Scene voice interaction method and system and storage medium

Abstract

The invention provides a scene voice interaction method and system and a storage medium, and the method comprises the steps: obtaining the current positioning information of a vehicle, and starting to record an audio; and storing the audio and the positioning information to a corresponding voice folder according to a character tag, and calling the audio for playing when the vehicle passes through a position corresponding to the positioning information next time or a trigger response instruction is received by the voice folder. According to the invention, by associating the audio with the specific positioning information, the system can play the related audio when the vehicle passes through a specific place, so that the emotional contact between the user and the driving process is enhanced; through personalized audio playing, the user can enjoy the voice content more conforming to the own situation according to own preferences and demands. The customized playing mode enables the driving process to be more pleasant and comfortable.

Description

Technical Field

[0001] The present application relates to the field of voice interaction technology, and in particular to a scene voice interaction method, system and storage medium. Background Art

[0002] As our most commonly used means of transportation, cars also accompany us for a large part of our time. We will pass through many places and leave memories in different places, some of which are heartwarming and some of which make people move forward. Cars are no longer a simple means of transportation, but a partner in which we share experiences and pour emotions. For people nowadays, life is stressful and lonely when they are alone. Even the strongest people will experience loss of mood. When they are at the lowest point in their lives, if they can hear a certain voice somewhere and think of a certain memory, they will want to move forward even if it is difficult. At present, modern cars are equipped with advanced voice recognition technology, which can control navigation, music playback, calls and other functions through voice, but the only thing missing is the voice recording for different people and playing when needed. Summary of the invention

[0003] To solve the above technical problems, the present application provides a scene voice interaction method, system and storage medium, which not only improves the convenience and comfort of driving, but also can help drivers cope with the stress and loneliness in life to a certain extent, making the car a more intimate companion.

[0004] In a first aspect, the present application proposes a scene voice interaction method, comprising the following steps: S1: Turn on the scene mode and enter the recording state; S2: Get the current location information of the vehicle and start recording audio; S3: The audio and positioning information are stored in a corresponding voice folder according to the character tag. The voice folder retrieves the audio for playback the next time a vehicle passes the position corresponding to the positioning information or receives a trigger response instruction.

[0005] This application can provide a more personalized driving experience by associating audio with specific locations. For example, when a vehicle passes a location where a special audio has been recorded, the system will play the relevant audio to evoke memories or provide specific feelings. At the same time, sound and location can be combined to help drivers recall specific experiences or emotions and enhance emotional connections in the car. The system can flexibly play audio based on trigger instructions or positioning information to adapt to different driving scenarios and personal needs. Overall, this method can provide drivers with a more personalized and emotional experience by combining location and audio, while also improving the intelligence and humanization of the vehicle system.

[0006] Preferably, the opening scenario mode further includes: Identify the current sound, and determine whether the character tag exists based on the existing audio in the voice folder. If so, directly record the audio for the character; otherwise, create a new character tag before entering the recording state.

[0007] Among them, the character tag corresponds to the voice of a unique character; the voice folder is named according to the character tag; and the audio is named according to the recording time after the recording is completed.

[0008] Preferably, the voice folder retrieves the audio to play when the vehicle passes the position corresponding to the positioning information next time, specifically including: Get the current GPS location of the vehicle, determine whether the GPS location and the location information in the voice folder are less than a preset distance, and if so, retrieve the most recently stored audio in the corresponding voice folder for playback; otherwise, do not play.

[0009] Preferably, when the trigger response instruction is received, the audio is retrieved for playing, specifically including: The user's intention is recognized through the in-vehicle language assistant, the character name is extracted according to the user's intention, the corresponding character tag is matched from the storage system according to the character name, and the latest audio in the voice folder corresponding to the character tag is retrieved for playback.

[0010] Preferably, when the trigger response instruction is received, the audio is retrieved for playing, specifically including: The user's intention is recognized through the in-vehicle language assistant, time information is extracted according to the user's intention, and all audio corresponding to the time is matched from the storage system according to the time and played.

[0011] Preferably, when the trigger response instruction is received, the audio is retrieved for playing, specifically including: By setting the playback time, whenever the vehicle system time coincides with the preset playback time, the audio of the corresponding time in the voice folder will be automatically retrieved for single or loop playback.

[0012] In a second aspect, the present application proposes a scene language interaction system, the interaction system comprising: The voice recording module enters the recording state in response to the command of the vehicle terminal and starts recording audio; A voice storage module, including a plurality of voice folders, each of which stores recorded audio, and location information and time information corresponding to the audio; A voice playing module, used to retrieve the audio in the voice folder for playing; Positioning module, used to obtain the current real-time positioning information of the vehicle; And a sound recognition module is used to recognize the current recorded sound.

[0013] The vehicle terminal further includes: a processing unit, which is used to retrieve the corresponding audio in the voice storage module when the vehicle passes the position corresponding to the positioning information next time, or according to an instruction input by the user.

[0014] In a third aspect, the present application proposes a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a control processor, a scene voice interaction method as described in the first aspect is implemented.

[0015] Compared with the prior art, this application has at least the following beneficial effects: By associating audio with specific location information, the system can play relevant audio when the vehicle passes a specific location, enhancing the user's emotional connection with the driving process; through personalized audio playback, users can enjoy voice content that is more in line with their own situation according to their preferences and needs. This customized playback method can make the driving process more pleasant and comfortable. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of a scene voice interaction method shown in an embodiment of the present application.

[0017] Figure 2 It is a schematic diagram of a scene language interaction system shown in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] Embodiment 1: like Figure 1 As shown, the present application proposes a scene voice interaction method, comprising the following steps: S1: Turn on the scene mode and enter the recording state; S2: Get the current location information of the vehicle and start recording audio; S3: The audio and positioning information are stored in a corresponding voice folder according to the character tag. The voice folder retrieves the audio for playback the next time a vehicle passes the position corresponding to the positioning information or receives a trigger response instruction.

[0020] Preferably, the opening scenario mode further includes: Identify the current sound, and determine whether the character tag exists based on the existing audio in the voice folder. If so, directly record the audio for the character; otherwise, create a new character tag before entering the recording state.

[0021] Among them, when the scene mode is turned on, the system will first identify the current environmental sound. This can include identifying background noise, voice, etc. The system will check whether the current environmental sound matches the audio already in the voice folder to determine whether there is a corresponding "person tag". If the system finds the corresponding person tag in the voice folder, it will directly enter the recording state and start recording new audio. This ensures that the audio records under the person tag are constantly updated. If the system does not find the corresponding person tag, it needs to create a new tag. After creating the new tag, the system enters the recording state, starts recording audio, and stores it under the newly created tag. By automatically identifying the current sound and judging the tag, the system can intelligently handle the recording operation, reduce the user's manual intervention, and improve the system's automation level. The system can manage audio according to different person tags, ensuring that the sound records of different people are correctly classified and stored, thereby providing a more personalized voice experience. Directly recording audio under existing tags avoids the steps of repeatedly creating tags, making the user experience smoother. And creating a new tag ensures that the system can process all new person information without missing any audio records.

[0022] The character tag corresponds to the voice of a unique character; the voice folder is named according to the character tag, which can be the name of the character; thus ensuring that the audio recording of each character is accurately distinguished and archived. Through the unique tag, the system can clearly identify and call the audio content of a specific character. At the same time, it avoids audio content management problems caused by repeated or confused tags, and improves the accuracy of the system.

[0023] After the audio is recorded, it is named according to the recording time. This ensures that each audio file has a unique identifier, avoiding the problem of duplicate file names. The timestamp naming method also enables the system to retain the history of audio recordings, allowing users to trace and review past recordings, increasing the practicality and traceability of the system. Preferably, the voice folder retrieves the audio to play when the vehicle passes the position corresponding to the positioning information next time, specifically including: Get the current GPS location of the vehicle, determine whether the GPS location and the location information in the voice folder are less than the preset distance, and if so, retrieve the most recently stored audio in the corresponding voice folder for playback; otherwise, do not play. Through the playback logic based on GPS location information and preset distance, the system can ensure the accuracy and relevance of audio playback. The corresponding audio will only be played when the vehicle approaches or passes a specific location, avoiding false triggering or unnecessary playback.

[0024] Preferably, when the trigger response instruction is received, the audio is retrieved for playing, specifically including: The user's intention is recognized through the in-vehicle language assistant, the character name is extracted according to the user's intention, the corresponding character tag is matched from the storage system according to the character name, and the latest audio in the voice folder corresponding to the character tag is retrieved for playback.

[0025] Preferably, when the trigger response instruction is received, the audio is retrieved for playing, specifically including: The user's intention is recognized through the in-vehicle language assistant, time information is extracted according to the user's intention, and all audio corresponding to the time is matched from the storage system according to the time and played.

[0026] Preferably, when the trigger response instruction is received, the audio is retrieved for playing, specifically including: By setting the playback time, whenever the vehicle system time coincides with the preset playback time, the audio of the corresponding time in the voice folder will be automatically retrieved for single or loop playback.

[0027] This application can provide a more personalized driving experience by associating audio with specific locations. For example, when a vehicle passes a location where a special audio has been recorded, the system will play the relevant audio to evoke memories or provide specific feelings. At the same time, sound and location can be combined to help drivers recall specific experiences or emotions and enhance emotional connections in the car. The system can flexibly play audio based on trigger instructions or positioning information to adapt to different driving scenarios and personal needs. Overall, this method can provide drivers with a more personalized and emotional experience by combining location and audio, while also improving the intelligence and humanization of the vehicle system.

[0028] Embodiment 2: like Figure 2 As shown, the present application proposes a scene language interaction system, the interaction system comprising: The voice recording module enters the recording state in response to the command of the vehicle terminal and starts recording audio; when the vehicle or user issues a command, the system can start recording, capture the sound inside or outside the car, and provide a data basis for subsequent voice management.

[0029] The voice storage module includes a plurality of voice folders, each of which stores recorded audio and location information and time information corresponding to the audio. The audio is classified and managed through the folder structure, making the retrieval and playback of audio data more efficient.

[0030] The voice playback module is used to retrieve the audio in the voice folder for playback; specifically, the voice playback module can select and play corresponding audio from the stored voice files according to positioning information, time information or user instructions, and provide users with relevant voice prompts or entertainment content.

[0031] The positioning module is used to obtain the current real-time positioning information of the vehicle; it is used to track the vehicle's position in real time and realize the position-related audio playback function in combination with the positioning information in the voice storage module. For example, when the vehicle approaches a specific location, the audio related to the location can be automatically played. The real-time location can also be obtained during recording for audio collection and storage.

[0032] And a sound recognition module is used to recognize the current recorded sound.

[0033] The vehicle terminal further includes: a processing unit, which is used to retrieve the corresponding audio in the voice storage module when the vehicle passes the position corresponding to the positioning information next time, or according to an instruction input by the user.

[0034] The scene speech interaction system provided by this application realizes intelligent and personalized voice interaction by integrating voice recording, storage, playback, positioning and sound recognition functions. Based on real-time positioning and sound recognition, the system can provide personalized voice content and prompts, and dynamically adjust audio playback according to user needs and environment. It can provide drivers with a more personalized and emotional experience, and also improve the intelligence and humanization level of the vehicle system. Example

[0035] The present application proposes a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a control processor, a scene voice interaction method as described in the first aspect is implemented.

[0036] In several embodiments provided in the present application, it is understood that each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.

[0037] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for an electronic device to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0038] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A scene voice interaction method, characterized in that: The following steps are involved: S1: Turn on the scene mode and enter the recording state; S2: Get the current location information of the vehicle and start recording audio; S3: The audio and positioning information are stored in a corresponding voice folder according to the character tag. The voice folder retrieves the audio for playback the next time a vehicle passes the position corresponding to the positioning information or receives a trigger response instruction.

2. A scene voice interaction method according to claim 1, characterized in that: The opening scenario mode also includes: Identify the current sound, and determine whether the character tag exists based on the existing audio in the voice folder. If so, directly record the audio for the character; otherwise, create a new character tag before entering the recording state.

3. A scene voice interaction method according to claim 2, characterized in that: The character tag corresponds to the voice of a unique character; the voice folder is named according to the character tag; and the audio is named according to the recording time after the recording is completed.

4. A scene voice interaction method according to claim 1, characterized in that: The voice folder retrieves the audio to play when the vehicle passes the position corresponding to the positioning information next time, specifically including: Get the current GPS location of the vehicle, determine whether the GPS location and the location information in the voice folder are less than a preset distance, and if so, retrieve the most recently stored audio in the corresponding voice folder for playback; otherwise, do not play.

5. A scene voice interaction method according to claim 1, characterized in that: When the trigger response instruction is received, the audio is retrieved for playback, specifically including: The user's intention is recognized through the in-vehicle language assistant, the character name is extracted according to the user's intention, the corresponding character tag is matched from the storage system according to the character name, and the latest audio in the voice folder corresponding to the character tag is retrieved for playback.

6. A scene voice interaction method according to claim 1, characterized in that: When the trigger response instruction is received, the audio is retrieved for playback, specifically including: The user's intention is recognized through the in-vehicle language assistant, time information is extracted according to the user's intention, and all audio corresponding to the time is matched from the storage system according to the time and played.

7. A scene voice interaction method according to claim 1, characterized in that: When the trigger response instruction is received, the audio is retrieved for playback, specifically including: By setting the playback time, whenever the vehicle system time coincides with the preset playback time, the audio of the corresponding time in the voice folder will be automatically retrieved for single or loop playback.

8. An interactive system for a scene voice interaction method as claimed in any one of claims 1 to 7, characterized in that: The interactive system comprises: The voice recording module enters the recording state in response to the command of the vehicle terminal and starts recording audio; A voice storage module, including a plurality of voice folders, each of which stores recorded audio, and location information and time information corresponding to the audio; A voice playing module, used to retrieve the audio in the voice folder for playing; Positioning module, used to obtain the current real-time positioning information of the vehicle; And a sound recognition module is used to recognize the current recorded sound.

9. The interactive system according to claim 8, characterized in that: The vehicle-mounted terminal also includes: A processing unit, the processing unit is used to retrieve the corresponding audio in the voice storage module when the vehicle passes the position corresponding to the positioning information next time, or according to an instruction input by the user.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that: When the computer executable instructions are executed by the control processor, a scene voice interaction method as described in any one of claims 1-7 is implemented.

Images