TW201810247A - Voiceprint recognition system capable of improving interactivity and data processing method thereof capable of achieving the aim of improving the media watching/listening loyalty by improving the interaction of the user - Google Patents

Abstract

The present invention discloses a voiceprint recognition system capable of improving interactivity, and a data processing method thereof. The method comprises the following steps: a user acquiring audio data of a media played by an audio playing device by virtue of a mobile device provided with an exclusive application program (APP) or acquiring the audio data of the media by virtue of a network, the mobile device acquiring a feature code after analyzing the audio and sending the feature code to a remote server by virtue of the network so as to execute a voiceprint recognition mode, the server sending feedback information with an activity content to the mobile device of the user according to a comparison result, the exclusive application program of the mobile device entering into an interactive information platform according to the feedback information, thus enabling the user to interact with a media practitioner on the information platform or participate in a real-time activity, accordingly, the aim of improving the media watching/listening loyalty by improving the interaction of the user is achieved.

Description

Voiceprint recognition system capable of increasing interaction and data processing method thereof

The invention relates to a voiceprint recognition system, in particular to a voiceprint recognition system and data processing method capable of increasing interaction.

With the advancement of the times, science and technology are changing with each passing day. Modern people ’s viewing / listening habits of the media are very different from those in the past. In the prior art, providers of media can not only play media content through wired / radio video channels, but also online. Media (such as YouTube, advertising broadcast), Internet TV programs or other media platforms, etc. Therefore, the devices that play the aforementioned media include computers, mobile phones, set-top boxes, multimedia players, digital TVs and other devices, but for the provision of media For operators, if they want to provide users with more information services related to the media content they are watching, it is difficult to know what media content they are watching.

For example, China's patent right No. I516100 "Voiceprint of Content Identification" (hereinafter referred to as the former case) is mainly to provide a method for identifying multimedia content sent to a TV, which obtains an audio signal (ie, audio) of a multimedia content. After analysis, a unique voiceprint (ie, audio characteristics) is generated, and then the audio signal is used to query the database content in a server to obtain content information that matches the voiceprint of the audio signal, and is identified by the content information The multimedia content is used to know the media content, related information or publicity media that the user is watching, or to generate an event that is displayed beside the content.

It can be known from the above-mentioned prior art that if the operator wants to provide more related information services, it is necessary to know the media content that the user is watching. Although the previous case provides a method to identify the multimedia content, in order to know the media content that the user is watching, Relevant information or propaganda media, and events appearing on the side of the content, but in fact, users who watch the media may not pay attention to the events on the side, meaning that the information services provided by the media unilaterally are not substantial Effect, and it is even more impossible to confirm whether the user is really interested in the media provided by the industry. Therefore, it is still necessary to propose a better solution to the problems in the prior art.

In view of the above-mentioned shortcomings of the prior art, the main object of the present invention is to provide a voiceprint recognition system and data processing method that can increase interactivity. The audio recognition technology can be used to learn the content of a media that is being viewed / listened, and use the Internet. Road information transmission technology allows users to interact with the provider of the media or to participate in real-time activities established by the provider of the media, thereby increasing the user's interaction and improving the user's adherence to media viewing / listening.

The main technical means adopted to achieve the above purpose is to make the data processing method of the aforementioned voiceprint recognition system capable of increasing interactivity, which is connected to the network through a mobile device installed with a dedicated application (APP), and the action The device performs the following steps: obtains audio from a media; obtains a feature code based on the audio, and sends the feature code to a remote end for identification; receives feedback information with activity content; enters an interactive based on the feedback information Information platform.

According to the foregoing method, the user operates on the mobile device and executes the exclusive application program of the mobile device. When the mobile device receives the audio, the corresponding feature code is obtained according to the content of the audio, and the feature is The code is sent to the remote end for identification in order to exchange the feedback information with the activity content. The mobile device enters the interactive information platform according to the feedback information, and the user can interact with the media industry or participate in real-time on the information platform. Sexual activities, by increasing user interaction to achieve the purpose of improving media viewing / listening adhesion.

In order to achieve the above purpose, another main technical means is to make the aforementioned voiceprint recognition system that can increase interactivity include: a server connected to the network; a mobile device installed with a dedicated application program, and through the network And the server is connected to the server; wherein, when the mobile device executes the exclusive application to obtain audio of a medium, a characteristic code is obtained according to the audio, and the characteristic code is sent to the server for identification; when the action When the device receives feedback information with activity content sent by the server, the device enters an interactive information platform based on the feedback information.

It can be known from the foregoing structure that the user operates the exclusive application on the mobile device. When obtaining the audio of the media, the mobile device obtains the feature code according to the content of the audio, and then sends the feature code to the server The feature code is identified to confirm the content of the audio. When the mobile device receives feedback information with active content generated by the server according to the recognition result, the mobile device enters the interactive information based on the feedback information. The information platform allows users to interact with the media industry or participate in real-time activities on the information platform, by increasing the user's interaction to achieve the purpose of improving media viewing / listening adhesion.

For a preferred embodiment of the voiceprint recognition system capable of increasing interactivity of the present invention, please refer to FIG. 1, which includes a mobile device 10 on the user side and a server 20 on the remote side, and is further described in this embodiment. Includes an audio playback device 30; the mobile device 10 is installed with a dedicated application (APP) and is connected to the server 20 via the network. The server 20 can be used by more than one media operator to preset most of Media related information.

The user can hold the mobile device 10 to operate and execute the dedicated application in a place, and the audio playback device 30 is playing audio of media (immediate media content, such as television, radio, etc.) belonging to one of the media operators, Alternatively, the user can directly play the audio (non-immediate media content, such as YouTube, advertisement, etc.) of another media that the media operator puts on the network through the mobile device 10 directly.

When the mobile device 10 obtains the audio of the media, the mobile device 10 obtains a signature based on the content of the audio, and sends the signature to the server 20 through the network to identify the signature, the server The device 20 executes a voiceprint recognition mode, and after the recognition is completed, generates feedback information with active content according to the recognition result, and transmits the feedback information to the user via the network.

When the user ’s mobile device 10 receives feedback information with activity content sent by the server 20, the exclusive application of the mobile device 10 is based on the content of the feedback information and causes the user to pass the action through the network The device 10 enters an interactive information platform 40. Therefore, users can directly interact with the media or participate in real-time activities established by the media industry on the information platform 40. By increasing the user's interaction with the media, Improve users' stickiness to media viewing / listening.

In this embodiment, the mobile device 10 may be a computer device such as a smart phone, a tablet computer, a portable electronic device, and the audio playback device 30 may be a digital television, a computer device, or a multimedia player. The information platform 40 can be presented in the form of a web page, and provided by the server 20.

According to the specific application method of the above-mentioned preferred embodiment of the present invention, a data processing method for a voiceprint recognition system that can increase interactivity can be further provided, which is mainly composed of the mobile device 10 installed with the foregoing dedicated application program and the network through the network. The server 20 is connected, and the server 20 receives the media-related information including the characteristic code provided by the media operator. As shown in FIG. 2, the method includes the following steps: The aforementioned audio playback device 30 continuously plays a media audio at a near end ( S21), and the user holds the mobile device 10 to obtain the audio of the media; in this embodiment, the user can also directly play the audio of the media placed by the media operator on the network through the mobile device 10 and use the action The device 10 captures the audio; uses the mobile device 10 to obtain a feature code according to the audio, and sends the feature code and audio to the remote server 20 for identification (S22); when the server 20 receives the feature Code and audio, execute a voiceprint recognition mode (S23), and generate feedback information with active content according to the comparison result between the feature code and media related information And transmitting the feedback information to the user's mobile device 10 (S24,); received by the feedback information of the mobile device 10 having active content, based on the feedback information into the interactive information with a platform 40 (S25).

In this embodiment, when the above steps are executed to the step of “execute a voiceprint recognition mode (S23)”, as shown in FIG. 3, the server 20 further executes the following sub-steps: providing a real-time database for comparison Pair (S231); in this embodiment, the real-time database has a data temporary storage area to store media-related information for real-time comparison; provide a non-real-time database for comparison (S232); this implementation In the example, the non-real-time database stores most of the media-related information used for non-real-time comparison in advance; by comparing the received feature code and audio with media-related information, to identify the media that the user is watching ( S233). According to the comparison result, corresponding feedback information is generated (S234). The step of "sending the feedback information to the user (S24)" in the above steps is continued.

In this embodiment, when the above steps are performed to the step of "receiving the feedback information with activity content by the mobile device 10 and entering an interactive information platform 40 (S25) according to the feedback information", as shown in FIG. 4 As shown, the mobile device 10 further executes the following sub-steps: receiving the feedback information with activity content (S251), and according to the content of the feedback information and connecting to an information platform with a gathering function through a network, a chat room Function information platform, an information platform with a message function, or an information platform with a product shopping guide function; when the feedback information is a point discount coupon information or an event ticket information, enter the aforementioned information platform with a collection function ( S252), and for the user to use the points or tickets obtained through the feedback information according to the activity content provided by the operator on the information platform with the gathering function; when the feedback information is the permission information of a chat room (Such as a password), enter the aforementioned information platform with chat room function (S253), so that users can communicate with them in the instant chat room. He watched / listened to the same media users and operators to interact with each other. When the feedback information is an instant broadcast information, he enters the aforementioned information platform with a message function (S254), and the content of the instant broadcast information passes the message function. Information platform audit, if approved, broadcast in the form of marquee on real-time media; when the feedback information is an advertisement product information, enter the aforementioned information platform with a shopping guide function (S255) for user reference The operator places the corresponding product page on the information platform with the function of shopping guide.

The server 20 of the above-mentioned preferred embodiment of the present invention identifies the media that the user is watching / listening to, and returns the feedback information to the user's mobile device 10 so that the user can directly connect with the information platform 40 and Media interaction or participating in real-time activities established by media operators to increase user interaction with the media and increase user adhesion to media viewing / listening.

10‧‧‧ mobile device
20‧‧‧Server
30‧‧‧Audio playback device
40‧‧‧Information Platform

FIG. 1 is a system architecture diagram of a preferred embodiment of the present invention. FIG. 2 is a flowchart of a data processing method according to a preferred embodiment of the present invention. FIG. 3 is a flowchart of a voiceprint recognition mode according to a preferred embodiment of the present invention. FIG. 4 is a flowchart of a real-time activity mode according to a preferred embodiment of the present invention.

10‧‧‧ mobile device

20‧‧‧Server

30‧‧‧Audio playback device

40‧‧‧Information Platform

Claims (10)

A data processing method for a voiceprint recognition system capable of increasing interactivity, which is connected to a network through a mobile device installed with a dedicated application program, and the mobile device executes the following steps: obtaining audio of a media; obtaining according to the audio A feature code, and sends the feature code to a remote end for identification; receives a feedback information with activity content; and enters an interactive information platform based on the feedback information. As described in claim 1, the data processing method of the voiceprint recognition system capable of increasing interactivity, when the remote end receives the feature code, a voiceprint recognition mode is executed, and the active content is generated according to the comparison result. Feedback information, and send the feedback information to the mobile device. As described in claim 2, the data processing method of the voiceprint recognition system that can increase interactivity. When the above steps are performed to the step of "executing a voiceprint recognition mode", the method further includes the following sub-steps: providing an instant database Compare and store real-time media-related information; Provide a non-real-time database for comparison, pre-store most non-real-time media-related information; compare this feature code with media-related information to identify users The media being watched. As described in claim 1, the data processing method of the voiceprint recognition system capable of increasing interaction, when the above steps are performed to the step of "entering an interactive information platform based on the feedback information", the method further includes the following sub-steps : Receiving the feedback information with activity content; linking to an information platform with a gathering function, an information platform with a chat room function, an information platform with a message function, or an information platform with a shopping guide function according to the feedback information. The data processing method of the voiceprint recognition system capable of increasing interaction as described in claim 4, wherein when the feedback information is a point discount coupon information or an event coupon information, it enters the aforementioned information platform with a collection function. The data processing method of the voiceprint recognition system capable of increasing interactivity as described in claim 4, wherein when the feedback information is permission information of a chat room, enter the aforementioned information platform with a chat room function. The data processing method of the voiceprint recognition system capable of increasing interactivity as described in claim 4, wherein when the feedback information is real-time broadcast information, the information platform with a message function is entered. The data processing method of the voiceprint identification system capable of increasing interactivity as described in claim 4, wherein when the feedback information is an advertisement product information, the information platform having the function of shopping guide of goods is entered. A voiceprint recognition system capable of increasing interactivity includes: a server connected to a network; a mobile device installed with a dedicated application and connected to the server through the network; wherein, when the action The device executes the exclusive application program to obtain audio of a media, then obtains a feature code according to the audio, and sends the feature code to the server for identification; when the mobile device receives the server sends an active content Feedback information, based on the feedback information, enter an interactive information platform. The interactive voiceprint recognition system according to claim 9, further comprising an audio playback device, which plays the audio to the mobile device in real time.