments. It will be appreciated that the segments may be displayed in accordance with the user's request, e.g., when the user wishes to modify the error in the identification string, or alternatively or alternatively, the segments may be automatically displayed in conjunction with the final identification (4). In some & embodiments, the segments may be displayed via a graphical user interface such as that shown in Figure 5, which will be described in detail below. A segment can be used as the basic unit for subsequent character recognition, and as such, as described above, the ideal word can be matched with - single and the entire character. A segment can consist of more strokes or more. As used herein, the term "stroke" is referred to as a 〆 character or a basic and inseparable element of the segment. It should be understood that in the step, the at least one segment can be displayed in a modifiable or editable manner. That is, the user can select and then adjust one segment, or - one or more strokes of the overall segment. For this purpose, 201237764 is required for the location information of these sections. The money til can be obtained from the previous segmentation procedure. As is well known in the art, when the user overlaps the handwriting method to perform the segmentation, for each result segment, the position information of each stroke included in the segment can be determined' regardless of the particular algorithm used. In other words, according to the segmentation procedure, the location information of each stroke can be obtained for future use, for example, a selection or selection of a stroke as described below. Thus, for each point of the handwriting, the section of the genus and the stroke(s) can be mosquitoes. In addition, time information for each stroke can be obtained. For example, the time information of the stroke can be obtained by recording the user's writing order during the handwriting. In fact, it may be difficult for a user to select a particular stroke from a segment based solely on location information, for example, when the structure of the segment is complex. In this case, you can use the time information of the stroke alone or combine the location information to select a stroke. For example, in a preferred embodiment, a timeline of the strokes can be drawn under each segment so that the user can select a portion of the timeline and then select one or more of the segments. Strokes. There may also be other options for selecting a stroke or portion based on the location and/or time information. It should be understood that any currently existing or future developed method can be used to perform segmentation of overlapping handwriting, and thus the position and/or time information of the stroke can be obtained in different ways. The scope of the invention is not limited in this respect. Next, in step S210, a request for correcting the segment may be received. As shown in step S205, the user finds that in the case of - or more errors in the segments, he/she can initiate the correction request in several ways. Thereafter, in step S215, in response to the request received in step S210, the at least one segment may be modified to obtain at least one new segment. The operation of step S210 and step S215 of 201237764 will now be described in detail. In a preferred embodiment of the invention, in the step coffee, the request can be received via a reader-level predetermined gesture, and the modification of the segment can be completed in step S210. As shown in Figures 3A through 3p, certain scenarios can be used to request a modified segment. One. Reference, 3A Map In some cases, the segmentation procedure may not be suitable for separating the handwriting of a single-character as more than one separate segment. For example, as shown in Section 3A®, the user wants to input the Chinese character element by the overlapping handwriting method as "Ming". However, in this segment, the handwriting of the single-character can be divided into two separate segments, one segment and one segment 31 日 "day," and a second segment 312 "month" for correcting the class. Error, in accordance with some embodiments of the present invention, in the method of the method, the user may request modification of the segment in the following manner. ~ First, the user can, for example, click or lend in or near a bounding box of the first section 31 by using a pointing device (such as a pen, a light pen, a finger, or a mouse) The first segment 310 is selected or selected by pressing a particular button. The user may then be allowed to pull the selected first segment 31〇 to a predetermined adjacent region of the second segment 312, that is, to the distance between the first and second segments 31〇 and 312. a position that is less than a predetermined critical distance. In response, as shown in Figure 3A, the modification of the first and second sections 31A and 315 can be performed as a section 314 "Bright". It should be understood that the above gestures are for illustrative purposes only and there may be other gestures. On the other hand, another type of segmentation error is the opposite of the case shown in the related Fig. 3A, in which the handwriting of two or more separate characters during the segmentation 201237764 is incorrectly combined into a single segment. Figure 3B shows an example of this type. In this example, the user wants to input two Chinese characters "day" and "month", but the segmentation engine generates a single segment 320 "Ming," according to an embodiment of the present invention, such errors can be The reference section performs re-segmentation to correct. The user may request re-segmentation by making the section a predetermined gesture. In some embodiments, the predetermined gesture may be, for example, double click, long time. Pressing, or any other suitable gesture. As shown in FIG. 3B, the user can make the predetermined gesture (eg, double click) on the section 320 "light". Thereafter, by using the relevant stroke The location and time information may be in response to performing a re-segmentation' such that the segment 320 is divided into segments (two segments 322 and 324 in the example shown in Figure 3B). It should be understood that double clicks are only used to request An example example of the predetermined gesture of re-segmentation, but also other gestures. Figure 3C shows a situation similar to Figure 3B, in which two or more segments are incorrectly combined during the segmentation. a single segment. However, unlike the 3B Some of these sections may be quite simple, each segment consisting of a number of strokes (eg, only one or two strokes). In accordance with an embodiment of the present invention, the segmentation module is instead executed by the segmentation module. Re-segmentation, the reducer may choose to open a depiction and a segment only by dragging the four parts to a predetermined area, such as a blank area. - As used herein, the term "part, reference" - or more strokes, pens, ° ° ° ° ° should know that ~ part of the choice can be obtained by selecting the segmentation program can be used by using the words "can be from the whole chapter", set and / Or time information to complete ^ For example, when you click on any part, you can select the stroke. 12 201237764 Continuing with the example of Figure 3C, depending on the selection and dragging to a predetermined zone, the operational portion can be moved from the initial segment and a new segment will be taken from the portion. For its part, a segment can be split into two, and the procedure can be repeated until the results are correct. In particular, as shown in Fig. 3C, the handwriting of the Chinese character "person" and the Chinese period "." are combined into one segment 330 by error. At this time, the user can first select the stroke of the period, and then drag the selected stroke to a blank area. In response, the stroke "." can be removed from the combined section 330 leaving only the "person". In addition, a new section 334 consisting of the pulling section can be created. As a result, two can be obtained. Separate sections 332 "person" and 334". It should be understood that although the depicted portion shown in FIG. 3C includes only one stroke, embodiments of the present invention may also be applied to a portion consisting of a plurality of strokes. Another type of segmentation error includes two or more portions. The order of the segments. Unlike the single character handwriting method, when using the overlap handwriting method, a user usually wants to input a plurality of characters at the same time, for example, a sentence or even a sentence. Therefore, the identification results not only confirm the respective With the correctness of each character, and also confirm the proper sequence of the character sequence. For example, referring to the 3D figure, the user initially wants to input a Chinese phrase "Clear Festival". However, due to user error Or a segmentation error, the order of the segments 342 "ming" and 340 "section" may be reversed. According to an embodiment of the invention, the user may, for example, select a segment and drag it to A position in the sequence of segments is required to correct the order of the segments. The order of the segments in the sequence can then be changed according to the target position. In particular, as shown in FIG. 3D, the user selects the Section 340 "section" and drag it to a position after the section "342" of the section 342. In response, the order of the sections 340 and 342 may be changed. Some of them 13 201237764 In his embodiment, one will be The segment is pulled to, for example, a position in a blank area to rearrange the sequence of segments. Referring now to Figure 3E, another example of segmentation correction is shown. In this example, a segment 352 "Country" "One stroke (a vertical stroke or "vertical") is incorrectly assigned to a second section 350 "middle". That is, a stroke error as described above may appear in the segment. As a result, Section 350 "Medium" has a stroke and the section 352 "Country" lacks a stroke, which is very likely to cause an identification error of the two sections. According to an embodiment of the invention, the user can request correction in the following manner Processing the segmentation error. The user may be allowed to select the incorrect assignment portion, which may include one or more strokes of the first segment. Thereafter, the selected portion of the first segment may be pulled Good to the part that will belong to one of the second sections of a reservation In response to the gesture, the modification of the first and second segments may be implemented such that the selection portion may be from the first segment based on, for example, location and time information of the associated strokes Removed, and added to the second section. In particular, as shown in Figure 3E, the user can select a vertical stroke in the section 350 and drag it to a predetermined proximity of the section 352. In this way, two modified new sections 354 and 356 can be obtained. In fact, the most error-prone stroke can be found as a stroke of the "boundary zone" of two adjacent characters, since during the segmentation Class strokes are most easily incorrectly assigned to another segment. For example, the first or more strokes of a segment can be assigned to a segment immediately preceding the segment (eg, Figure 3E). The last one or more strokes of a segment are typically assigned to a segment immediately after the reference segment. According to an embodiment of the present invention, in order to more properly handle the common situation of the .-.Ά,·^- 14 201237764, a specific gesture can be provided to enable the user to select a character more easily and accurately. One or the last stroke. One example of this type of gesture is shaking. For example, the first or more strokes of a segment can be selected by quickly moving to the left after clicking in the bounding box of the segment, by clicking in the bounding box and quickly moving to the right. To select the last one or more strokes. As described above, given a segment, the first or last stroke or strokes may be selected due to the availability of time information (i.e., the write order) of each stroke. Of course, there may be other gestures for selecting the first/last stroke of a segment. However, the scope of the invention is not limited in this respect. Note that although a stroke error is shown in Fig. 3E, the embodiment of the present invention can be applied to the case where more than one stroke is incorrectly assigned to another segment in one segment. Referring to Figure 3F, the user may also be allowed to add one or more strokes to an existing section in accordance with an embodiment of the present invention. Sometimes one or more strokes of a character are missed due to errors or a segmentation error written by the user. Therefore, the segment will lack one or more strokes compared to the character that the user initially wants to enter. In another event, the user may want to change his/her own input. In each case, the user can directly add a portion (i.e., one or more strokes) to any existing segment instead of deleting it. In response, a new section can be created based on the sections and sections mentioned. As shown in Fig. 3F, by adding a stroke to a segment 360 "person", another segment 362 "large" consisting of the segment 360 "person" and the joining portion "one" can be generated. 15 201237764 From the above description, it can be seen that when segmentation correction is required, a user can be selected to include one or more strokes, or one of the specific segments of the overall segment. For this purpose, the gestures for partial selection and segment selection should be clearly distinguishable. According to some embodiments of the invention, the difference can be achieved by the duration of the 3-shot press. For example, a short press or click can correspond to a stroke selection, and a long press or click can correspond to the selection of an entire segment. In another example, it can provide one option or 7 flag that the user can set. If the option or flag is set to a first state, the gesture Z is converted to a partial selection. On the other hand, if the option or flag is set to the -= state, the gesture will be used for segment selection. These are just some examples of what to say. It is also possible to use any other mechanism for distinguishing between sections or sections of the entire section. Her L has the above gestures to be matched. That is, a user can add a new gesture, remove a gesture, fish, or modify an existing gesture based on his or her status. Alternatively or additionally, various parameters relating to the gestures, such as the predetermined neighborhood (the critical transition), the predetermined zone 'and/or the predetermined location' may also be assembled by the user. Further, as is well recognized by those skilled in the art, Figures 3a through 3 show some illustrative and non-limiting examples of gestures and countermeasures for segmentation correction in accordance with embodiments of the present invention. Given the above teachings, = who is familiar with this technique can easily imagine other (4) to ask for the right. In addition, the interaction = method, not the gesture, can be used to request a correction segment. For example, the use of touch, softkey, and drop-down list controls for individual or group t to input I correction requirements. In another example, the user can directly enter a specific pre-requisite 16 201237764 instruction to initiate the request. However, this issue is back to the fine, step by step 2, the material is not limited to this aspect. The paragraph is highlighted. The user can be clarified by making the part of the field during the operation or part of the change during the period. This eye-catching mention...咐(4) can avoid being mixed and 70% water. For example, the continued blue color can be changed from the color, appearance, shadow, font and/or size of the two pieces. The 'generation or additional' effect may be in the form of a part and reference to the figure 4 to 4B, which shows an example according to the invention of the present invention, wherein a part or section of the operation is made with a fisheye lens. In the case of the display, when the user activates a specific portion (the fourth side or the - section (the side), the part or section of the operation will be displayed by a fisheye. For example, according to the action of the operation part or section, the movement may be during the tampering. In addition to the touch, the content displayed in the *eye may also be dynamically updated during the tempo. For example, the example shown in the _ When the user selects the segment for the first time, the segment 350 and the selected stroke are included in the fisheye, and the color of the pen may be changed. The selected stroke is dragged to the segment. At 352, it can be highlighted in the fisheye. Finally, when the stroke is combined with the section 352, the section of the result will be in the fisheye. The fisheye should be understood as an oil for example. And may be used in conjunction with - or more other eye-catching prompt effects (eg, color changes as shown in Figures 4A through 4B). It should also be noted that step S220 is optional as the user may choose to The eye-catching function of the operating element is not enabled/disabled. In addition, these eye-catching prompts The user can be assigned. That is, the user can add new effects, remove existing effects, and/or assemble various different related parameters according to his/her preference or the state of the device 17 201237764. Next, the steps In S225, at least one new segment 'obtained in step S215 can be identified to output one or more characters. The method is terminated after 2。. As described above, any existing existing or later developed identification method can be used to The segments are converted to characters, and the scope of the invention is not limited in this respect. Further, step S225 is optional, as in some applications, segments representing the initial track of the user may be stored. And used directly without identification. One example of such an application is an application for writing exercises. Figure 5 shows a graphical user interface (GUI) 500 suitable for implementing embodiments of the present invention. In some embodiments, the gui 5 can be used in conjunction with the method 200 and can be generated and presented, for example, by the apparatus described below with reference to Figures 6 and 7. As shown, the GUI 500 includes an editor area 5 5. A candidate character area 510, a segmentation result area 515, a write area 52A, and a control area 525. In operation, the user can write in an overlap manner in the write area 52A. Multiple characters are entered. The segmentation and recognition of the user's handwriting can then be performed. The last characters can be displayed in the editor area 5〇5, and a candidate child/monthly order can be displayed in §Xuan In the candidate character region 51. In particular, according to an embodiment of the present invention, one or more segments of the result may be displayed in the segmentation result region 515. For example, the user finds that the segmentation is caused by an error. When an error is identified, he/she can interact with the segmentation result area 515 in the manner described above to correct the error (if any) of the s-segment segment. After the correction, the user can confirm that the segment has no error, The equal sections can be identified. The editor area 5〇5 and the 18 201237764 candidate sub-area area 510 can then be updated accordingly. Alternatively or additionally, the identification may be performed to enable the 6-Hai user to check and correct the segmentation results as indicated in the segmentation result area 515. In the control area 525, the user can control the program of the overlay handwriting such as a button, one or more of the soft keys, or any other suitable control. It should be understood that the GUI 500 shown in Fig. 5 is merely an example of an illustrative example. The GUI suitable for implementing embodiments of the present invention may include fewer, additional, and/or different components. Alternatively or additionally, the layout or arrangement of components on such GUIs in other embodiments may be varied. Figure 6 shows a simplified block diagram of a device 600 for overlapping handwriting in accordance with an embodiment of the present invention. As described above, the device 6 can generate a GUI that presents the GUI 500 as shown in FIG. As shown in FIG. 6, the apparatus 600 can include a segment display device 605, a correction request device 61, a segment modification device 615, a modified eye-catching device 620 (optional), and a character recognition device 625 (optional). ). The segment display device 605 can be configured to display at least one segment obtained by a segment of an overlay handwriting. The correction requires that the device 61 can be configured to receive a request to correct one of the segments. The segment modification mechanism 615 can be configured to modify the at least one segment in response to the receiving request to obtain at least -·*· new segments. In particular, the segment modification device 615 can be configured to perform the following/or more steps: in response to dragging a first segment to a predetermined neighborhood of a second segment, the first Combining the second segment into a segment; in response to a predetermined gesture on a portion of the first segment, performing one of the re-segmentation of one of the 19th 201237764 segments to obtain two or more segments; Responding to dragging a portion of a first segment to a predetermined region, removing the portion from the first segment, and establishing a new segment based on the portion; responsive to placing a first segment Dragging to a position in the sequence of segments, and changing the order of the first segments in the sequence; in response to dragging a first segment to a predetermined neighborhood of a second segment, from the first The section removes the portion and adds the portion to the second section; and in response to adding a portion to a first section, creating a new section consisting of the first section and the joining section Segment to replace the first segment. During operation of the segment modification device 615, the modified eye-catching prompt device 620 can be configured to make a portion or section of the operation a prominent prompt. The character recognition device 625 can be configured to perform recognition in cooperation with the segment modification device 615 to convert the modified segments into editable characters. It will be appreciated that the apparatus 600 can be embodied in hardware or special purpose circuits, software, logic, or any combination thereof. Thus, the various devices of the device 600 can be embodied as software modules, and/or hardware blocks, units, or components. Embodiments of the above described procedures or methods (e.g., method 200 as shown in Fig. 2) may be performed by any suitable means. Figure 7 shows a simplified block diagram of a device 700 suitable for use in practicing embodiments of the present invention. In some embodiments, the device 700 can be embodied as a mobile terminal. However, it is to be understood that a mobile terminal is merely illustrative of one type of device that may benefit from embodiments of the present invention and, therefore, should not be considered as limiting the scope of the embodiments of the present invention.
20 201237764 s亥裝置700可包括操作上與一發送器714以及一接收器 716通说之-天線7u(或錄天線）。該裝置糊可進一步包 括至少-處理益或控制器72〇。應了解該控制器72〇可包括 執饤重疊手寫法所需之電路以及該裝置之邏輯功能。例 如，該控制11720可由—數位信號處理㈣備…微處理器 設備、與各種不同的類比數位轉換器、數位類比轉換器、 以及其他支援電路缝成。《㈣〇之㈣與資訊處理功 能可根據其個別功能在該等設備之間配置。 4裝置7GG亦可包含_使用者介面，其包括諸如一耳機 或揚聲器724、-振鋒器722、—麥克風m、一顯示器瓜 之一輸出設備’以及-使用者輪人介面，其所有構件皆耦 合至該控制器™。該使用者輪人介面可包括允許該裝置 接收資料之若干設備的任何—個，諸如—鍵板或鍵盤 、一寫人設備731、或其他輪入設備。例如，該寫入設 備731可包括，但不偶限於，-觸控榮幕、-鄰近區營幕、 -寫入墊、等等。特別是’該寫入設備731能夠接收一使用 者輸入之重疊手寫法。就本身”，料錢備731可包括 支援重疊手寫法所需之所有硬體、軟體與/或勤體。 額外或替代地，該裝置7〇〇可包括諸如 用者輸入介面之一介面設備。該 干S 、 邊凌置700可進一步包括一 ^組734，諸如-振動電池組，來㈣作該裝需之 各種不同的電路供電，以及住 可檢測輸出。 供機械振動來作為- 制器720通訊 某些實_巾’賴置7(^包括與該控 21 201237764 視訊與/或音訊模組 。該 之一媒體擷取元件，諸如一相機、 媒體擷取^可制⑽貞取1像、視訊與/或音訊以儲 存、顯示或傳輸之任何裝置。例如，於該媒體触元件為 -相機模組736之-示範實施例中，該相機模组7%可包括 能夠從-娜影像形成-數位影像㈣之—數位相機。該 裝置700作為-行動端子來料具體化時，其可進—步包括 一通用識別模組(UIM)73 8。該UIM 738典型為具有一内建 處理器之一記憶體設備。該UIM 738可包括，例如，一用戶 識別模組（SIM)、一通用積體電路卡(UICC)、一通用用戶識 別模組(USIM)、一可移除使用者識別模組(R uim)、等等。 該UIM 73 8典型可儲存與一用戶相關之資訊元件。 該裝置7GG可配備至少__記髓^例如，該裝置7〇〇可 包括依電性圯憶體740，諸如包括資料暫時儲存之一快取區 之依電性隨機存取記憶體(RAM)。該裝置700亦可包括可内 嵌與/或可移除之其他非依電性記憶體742。該非依電性記 憶體742可額外或替代地包含一EEpR〇M、快取記憶體等 等。該等記憶體可儲存該裝置7〇〇使用之若干資訊、程式、 與資料之任何一個以執行該裝置7〇〇之功能。例如，該等記 憶體可儲存電腦可執行碼之程式，其可以該控制器72〇組配 來使該裝置700至少執行如上述方法2〇〇的步驟。 本發明之實施例亦可作為一電腦程式產品來予以執 行，其包含具有儲存於此之一電腦可讀程式碼部分的至少 一電腦可讀儲存媒體。該類實施例中，該電腦可讀程式碼 部分至少包含用以執行如上述方法2〇〇的步 驟之編碼。 22 201237764 ，j暫示本發明之s a丨 如上所述，本發二Γ，已說明其某些特定實施例。 ❹'產品’而特別是，可讓使用者交互修 之重叠差。根據本發明之實施例，卜使用者輪入 示。特別取得的部段可以—可修改或可編輯的方式顯 的位置可取得包切每—雜巾之每-部分(或筆劃） γ訊與時間資訊(寫入順序），使得該使用者可選擇任 β敫之任何部分，並例如，#+ Α 修改該部分。社果β，= 預疋筆勢來如所欲 °疋可提供該使用者一有效且便利的方 2修正該等重疊手寫法辨識結果。替代或額外地，執行 成之前該㈣者亦可選擇檢查與修正料分段結果，而 因此可確認待辨識之部段為無誤差。實際上，該分段修正 可於該字元_之前、—起、或之後執行，而本發明之範 _並不侷限於此方面。 相較於習知技術重疊手寫法之解決方案，實驗已指出 由於本發明之實關，已可增加針對分段誤差造成之重疊 手寫法的修正辨識誤差之效能。此外，該使用者之經驗與 滿意度可獲得改善’ SJ為在賴誤差的情況巾使用者不需 要重新寫入一或更多字元。 般而5 ’各種刊的示範實施例可以硬體或專用電 路、軟體、邏輯或其任何組合來執行。例如，某些方面可 以硬體來執行，而其他方面可以由―㈣器、微處理器或 其他計算設備執行之㈣妹體來執行，_本發明並不 於此。而本發明之示範實施㈣各種不同方面可以方 23 201237764 塊圖、流程圖、或使用某些其他圖形表示法來予以繪示與 說明，可相當了解本文所述之該等方塊、裝置、系統、技 術或方法可以，如非限制範例、硬體、軟體、韌體、專用 電路或邏輯、通用硬體或控制器或其他計算設備、或其某 些組合來執行。 第2圖所示之各種不同方塊可以由電腦程式碼之操作 產生的方法步驟、與/或操作、以及/或者以建構來實現該等 相關功能之多個耦合邏輯電路元件來視之。本發明之示範 實施例的至少某些觀點可以諸如積體電路晶片與模組之各 種不同構件來加以實作，而本發明之示範實施例可於作為 一積體電路來予以具體化之一裝置中實現。該積體電路、 或電路可包含用來將可組配來根據本發明之示範實施例操 作的一資料處理器或多個資料處理器、一數位信號處理器 或多個處理器、基頻電路與射頻電路具體化之電路（以及可 能的韌體）。 有鑑於上述說明，連同該等附圖閱讀時，本發明之上 述示範實施例的各種不同修改、調適對相關業界熟於此技 者而言會變得更加明顯。任何以及所有修改仍將位於本發 明之非限制與示範實施例的範疇中。此外，本文提出之本 發明其他實施例將浮現在對有關本發明之實施例的業界熟 於此技者的腦海中，其具有上述說明與相關聯圖形中呈現 之教示優點。 因此，應了解本發明之實施例不應侷限在本文揭示之 特定實施例中，而若干修改與其他實施例意欲包括在該等 24 201237764 後附申叫專利範圍之範疇中。雖然本文中使用某些特定術 οσ但其可僅以一般與說明觀點來使用而非用於限制。 【圖式簡單說明】 第1圖是一顯示繪示—重疊手寫法之一般程序的高階 示意圖； 第2圖顯示一根據本發明之實施例，用於重疊手寫法之 一方法的流程圖； 第3Α圖至第3F圖顯示根據本發明之實施例，可用來要 求修正部段及其個別修改之若干筆勢的範例； 第4Α圖至第4Β圖顯示根據本發明之實施例，使操作令 之部分或部段以醒目提示的範例； 第5圖顯示一適合用於實作本發明之實施例的一圖形 使用者介面（GUI)之示意圖； • 第6圖顯示一根據本發明之實施例，用於重疊手寫法之 一裝置的簡化方塊圖；以及 第7圖顯示一適合用於實作本發明之實施例的一裝置 之簡化方塊圖。 【主要元件符號說明】 102.. .筆跡 104、314、320、322、324、330、332、334、340、342、344、 352、354、356、360、362·.·部段 106.. .字元 200.. .方法 310…第一部段 312、315、350...第二部段 500…圖形使用者介面 25 201237764 505.. .編輯器區 510.. .候選字元區 515.. .分段結果區 520.. .寫入區 525.. .控制區 600、700.··裝置 605.. .分段顯示裝置 610.. .修正要求裝置 615.. .分段修改裝置 620.. .修改醒目提示裝置 625.. .字元辨識裝置 712.. .天線 714.. .發送器 716.. .接收器 720.. .處理器或控制器 722.. .振鈴器 724.. .耳機或揚聲器 726.. .麥克風 728.. .顯示器 730.. .鍵板或鍵盤 731.. .寫入設備 734.. .電池組 736.. .相機模組 738.. .通用識別模組 740.. .依電性記憶體 742.. .非依電性記憶體 S205、S210、S215、S220、225…步驟 2620 201237764 The device 700 can include an antenna 7u (or a recording antenna) operatively associated with a transmitter 714 and a receiver 716. The device paste may further comprise at least a processing benefit or controller 72A. It will be appreciated that the controller 72 can include the circuitry required to perform the overlay handwriting and the logic functions of the device. For example, the control 11720 can be processed by a digital signal processing (four) microprocessor device, with various analog digital converters, digital analog converters, and other support circuits. (4) 〇 (4) and information processing functions can be configured between these devices according to their individual functions. 4 device 7GG may also include a user interface including, for example, a headphone or speaker 724, a vibrator 722, a microphone m, a display device, and a user wheel interface, all of which are Coupled to the controller TM. The user wheel interface can include any of a number of devices that allow the device to receive data, such as a keypad or keyboard, a writer device 731, or other wheeling device. For example, the writing device 731 can include, but is not limited to, a touch screen, a neighboring scene, a write pad, and the like. In particular, the writing device 731 is capable of receiving an overlay handwriting input by a user. As such, the 730 can include all of the hardware, software, and/or work required to support overlapping handwriting. Additionally or alternatively, the device 7 can include an interface device such as a user input interface. The dry S and the edge 700 may further comprise a group 734, such as a vibrating battery pack, to (4) supply different kinds of circuits for the installation, and to live detectable output. For mechanical vibration as a controller 720 Communication Some _ 巾 ' 赖 ( 7 (^ Included with the control 21 201237764 video and / or audio module. The one of the media capture components, such as a camera, media capture ^ can be made (10) to capture 1 image, Video and/or audio for any device that is stored, displayed, or transmitted. For example, in the exemplary embodiment where the media touch element is - camera module 736, the camera module 7% can include a capable image from - Digital Image (D) - Digital Camera. When the device 700 is embodied as a mobile terminal, it can further include a Universal Identification Module (UIM) 73 8. The UIM 738 typically has a built-in processor. a memory device. The UIM 738 can include, for example For example, a user identification module (SIM), a universal integrated circuit card (UICC), a universal user identification module (USIM), a removable user identification module (R uim), etc. The UIM 73 8 typically stores information elements associated with a user. The device 7GG can be equipped with at least a __ memory, for example, the device 7 can include an electrical memory 740, such as a cache that includes temporary storage of data. The area of electrical random access memory (RAM). The device 700 can also include other non-electrical memory 742 that can be embedded and/or removable. The non-electrical memory 742 can be used in addition to or in place of The ground includes an EEpR〇M, a cache memory, etc. The memory stores any of a number of information, programs, and materials used by the device to perform the functions of the device. For example, The memory can store a computer executable code program, which can be configured by the controller 72 to cause the device 700 to perform at least the steps of the above method. The embodiment of the present invention can also be used as a computer program product. Executed, it contains a computer that has stored on this one At least one computer readable storage medium of the code portion. In such an embodiment, the computer readable program code portion includes at least a code for performing the steps of the method 2 above. 22 201237764, j. Sa丨 As described above, the present invention has been described in some specific embodiments. The 'product' and, in particular, allows the user to interact with each other to improve the overlap. According to an embodiment of the present invention, the user turns in the display. Specially obtained sections can be modified or editable in such a way as to obtain a per-part (or stroke) gamma and time information (write order) for the user to Select any part of β敫 and, for example, #+ 修改 modify the part. The fruit β, = pre-emptive gestures can provide the user with an effective and convenient way to correct the overlapping handwritten recognition results. Alternatively or additionally, the (4) person may also select the inspection and correction material segmentation results before the execution, and thus the segment to be identified may be confirmed to be error-free. In fact, the segmentation correction can be performed before, after, or after the character_, and the invention is not limited in this respect. Compared to the solution of the prior art overlap handwriting method, experiments have shown that the effectiveness of the modified identification error for overlapping handwriting caused by segmentation errors can be increased due to the practical aspects of the present invention. In addition, the user's experience and satisfaction can be improved. SJ is the case where the user does not need to rewrite one or more characters. Exemplary embodiments of the various publications may be implemented in hardware or special purpose circuits, software, logic, or any combination thereof. For example, some aspects may be implemented in hardware, while other aspects may be performed by a (four) singer executed by a "fourth" device, a microprocessor, or other computing device, and the present invention is not. While the exemplary implementation of the present invention (4) various aspects may be illustrated and illustrated by the block diagrams, flowcharts, or some other graphical representations, the blocks, devices, systems, and Techniques or methods may be performed, such as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof. The various blocks shown in Figure 2 can be viewed by method steps, and/or operations, and/or by a plurality of coupled logic circuit elements constructed to perform such related functions. At least some aspects of the exemplary embodiments of the present invention may be implemented in various components such as integrated circuit chips and modules, and exemplary embodiments of the present invention may be embodied as an integrated circuit. Implemented in . The integrated circuit, or circuit, can include a data processor or data processors, a digital signal processor or multiple processors, a baseband circuit that can be configured to operate in accordance with exemplary embodiments of the present invention. A circuit (and possibly a firmware) that is embodied with a radio frequency circuit. In view of the foregoing description, various modifications and adaptations of the exemplary embodiments of the present invention will become more apparent to those skilled in the art. Any and all modifications will still be within the scope of the non-limiting and exemplary embodiments of the invention. Moreover, other embodiments of the invention as set forth herein will come to mind in the mind of those skilled in the <RTIgt; Therefore, it should be understood that the embodiments of the invention are not limited to the specific embodiments disclosed herein, and that certain modifications and other embodiments are intended to be included in the scope of the appended claims. Although certain specific techniques are used herein, they may be used in a generic and illustrative context only and not for limitation. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a high-order diagram showing a general procedure of an overlay-overlapping handwriting method; FIG. 2 is a flow chart showing a method for overlapping handwriting according to an embodiment of the present invention; 3D through 3F show examples of several gestures that may be used to request correction of segments and their individual modifications in accordance with an embodiment of the present invention; Figures 4 through 4 show portions of the operational commands in accordance with an embodiment of the present invention Or a section with an eye-catching example; Figure 5 shows a schematic diagram of a graphical user interface (GUI) suitable for use in practicing embodiments of the present invention; • Figure 6 shows an embodiment in accordance with the present invention, A simplified block diagram of one of the means for overlapping handwriting; and Figure 7 shows a simplified block diagram of a device suitable for use in practicing embodiments of the present invention. [Main component symbol description] 102.. . Handwriting 104, 314, 320, 322, 324, 330, 332, 334, 340, 342, 344, 352, 354, 356, 360, 362.. Section 106.. Character 200.. Method 310... First Segment 312, 315, 350... Second Segment 500... Graphic User Interface 25 201237764 505.. Editor Area 510.. Candidate Character Area 515 .. . Segmentation result area 520.. Write area 525.. Control area 600, 700.. Device 605.. . Segment display device 610.. Correction request device 615.. Section modification device 620.. Modify the eye-catching device 625.. Character recognition device 712.. Antenna 714.. Transmitter 716.. Receiver 720.. Processor or controller 722.. Ringer 724. . . Headphones or Speakers 726.. Microphone 728.. Display 730.. Keypad or Keyboard 731.. Write Device 734.. Battery Pack 736.. Camera Module 738.. General Identification Mode Group 740.. Dependent on electrical memory 742.. Non-electrical memory S205, S210, S215, S220, 225... Step 26