TWM560646U - Voice control trading system - Google Patents
Voice control trading system Download PDFInfo
- Publication number
- TWM560646U TWM560646U TW107200209U TW107200209U TWM560646U TW M560646 U TWM560646 U TW M560646U TW 107200209 U TW107200209 U TW 107200209U TW 107200209 U TW107200209 U TW 107200209U TW M560646 U TWM560646 U TW M560646U
- Authority
- TW
- Taiwan
- Prior art keywords
- processor
- unit
- voice
- storage unit
- signal
- Prior art date
Links
Landscapes
- Telephonic Communication Services (AREA)
Abstract
Description
本新型是有關於一種智能語音交易系統。The new model is related to an intelligent voice transaction system.
一般而言,使用者得透過諸如手機、電腦等終端裝置傳送指令至銀行主機,以進行銀行所提供的業務服務。傳統上,使用者依照終端裝置所顯示之選項,手動操作以輸入指令,從而傳送至銀行主機。然而,對於一些特定使用者(例如老人)而言,手動操作過於複雜,以至於無法順利使用銀行所提供的業務服務。再者,當使用者已有一欲進行的業務目的時,仍然需要依照終端裝置所顯示之各階層選項,一層一層地選擇以完成指令的輸入,既耗時又耗力。Generally, a user may transmit an instruction to a bank host through a terminal device such as a mobile phone or a computer to perform a business service provided by the bank. Traditionally, the user manually operates to input an instruction in accordance with the options displayed by the terminal device, thereby transmitting to the bank host. However, for some specific users (such as the elderly), the manual operation is too complicated to use the business services provided by the bank. Moreover, when the user has a business purpose to be performed, it is still necessary to select the layer-by-layer selection to complete the instruction input according to the various layer options displayed by the terminal device, which is time consuming and labor intensive.
由此可見,上述現有的方式,顯然仍存在不便與缺陷,而有待改進。為了解決上述問題,相關領域莫不費盡心思來謀求解決之道,但長久以來仍未發展出適當的解決方案。It can be seen that the above existing methods obviously have inconveniences and defects, and need to be improved. In order to solve the above problems, the relevant fields have not tried their best to find a solution, but for a long time, no suitable solution has been developed.
本新型之一態樣係提供一種智能語音交易系統。智能語音交易系統包括一處理主機。處理主機包括一第一儲存單元、一第一處理器、以及一第一傳輸單元。第一處理器電性連接至第一儲存單元和第一傳輸單元。第一傳輸單元用以接收一文字訊號。第一處理器用以執行儲存於第一儲存單元的一語意辨識模組。語意辨識模組進行文字訊號與儲存於第一儲存單元的一資料庫中的複數個指令選項的匹配,從而產生對應指令選項的複數個信心指數。其中,第一處理器根據信心指數進行一反應,包括(a) 當信心指數中之一者大於一預設值時,執行大於預設值之信心指數所對應的指令選項的動作。One aspect of the present invention provides an intelligent voice transaction system. The intelligent voice transaction system includes a processing host. The processing host includes a first storage unit, a first processor, and a first transmission unit. The first processor is electrically connected to the first storage unit and the first transmission unit. The first transmission unit is configured to receive a text signal. The first processor is configured to execute a semantic recognition module stored in the first storage unit. The semantic recognition module matches the text signal with a plurality of instruction options stored in a database of the first storage unit, thereby generating a plurality of confidence indices corresponding to the instruction options. The first processor performs a response according to the confidence index, including (a) when one of the confidence indexes is greater than a preset value, performing an action of an instruction option corresponding to the confidence index of the preset value.
於一實施例中,智能語音交易系統進一步包括一電子裝置。電子裝置包括一語音輸入單元、一第二儲存單元、一第二處理器、以及一第二傳輸單元。第二處理器電性連接至語音輸入單元、第二儲存單元、以及第二傳輸單元。第二處理器用以執行儲存於第二儲存單元的一語音分析模組以分析藉由語音輸入單元所接收的一語音訊號,從而產生文字訊號。第二傳輸單元設置以與第一傳輸單元建立一通訊連結以傳送文字訊號。In an embodiment, the intelligent voice transaction system further includes an electronic device. The electronic device includes a voice input unit, a second storage unit, a second processor, and a second transmission unit. The second processor is electrically connected to the voice input unit, the second storage unit, and the second transmission unit. The second processor is configured to execute a voice analysis module stored in the second storage unit to analyze a voice signal received by the voice input unit, thereby generating a text signal. The second transmission unit is configured to establish a communication link with the first transmission unit to transmit the text signal.
於一實施例中,通訊連結為一網路。In one embodiment, the communication link is a network.
於一實施例中,一應用程式儲存於第二儲存單元。應用程式被第二處理器所執行。當語音分析模組產生與一預設文字相同之文字訊號時,進行已產生的文字訊號之傳送,從而傳送文字訊號至處理主機。In one embodiment, an application is stored in the second storage unit. The application is executed by the second processor. When the voice analysis module generates the same text signal as the preset text, the generated text signal is transmitted, thereby transmitting the text signal to the processing host.
於一實施例中,電子裝置進一步包括一顯示單元。第二處理器電性連接至顯示單元。在第一處理器進行(a)反應之後,回傳一執行結果至電子裝置。顯示單元顯示執行結果。In an embodiment, the electronic device further includes a display unit. The second processor is electrically connected to the display unit. After the first processor performs the (a) reaction, an execution result is returned to the electronic device. The display unit displays the execution result.
於一實施例中,一應用程式儲存於第二儲存單元。應用程式被第二處理器所執行。電子裝置進一步包括一播放單元。第二處理器電性連接至播放單元。在第一處理器進行(a)反應之後,回傳一執行結果至電子裝置。應用程式產生對應執行結果之一語音撥放訊號。播放單元撥放語音撥放訊號。In one embodiment, an application is stored in the second storage unit. The application is executed by the second processor. The electronic device further includes a playback unit. The second processor is electrically connected to the playing unit. After the first processor performs the (a) reaction, an execution result is returned to the electronic device. The application generates a voice dialing signal corresponding to the execution result. The playback unit plays a voice dialing signal.
於一實施例中,反應進一步包括(b) 當信心指數皆小於預設值時,回傳信心指數中數值較高的3至5個所對應的指令選項至電子裝置。In an embodiment, the reacting further comprises: (b) when the confidence index is less than a preset value, returning 3 to 5 corresponding instruction options having a higher value in the confidence index to the electronic device.
於一實施例中,一應用程式儲存於第二儲存單元。應用程式被第二處理器所執行。電子裝置進一步包括一播放單元。第二處理器電性連接至播放單元。在第一處理器進行(b)反應之後,應用程式產生對應回傳的指令選項之一語音撥放訊號。播放單元撥放語音撥放訊號。In one embodiment, an application is stored in the second storage unit. The application is executed by the second processor. The electronic device further includes a playback unit. The second processor is electrically connected to the playing unit. After the first processor performs the (b) reaction, the application generates a voice dialing signal corresponding to one of the command options for the return. The playback unit plays a voice dialing signal.
於一實施例中,電子裝置進一步包括一輸入單元。第二處理器電性連接至輸入單元。在第一處理器進行(b)反應之後,傳送藉由輸入單元所輸入之一輸入訊號至處理主機以選擇回傳的指令選項,使第一處理器執行選擇的指令選項的動作。In an embodiment, the electronic device further includes an input unit. The second processor is electrically connected to the input unit. After the (b) response is performed by the first processor, the input of the input signal to the processing host by the input unit to select the returned command option causes the first processor to perform the action of the selected instruction option.
於一實施例中,一應用程式儲存於第二儲存單元。應用程式被第二處理器所執行。在第一處理器進行(b)反應之後,當語音分析模組產生與一預設文字相同之文字訊號時,進行已產生的文字訊號之傳送,從而選擇回傳的指令選項,使第一處理器執行選擇的指令選項的動作。In one embodiment, an application is stored in the second storage unit. The application is executed by the second processor. After the (b) response is performed by the first processor, when the voice analysis module generates the same text signal as the preset text, the generated text signal is transmitted, thereby selecting the returned command option to make the first processing The action of the selected instruction option.
以下將以實施方式對上述之說明作詳細的描述,並對本新型之技術方案提供更進一步的解釋。The above description will be described in detail in the following embodiments, and further explanation of the technical solutions of the present invention will be provided.
為了使本新型之敘述更加詳盡與完備,可參照所附之圖式及以下所述各種實施例,圖式中相同之號碼代表相同或相似之元件。另一方面,眾所週知的元件與步驟並未描述於實施例中,以避免對本新型造成不必要的限制。In order to make the description of the present invention more complete and complete, reference is made to the accompanying drawings and the accompanying drawings. On the other hand, well-known elements and steps are not described in the embodiments to avoid unnecessarily limiting the present invention.
請參照第1圖,第1圖為根據本揭示內容之一實施例之一種智能語音交易系統100。如第1圖所示,智能語音交易系統100包括處理主機120。處理主機120包括第一儲存單元122、第一處理器123、以及第一傳輸單元124。在連接關係上,第一處理器123電性連接至第一儲存單元122和第一傳輸單元124。應理解的是,第一傳輸單元124用以接收一文字訊號,而第一處理器123用以執行儲存於第一儲存單元122的語意辨識模組122a。語意辨識模組122a進行文字訊號與儲存於第一儲存單元122的資料庫122b中的多個指令選項的匹配,從而產生對應所述多個指令選項的多個信心指數。在一實施例中,當多個信心指數中之一者大於一預設值時,第一處理器123執行大於預設值之信心指數所對應的指令選項的動作。所謂「語意辨識模組」可為用於辨識文字訊號與特定的指令選項之間的相似度之任何本領域所習知的程式,而所謂「信心指數」則為文字訊號與特定的指令選項之間的相似度值。也就是說,當信心指數越高時,意味著文字訊號與特定的指令選項越相似。進一步地,可設定一預設值,當信心指數大於此預設值時,第一處理器123可直接執行此特定的指令選項的動作。值得一提的是,雖然使用任何本領域所習知的程式作為語意辨識模組已可辨識出最接近的指令選項,但此最接近的指令選項可能並非使用者所欲進行的業務目的。若第一處理器123冒然地直接執行此最接近的指令選項,將對使用者造成困擾。然而,藉由本揭示內容所提出的預設值門檻機制,在信心指數低於預設值時不予執行最接近的指令選項,將可大幅地提升辨識的精確度。Please refer to FIG. 1. FIG. 1 is an intelligent voice transaction system 100 according to an embodiment of the present disclosure. As shown in FIG. 1, the intelligent voice transaction system 100 includes a processing host 120. The processing host 120 includes a first storage unit 122, a first processor 123, and a first transmission unit 124. In the connection relationship, the first processor 123 is electrically connected to the first storage unit 122 and the first transmission unit 124. It should be understood that the first transmission unit 124 is configured to receive a text signal, and the first processor 123 is configured to execute the semantic recognition module 122a stored in the first storage unit 122. The semantic recognition module 122a performs matching of the text signal with a plurality of instruction options stored in the database 122b of the first storage unit 122, thereby generating a plurality of confidence indices corresponding to the plurality of instruction options. In an embodiment, when one of the plurality of confidence indexes is greater than a predetermined value, the first processor 123 performs an action of the instruction option corresponding to the confidence index of the preset value. The so-called "speech recognition module" can be any program known in the art for recognizing the similarity between a text signal and a specific command option, and the so-called "confidence index" is a text signal and a specific command option. The similarity value between. In other words, when the confidence index is higher, it means that the text signal is more similar to a specific command option. Further, a preset value may be set. When the confidence index is greater than the preset value, the first processor 123 may directly perform the action of the specific instruction option. It is worth mentioning that although any program known in the art can be used as a semantic module to identify the closest instruction option, the closest instruction option may not be the business purpose of the user. If the first processor 123 voluntarily executes this closest instruction option, it will cause trouble to the user. However, with the preset threshold mechanism proposed in the present disclosure, the closest instruction option is not executed when the confidence index is lower than the preset value, and the accuracy of the recognition can be greatly improved.
在此亦揭示第一傳輸單元124所接收的文字訊號來源。使用者得操作一電子裝置110以產生所述文字訊號,並藉由通訊連結L1傳送此文字訊號至處理主機120。具體來說,智能語音交易系統100進一步包括電子裝置110。電子裝置110包括語音輸入單元111、第二儲存單元112、第二處理器113、以及第二傳輸單元114。在連接關係上,第二處理器113電性連接至語音輸入單元111、第二儲存單元112、以及第二傳輸單元114。應理解的是,第二處理器113用以執行儲存於第二儲存單元112的語音分析模組112a以分析藉由語音輸入單元111所接收的一語音訊號,從而產生所述文字訊號。第二傳輸單元114設置以與第一傳輸單元124建立通訊連結L1以傳送所述文字訊號。The source of the text signal received by the first transmission unit 124 is also disclosed herein. The user has to operate an electronic device 110 to generate the text signal, and transmit the text signal to the processing host 120 via the communication link L1. In particular, the intelligent voice transaction system 100 further includes an electronic device 110. The electronic device 110 includes a voice input unit 111, a second storage unit 112, a second processor 113, and a second transmission unit 114. In the connection relationship, the second processor 113 is electrically connected to the voice input unit 111, the second storage unit 112, and the second transmission unit 114. It should be understood that the second processor 113 is configured to execute the voice analysis module 112a stored in the second storage unit 112 to analyze a voice signal received by the voice input unit 111, thereby generating the text signal. The second transmission unit 114 is configured to establish a communication link L1 with the first transmission unit 124 to transmit the text signal.
在一實施例中,電子裝置110可為個人電腦、筆記型電腦、平板電腦或手機等。在一實施例中,語音輸入單元111可為話筒或麥克風。在一實施例中,第一儲存單元122和第二儲存單元112可為硬碟、快閃記憶體或其他記錄媒體。在一實施例中,第一處理器123和第二處理器113可為中央處理器、微控制器或其他電路。在一實施例中,第一傳輸單元124和第二傳輸單元114可為無線收發器、網路卡或其他通訊裝置。在一實施例中,通訊連結L1可為網路。In an embodiment, the electronic device 110 can be a personal computer, a notebook computer, a tablet computer, or a mobile phone. In an embodiment, the voice input unit 111 can be a microphone or a microphone. In an embodiment, the first storage unit 122 and the second storage unit 112 may be hard disks, flash memory or other recording media. In an embodiment, the first processor 123 and the second processor 113 can be central processing units, microcontrollers, or other circuits. In an embodiment, the first transmission unit 124 and the second transmission unit 114 may be wireless transceivers, network cards, or other communication devices. In an embodiment, the communication link L1 can be a network.
應理解的是,為了達到更方便使用之目的,可在電子裝置110中安裝一應用程式112b以進行聲控訊號傳送。具體來說,所述應用程式112b儲存於第二儲存單元112。使用者得進行操作以使第二處理器113執行應用程式112b。在應用程式112b被第二處理器113執行的情況下,當語音分析模組112a產生與一預設文字相同之文字訊號時,進行已產生的文字訊號之傳送。舉例來說,所述「預設文字」可為「傳送」。當使用者說出「餘額查詢,傳送」時,語音輸入單元111接收使用者的話語(即語音訊號),並經由語音分析模組112a進行分析,從而產生文字訊號「餘額查詢,傳送」。如此,因為所產生的文字訊號中包含與所設定之「預設文字」相同之「傳送」,即將已產生的文字訊號「餘額查詢」傳送至處理主機120。It should be understood that an application 112b may be installed in the electronic device 110 for voice signal transmission for the purpose of more convenient use. Specifically, the application 112b is stored in the second storage unit 112. The user has to operate to cause the second processor 113 to execute the application 112b. In the case where the application 112b is executed by the second processor 113, when the speech analysis module 112a generates the same text signal as a predetermined text, the transmission of the generated text signal is performed. For example, the "preset text" may be "transfer". When the user speaks "balance inquiry, transmission", the voice input unit 111 receives the user's utterance (ie, voice signal) and analyzes it via the voice analysis module 112a, thereby generating a text message "balance inquiry, transmission". In this way, since the generated text signal includes the same "transfer" as the set "preset text", the generated text signal "balance inquiry" is transmitted to the processing host 120.
在一實施例中,電子裝置110進一步包括顯示單元115。在連結關係上,第二處理器113電性連接至顯示單元115。如上所述,當語意辨識模組122a進行文字訊號與多個指令選項的匹配而產生的信心指數大於預設值時,第一處理器123執行對應的指令選項的動作。進一步地,在第一處理器123執行對應的指令選項的動作之後,可回傳一執行結果至電子裝置110,從而顯示單元115可顯示此回傳的執行結果。舉例來說,當傳送至處理主機120的文字訊號「餘額查詢」經語意辨識模組122a匹配到信心指數大於預設值之指令選項,並且第一處理器123執行此指令選項的動作(即進行餘額查詢)之後,回傳的執行結果(例如帳戶中的活存餘額)可藉由顯示單元115來顯示,從而使用者得知悉回傳的執行結果內容。在一實施例中,顯示單元115可為液晶顯示器、陰極射線管顯示器、電子紙顯示器或其他顯示裝置。In an embodiment, the electronic device 110 further includes a display unit 115. In the connection relationship, the second processor 113 is electrically connected to the display unit 115. As described above, when the confidence index generated by the semantic recognition module 122a matching the text signal and the plurality of command options is greater than the preset value, the first processor 123 performs the action of the corresponding command option. Further, after the first processor 123 performs the action of the corresponding instruction option, an execution result may be returned to the electronic device 110, so that the display unit 115 may display the execution result of the backhaul. For example, when the text message "balance inquiry" transmitted to the processing host 120 is matched by the semantic recognition module 122a to an instruction option whose confidence index is greater than a preset value, and the first processor 123 performs the action of the instruction option (ie, performs After the balance inquiry, the execution result of the return (for example, the live balance in the account) can be displayed by the display unit 115, so that the user knows the content of the execution result of the return. In an embodiment, the display unit 115 can be a liquid crystal display, a cathode ray tube display, an electronic paper display, or other display device.
在一實施例中,電子裝置110進一步包括播放單元116。在連結關係上,第二處理器113電性連接至播放單元116。如上所述,可在電子裝置110中安裝一應用程式112b。在一實施例中,所述應用程式112b儲存於第二儲存單元112,且係用以產生語音撥放訊號。詳細而言,在應用程式112b被第二處理器113執行的情況下,應用程式112b可產生對應回傳的執行結果之語音撥放訊號,並且播放單元116可撥放此語音撥放訊號。例如,回傳的執行結果為帳戶中的活存餘額,則應用程式112b可針對此回傳的執行結果產生一語音撥放訊號(例如活存餘額的量的語音)。因此,播放單元116可撥放此語音撥放訊號,從而使用者得不用觀看顯示螢幕,即可知悉回傳的執行結果內容。在一實施例中,播放單元116可為喇叭或揚聲器。In an embodiment, the electronic device 110 further includes a playing unit 116. In the connection relationship, the second processor 113 is electrically connected to the playing unit 116. As described above, an application 112b can be installed in the electronic device 110. In an embodiment, the application 112b is stored in the second storage unit 112 and is used to generate a voice dialing signal. In detail, in the case that the application 112b is executed by the second processor 113, the application 112b can generate a voice dialing signal corresponding to the execution result of the backhaul, and the playing unit 116 can play the voice dialing signal. For example, if the execution result of the backhaul is the live balance in the account, the application 112b may generate a voice dialing signal (for example, the voice of the amount of the live balance) for the execution result of the backhaul. Therefore, the playing unit 116 can play the voice dialing signal, so that the user can know the content of the execution result of the backhaul without viewing the display screen. In an embodiment, the playback unit 116 can be a speaker or a speaker.
如上所述,語意辨識模組122a進行文字訊號與資料庫122b中的多個指令選項的匹配,從而產生對應所述多個指令選項的多個信心指數。在一實施例中,當多個信心指數皆小於預設值時,回傳所述多個信心指數中數值較高的3至5個所對應的指令選項至電子裝置110。亦即,回傳與文字訊號最相似的3至5個指令選項至電子裝置110。因此,雖然多個信心指數皆低於預設值而不予執行最接近的指令選項,但使用者藉此能知悉最相似的3至5個指令選項,進而可思考下一步動作,例如為執行此3至5個指令選項之一者,或進行別的操作。另外,作為使用者知悉最相似的3至5個指令選項的方式可為視覺方式或聽覺方式。舉例來說,在電子裝置110包括顯示單元115的實施例中,顯示單元115可顯示此3至5個指令選項,從而使用者可經由視覺方式知悉指令選項。或者,在電子裝置110包括播放單元116的實施例中,儲存於第二儲存單元112的應用程式112b產生對應此3至5個指令選項之一語音撥放訊號(例如講解各指令選項的語音)。接著,播放單元116可撥放此語音撥放訊號,從而使用者得經由聽覺方式知悉指令選項。As described above, the semantic recognition module 122a performs matching of the text signal with a plurality of instruction options in the database 122b, thereby generating a plurality of confidence indices corresponding to the plurality of instruction options. In an embodiment, when the plurality of confidence indexes are less than the preset value, 3 to 5 corresponding instruction options having higher values among the plurality of confidence indexes are returned to the electronic device 110. That is, 3 to 5 instruction options most similar to the text signal are returned to the electronic device 110. Therefore, although multiple confidence indices are lower than the preset value and the closest instruction option is not executed, the user can know the most similar 3 to 5 instruction options, and then can think about the next action, for example, for execution. One of these 3 to 5 command options, or perform other operations. In addition, the manner in which the user knows the most similar 3 to 5 command options may be visual or audible. For example, in an embodiment where the electronic device 110 includes the display unit 115, the display unit 115 can display the 3 to 5 instruction options such that the user can visually know the instruction options. Alternatively, in the embodiment where the electronic device 110 includes the playing unit 116, the application 112b stored in the second storage unit 112 generates a voice dialing signal corresponding to one of the 3 to 5 command options (for example, a voice explaining each command option). . Then, the playing unit 116 can play the voice dialing signal, so that the user can know the command options via the hearing.
在一實施例中,電子裝置110進一步包括輸入單元117。在連結關係上,第二處理器113電性連接至輸入單元117。在一實施例中,輸入單元117可為觸控裝置、鍵盤、滑鼠或其他輸入元件。如上所述,使用者知悉最相似的3至5個指令選項之後,可執行此3至5個指令選項中之一者。詳細而言,使用者得藉由輸入單元117輸入一輸入訊號,並傳送至處理主機120以選擇回傳的指令選項。舉例而言,使用者透過輸入單元117點選顯示單元115上所呈現的3至5個指令選項,使得輸入訊號(點選的指令選項的訊號)被傳送至處理主機120,從而第一處理器123可執行所點選的指令選項的動作。In an embodiment, the electronic device 110 further includes an input unit 117. In the connection relationship, the second processor 113 is electrically connected to the input unit 117. In an embodiment, the input unit 117 can be a touch device, a keyboard, a mouse, or other input element. As described above, one of the 3 to 5 instruction options can be executed after the user knows the most similar 3 to 5 instruction options. In detail, the user has to input an input signal through the input unit 117 and transmit it to the processing host 120 to select the returned command option. For example, the user selects 3 to 5 instruction options presented on the display unit 115 through the input unit 117, so that the input signal (the signal of the selected instruction option) is transmitted to the processing host 120, so that the first processor 123 can perform the action of the selected instruction option.
可替代地,亦可藉由儲存於第二儲存單元112的應用程式112b來進行聲控訊號傳送以選擇回傳的指令選項。具體而言,在應用程式112b被第二處理器113執行的情況下,當語音分析模組112a產生與一預設文字相同之文字訊號時,進行已產生的文字訊號之傳送,從而選擇回傳的指令選項。舉例來說,所述「預設文字」可為「傳送」,而最相似的3至5個指令選項例如為「餘額查詢」、「轉帳查詢」、以及「繳費查詢」。當使用者說出「餘額查詢,傳送」時,語音輸入單元111接收使用者的話語(即語音訊號),並經由語音分析模組112a進行分析,從而產生文字訊號「餘額查詢,傳送」。如此,因為所產生的文字訊號中包含與所設定之「預設文字」相同之「傳送」,即將已產生的文字訊號「餘額查詢」傳送至處理主機120,從而第一處理器123可執行所選擇的指令選項(餘額查詢)的動作。Alternatively, the voice signal transmission may be performed by the application 112b stored in the second storage unit 112 to select the returned command option. Specifically, when the application 112b is executed by the second processor 113, when the speech analysis module 112a generates the same text signal as the preset text, the transmission of the generated text signal is performed, thereby selecting the return. Instruction options. For example, the "preset text" may be "transfer", and the most similar 3 to 5 command options are, for example, "balance inquiry", "transfer inquiry", and "payment inquiry". When the user speaks "balance inquiry, transmission", the voice input unit 111 receives the user's utterance (ie, voice signal) and analyzes it via the voice analysis module 112a, thereby generating a text message "balance inquiry, transmission". In this way, since the generated text signal includes the same "transfer" as the set "preset text", the generated text signal "balance inquiry" is transmitted to the processing host 120, so that the first processor 123 can execute the The action of the selected command option (balance inquiry).
為了詳加敘述智能語音交易系統100的運作方式,以下將搭配第2A圖和第2B圖來做說明。第2A圖和第2B圖繪示智能語音交易系統的運作方法200的流程圖。應瞭解到,在第2A圖和第2B圖中所提及的步驟,除特別敘明其順序者外,均可依實際需要調整其前後順序,亦可同時或部分同時執行,甚至可增加額外步驟或省略部份步驟。In order to describe in detail the operation of the intelligent voice transaction system 100, the following description will be made with reference to FIGS. 2A and 2B. 2A and 2B are flow diagrams illustrating a method 200 of operation of an intelligent voice transaction system. It should be understood that the steps mentioned in Figures 2A and 2B can be adjusted according to actual needs, except for the order in which they are specifically stated. They can also be executed simultaneously or partially simultaneously, and even additional Step or omit some steps.
首先,請同時參照第1圖、第2A圖、以及第2B圖,於步驟201中,使用者開啟電子裝置110的應用程式112b(例如銀行應用程式)。舉例而言,使用者可透過輸入單元117點選顯示單元115上所呈現的應用程式112b的圖標(icon),從而第二處理器113執行儲存於第二儲存單元112的應用程式112b。接著,在步驟202中,電子裝置110的語音輸入單元111接收一語音訊號。接下來,於步驟203中,第二處理器113執行語音分析模組112a以分析語音訊號,從而產生一文字訊號。接著,於步驟204中,此文字訊號通過通訊連結L1傳送至處理主機120。隨後,於步驟205中,第一處理器123執行語意辨識模組122a以進行文字訊號與資料庫122b中的多個指令選項的匹配,從而產生對應多個指令選項的多個信心指數。First, please refer to FIG. 1 , FIG. 2A, and FIG. 2B simultaneously. In step 201, the user opens an application 112b (eg, a banking application) of the electronic device 110. For example, the user can click the icon of the application 112b presented on the display unit 115 through the input unit 117, so that the second processor 113 executes the application 112b stored in the second storage unit 112. Next, in step 202, the voice input unit 111 of the electronic device 110 receives a voice signal. Next, in step 203, the second processor 113 executes the speech analysis module 112a to analyze the speech signal to generate a text signal. Then, in step 204, the text signal is transmitted to the processing host 120 through the communication link L1. Then, in step 205, the first processor 123 executes the semantic recognition module 122a to perform matching of the text signal with the plurality of instruction options in the database 122b, thereby generating a plurality of confidence indices corresponding to the plurality of instruction options.
若多個信心指數中之一者大於一預設值,於步驟206中,第一處理器123執行大於預設值之信心指數所對應的指令選項的動作,並回傳一執行結果至電子裝置110。應理解,在電子裝置110包括顯示單元115的實施例中,顯示單元115可顯示回傳的執行結果。或者,在電子裝置110包括播放單元116的實施例中,應用程式112b產生對應回傳的執行結果之語音撥放訊號,並且播放單元116可撥放此語音撥放訊號。If one of the plurality of confidence indexes is greater than a preset value, in step 206, the first processor 123 performs an action of the command option corresponding to the confidence index of the preset value, and returns an execution result to the electronic device. 110. It should be understood that in an embodiment in which the electronic device 110 includes the display unit 115, the display unit 115 may display the execution result of the postback. Alternatively, in an embodiment where the electronic device 110 includes the playback unit 116, the application 112b generates a voice dialing signal corresponding to the execution result of the backhaul, and the playing unit 116 can play the voice dialing signal.
另一方面,若多個信心指數皆小於預設值,於步驟207中,回傳多個信心指數中數值較高的3至5個所對應的指令選項至電子裝置110。類似地,在電子裝置110包括顯示單元115的實施例中,顯示單元115可顯示回傳的3至5個指令選項。或者,在電子裝置110包括播放單元116的實施例中,應用程式112b產生對應回傳的3至5個指令選項之語音撥放訊號,並且播放單元116可撥放此語音撥放訊號。接下來,於步驟208中,使用者可藉由語音輸入單元111進行聲控訊號傳送,或藉由輸入單元117輸入訊號,並傳送至處理主機120以選擇回傳的指令選項。On the other hand, if the plurality of confidence indexes are all smaller than the preset value, in step 207, 3 to 5 corresponding instruction options having higher values among the plurality of confidence indexes are returned to the electronic device 110. Similarly, in embodiments where the electronic device 110 includes the display unit 115, the display unit 115 can display 3 to 5 instruction options for the return. Alternatively, in the embodiment where the electronic device 110 includes the playing unit 116, the application 112b generates a voice dialing signal corresponding to the returned 3 to 5 command options, and the playing unit 116 can play the voice dialing signal. Next, in step 208, the user can perform voice signal transmission by the voice input unit 111, or input the signal through the input unit 117, and transmit to the processing host 120 to select the returned command option.
綜上所述,本新型的智能語音交易系統,提供了系統性、且合適的智能語音交易方法,有助於改善手動操作之繁雜手續問題,讓一些特定使用者(例如老人)得以更簡單的操作,進而完成其業務目的。並且,藉由語音撥放方式,使用者得不用觀看顯示螢幕,即可知悉回傳的執行結果,讓一些特定使用者(例如視障人士)亦得進行操作。此外,藉由此系統,將更快速、正確地執行使用者之業務目的,提昇作業效率,避免需要依照所顯示之各階層選項,一層一層地選擇之耗費時間問題。In summary, the novel intelligent voice transaction system provides a systematic and suitable intelligent voice transaction method, which helps to improve the complicated procedures of manual operation, and makes some specific users (such as the elderly) easier. Operation to complete its business purposes. Moreover, by means of voice dialing, the user can know the execution result of the backhaul without having to watch the display screen, so that some specific users (such as visually impaired persons) also have to operate. In addition, with this system, the user's business purpose will be executed more quickly and correctly, the work efficiency is improved, and the time-consuming problem of selecting one layer at a time according to the various hierarchical options displayed is avoided.
雖然本新型已以實施方式揭露如上,然其並非用以限定本新型,任何熟習此技藝者,於不脫離本新型之精神和範圍內,當可作各種之更動與潤飾,因此本新型之保護範圍當視後附之申請專利範圍所界定者為準。Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention. Any one skilled in the art can make various changes and retouchings without departing from the spirit and scope of the present invention. The scope is subject to the definition of the scope of the patent application attached.
為讓本新型之上述和其他目的、特徵、優點與實施例能更明顯易懂,所附符號之說明如下:
100‧‧‧智能語音交易系統
110‧‧‧電子裝置
111‧‧‧語音輸入單元
112‧‧‧儲存單元
112a‧‧‧語音分析模組
112b‧‧‧應用程式
113‧‧‧處理器
114‧‧‧傳輸單元
115‧‧‧顯示單元
116‧‧‧播放單元
117‧‧‧輸入單元
120‧‧‧處理主機
122‧‧‧儲存單元
122a‧‧‧語意辨識模組
122b‧‧‧資料庫
123‧‧‧處理器
124‧‧‧傳輸單元
200‧‧‧方法
201~208‧‧‧步驟
L1‧‧‧通訊連結The above and other objects, features, advantages and embodiments of the present invention will become more apparent and understood.
100‧‧‧Intelligent Voice Trading System
110‧‧‧Electronic devices
111‧‧‧Voice input unit
112‧‧‧storage unit
112a‧‧‧Voice Analysis Module
112b‧‧‧Application
113‧‧‧ Processor
114‧‧‧Transportation unit
115‧‧‧Display unit
116‧‧‧Play unit
117‧‧‧ input unit
120‧‧‧Processing host
122‧‧‧storage unit
122a‧‧‧Speech Identification Module
122b‧‧‧Database
123‧‧‧ processor
124‧‧‧Transmission unit
200‧‧‧ method
201~208‧‧‧Steps
L1‧‧‧Communication link
為讓本新型之上述和其他目的、特徵、優點與實施例能更明顯易懂,所附圖式之說明如下: 第1圖為根據本揭示內容之一實施例之一種智能語音交易系統100的方塊圖; 第2A圖和第2B圖為根據本揭示內容之一實施例之一種智能語音交易系統的運作方法200的流程圖。The above and other objects, features, advantages and embodiments of the present invention will become more apparent and understood. Block Diagram; Figures 2A and 2B are flow diagrams of a method 200 of operation of an intelligent voice transaction system in accordance with an embodiment of the present disclosure.
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW107200209U TWM560646U (en) | 2018-01-05 | 2018-01-05 | Voice control trading system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW107200209U TWM560646U (en) | 2018-01-05 | 2018-01-05 | Voice control trading system |
Publications (1)
Publication Number | Publication Date |
---|---|
TWM560646U true TWM560646U (en) | 2018-05-21 |
Family
ID=62950327
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW107200209U TWM560646U (en) | 2018-01-05 | 2018-01-05 | Voice control trading system |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWM560646U (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI673673B (en) * | 2018-01-05 | 2019-10-01 | 華南商業銀行股份有限公司 | Voice control trading system |
TWI737006B (en) * | 2019-01-31 | 2021-08-21 | 大陸商深圳市商湯科技有限公司 | Cross-modal information retrieval method, device and storage medium |
TWI803815B (en) * | 2021-01-20 | 2023-06-01 | 中華電信股份有限公司 | Interactive natural language processing system and method thereof and computer readable medium |
-
2018
- 2018-01-05 TW TW107200209U patent/TWM560646U/en unknown
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI673673B (en) * | 2018-01-05 | 2019-10-01 | 華南商業銀行股份有限公司 | Voice control trading system |
TWI737006B (en) * | 2019-01-31 | 2021-08-21 | 大陸商深圳市商湯科技有限公司 | Cross-modal information retrieval method, device and storage medium |
TWI803815B (en) * | 2021-01-20 | 2023-06-01 | 中華電信股份有限公司 | Interactive natural language processing system and method thereof and computer readable medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11475898B2 (en) | Low-latency multi-speaker speech recognition | |
US11290834B2 (en) | Determining head pose based on room reverberation | |
US20220406309A1 (en) | Multi-modal inputs for voice commands | |
US11638059B2 (en) | Content playback on multiple devices | |
US20220028387A1 (en) | Application integration with a digital assistant | |
US20200236071A1 (en) | Automated population of deep-linked interfaces during programmatically established chatbot sessions | |
US20190027147A1 (en) | Automatic integration of image capture and recognition in a voice-based query to understand intent | |
US20230222316A1 (en) | Systems and methods for predicting and providing automated online chat assistance | |
US8626511B2 (en) | Multi-dimensional disambiguation of voice commands | |
US20130262123A1 (en) | Computer-Readable Medium, System and Method of Providing Domain-Specific Information | |
TW202008261A (en) | Payment processing method and device | |
WO2019024692A1 (en) | Speech input method and device, computer equipment and storage medium | |
US20210349948A1 (en) | Automated population of digital interfaces based on dynamically generated contextual data | |
TWM560646U (en) | Voice control trading system | |
US11689484B2 (en) | Dynamic configuration and population of digital interfaces during programmatically established chatbot sessions | |
KR20240021834A (en) | Method, apparatus, and system for dynamically navigating interactive communication systems | |
CN110308886A (en) | The system and method for voice command service associated with personalized task are provided | |
WO2020005302A1 (en) | Graphical user interface for a voice response system | |
EP3851803B1 (en) | Method and apparatus for guiding speech packet recording function, device, and computer storage medium | |
TW201931267A (en) | Voice control trading system | |
JP2020004192A (en) | Communication device and voice recognition terminal device with communication device | |
CN117882365A (en) | Verbal menu for determining and visually displaying calls | |
TWI770395B (en) | Device and method of a voice-activated banking transfer application on a tv | |
US10055749B2 (en) | Local contextual display | |
JP2020190797A (en) | Data processing device, data processing method, data processing program, control program, and terminal device |