TWI761765B - Acoustic fingerprinting access control system - Google Patents
Acoustic fingerprinting access control system Download PDFInfo
- Publication number
- TWI761765B TWI761765B TW109104886A TW109104886A TWI761765B TW I761765 B TWI761765 B TW I761765B TW 109104886 A TW109104886 A TW 109104886A TW 109104886 A TW109104886 A TW 109104886A TW I761765 B TWI761765 B TW I761765B
- Authority
- TW
- Taiwan
- Prior art keywords
- communication module
- processor
- preset
- voice
- signal
- Prior art date
Links
Images
Landscapes
- Lock And Its Accessories (AREA)
Abstract
Description
本發明是關於一種聲紋辨識門禁管理系統,特別是關於一種藉由雲端伺服器中的處理器進行判斷流程以辨識聲紋的門禁管理系統。 The present invention relates to a voiceprint recognition access control management system, in particular to an access control management system that uses a processor in a cloud server to perform a judgment process to identify voiceprints.
門鎖是居家安全的第一道防線,從傳統的單一鎖頭乃至於至複雜的複合鎖,目的均是為了保護生命財產。隨著半導體技術的演進,部分的使用者將機械鎖更換為電子鎖,以改善攜帶鑰匙的不便利性。這些電子鎖使用密碼或是指紋辨識技術來辨別使用者。然而,密碼在輸入時有被他人窺視的風險,或是可以根據輸入面板上的痕跡解讀,更進一步地,若密碼太簡單容易被他人猜到,但設定的太難又可能導致使用者本人難以記憶。使用生物特徵的指紋辨識技術對於指紋不明顯或是易流手汗的人而言,也仍有不易辨識的情況存在。 Door locks are the first line of defense for home security. From traditional single locks to complex composite locks, the purpose is to protect life and property. With the evolution of semiconductor technology, some users have replaced mechanical locks with electronic locks to improve the inconvenience of carrying keys. These electronic locks use passwords or fingerprint recognition technology to identify users. However, when the password is entered, there is a risk of being peeped by others, or it can be interpreted according to the traces on the input panel. Further, if the password is too simple, it is easy for others to guess, but the setting is too difficult, which may make it difficult for the user himself. memory. Fingerprint identification technology using biometrics is still difficult to identify for people whose fingerprints are not obvious or who are prone to sweaty hands.
除此之外,電子鎖不見得適用於任何的門,安裝電子鎖時需要考量門的種類、厚度或是居家環境。在這種情況下,一種能夠適合各式大門,且具有良好的生物特徵辨識系統便成為需要解決的議題。 In addition, electronic locks are not necessarily suitable for any door. When installing electronic locks, you need to consider the type, thickness or home environment of the door. In this case, a biometric identification system that can fit all kinds of doors and has a good biometric identification system becomes an issue that needs to be solved.
有鑒於此,本發明提供一種聲紋辨識門禁管理系統,藉由聲紋辨識技術辨識使用者,在不用更換原始門鎖的情況下安裝並實施,以保障居家安全。 In view of this, the present invention provides a voiceprint recognition access control management system, which uses the voiceprint recognition technology to identify users, installs and implements without replacing the original door lock, so as to ensure home security.
有鑑於上述習知之問題,本發明的目的在於提供聲紋辨識門禁管理系統,用以解決習知技術中所面臨之問題。 In view of the above-mentioned conventional problems, the purpose of the present invention is to provide a voiceprint recognition access control management system to solve the problems faced in the conventional technology.
根據本發明之目的,提出一種聲紋辨識門禁管理系統,其包含門鎖裝置、第一語音輸入裝置、雲端伺服器以及居家管理裝置。門鎖裝置設置在居住環境的出入口。第一語音輸入裝置設置在出入口,且包含第一收音模組以及第一通訊模組。第一收音模組接收來自外部的第一語音訊息以產生第一語音訊號,並利用第一通訊模組發送第一語音訊號。雲端伺服器包含第二通訊模組、資料庫以及處理器。第二通訊模組連接第一通訊模組以接收第一語音訊號。資料庫儲存複數個預設聲紋特徵。處理器電性連接第二通訊模組以及資料庫,處理器提取第一語音訊號中的聲紋特徵,並執行判斷流程,判斷流程為比對聲紋特徵是否符合資料庫中的複數個預設聲紋特徵中的一個,當處理器判斷符合時,處理器產生回饋訊號,並利用第二通訊模組發送回饋訊號。居家管理裝置電性連接門鎖裝置並包含第三通訊模組。第三通訊模組連接雲端伺服器以接收回饋訊號,進而居家管理裝置依據回饋訊號控制門鎖裝置開啟。 According to the purpose of the present invention, a voiceprint recognition access control management system is provided, which includes a door lock device, a first voice input device, a cloud server and a home management device. The door lock device is arranged at the entrance and exit of the living environment. The first voice input device is arranged at the entrance and exit, and includes a first radio module and a first communication module. The first radio module receives the first voice message from the outside to generate the first voice signal, and uses the first communication module to send the first voice signal. The cloud server includes a second communication module, a database and a processor. The second communication module is connected to the first communication module to receive the first voice signal. The database stores a plurality of preset voiceprint features. The processor is electrically connected to the second communication module and the database, and the processor extracts the voiceprint feature in the first voice signal, and executes a judgment process, and the judgment process is to compare whether the voiceprint feature conforms to a plurality of presets in the database One of the voiceprint features, when the processor determines that it matches, the processor generates a feedback signal, and uses the second communication module to send the feedback signal. The home management device is electrically connected to the door lock device and includes a third communication module. The third communication module is connected to the cloud server to receive the feedback signal, and then the home management device controls the door lock device to open according to the feedback signal.
較佳地,可進一步包含至少一家電裝置,家電裝置連接居家管理裝置,且資料庫可進一步儲存分別對應各預設聲紋特徵的複數個預設操控指 令,回饋訊號可進一步包含對應於聲紋特徵所符合的預設聲紋特徵的預設操控指令,居家管理裝置依據預設操控指令控制至少一家電裝置運作。 Preferably, it can further include at least one home appliance device, the home appliance device is connected to the home management device, and the database can further store a plurality of preset control commands corresponding to each preset voiceprint feature. Therefore, the feedback signal may further include a preset control instruction corresponding to the preset voiceprint feature matched by the voiceprint feature, and the home management device controls the operation of at least one electrical device according to the preset control instruction.
較佳地,可進一步包含至少一家電裝置,家電裝置連接居家管理裝置,且資料庫可進一步儲存分別對應各預設聲紋特徵的複數個情境資訊,各情境資訊至少包含第一預設情境以及第二預設情境,當在判斷流程判斷符合時,處理器依據第一語音訊號的對話內容,以決定依據第一預設情境的第一操控指令或第二預設情境的第二操控指令而產生包含第一操控指令或第二操控指令的回饋訊號,居家管理裝置依據第一操控指令或第二操控指令控制至少一家電裝置運作。 Preferably, it can further include at least one home appliance device, the home appliance device is connected to the home management device, and the database can further store a plurality of context information corresponding to each preset voiceprint feature, and each context information at least includes a first preset context and In the second preset situation, when it is determined in the judgment process that the process is satisfied, the processor determines the first control command according to the first preset situation or the second control command of the second preset situation according to the dialogue content of the first voice signal. A feedback signal including the first control command or the second control command is generated, and the home management device controls the operation of at least one electrical device according to the first control command or the second control command.
較佳地,可進一步包含設置在居住環境中的第二語音輸入裝置以及至少一家電裝置,且資料庫可進一步儲存複數個特定單詞以及對應各特定單詞的第三預設情境,且各第三預設情境分別包含第三操控指令,第二語音輸入裝置可包含第二收音模組以及第四通訊模組,第二收音模組可接收來居住環境中的第二語音訊息以產生第二語音訊號,並利用第四通訊模組發送第二語音訊號至居家管理裝置並傳送至雲端伺服器,處理器在判斷流程判斷符合時,處理器依據第二語音訊號中的特定單詞,並依據對應的第三操控指令產生控制訊號,且傳送控制訊號至居家管理裝置,居家管理裝置依據控制訊號控制至少一家電裝置運作。 Preferably, it can further include a second voice input device and at least one electrical device set in the living environment, and the database can further store a plurality of specific words and a third preset context corresponding to each specific word, and each third The preset situations respectively include third manipulation commands, the second voice input device may include a second radio module and a fourth communication module, and the second radio module may receive the second voice message in the living environment to generate the second voice signal, and use the fourth communication module to send the second voice signal to the home management device and send it to the cloud server. When the processor judges that the process is consistent, the processor according to the specific word in the second voice signal, and according to the corresponding The third control command generates a control signal, and transmits the control signal to the home management device, and the home management device controls the operation of at least one electrical device according to the control signal.
較佳地,其中資料庫可進一步儲存對應各預設聲紋特徵的使用者帳號,且各使用者帳號分別具有連絡資訊,當處理器執行判斷流程並判斷不符合時,處理器依據連絡資訊發送通知訊號至智慧終端裝置,智慧終端裝置藉由 應用程式以感應觸發行為而產生控制訊號,居家管理裝置依據控制訊號控制門鎖裝置開啟。 Preferably, the database can further store user accounts corresponding to each preset voiceprint feature, and each user account has contact information respectively. When the processor executes the judgment process and judges that it does not match, the processor sends the information according to the contact information. The notification signal is sent to the smart terminal device, and the smart terminal device uses the The application generates a control signal by sensing the trigger behavior, and the home management device controls the door lock device to open according to the control signal.
較佳地,其中處理器可進一步依據控制訊號以將當前的聲紋特徵設定為訪客帳號,使用者帳號的使用權限大於訪客帳號的使用權限,處理器判斷聲紋特徵為使用者帳號時產生對應第三預設情境的第三操控指令。 Preferably, the processor can further set the current voiceprint feature as the guest account according to the control signal, the use authority of the user account is greater than the use authority of the guest account, and the processor generates a corresponding voiceprint feature when it determines that the voiceprint feature is the user account. The third manipulation instruction of the third preset situation.
較佳地,其中各使用者帳號可分別具有權重值,當處理器接收至少二的聲紋特徵時,處理器產生對應至少二的聲紋特徵中具有最高權重值的聲紋特徵的第三操控指令。 Preferably, each user account may have a weight value respectively, and when the processor receives at least two voiceprint features, the processor generates a third manipulation corresponding to the voiceprint feature with the highest weight value among the at least two voiceprint features. instruction.
1、2、3、4、5:聲紋辨識門禁管理系統 1, 2, 3, 4, 5: voiceprint recognition access control management system
10:門鎖裝置 10: Door lock device
20:第一語音輸入裝置 20: First voice input device
201:第一收音模組 201: The first radio module
202:第一通訊模組 202: The first communication module
30:雲端伺服器 30: Cloud server
301:第二通訊模組 301: The second communication module
302:處理器 302: Processor
303:資料庫 303:Database
40:居家管理裝置 40: Home management device
401:第三通訊模組 401: The third communication module
50:家電裝置 50: Appliances
60:第二語音輸入裝置 60: Second voice input device
601:第二收音模組 601: The second radio module
602:第四通訊模組 602: Fourth communication module
70:智慧終端裝置 70: Smart Terminal Device
AF:聲紋特徵 AF: Voiceprint Features
FS:回饋訊號 FS: feedback signal
OI1:第一操控指令 OI1: The first manipulation command
OI2:第二操控指令 OI2: The second manipulation command
OI3:第三操控指令 OI3: The third manipulation command
PAF:預設聲紋特徵 PAF: Preset Voiceprint Features
POI:預設操控指令 POI: Preset manipulation command
PS1:第一預設情境 PS1: The first preset situation
PS2:第二預設情境 PS2: The second preset situation
PS3:第三預設情境 PS3: The third preset situation
VM1:第一語音訊息 VM1: First Voice Message
VM2:第二語音訊息 VM2: Second Voice Message
VS1:第一語音訊號 VS1: The first voice signal
VS2:第二語音訊號 VS2: Second voice signal
為使本發明之技術特徵、內容與優點及其所能達成之功效更為顯而易見,茲將本發明配合附圖,並以實施例之表達形式詳細說明如下:第1圖是根據本發明之聲紋辨識門禁管理系統的第一實施例的示意圖;第2圖是根據本發明之聲紋辨識門禁管理系統的第一實施例的方塊圖;第3圖是根據本發明之聲紋辨識門禁管理系統的第二實施例的方塊圖;第4圖是根據本發明之聲紋辨識門禁管理系統的第三實施例的方塊圖;第5圖是根據本發明之聲紋辨識門禁管理系統的第四實施例的示意圖;第6圖是根據本發明之聲紋辨識門禁管理系統的第四實施例的方塊圖;第7圖是根據本發明之聲紋辨識門禁管理系統的第五實施例的示意圖;第8圖是根據本發明之聲紋辨識門禁管理系統的第五實施例的方塊圖。 In order to make the technical features, content and advantages of the present invention and the effects that can be achieved more obvious, the present invention is hereby combined with the accompanying drawings and described in detail in the form of embodiments as follows: Figure 1 is based on the sound of the present invention Figure 2 is a block diagram of the first embodiment of the voiceprint recognition access control management system according to the present invention; Figure 3 is the voiceprint recognition access control management system according to the present invention. Figure 4 is a block diagram of a third embodiment of the voiceprint recognition access control management system according to the present invention; Figure 5 is a fourth implementation of the voiceprint recognition access control management system according to the present invention. Figure 6 is a block diagram of a fourth embodiment of a voiceprint recognition access control management system according to the present invention; Figure 7 is a schematic diagram of a fifth embodiment of the voiceprint recognition access control management system according to the present invention; 8 is a block diagram of a fifth embodiment of the voiceprint recognition access control management system according to the present invention.
為利貴審查員瞭解本發明之特徵、內容與優點及其所能達成之功效,茲將本發明配合圖式,並以實施例之表達形式詳細說明如下,而其中所使用之圖式,其主旨僅為示意及輔助說明書之用,未必為本發明實施後之真實比例與精準配置,故不應就所附之圖式的比例與配置關係解讀、侷限本發明於實際實施上的權利範圍。 In order to help the examiners understand the features, contents and advantages of the present invention and the effects that can be achieved, the present invention is hereby described in detail as follows in the form of the drawings and embodiments, and the drawings used therein, the gist of the present invention It is only for illustration and auxiliary description, and may not be the real scale and precise configuration after the implementation of the present invention. Therefore, the proportion and configuration relationship of the attached drawings should not be interpreted or limited to the scope of rights of the present invention in actual implementation.
本發明之優點、特徵以及達到之技術方法將參照例示性實施例及所附圖式進行更詳細地描述而更容易理解,且本發明或可以不同形式來實現,故不應被理解僅限於此處所陳述的實施例,相反地,對所屬技術領域具有通常知識者而言,所提供的實施例將使本揭露更加透徹與全面且完整地傳達本發明的範疇,且本發明將僅為所附加的申請專利範圍所定義。 The advantages, features, and technical methods of the present invention will be described in more detail with reference to the exemplary embodiments and the accompanying drawings for easier understanding, and the present invention may be implemented in different forms, so it should not be construed as limited thereto. Instead, the embodiments are provided so that this disclosure will be thorough, complete and complete to convey the scope of the invention to those of ordinary skill in the art, and the invention will only be added defined by the scope of the patent application.
第1圖是根據本發明之聲紋辨識門禁管理系統的第一實施例的示意圖,第2圖是根據本發明之聲紋辨識門禁管理系統的第一實施例的方塊圖。 FIG. 1 is a schematic diagram of the first embodiment of the voiceprint recognition access control management system according to the present invention, and FIG. 2 is a block diagram of the first embodiment of the voiceprint recognition access control management system according to the present invention.
如圖所示,聲紋辨識門禁管理系統1包含門鎖裝置10、第一語音輸入裝置20、雲端伺服器30以及居家管理裝置40。門鎖裝置10設置在居住環境的出入口,居住環境可以是套房、公寓或是透天厝等,而出入口可以是套房的房門、公寓的一樓大門或是透天厝的前門或後門等。門鎖裝置10在這裡是傳統的機械鎖,然而,本實施例不限於此,門鎖裝置10亦可是藉由指紋辨識進行管制的電子鎖,亦即本發明可以應用在各式門鎖上,並不受限於門鎖的種類。
As shown in the figure, the voiceprint recognition access control management system 1 includes a
第一語音輸入裝置20設置在如上所述的出入口,並包含第一收音模組201以及第一通訊模組202。第一收音模組201在這裡是麥克風裝置,用於接收來自外部的第一語音訊息VM1,並利用麥克風裝置中的類比數位轉換器(Analogy to Digital coverter)將第一語音訊息VM1(例如,使用者說出「我到家了」的訊息)轉換為第一語音訊號VS1。接著第一通訊模組202將第一語音訊號VS1發
送至雲端伺服器30。更具體地,第一語音輸入裝置20可以包含一按鈕元件,按鈕元件根據按壓開始感應第一語音訊號VM1。然而,本實施例不限於此,第一語音輸入裝置20也可以是接收到一定音量(例如,大於30dB)就開啟感應模式的裝置,可以不用經由觸碰才開啟。
The first
雲端伺服器30包含第二通訊模組301、處理器302以及資料庫303。第二通訊模組301與第一通訊模組202連接,以接收第一語音訊號VS1。進一步而言,本實施例是藉由第五代通訊技術(5G)連接第二通訊模組301與第一通訊模組202。資料庫303中則儲存有複數個預設聲紋特徵PAF(例如,使用者以及他的家人的聲紋特徵)。
The
處理器302電性連接到第二通訊模組301以及資料庫303。當處理器302接收到第一語音訊號VS1時,處理器302提取第一語音訊號VS1中的聲紋特徵AF,並執行一個判斷流程,這個判斷流程具體實施方式為:比對聲紋特徵AF與資料庫302中的複數個預設聲紋特徵PAF,如果處理器302判斷符合時,處理器302會產生一個回饋訊號FS,再藉由第二通訊模組301發送。聲紋特徵AF參數的提取可以使用線性預測倒譜係數(linear predictive cepstrum coefficient,LPCC)、感知線性預測係數(perceptual linear predictive,PLP)、梅爾倒譜係數(Mel frequency cepstrum coefficient,MFCC)中的一種。而聲紋辨識則主要使用機率模型法中的隱馬爾可夫模型(Hidden Markov Model)。然而,本實施例不限於此,聲紋辨識技術可以是所屬技術領域中具有通常知識者所認知的任何一種方式,其目的在於確認使用者身分。
The processor 302 is electrically connected to the second communication module 301 and the
居家管理裝置40設置在居家環境中,並電性連接到門鎖裝置10。此外,居家管理裝置40包含第三通訊模組401。第三通訊模組401與第二通訊模組301連接,以接收回饋訊號FS。進一步而言,本實施例是藉由第五代通訊技術
(5G)連接第三通訊模組401與第二通訊模組301。當居家管理裝置40接收到回饋訊號VS後據此開啟門鎖裝置10。
The
具體的步驟為,當一使用者在家門口時,對著第一語音輸入裝置20說出第一語音訊息VM1(例如,「我到家了」),第一收音模組201接收後產生第一語音訊號VS1並藉由第一通訊模組202發送至雲端伺服器30。雲端伺服器30藉由第二通訊模組301接收第一語音訊號VS1,再利用處理器302提取出聲紋特徵AF並比對資料庫303中的複數個預設聲紋特徵PAF,當判斷符合時發送回饋訊號FS至居家管理裝置40。居家管理裝置40藉由第三通訊模組401接收回饋訊號FS並據此開啟門鎖裝置10。
The specific steps are: when a user speaks the first voice message VM1 (for example, "I'm home") to the first
透過本實施例中的聲紋辨識門禁管理系統1,使用者可以藉由聲紋辨識技術保障居家安全,且此系統可以適用於各種類型的門鎖裝置10。
Through the voiceprint recognition access control management system 1 in this embodiment, the user can use the voiceprint recognition technology to ensure home security, and the system can be applied to various types of
第3圖是根據本發明之聲紋辨識門禁管理系統的第二實施例的方塊圖。圖式中,相同的元件是由相同的元件符號表示,其可相同或類似於參考第一實施例的描述,因此不再重複說明。 FIG. 3 is a block diagram of a second embodiment of the voiceprint recognition access control management system according to the present invention. In the drawings, the same elements are denoted by the same element symbols, which may be the same or similar to the description with reference to the first embodiment, and thus will not be repeated.
在本實施例中,聲紋辨識門禁管理系統2包含門鎖裝置10、第一語音輸入裝置20、雲端伺服器30、居家管理裝置40以及家電裝置50。家電裝置50連接居家管理裝置40,舉例而言,家電裝置50可以是冷氣、電燈以及音響等。除此之外,雲端伺服器30中的資料庫303,進一步儲存對應預設聲紋特徵PAF的複數個預設操控指令POI,具體地說,複數個預設操控指令POI可以是:開冷氣、開電燈以及開音響。當處理器302執行判斷流程時,判斷符合所產生之回饋訊號FS會包含上述的複數個預設操控指令POI。然而,本實施例不限於上述所提到的指令,且不同的使用者也可以儲存不同的預設操控指令POI,例如,第一使用者的預設操控指令POI為開冷氣,而第二使用者的預設操控指令POI為開電視。
In this embodiment, the voiceprint recognition access control management system 2 includes a
因此,具體的步驟為,當一使用者在家門口時,對著第一語音輸入裝置20說出第一語音訊息VM1(例如,「我到家了」),第一收音模組201接收後產生第一語音訊號VS1並藉由第一通訊模組202發送至雲端伺服器30。雲端伺服器30藉由第二通訊模組301接收第一語音訊號VS1,再利用處理器302提取出聲紋特徵AF並比對資料庫303中的複數個預設聲紋特徵PAF,當判斷符合時發送回饋訊號FS至居家管理裝置40,且回饋訊號FS包含對應於當前聲紋特徵PAF的三個預設操控指令POI:開冷氣、開電燈以及開音響。居家管理裝置40藉由第三通訊模組401接收回饋訊號FS並據此開啟門鎖裝置10,且依據三個預設操控指令POI分別開啟家電裝置50中的冷氣、電燈以及音響。
Therefore, the specific steps are as follows: when a user speaks the first voice message VM1 (for example, "I'm home") to the first
透過本實施例中的聲紋辨識門禁管理系統2,可以根據不同使用者的習慣,讓使用者進入居家環境中時立即營造出舒適的環境,在保障安全的情況下進一步提高使用者感受。 Through the voiceprint recognition access control management system 2 in this embodiment, according to the habits of different users, a comfortable environment can be created immediately when the user enters the home environment, and the user's experience can be further improved under the condition of ensuring safety.
第4圖是根據本發明之聲紋辨識門禁管理系統的第三實施例的方塊圖。圖式中,相同的元件是由相同的元件符號表示,其可相同或類似於參考第一實施例以及第二實施例的描述,因此不再重複說明。 FIG. 4 is a block diagram of a third embodiment of the voiceprint recognition access control management system according to the present invention. In the drawings, the same elements are denoted by the same element symbols, which may be the same or similar to the descriptions with reference to the first embodiment and the second embodiment, and thus the description will not be repeated.
在本實施例中,聲紋辨識門禁管理系統3包含門鎖裝置10、第一語音輸入裝置20、雲端伺服器30、居家管理裝置40以及家電裝置50。在本實施例中,雲端伺服器30中的資料庫303,進一步儲存對應預設聲紋特徵PAF的情境資訊,情境資訊至少包含第一預設情境PS1以及第二預設情境PS2,且第一預設情境PS1包含第一操控指令OI1,第二預設情境PS2包含第二操控指令OI2。舉例而言,第一預設情境PS1可以是使用者預先設定好的對話內容「我到家了」,而第二預設情境PS2則為使用者預先設定好的對話內容「我帶朋友來作客」。對應第一預設情境PS1的第一操控指令OI1為:開臥室冷氣以及開臥室電燈。對應第二預設情境PS2的第二操控指令OI2為:開客廳冷氣、開客廳電燈以及開客廳電
視。當處理器302比對完聲紋特徵AF以及預設聲紋特徵PAF並判斷符合後,處理器302會在依據對話的內容是符合哪一個情境資訊(例如,第一預設情境PS1),發送包含有第一操控指令OI1的回饋訊號FS。使居家管理裝置40依據第一操控指令OI1控制家電裝置50運作。
In this embodiment, the voiceprint recognition access control management system 3 includes a
因此,具體的步驟為,當一使用者在家門口時,對著第一語音輸入裝置20說出第一語音訊息VM1(例如,「我帶朋友來作客」),第一收音模組201接收後產生第一語音訊號VS1並藉由第一通訊模組202發送至雲端伺服器30。雲端伺服器30藉由第二通訊模組301接收第一語音訊號VS1,再利用處理器302提取出聲紋特徵AF並比對資料庫303中的複數個預設聲紋特徵PAF,當判斷符合時,進一步比對對話內容所符合的情境資訊(例如,在這裡是第二預設情境PS2)。雲端伺服器30會發送包含有第二操控指令OI2的回饋訊號FS至居家管理裝置40。居家管理裝置40藉由第三通訊模組401接收回饋訊號FS並據此開啟門鎖裝置10,且依據第二操控指令OI2分別開啟家電裝置50中的客廳冷氣、客廳電燈以及客廳電視。
Therefore, the specific steps are, when a user speaks the first voice message VM1 to the first voice input device 20 (for example, "I brought a friend as a guest") when the user is at the door of the house, the first voice module 201 receives the first voice message VM1. The first voice signal VS1 is generated and sent to the
透過本實施例中的聲紋辨識門禁管理系統3,可以根據預設的情境資訊更進一步的調整要開啟的家電裝置50,讓使用者能夠因應不同的情況。
Through the voiceprint recognition access control management system 3 in this embodiment, the
第5圖是根據本發明之聲紋辨識門禁管理系統的第四實施例的示意圖;第6圖是根據本發明之聲紋辨識門禁管理系統的第四實施例的方塊圖。圖式中,相同的元件是由相同的元件符號表示,其可相同或類似於參考第一實施例至第三實施例的描述,因此不再重複說明。 FIG. 5 is a schematic diagram of a fourth embodiment of the voiceprint recognition access control management system according to the present invention; FIG. 6 is a block diagram of the fourth embodiment of the voiceprint recognition access control management system according to the present invention. In the drawings, the same elements are denoted by the same element symbols, which may be the same or similar to the descriptions with reference to the first to third embodiments, and thus will not be repeated.
如圖所示,聲紋辨識門禁管理系統4包含門鎖裝置10、第一語音輸入裝置20、第二語音輸入裝置60、雲端伺服器30、居家管理裝置40以及家電裝置50。第二語音輸入裝置60設置在居家環境中,並包含第二收音模組601以及第四通訊模組602。第二收音模組601在這裡是設置在居家環境中的麥克風裝
置,用於接收來自外部的第二語音訊息VM2,並利用麥克風裝置中的類比數位轉換器(Analogy to Digital coverter)將第一語音訊息VM2(例如,使用者說出「開冷氣」的訊息)轉換為第二語音訊號VS2。接著第二通訊模組602將第二語音訊號VS2發送至雲端伺服器30。
As shown in the figure, the voiceprint recognition access control management system 4 includes a
除此之外,資料庫303可進一步儲存複數個特定單詞以及對應各該特定單詞的第三預設情境PS3,且第三預設情境PS3包含第三操控指令OI3。舉例而言,這些特定單詞可以是「熱」、「冷」、「亮」、「暗」、「天氣」、「Cold」、「Hot」等用於語音辨識的中文或是英文。但本實施例不限於上述提到的單字或是語言,例如,這些單字也可以是日文或是藉由使用者自行設定的特殊單字。更進一步地,亦可以用機器學習等方式逐漸提高辨識程度。
Besides, the
本實施例的實施步驟為,當一使用者在家中時(例如,在自己的臥室中),對著第二語音輸入裝置60說出第二語音訊息VM2(例如,「太熱了,我想吹冷氣」),第二收音模組601接收後產生第二語音訊號VS2並藉由第四通訊模組602發送至雲端伺服器30。雲端伺服器30藉由第二通訊模組301接收第二語音訊號VS2,再利用處理器602提取出聲紋特徵AF並比對資料庫303中的複數個預設聲紋特徵PAF,當判斷符合時,進一步比對對話內容所符合的情境資訊(例如,提取關鍵字「熱」以及「冷氣」)後,處理器302判斷此情境資訊是屬於第三預設情境PS3,因此產生用於開啟房間冷氣的第三操控指令OI3。雲端伺服器30會發送包含有第三操控指令OI3的回饋訊號FS至居家管理裝置40。居家管理裝置40藉由第三通訊模組401接收回饋訊號FS,且依據第三操控指令OI3開啟家電裝置50中的房間冷氣。
The implementation steps of this embodiment are, when a user is at home (for example, in his bedroom), speaks the second voice message VM2 to the second voice input device 60 (for example, "It's too hot, I think Blowing cold air”), the second voice signal module 601 generates a second voice signal VS2 after receiving it, and sends it to the
透過本實施例中的聲紋辨識門禁管理系統4,讓使用者在居家環境中仍可以享受居家管理裝置的控制效果,並進一步整合家中電器,使生活更加便利。 Through the voiceprint recognition access control management system 4 in this embodiment, the user can still enjoy the control effect of the home management device in the home environment, and further integrates the home appliances to make life more convenient.
第7圖是根據本發明之聲紋辨識門禁管理系統的第五實施例的示意圖(部分裝置並未示出);第8圖是根據本發明之聲紋辨識門禁管理系統的第五實施例的方塊圖。圖式中,相同的元件是由相同的元件符號表示,其可相同或類似於參考第一實施例至第四實施例的描述,因此不再重複說明。 Figure 7 is a schematic diagram of a fifth embodiment of the voiceprint recognition access control management system according to the present invention (some devices are not shown); Figure 8 is a fifth embodiment of the voiceprint recognition access control management system according to the present invention block diagram. In the drawings, the same elements are denoted by the same element symbols, which may be the same or similar to the descriptions with reference to the first to fourth embodiments, and thus will not be repeated.
如圖所示,聲紋辨識門禁管理系統4包含門鎖裝置10、第一語音輸入裝置20、第二語音輸入裝置60、雲端伺服器30、居家管理裝置40、家電裝置50以及智慧終端裝置70。
As shown in the figure, the voiceprint recognition access control management system 4 includes a
在本實施例中,資料庫303可進一步儲存對應預設聲紋特徵PAF中的使用者帳號以及訪客帳號。使用者帳號的使用權限大於訪客帳號的使用權限,舉例而言,使用者帳號具有操控所有的家電裝置50以及門鎖裝置10的權限,而訪客帳號僅有操控部分的家電裝置50的權限。且更具體地,使用者帳號以及訪客帳號更具有一個權重值,當處理器302接受兩個以上的聲紋特徵AF時,處理器會依據較大的權重值執行判斷流程並產生操控指令。例如,一使用者A的聲紋特徵AF是對應權限值70的使用者帳號,使用者B的聲紋特徵AF是對應權限值100的使用者帳號,而使用者C的聲紋特徵AF是對應權限值30的訪客帳號,在這種情況下,使用者C僅能開啟部分的家電裝置50,而當使用者A以及使用者B同時發出「開冷氣」以及「開暖氣」的指令時,處理器302會依據權限值較高的使用者B產生包含「開暖氣」的第三操控指令OI3的回饋訊號FS。
In this embodiment, the
更進一步地,每個使用者帳號還具有一個連絡資訊,當處理器302執行判斷流程判斷不符合時,會依據連絡資訊發送通知訊號到智慧終端裝置70,以提醒使用者有人試圖進入居家環境。這裡的智慧終端裝置70可以是智慧手機、平板電腦或是筆記型電腦等可攜帶式終端。其目的是藉由安裝於智慧終端裝置70上的應用程式監控居家環境的出入口。在收到通知的情況下,使用者
若確認了訪客身份(例如,朋友來訪已先行通知),可透過智慧終端裝置70產生並發送控制訊號到居家管理裝置40以開啟門鎖裝置10。
Furthermore, each user account also has a piece of contact information. When the processor 302 executes the judgment process and judges that it is inconsistent, it will send a notification signal to the
在本實施例中,使用者除了可以透過智慧終端裝置70開啟門鎖裝置10讓訪客進門,亦可以使用智慧終端裝置70上的應用程式將當前訪客的聲紋特徵AF設定為訪客帳號,使訪客的聲紋特徵AF被儲存在資料庫303中,並能夠具有一定權限以開啟家電裝置50或是門鎖裝置10。
In this embodiment, the user can not only open the
因此,具體的實施步驟為,當一訪客對著第一語音輸入裝置20發出第一語音訊息VM1(例如,「您好,我是XXX」),第一收音模組201接收後產生第一語音訊號VS1並藉由第一通訊模組202發送至雲端伺服器30。雲端伺服器30藉由第二通訊模組301接收第二語音訊號VS2,再利用處理器602提取出聲紋特徵AF並比對資料庫303中的複數個預設聲紋特徵PAF,當判斷不符合時,處理器302依據使用者帳號中的連絡資訊發送通知訊號至智慧終端裝置70(例如,使用者的手機),使用者確認訪客身分後,利用應用程式發出控制訊號至居家管理裝置開啟門鎖裝置10,並將訪客的聲紋特徵AF設定為訪客帳號,使訪客具有使用家電裝置50的權限。訪客進到居家環境後即可利用第二語音輸入裝置60控制家電裝置50。
Therefore, the specific implementation steps are, when a visitor sends a first voice message VM1 (for example, "Hello, I'm XXX") to the first
透過本實施例中的聲紋辨識門禁管理系統5,讓使用者可以設立多組帳號以提供不同的人使用聲紋辨識門禁管理系統5,且在同時想要操控家電裝置50或門鎖裝置10的情況下,處理器302可以依照權重值判斷執行哪一道指令,以確立主客關係。
Through the voiceprint recognition access control management system 5 in this embodiment, the user can set up multiple sets of accounts to provide different people using the voiceprint recognition access control management system 5 and want to control the
以上所述之實施例僅係為說明本發明之技術思想及特點,其目的在使熟習此項技藝之人士能夠瞭解本發明之內容並據以實施,當不能以之限定本發明之專利範圍,即大凡依本發明所揭示之精神所作之均等變化或修飾,仍應涵蓋在本發明之專利範圍內。 The above-mentioned embodiments are only to illustrate the technical ideas and characteristics of the present invention, and the purpose is to enable those who are familiar with the art to understand the content of the present invention and implement it accordingly. It should not be used to limit the patent scope of the present invention. That is, all equivalent changes or modifications made according to the spirit disclosed in the present invention should still be covered within the patent scope of the present invention.
1:聲紋辨識門禁管理系統 1: Voiceprint recognition access control management system
10:門鎖裝置 10: Door lock device
20:第一語音輸入裝置 20: First voice input device
201:第一收音模組 201: The first radio module
202:第一通訊模組 202: The first communication module
30:雲端伺服器 30: Cloud server
301:第二通訊模組 301: The second communication module
302:處理器 302: Processor
303:資料庫 303:Database
40:居家管理裝置 40: Home management device
401:第三通訊模組 401: The third communication module
AF:聲紋特徵 AF: Voiceprint Features
FS:回饋訊號 FS: feedback signal
PAF:預設聲紋特徵 PAF: Preset Voiceprint Features
VM1:第一語音訊息 VM1: First Voice Message
VS1:第一語音訊號 VS1: The first voice signal
Claims (5)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109104886A TWI761765B (en) | 2020-02-15 | 2020-02-15 | Acoustic fingerprinting access control system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109104886A TWI761765B (en) | 2020-02-15 | 2020-02-15 | Acoustic fingerprinting access control system |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202133145A TW202133145A (en) | 2021-09-01 |
TWI761765B true TWI761765B (en) | 2022-04-21 |
Family
ID=78777621
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW109104886A TWI761765B (en) | 2020-02-15 | 2020-02-15 | Acoustic fingerprinting access control system |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI761765B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170092276A1 (en) * | 2014-07-31 | 2017-03-30 | Tencent Technology (Shenzhen) Company Limited | Voiceprint Verification Method And Device |
TWM562879U (en) * | 2018-03-29 | 2018-07-01 | 陳澤興 | Wireless door lock device and biometric door lock controlling system having the wireless door lock device |
TWM567456U (en) * | 2018-05-04 | 2018-09-21 | 積佳科技股份有限公司 | Cloud type door access control management system |
TWM571996U (en) * | 2018-12-21 | Active intelligent identification system | ||
TW202001594A (en) * | 2018-06-06 | 2020-01-01 | 崑山科技大學 | Access control system and access control management method including an access controller, an identifier, a cloud server, and a processing module |
-
2020
- 2020-02-15 TW TW109104886A patent/TWI761765B/en active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWM571996U (en) * | 2018-12-21 | Active intelligent identification system | ||
US20170092276A1 (en) * | 2014-07-31 | 2017-03-30 | Tencent Technology (Shenzhen) Company Limited | Voiceprint Verification Method And Device |
TWM562879U (en) * | 2018-03-29 | 2018-07-01 | 陳澤興 | Wireless door lock device and biometric door lock controlling system having the wireless door lock device |
TWM567456U (en) * | 2018-05-04 | 2018-09-21 | 積佳科技股份有限公司 | Cloud type door access control management system |
TW202001594A (en) * | 2018-06-06 | 2020-01-01 | 崑山科技大學 | Access control system and access control management method including an access controller, an identifier, a cloud server, and a processing module |
Also Published As
Publication number | Publication date |
---|---|
TW202133145A (en) | 2021-09-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9043210B1 (en) | Biometric voice command and control switching device and method of use | |
KR100665641B1 (en) | Personal authentication apparatus and personal authentication method | |
KR102002903B1 (en) | Method for certifying speaker and system for recognizing speech | |
TW200837597A (en) | Speech control apparatus and method | |
CN107395352A (en) | Personal identification method and device based on vocal print | |
US20060293891A1 (en) | Biometric control systems and associated methods of use | |
WO2019075794A1 (en) | Voice control method and apparatus, and terminal device | |
CN104952138A (en) | Voice interactive access control system and achievement method thereof | |
US20200098207A1 (en) | Smart locking system with biometrics authentication | |
WO2017181610A1 (en) | Voice unlocking method and device | |
CN107680221A (en) | Door opening method and device, entrance guard device and computer-readable recording medium | |
CN109389711A (en) | Gate inhibition's unlocking method, device, equipment and medium based on living things feature recognition | |
CN109727342A (en) | Recognition methods, device, access control system and the storage medium of access control system | |
WO2018151730A1 (en) | Door access device | |
CN110149618B (en) | Intelligent device access method, device, equipment and medium based on voiceprint authorization | |
US11302130B2 (en) | Smart locking system with biometrics authentication | |
Okafor et al. | Door access control using RFID and voice recognition system | |
TWI761765B (en) | Acoustic fingerprinting access control system | |
KR101181060B1 (en) | Voice recognition system and method for speaker recognition using thereof | |
CN113628367A (en) | Lock control method, device and system, storage medium and electronic equipment | |
Imario et al. | The validated voice recognition measurement of several tribes in Indonesia using easy VR 3.0. Case study: The prototype of automated doors | |
CN112417412A (en) | Bank account balance inquiry method, device and system | |
Agarwal et al. | BRAIN—THE AI (personal voice assistant) | |
CN113963467A (en) | Intelligent door lock control method, control device, intelligent equipment and storage medium | |
Hegde et al. | Illumination enhanced face recognition for smart access system |