CN111402869B - Multi-voice mode man-machine dialogue system - Google Patents

Abstract

The invention discloses a man-machine dialogue system with multiple voice modes, which solves the problem that the voice mode of the traditional voice interaction system is single, and the technical scheme is characterized in that a calling module is used for calling voice data in a storage module and sending the voice data to a voice interaction module; the audio input module can collect voice information of a user, and the audio output module can output the content replied by the voice interaction module in a voice mode, so that voice interaction between the voice interaction module and the user is realized.

Description

Multi-voice mode man-machine dialogue system

technical field

The invention relates to a voice interaction system, in particular to a multi-voice mode man-machine dialogue system.

Background technique

Intelligent voice interaction is a new generation of interaction mode based on voice input. You can get feedback results by speaking. Voice assistant is a typical application scenario. However, in the actual application process, when the voice interaction system interacts with the user, its vocalization form is too single, resulting in limited application scenarios, so there is still room for improvement.

Contents of the invention

The purpose of the present invention is to provide a multi-voice mode man-machine dialogue system capable of switching voice modes according to application scenarios.

Above-mentioned technical purpose of the present invention is achieved through the following technical solutions:

A multi-voice mode human-machine dialogue system, including an audio input module, a control module and an audio output module coupled in sequence; the control module includes a voice interaction module, a storage module, a switching module and a calling module, and the storage module There are a plurality of voice data in different voice forms pre-stored in it; the audio input module is used to collect the voice information of external users and send the information to the voice interaction module, and the call module is used to call the voice data in the storage module And send to the voice interaction module, the voice interaction module performs voice interaction with the user through the audio output module according to the received voice information and voice data; the switching module is used to switch the voice data retrieved by the calling module.

By adopting the above solution, the user can select voice data packets in different voice forms during voice interaction with the voice interaction module, so that the audio output module can communicate with the user in different voice modes (such as people of different ages), To adapt to different application scenarios, it is more humanized; the audio input module can collect the user's voice information, and the audio output module can output the content replied by the voice interaction module in the form of voice, thereby realizing the voice interaction between the voice interaction module and the user.

Preferably, the control module further includes a counting module, and the control module is also coupled to a biometric identification module;

When the audio input module starts to collect the voice information of external users, the biometric identification module is used to obtain the unique biometric information of the user and send the characteristic information to the control module, and the counting module is used to count the unique biometric information Lower the number of voice data retrieved by the retrieval module; when the biometric identification module acquires the unique biometric information of the same user again, the retrieval module can retrieve the voice data with the most current retrieval times from the storage module.

Using the above scheme, the biometric identification module can identify the unique biometric characteristics of each user, thereby determining the identity of the current user; the counting module can count the number of times each user calls each type of voice data through the calling module, so that the user In the next voice interaction, the calling module can preferentially call the voice data with the highest frequency, which improves the operation efficiency and is more humanized.

As a preference, the control module is also coupled with a display module, and the control module also includes a numbering module; the numbering module sequentially numbers each voice data in the storage module; when the call module calls the corresponding voice data , the display module can display the number corresponding to the voice data.

By adopting the above solution, the user can view the voice data currently retrieved by the retrieval module through the display module, so as to know the voice mode corresponding to the voice data, so as to improve the operation efficiency and be more humanized.

Preferably, the biometric identification module is a face recognition module.

Using the above solution, face recognition is a biometric technology for identity recognition based on human facial feature information. A series of related technologies that use a camera or camera to collect images or video streams containing human faces, automatically detect and track human faces in the images, and then recognize the detected faces. Face recognition has the advantages of high recognition accuracy, fast response speed, natural recognition process, and not easy to be detected.

Preferably, it also includes a mobile terminal, the control module also includes an authorization module, and the control module is also coupled with a wireless communication module for remote data exchange with the mobile terminal; the mobile terminal can respond to external triggers to wirelessly communicate The module remotely sends an authorization command, the wireless communication module sends the received authorization command to the authorization module, and the authorization module authorizes the call module to call the voice data in the storage module to the voice interaction module, and the mobile terminal starts to collect the user's voice at the same time information and remotely send the information to the wireless communication module, the wireless communication module sends the received voice information to the voice interaction module, the voice interaction module generates a reply instruction according to the received voice information and voice data, and sends the reply instruction Remotely send to the mobile terminal through the wireless communication module, and the mobile terminal converts the text content of the reply instruction into voice content, and performs voice interaction with the user according to the voice corresponding to the voice data.

By adopting the above solution, the user can perform remote voice interaction through the mobile terminal and the voice interaction module, thereby improving the efficiency and convenience of the voice interaction and making it more humanized.

Preferably, the control module further includes a distance judging module, the mobile terminal includes a positioning module, and the distance judging module presets a reference distance value; the positioning module is used to acquire the current location information of the mobile terminal and The location information is remotely sent to the wireless communication module; the wireless communication module sends the received location information to the distance judgment module, and the distance judgment module calculates the actual distance value between the control module and the mobile terminal and calculates the actual distance The distance value is compared with the reference distance value;

If the actual distance value is greater than the reference distance value, the control module controls the voice interaction module to perform remote voice interaction with the mobile terminal through the wireless communication module; otherwise, if the actual distance value is less than or equal to the reference distance value, the control module controls the voice interaction module to pass The audio input module and the audio output module perform near-end voice interaction with the user.

By adopting the above scheme, the distance judging module can calculate the actual distance value between the mobile terminal and the control module in real time during the voice interaction process between the user and the voice interaction module, and compare the actual distance value with the reference distance value; if the actual If the distance value is greater than the reference distance value, it means that the mobile terminal is far away from the control module. At this time, the control module can automatically switch the interactive object of the voice interaction module to the mobile terminal to realize remote voice interaction; otherwise, if the actual distance value is less than or equal to the reference distance value, it means that the mobile terminal is relatively close to the control module. At this time, the control module can switch the interactive object of the voice interaction module to the audio input module and the audio output module to realize the user's local voice interaction; The actual distance between modules is used to automatically switch voice interaction objects, which is more efficient, more convenient, and more humanized.

Preferably, the positioning module is a GPS module.

Using the above scheme, the GPS module can locate and navigate in real time around the world, which is called the global satellite positioning system. Navigation information such as low-cost, high-precision three-dimensional position, speed and precise timing is a model for the application of satellite communication technology in the field of navigation.

Preferably, the display module is a display screen or a touch screen.

By adopting the above solution, the display screen or touch screen can present high-definition video images with high quality, so as to improve the user's voice interaction experience.

In summary, the present invention has the following beneficial effects: in the process of voice interaction with the voice interaction module, the user can select voice data packets in different voice forms, so that the audio output module can use different voice modes (such as different ages) stage crowd) to chat with users to adapt to different application scenarios and be more humane; the audio input module can collect the user's voice information, and the audio output module can output the content replied by the voice interaction module in the form of voice, so as to realize the interaction between the voice interaction module and Voice interaction between users.

Description of drawings

FIG. 1 is a schematic diagram of the system structure of this embodiment.

In the figure: 1. Audio input module; 2. Control module; 3. Audio output module; 4. Biometric identification module; 5. Display module; 6. Mobile terminal; 7. Wireless communication module; 8. Positioning module.

Detailed ways

The present invention will be described in further detail below in conjunction with the accompanying drawings.

A multi-voice mode man-machine dialogue system disclosed in this embodiment, as shown in FIG. 1 , includes an audio input module 1 , a control module 2 and an audio output module 3 coupled in sequence. Wherein, the control module 2 is a chip with data processing capability, including but not limited to CPU, ARM, MCU, single-chip microcomputer, DSP, etc.; the audio input module 1 can be a microphone, a pickup, etc.; the audio output module 3 can be a loudspeaker, an electric horn or buzzer etc. In this embodiment, the control module 2 includes a voice interaction module, a storage module, a switching module and a calling module, wherein the storage module is a chip with data storage capability, including but not limited to a floppy disk, a hard disk, a CD, a U disk, etc.; the switching module It can be a physical button or a virtual button integrated in the touch screen, which can output a corresponding switching instruction to the calling module in response to an external trigger. A plurality of voice data in different voice forms are pre-stored in the storage module, and the voice data correspond to voices of different types of people, such as male voices, female voices, and voices of different ages.

More specifically, the audio input module 1 is used to collect voice information of external users and send the information to the voice interaction module. The voice interaction module can convert the received voice information into text instructions and intelligently generate corresponding reply instructions according to the text instructions , and convert the reply command into voice information and send it to the audio output module 3; the calling module is used to call the voice data in the storage module and send it to the voice interaction module, that is, the user can call the voice data corresponding to the desired sound as needed ; The voice interaction module performs voice interaction with the user through the audio output module 3 according to the received voice information and voice data. The switching module is used to switch the voice data retrieved by the retrieval module. By triggering the switching module, the voice data retrieved by the retrieval module can be changed to switch the sounding mode of the audio output module 3, so that the voice interaction module can A voice mode to realize voice interaction with the user.

Furthermore, the control module 2 also includes a counting module, and the control module 2 is also coupled to a biometric identification module 4, which is a face recognition module. When the audio input module 1 starts to collect the sound information of the external user, the biological feature recognition module 4 is used to obtain the user's unique biological feature information and send the feature information to the control module 2, and the control module 2 can receive the unique biological feature information Set up the user information database, and store the database in the storage module; the counting module is used to count the number of times of each kind of voice data transferred by the unique biometric information retrieval module, that is, the counting module can calculate the number of times of each voice data The number of calling times is stored in the corresponding user information database, so as to count the frequency of use of each voice data by each user.

When the biometric identification module 4 obtains the unique biometric information of the same user again, the calling module can call the voice data with the most current call times from the storage module, that is, when the user performs voice interaction with the voice interaction module again, the calling module The most frequently used voice data can be automatically retrieved from the storage module.

Furthermore, the control module 2 is also coupled to a display module 5, which is a display screen or a touch screen. The control module 2 also includes a numbering module, which sequentially numbers each voice data in the storage module, and the numbering is a mark with an identification effect, including but not limited to a number mark, a letter mark, a Chinese mark, an English mark, etc. After the calling module calls the corresponding voice data, the display module 5 can display the number corresponding to the voice data, so that the user can understand the sound mode currently used by the audio output module 3 .

Furthermore, the multi-voice mode human-machine dialogue system also includes a mobile terminal 6, which can be a remote communication device with a voice call function such as a smart phone or a tablet computer. The mobile terminal 6 mentioned in this embodiment is Owned by the user performing the voice interaction. The control module 2 also includes an authorization module, the control module 2 is also coupled with the wireless communication module 7 for remote data exchange with the mobile terminal 6, the wireless communication module 7 can be 4G-LTE, WCDMA, HSPA, bluetooth, infrared, laser , Microwave, CDPD, communication technology following the IEEE802.11 protocol or IEEE802.16 protocol, so as to be able to communicate remotely with the outside world.

In this embodiment, when the user needs to perform voice interaction remotely, by triggering the mobile terminal 6, the mobile terminal 6 can remotely send an authorization instruction to the wireless communication module 7 in response to an external trigger, and the wireless communication module 7 sends the received authorization instruction to the authorization module, the authorization module authorizes the calling module to call the voice data in the storage module to the voice interaction module, and at the same time, the mobile terminal 6 starts to collect the user's voice information and sends the information to the wireless communication module 7 remotely, and the wireless communication module 7 will receive the voice data. The voice information is sent to the voice interaction module, and the voice interaction module generates a reply command according to the received voice information and voice data, and sends the reply command remotely to the mobile terminal 6 through the wireless communication module 7, and the mobile terminal 6 converts the text content of the reply command into voice content, and perform voice interaction with the user according to the voice mode corresponding to the voice data, so that the user can perform remote voice interaction through the mobile terminal 6 and the voice interaction module, which increases call efficiency and convenience, and is more humanized.

Furthermore, the control module 2 also includes a distance judging module, and the mobile terminal 6 includes a positioning module 8, which is a GPS module. The distance judging module presets a reference distance value. In this embodiment, the positioning module 8 is used to obtain the current location information of the mobile terminal 6 and remotely send the location information to the wireless communication module 7; the wireless communication module 7 sends the received location information to the distance judgment module, and the distance judgment module calculates Control the actual distance between the module 2 and the mobile terminal 6 and compare the calculated actual distance with the reference distance to determine whether the mobile terminal 6 is close to the control module 2 . More specifically, if the actual distance value is greater than the reference distance value, it means that the mobile terminal 6 is far away from the control module 2. At this time, the control module 2 controls the voice interaction module to perform remote voice interaction with the mobile terminal 6 through the wireless communication module 7, which is more convenient. Conversely, if the actual distance value is less than or equal to the reference distance value, it means that the mobile terminal 6 is relatively close to the control module 2. At this time, the control module 2 controls the voice interaction module to perform near-end voice interaction with the user through the audio input module 1 and the audio output module 3. In order to reduce the energy consumption of the mobile terminal 6, thereby extending the battery life of the mobile terminal 6, it is more energy-saving and environment-friendly.

This specific embodiment is only an explanation of the present invention, and it is not a limitation of the present invention. Those skilled in the art can make modifications to this embodiment without creative contribution as required after reading this specification, but as long as they are within the rights of the present invention All claims are protected by patent law.

Claims (6)

1. A multi-voice mode man-machine dialogue system is characterized in that: comprise an audio input module (1), a control module (2) and an audio output module (3) coupled in sequence; the control module (2) includes A voice interaction module, a storage module, a switching module and a calling module, the voice data of a plurality of different voice forms are pre-stored in the storage module; Send to the voice interaction module, the calling module is used to call the voice data in the storage module and send to the voice interaction module, the voice interaction module is based on the received voice information and voice data and through the audio output module (3) and The user performs voice interaction; the switching module is used to switch the voice data retrieved by the calling module; It also includes a mobile terminal (6), the control module (2) also includes an authorization module, and the control module (2) is also coupled with a wireless communication module (7) for remote data exchange with the mobile terminal (6); The mobile terminal (6) can remotely send an authorization instruction to the wireless communication module (7) in response to an external trigger, and the wireless communication module (7) sends the received authorization instruction to the authorization module, and the authorization module authorizes the retrieval module Call the voice data in the storage module to the voice interaction module, and at the same time, the mobile terminal (6) starts to collect the voice information of the user and remotely sends the information to the wireless communication module (7), and the wireless communication module (7) will receive The voice information is sent to the voice interaction module, and the voice interaction module generates a reply instruction according to the received voice information and voice data, and sends the reply instruction to the mobile terminal (6) remotely through the wireless communication module (7), and the mobile terminal (6) Convert the text content of the reply command into voice content, and perform voice interaction with the user according to the voice corresponding to the voice data; The control module (2) also includes a distance judging module, the mobile terminal (6) contains a positioning module (8), and the distance judging module is preset with a reference distance value; the positioning module (8) is used for Obtain the current location information of the mobile terminal (6) and remotely send the location information to the wireless communication module (7); the wireless communication module (7) sends the received location information to the distance judgment module, and the distance judgment module calculates The actual distance value between the control module (2) and the mobile terminal (6) and the calculated actual distance value is compared with the reference distance value; if the actual distance value is greater than the reference distance value, the control module (2) Control the voice interaction module to carry out remote voice interaction with the mobile terminal (6) through the wireless communication module (7); otherwise, if the actual distance value is less than or equal to the reference distance value, the control module (2) controls the voice interaction module through the audio input module ( 1) and the audio output module (3) perform near-end voice interaction with the user. 2. The multi-voice mode man-machine dialogue system according to claim 1, characterized in that: the control module (2) also includes a counting module, and the control module (2) is also coupled to a biometric identification module ( 4); when the audio input module (1) starts to collect the sound information of the external user, the biological feature recognition module (4) is used to obtain the user's unique biological feature information and send the feature information to the control module (2), The counting module is used to count the number of times of each kind of voice data transferred by the calling module under the unique biological feature information; when the biological feature identification module (4) obtains the unique biological feature information of the same user again, the calling module The voice data with the most current calls can be retrieved from the storage module. 3. The multi-voice mode man-machine dialogue system according to claim 2, characterized in that: the control module (2) is also coupled with a display module (5), and the control module (2) also includes a serial number module; the numbering module sequentially numbers each voice data in the storage module; when the call module calls the corresponding voice data, the display module (5) can display the number corresponding to the voice data. 4. The multi-voice mode man-machine dialogue system according to claim 2, characterized in that: the biometric identification module (4) is a face recognition module. 5. The multi-voice mode man-machine dialogue system according to claim 1, characterized in that: the positioning module (8) is a GPS module. 6. The multi-voice mode man-machine dialogue system according to claim 3, characterized in that: the display module (5) is a display screen or a touch screen.