TWM610794U - Voice-controlled operating apparatus - Google Patents

Abstract

The present model provides a voice control operation device, which can be installed in a mobile device and includes a database, an acquisition module, a comparison module and a processing module. The database stores a built-in data, which includes built-in voiceprint features and built-in keywords. The capturing module receives voice commands to capture voice features and voice keywords of the voice commands. The comparison module communicates with the database to capture the above-mentioned built-in data, and communicates with the capture module to receive voice voiceprint features and voice keywords, and determine whether the voice voiceprint feature matches any of the built-in voices. The pattern features are similar, and it is determined whether any voice keyword is similar to any built-in keyword. The processing module is a communication connection comparison module, receiving and executing voice commands to output processing results.

Description

Voice control device

The model relates to a voice control operating device, in particular to a voice control operating device installed in a mobile device.

Currently known mobile devices (such as smart phones) can be controlled by voice through applications such as iPhone’s Siri to turn on, turn off, or perform automatic searches. However, the conventional mobile device still cannot use the voice provided by the user to further operate other applications (app). Therefore, the user still needs to stare at the screen and manually input text or commands to continue to operate the application of the conventional mobile device.

Accordingly, how to provide an application program that can be operated without receiving screen information through the user's vision has become a problem to be solved in the technical field.

In order to solve the above-mentioned problems, the embodiment of the present invention develops a voice-controlled operation device, which can be installed in a mobile device to capture the voiceprint features and voice keywords in the voice command by receiving the user's voice command. Then, by comparing whether the user’s voice voiceprint features are consistent with the built-in voiceprint features in the database, we can further determine whether he is the person, instead of manually typing in text or graphic passwords, or using fingerprints or people. Facial features to confirm the authorization technology of the user's identity. When it is determined that it is the user, it is compared whether the voice keyword matches any built-in keyword in the database, so as to further execute the voice command and output the processing result. In this way, the embodiments of the present invention can indeed replace the conventional technology that requires visual and manual operation of application programs, and provide a more user-friendly, more convenient, and at the same time, a voice-controlled operation device that can also take into account data security.

Specifically, the embodiment of the present invention provides a voice control operation device, which can be installed in a computer or a mobile device. The voice control operation device includes a database, an acquisition module, a comparison module, and a processing module. The database is used to store a built-in data, and the built-in data includes a plurality of built-in voiceprint features and a plurality of built-in keywords. The capture module is used to receive a user's voice command to capture and output the voice voiceprint features and voice keywords of the voice command. The comparison module is used to communicate with the database to retrieve the above-mentioned built-in data, and the comparison module is used to communicate with the capture module to receive voice voiceprint features and voice keywords, and determine the above Whether the voice voiceprint feature is the same or similar to any built-in voiceprint feature, and whether any voice keyword is the same or similar to any built-in keyword is determined. The above-mentioned processing module is used to communicate with the comparison module to receive and execute voice commands to output a processing result.

According to an embodiment, when it is determined that the voice voiceprint feature is the same or similar to any built-in voiceprint feature, the comparison module is used to determine whether the voice keyword is the same or similar to any built-in keyword.

According to another embodiment, when it is determined that any voice keyword is the same or similar to any built-in keyword, the processing module is used to execute the voice command.

According to another embodiment, when it is determined that the voice voiceprint feature is the same or similar to any one of the built-in voiceprint features, and when it is determined that the voice keyword is the same or similar to any one of the built-in keywords, The above-mentioned comparison module is used to execute voice commands.

According to another embodiment, the comparison module 230 compares the waveform or frequency spectrum of the voice voiceprint feature to determine whether the voice voiceprint feature is the same or similar to any built-in voiceprint feature.

Based on the above technical features, the embodiments of the present invention have the following effects:

(1) By capturing the voice voiceprint feature in the user's voice command, and comparing it with the built-in voiceprint feature in the database. When the above two have the same voiceprint characteristics, quickly complete the login and the operation can be carried out smoothly. In this way, the embodiments of the present invention can indeed provide a more convenient and safe voice-controlled operating device, and can successfully replace the conventional technology that can only log in to the device visually or manually.

(2) By capturing the voice keywords in the user's voice commands, and comparing them with the built-in keywords in the database. When any of the above two keywords match, the corresponding operation content is quickly executed according to the voice command, and the processing result is output after the execution is completed. In this way, the embodiments of the present invention can indeed provide a more intuitive and user-friendly voice-controlled operating device, without the need to operate the device visually or manually. Accordingly, the embodiments of the present invention can further enable users who have poor visual ability, or who cannot use vision or manual operation in real time, can still operate the device without obstacles.

In view of the above-mentioned problems to be overcome, the embodiments of the present invention develop a voice control operation device, which can be installed in various computers or mobile devices. The voice control operation device receives the user's voice command through the capturing module, so as to further capture the voice voiceprint features and voice keywords in the voice command. Then, through the comparison module, the speech voiceprint features and speech keywords are respectively compared with the built-in data in the database. Then, when the comparison module confirms that the voice voiceprint feature does match the built-in voiceprint feature, and the voice keyword does match any built-in keyword, the processing module will perform the operation corresponding to the voice command content.

In order to more specifically illustrate the various embodiments of the present invention, the following description is supplemented with the accompanying drawings.

Please refer to FIG. 1. FIG. 1 is a flowchart of a voice control operation method according to an embodiment of the present invention. In FIG. 1, according to an embodiment of the present invention, a voice control operation method 100 is provided, which includes the following steps.

First, in step 110, a voice command from a user is received, where the voice command can be understood as any signal transmitted through sound waves. Therefore, more specifically, the above-mentioned voice command may include voice voiceprint features and voice keywords.

Then, in step 120, the voice voiceprint feature of the voice command is captured, so as to further compare the voice voiceprint feature with the built-in voiceprint feature in step 130, and determine whether the voice voiceprint feature matches any one of them. Built-in voiceprint feature. The above-mentioned built-in voiceprint features can be provided in advance by the user, for example, for subsequent comparison with the basic voiceprint features. In this way, it can be determined whether the voice voiceprint feature is from the user himself.

Among them, for example, using a specific length of time as a unit, the voice waveform extracted by cutting for each voice command is regarded as a frame. When the user utters a voice, he can capture the corresponding waveform or spectrum and other voice commands. By analyzing the waveforms of voice voiceprint features and built-in voiceprint features under certain sound frames (such as period, peak and/or trough amplitude, or overall wave shape, etc.), you can compare whether the two have the same waveform , In order to further determine whether it is indeed the user's own voiceprint characteristics.

At the same time, it may be possible to analyze the frequency spectrum of voice voiceprint features and built-in voiceprint features under certain sound frames (such as fundamental frequency, harmonic frequency, or pitch, etc.), that is It can be compared whether the two have the same frequency spectrum to further determine whether it is indeed the user's own voiceprint feature.

Then, in step 131, when it is determined that the waveform or frequency spectrum of the voice voiceprint feature does not match the built-in voice feature, any subsequent actions are stopped, and the voice control operation method is ended.

Or then, in step 132, when it is determined that the waveform or frequency spectrum of the voice voiceprint feature is indeed consistent with the built-in voice feature, that is, the voice command is indeed from the user himself, then continue to capture the voice keywords of the voice command.

Then, in step 140, the captured voice keywords are further compared with the built-in keywords to determine whether the voice keywords are the same as the built-in keywords. For example, the above built-in keywords can be various pre-set keywords, such as operation actions (such as remittance), digital amount (such as 4000 yuan), bank name (such as Bank of Taiwan or Bank of Taiwan, Yushan or Yushan Bank, etc.), account Number (for example, 1234567890), etc. In this way, it is possible to further determine to perform the operation content that the user wants to perform.

Then, in step 131, when it is determined that the built-in keyword does not match any of the built-in keywords, any subsequent actions are stopped, and the voice control operation method is ended.

Or then, in step 141, the voice command is executed according to any of the matching built-in keywords. Then, in step 142, after the execution is completed, for example, the voice command input by the user is "Hello Taiwan Bank, I want to remit 4000 yuan to Yushan account 1234567890", the first voice keyword "remittance" can be retrieved, The second voice keyword "4000 yuan", the third voice keyword "Yushan Bank" and the fourth voice keyword "account 1234567890". Therefore, according to the built-in keywords "remittance", "4000 yuan", "Yushan Bank", "account" and "1234567890", actions such as the voice command "remit 4000 yuan to Yushan account 1234567890" can be performed. Then, after performing an action such as "Remit 4000 RMB to Yushan Account 1234567890", output the processing result such as "The remittance has been completed, the remittance amount is 4000 RMB, the remittance bank is Yushan Bank, and the remittance account is 1234567890" to directly Notify users of the processing status of their voice commands. Or, for example, when the balance of the exported account is insufficient, the processing result such as "Sorry, the account balance is insufficient" can be output to directly notify the user of the processing status of the voice command.

In addition, the above-mentioned processing result can be a text message or a voice message, which is not limited here. When the above processing result is output in the form of voice messages, the above voice control operation method can be completed through voice control all the way, that is, it does not need to be visually or manually performed.

In addition to the above-mentioned voice control operation method, the embodiment of the present invention additionally provides a voice control operation device. Please refer to FIG. 2, which is a schematic diagram of a voice control operation device according to an embodiment of the present invention. In FIG. 2, according to another embodiment of the present invention, a voice control operation device 200 is provided, which can be installed in various computers (such as tablet computers) or mobile devices (such as smart phones or smart watches, etc.). The above-mentioned voice control operation device 200 includes a database 220, an acquisition module 210, a comparison module 230 and a processing module 240.

The above-mentioned database 220 is further explained as follows. The database 220 is used to store a built-in data. The built-in data includes a plurality of built-in voiceprint features and a plurality of built-in keywords. For example, the above-mentioned built-in voiceprint feature may be provided by the user 300 in advance, so as to be stored in the database 200 and used for subsequent further comparison to confirm whether it is the user 300 himself. The details are as mentioned before, so I won't repeat them here.

Regarding the aforementioned capturing module 210, further description is as follows. The capturing module 210 is used to receive a voice command from the user 300, and after capturing the voice command, capture voice features and voice keywords in the voice command. Then, after the voice voiceprint features and voice keywords are successfully captured, the capture module 210 can output the voice voiceprint features and voice keywords, respectively. The details are as mentioned before, so I won't repeat them here.

Regarding the above-mentioned comparison module 230, further description is as follows. The comparison module 230 is used to communicate with the database 220 to retrieve built-in data (including built-in voiceprint features and built-in keywords). In addition, the above-mentioned comparison module 230 is further used to communicate with the capturing module 210 to receive voice voiceprint features and voice keywords. The comparison module 230 can be used to compare and determine whether the voice print feature (such as waveform or spectrum) is the same or similar to any built-in voice print feature (such as waveform or spectrum), and compare and determine any voice. Whether the keyword is the same or similar to any of the built-in keywords. The details are as mentioned before, so I won't repeat them here.

According to an embodiment, when it is determined that the voice voiceprint feature is the same or similar to any built-in voiceprint feature, the comparison module 230 continues to determine whether the voice keyword is the same or similar to any built-in keyword. similar.

The processing module 240 described above is further described as follows. The above-mentioned processing module 240 is used to communicate with the comparison module 230 to receive a voice command, and execute according to the voice command to output a processing result. The details are as mentioned before, so I won't repeat them here.

According to another embodiment, when it is determined that any voice keyword is the same or similar to any built-in keyword, the processing module 240 continues to execute the voice command to output a processing result. The details are as mentioned before, so I won't repeat them here.

In summary, the embodiment of the present invention is capable of extracting voice features and voice keywords in voice commands due to the introduction of the capture module. Through the comparison module, the voice voiceprint feature is compared with the built-in voiceprint feature in the database, and the voice keywords are compared with the built-in keywords in the database. When the voice voiceprint feature is confirmed to be the user, and the voice keyword matches the built-in keyword, the processing module can quickly execute the user's voice command according to the action content corresponding to the voice keyword. As a result, the embodiments of the present invention can indeed provide a voice-controlled operating device, and the user can use such a voice-activated operating device to quickly receive screen information without visually or manually inputting instructions. And convenient operation to complete the content of the action you want to perform.

The present invention is disclosed in the preferred embodiments in this text. However, anyone familiar with the technical field should understand that the above-mentioned embodiments are only used to describe the present invention and are not intended to limit the scope of the patent rights claimed by the present invention. Any changes or substitutions that are equal or equivalent to the above-mentioned embodiments should be interpreted as being covered by the spirit or scope of the present invention. Therefore, the scope of protection of this new model shall be subject to the scope of the following patent applications.

100: Voice control operation method 110-140, 131-132, 141-142: steps 200: Voice-activated operating device 210: Capture module 220: database 230: comparison module 240: Processing module 300: User 400: server

In order to make the above and other objectives, features, advantages and embodiments of the present invention more comprehensible, the description of the attached drawings is as follows: FIG. 1 is a flowchart of a voice control operation method according to an embodiment of the present invention. FIG. 2 is a schematic diagram of a voice control operation device according to an embodiment of the present invention.

200: Voice-activated operating device

210: Capture module

220: database

230: comparison module

240: Processing module

300: User

400: server

Claims (5)

A voice control operating device installed in a computer or mobile device, including: A database, storing a built-in data, the built-in data includes a plurality of built-in voiceprint features and a plurality of built-in keywords; A capturing module that receives a voice command from a user to capture and output a voice voiceprint feature and a plurality of voice keywords of the voice command; A comparison module is communicatively connected to the database to capture the built-in data, and communicatively connected to the capture module to receive the voice voiceprint feature and the voice keywords, and determine the voice voiceprint feature Whether it is the same or similar to any of the built-in voiceprint features, and determine whether any of the speech keywords are the same or similar to any of the built-in keywords; and A processing module is communicatively connected to the comparison module to receive and execute the voice command to output a processing result. The voice control operation device according to claim 1, wherein: The comparison module determines whether the voice keywords are the same or similar to any of the built-in keywords, when determining that the voice voiceprint feature is the same or similar to any of the built-in voiceprint features. The voice control operation device according to claim 1, wherein: The processing module executes the voice command when it is determined that any of the voice keywords is the same or similar to any of the built-in keywords. The voice control operation device according to claim 1, wherein: The processing module executes the voice command, when it is determined that the voice voiceprint feature is the same or similar to any of the built-in voiceprint features, and when it is determined that the voice keyword is the same or similar to any of the built-in keywords . The voice control operation device according to any one of claims 1-4, wherein: The comparison module compares the waveform or frequency spectrum in the voice voiceprint feature to determine whether the voice voiceprint feature is the same or similar to any of the built-in voiceprint features.

Images