Voice data processing method and device, equipment, medium and product
By recording voice data on the vehicle machine and generating target notes using AI models, the problem of difficulty in recording and displaying voice calls in the vehicle is solved, and efficient and safe voice calls recording and display are achieved.
Patent Information
- Application Number
- CN202411732431.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-28
- Publication Date
- 2025-04-08
Smart Images
Figure CN119785793A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to the technical fields of intelligent driving, intelligent cockpit, large models, etc., and in particular to a voice data processing method, device, equipment, medium and product. Background Art
[0002] Users are using voice calls more and more frequently while driving. In some scenarios, the content of voice calls needs to be recorded. For example, when a user is in the vehicle cabin, there may be a need for a multi-person meeting. At this time, the content of the meeting needs to be recorded. Summary of the invention
[0003] The present disclosure provides a voice data processing method, apparatus, device, medium and product.
[0004] According to one aspect of the present disclosure, a voice data processing method is provided, including: recording voice data collected by a vehicle computer; obtaining target notes corresponding to the voice data, wherein the target notes are generated after processing the voice data using an AI model; and displaying the target notes in response to a note display instruction.
[0005] According to another aspect of the present disclosure, a voice data processing method is provided, including: obtaining text data corresponding to the voice data collected by a vehicle computer; processing the text data based on an AI model to obtain target notes; and sending the target notes to the vehicle computer so that the vehicle computer displays the target notes after receiving a note display instruction.
[0006] According to another aspect of the present disclosure, a voice data processing device is provided, including: a recording module for recording voice data collected by a vehicle computer; an acquisition module for acquiring target notes corresponding to the voice data, wherein the target notes are generated after processing the voice data using an AI model; and a display module for displaying the target notes in response to a note display instruction.
[0007] According to another aspect of the present disclosure, a voice data processing device is provided, including: an acquisition module for acquiring text data corresponding to the voice data collected by the vehicle computer; a processing module for processing the text data based on an AI model to obtain a target note; and a sending module for sending the target note to the vehicle computer so that the vehicle computer displays the target note after receiving a note display instruction.
[0008] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any method as described in any of the above aspects.
[0009] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods according to any one of the above aspects.
[0010] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the computer program implements any one of the methods described in any one of the above aspects.
[0011] According to the embodiments of the present disclosure, driving safety can be guaranteed and the effectiveness of recorded voice call content can be improved.
[0012] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.
[0014] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;
[0015] Figure 2 is a schematic diagram of an application scenario for implementing an embodiment of the present disclosure;
[0016] Figure 3 is a schematic diagram of the structure of the vehicle machine and the cloud according to an embodiment of the present disclosure;
[0017] Figure 4 is a schematic diagram according to a second embodiment of the present disclosure;
[0018] Figure 5 is a schematic diagram according to a third embodiment of the present disclosure;
[0019] Figure 6 is a schematic diagram according to a fourth embodiment of the present disclosure;
[0020] Figure 7 is a schematic diagram according to a fifth embodiment of the present disclosure;
[0021] Figure 8is a schematic diagram according to a sixth embodiment of the present disclosure;
[0022] Fig. 9 It is a schematic diagram of an electronic device used to implement the voice data processing method of the embodiment of the present disclosure. DETAILED DESCRIPTION
[0023] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.
[0024] In the related art, users can manually record the content of voice calls, but this will affect driving safety, and because it is a manual record, there may be problems such as forgetfulness. Alternatively, voice data can be recorded, but this method requires users to screen important information by themselves, which is not effective enough.
[0025] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure. This embodiment provides a method for processing speech data, such as Figure 1 As shown, the method includes:
[0026] 101. Record the voice data collected by the vehicle computer.
[0027] 102. Obtain a target note corresponding to the voice data, where the target note is generated after processing the voice data based on an artificial intelligence (AI) model.
[0028] 103. In response to the note display instruction, display the target note.
[0029] The method of this embodiment is executed by the vehicle computer.
[0030] In the vehicle, if a voice call occurs and there is a need to record the voice, the voice data corresponding to the voice call can be recorded. The voice call can be a phone call or a call within an application (Application, APP).
[0031] For phone calls, after the mobile phone and the car computer establish a Bluetooth connection, the car computer obtains the telephone voice data from the mobile phone through the Bluetooth connection and records it; for calls within the APP, it can be a call generated within the APP installed on the car computer. At this time, the car computer collects the voice data of the call generated within its own APP and records it, or the APP can also be installed on the mobile phone. The car computer obtains the voice data of the call within the mobile phone APP through the Bluetooth connection of the mobile phone and records it.
[0032] The above-mentioned voice call is generated by a user in the vehicle. Based on compliance with relevant laws and regulations, the user may be the driver and / or passenger of the vehicle. The voice call may be generated while the vehicle is driving and / or when the vehicle is stopped.
[0033] After recording the voice data, the voice data is processed through the AI model to obtain the target notes corresponding to the voice data.
[0034] Notes are important things or information recorded down. They are usually to help people remember and review important knowledge points, experiences or viewpoints, and can help people remember and understand knowledge.
[0035] Target notes refer to the notes corresponding to the voice data collected by the vehicle computer, which are a concise and key summary of the voice data content. In different scenarios, the specific content of the target notes can be different. For example, in a multi-person meeting scenario, the target notes can record: meeting topics, everyone's opinions, meeting issues, meeting arrangements, etc.; in a normal call scenario, the target notes can record the matters communicated by both parties on the call, etc.
[0036] After receiving the note display instruction, the target note can be displayed to the user on the vehicle computer.
[0037] In this way, the user can learn the content of the voice call through the target note.
[0038] In this embodiment, by recording the voice data collected by the vehicle computer and obtaining the notes corresponding to the voice data through the AI model, the user does not need to manually record the voice content, which will not interfere with the user's driving behavior, and can ensure driving safety. In addition, important information can be screened out through the notes, which can improve the effectiveness of the recorded voice content. Since the voice data collected by the vehicle computer is recorded and the corresponding target notes are generated, it can be applied to vehicle computer processing scenarios, such as recording the content of multi-person meetings in the vehicle. This can enrich the functions of the vehicle computer. On the basis of ensuring driving safety, the vehicle computer can be used to complete more functions, such as using the vehicle computer to record notes corresponding to the voice data, improve the intelligence of the vehicle computer and its smart cockpit, and improve the user experience.
[0039] The AI model can be a model specially trained for generating notes. In this case, the text data after speech recognition can be input into the AI model on the vehicle side or in the cloud, and the output is the target notes.
[0040] For example, after a trigger command is generated (the user clicks a preset button in the vehicle), the vehicle computer or the cloud inputs the text data after voice recognition into the preset AI model through a preset interface. The AI model is a pre-trained model specifically used to generate the target notes. After processing by the AI model, the output is the target notes.
[0041] The above example uses an AI model that is specially trained to generate notes. In some cases, the AI model can also be a large language model (LLM).
[0042] LLM is a hot technology in the field of artificial intelligence in recent years. The large language model is a pre-trained language model. By pre-training on massive text data, it has learned rich language knowledge and world knowledge, so that it can achieve amazing results in various natural language processing (NLP) and image generation tasks.
[0043] LLM is a general model that can be applied to operations in a variety of scenarios, such as text processing and image generation. LLM performs specific operations based on prompts.
[0044] If the AI model is LLM, a prompt can be preset to instruct LLM to extract the note content, such as "Please extract the notes for this voice" or "Please extract the notes for this text". Generally speaking, LLM is deployed in the cloud, so when the car sends voice data or corresponding text data, it can also send the prompt information to the cloud. The LLM deployed in the cloud can process the text data corresponding to the voice data according to the prompt information to obtain the target notes.
[0045] The above takes the preset prompt information as an example. The prompt information can also be input by the user. In this case, the user can enter the prompt information for extracting the notes, such as the above-mentioned "Please extract the notes of this voice" and other information. Furthermore, the prompt information entered by the user can also indicate the specific extraction content. For example, if the user needs to hold a multi-person meeting, he can enter "Please extract the meeting topic targeted by this voice, everyone's opinions..." and other similar content in the form of voice or text, thereby instructing LLM to extract specific content to generate the target notes.
[0046] The above takes LLM deployed in the cloud as an example. It can be understood that if the vehicle has relevant capabilities, the LLM deployed on the vehicle can also be used for corresponding processing.
[0047] In this embodiment, the target notes are obtained based on the LLM, and the excellent text generation ability of the LLM can be used to improve the accuracy of the target notes.
[0048] In addition, the AI model may include an AI model on the vehicle side and / or an AI model on the cloud side.
[0049] For the sake of distinction, the AI model deployed locally in the vehicle computer can be called the first AI model, and the AI model deployed in the cloud can be called the second AI model. Based on this, the first AI model deployed locally in the vehicle computer and / or the second AI model deployed in the cloud can be used to process the voice data to obtain the target notes.
[0050] For example, the vehicle computer can first perform speech recognition on the voice data to obtain the corresponding text data, and then use the first AI model deployed locally in the vehicle computer to process the text data to obtain the target note. Alternatively, the vehicle computer sends the recorded voice data or the text data after speech recognition to the cloud, and the cloud uses the AI model deployed in the cloud to obtain the target note, and then sends the target note to the vehicle end.
[0051] In this embodiment, obtaining target notes through the first AI model and / or the second AI model can improve processing flexibility.
[0052] In this embodiment, the target notes are obtained through the first AI model. Since the first AI model is located in the vehicle computer, the target notes can be generated locally on the vehicle computer, thereby improving processing efficiency. The target notes are obtained through the second AI model. Since the second AI model is located in the cloud, it usually has better performance and can improve processing accuracy.
[0053] In order to better understand the present disclosure, the application scenarios involved in the present disclosure are described as follows:
[0054] Figure 2 It is a schematic diagram of an application scenario for implementing the embodiment of the present disclosure.
[0055] In this embodiment, the interaction between the vehicle computer 201 and the cloud 202 is taken as an example, and the vehicle computer sends voice data to the cloud as an example.
[0056] The vehicle computer 201 is used to record voice data.
[0057] After the car computer records the voice data, it sends the voice data to the cloud. In order to ensure data security, the voice data can be encrypted and sent to the cloud.
[0058] The cloud 202 is used to perform speech recognition on the speech data to obtain text data, and use the AI model deployed in the cloud to process the text data to obtain the target notes corresponding to the speech data.
[0059] After the cloud obtains the note, it sends the note to the vehicle computer, and after receiving the note display instruction, the vehicle computer displays the target note to the user. For example, the target note is displayed to the user in the form of text or voice.
[0060] Figure 3 It is a structural diagram of the vehicle computer and the cloud provided according to an embodiment of the present disclosure.
[0061] like Figure 3 As shown, the vehicle computer includes: a user authorization module, a voice data recording trigger module, a voice data acquisition module, a vehicle computer information storage module, an AI note display module and a vehicle computer communication module.
[0062] The user authorization module is used to obtain user authorization. In this way, the voice data of the user during the voice call can be obtained legally and with the user's permission.
[0063] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0064] The voice data recording trigger module is used to trigger the voice data recording process, including triggering the start of recording and triggering the end of recording. Specifically, the start and end of the recording process can be triggered by voice commands; or, the start and end of the recording process can be triggered by physical buttons in the car (such as physical buttons on the center console or steering wheel).
[0065] The voice data collection module is used to collect voice data during voice calls. Specifically, the voice data can be collected through the microphone and speaker in the car.
[0066] The vehicle-side information storage module is used to store relevant information in the vehicle, such as user account, authorization information, collected voice data, etc. In addition, in order to ensure data security, this information can be encrypted and stored.
[0067] The AI note display module is used to display the target notes obtained by the AI model after receiving the note display instruction. The note display instruction can be a voice command or implemented by a physical button or a software button in the APP. The target note can be displayed in text form on the screen of the vehicle computer, and / or, after the target note is voice synthesized, it can be voice broadcast through the speaker and other devices in the vehicle.
[0068] The vehicle-side communication module is used to communicate with the cloud, transmit voice data to the cloud, and receive target notes sent by the cloud.
[0069] The cloud includes: speech recognition module, AI note generation module, cloud communication module and cloud information storage module.
[0070] The speech recognition module is used to perform speech recognition on the speech data sent by the vehicle computer to obtain the corresponding text data.
[0071] The AI note generation module is used to process the above text data using the AI model deployed in the cloud to obtain the target notes.
[0072] The cloud communication module is used to communicate with the vehicle computer, such as receiving voice data sent by the vehicle computer and sending the generated target notes to the vehicle computer.
[0073] The cloud information storage module is used to store relevant information in the cloud, such as user information, and correspondingly store target notes obtained based on the user's voice data.
[0074] In combination with the above application scenarios, the present disclosure also provides the following embodiments.
[0075] Figure 4 is a schematic diagram according to the second embodiment of the present disclosure. This embodiment provides a method for processing speech data, such as Figure 4 As shown, the method includes:
[0076] 401. Obtain text data corresponding to the voice data collected by the vehicle computer.
[0077] 402. Process the text data based on the AI model to obtain target notes.
[0078] 403. Send the target note to the vehicle computer, so that the vehicle computer displays the target note after receiving the note display instruction.
[0079] The method of this embodiment is executed by the cloud.
[0080] In this embodiment, voice data is recorded and notes corresponding to the voice data are obtained through an AI model. This eliminates the need for users to record voice content, thereby ensuring driving safety. Important information can be screened out through notes, thereby improving the effectiveness of the recorded voice content.
[0081] During the driving of the vehicle, if a voice call occurs and there is a need to record the voice, the voice data corresponding to the voice call can be recorded. The voice call can be a phone call or a call within an application (Application, APP).
[0082] After the car computer records the voice data, the voice data can be sent to the cloud; or, after voice recognition is performed on the voice data to obtain the corresponding text data, the text data can be sent to the cloud.
[0083] If the cloud receives voice data, it can perform voice recognition on the voice data to obtain the corresponding text data, and then use the AI model deployed on the cloud to process the text data to obtain the target note. Alternatively, if the cloud receives text data, the AI model deployed on the cloud is directly used to process the text data to obtain the target note.
[0084] In this embodiment, the cloud can receive the voice data sent by the vehicle computer and perform voice recognition on the voice data to obtain text data, which can improve processing accuracy; or, the cloud can directly receive the text data sent by the vehicle computer, which can improve processing efficiency.
[0085] The AI model deployed in the cloud can be a specially trained model for generating notes. For example, the AI model is obtained by fine-tuning an existing pre-trained model using note-related samples. When the AI model is applied, text data can be input into the AI model, and the output is notes.
[0086] The AI model deployed in the cloud can also be LLM. In this case, when the vehicle computer sends voice data or text data, it can also send prompt information to the cloud at the same time. The prompt information is used to instruct LLM to generate notes, so that LLM can obtain notes based on the text data according to the prompt information.
[0087] In this embodiment, the target notes are obtained based on the LLM, and the excellent text generation ability of the LLM can be used to improve the accuracy of the target notes.
[0088] After the cloud obtains the target notes using the AI model, it returns the target notes to the vehicle computer.
[0089] After receiving the note display instruction, the vehicle computer displays the target note to the user. Specifically, the target note can be displayed to the user in the form of text and / or voice.
[0090] In this way, users can know the content of the voice call through the notes.
[0091] Figure 5 is a schematic diagram according to the third embodiment of the present disclosure. This embodiment provides a method for processing voice data. This embodiment takes obtaining target notes by using the cloud as an example. The method includes:
[0092] 501. Obtain user authorization.
[0093] For example, refer to Figure 3, the user authorization can be obtained through the user authorization module in the vehicle computer, and the voice data of the user during the voice call can be recorded based on the authorization.
[0094] 502. Record the voice data collected by the vehicle computer.
[0095] During the driving of the vehicle, there may be voice calls, for example, the user makes a phone call. After the user terminal (such as a mobile phone) is connected to the vehicle computer, the vehicle computer can record the voice data corresponding to the voice call generated by the mobile phone.
[0096] The voice data recording process can be started in response to a voice recording start instruction; and the voice data recording process can be ended in response to a voice recording end instruction, thereby realizing the recording of voice data.
[0097] refer to Figure 3 The start or end of the recording process can be triggered by the voice data recording trigger module in the car computer.
[0098] The above-mentioned voice recording start command and voice recording end command can be a voice command issued by the user, or a command issued by the user through a physical button in the car, or a software button in the APP.
[0099] After the voice data is recorded, the voice data can be stored.
[0100] For example, refer to Figure 3 , the recorded voice data can be stored through the vehicle-side information storage module.
[0101] In addition, in order to ensure data security, voice data can also be encrypted and stored.
[0102] 503. Encrypt the voice data, and send the encrypted voice data to the cloud.
[0103] 504. The cloud decrypts the voice data, and performs voice recognition on the decrypted voice data to obtain text data.
[0104] Among them, the cloud and the vehicle computer can negotiate the encryption key in advance, so that after the cloud receives the encrypted voice data, it can use the corresponding encryption key to perform decryption operations.
[0105] After obtaining the decrypted voice data, see Figure 3 ,The cloud can use a speech recognition module to perform speech recognition on the decrypted speech data to obtain the corresponding text data.
[0106] 505. Use the AI model deployed in the cloud to process the text data and obtain the target notes.
[0107] For example, see Figure 3,The AI note generation module is used to process the target notes using the AI model deployed in the cloud.
[0108] 506. The cloud sends the target note to the vehicle computer.
[0109] 507. The vehicle computer displays the target note in response to the note display instruction.
[0110] The note display instruction may be a voice instruction, or an instruction generated by the user through a physical key or a software button.
[0111] Target notes can be presented in text and / or audio form.
[0112] In addition, the car computer can also perform voice recognition on voice data to obtain corresponding text data. When displaying, it can also display the target notes and text data separately in different areas of the display interface, so that users can understand more comprehensive information.
[0113] In this embodiment, the target notes are obtained by using an AI model deployed in the cloud, which can improve the accuracy of the target notes.
[0114] Figure 6 is a schematic diagram according to the fourth embodiment of the present disclosure. This embodiment provides a method for processing voice data. This embodiment takes the interaction between the vehicle terminal and the cloud as an example. The method includes:
[0115] 601. The vehicle computer sends the voice data or the text data corresponding to the voice data to the cloud, so that the cloud uses the second AI model to process the text data corresponding to the voice data.
[0116] 602. The vehicle computer determines whether the notes returned from the cloud are received. If so, execute 603; otherwise, execute 604.
[0117] 603. The car computer takes the notes returned from the cloud as target notes.
[0118] 604. Use the first AI model deployed in the vehicle computer to process the text data corresponding to the voice data to obtain the target notes.
[0119] Among them, the model parameter amount of the first AI model is smaller than the model parameter amount of the second AI model.
[0120] 605. The vehicle computer displays the target note in response to the note display instruction.
[0121] When the vehicle computer interacts with the cloud, the data sent by the vehicle computer may not reach the cloud, or the data returned by the cloud may not reach the vehicle computer due to network problems.
[0122] In this embodiment, by giving priority to the notes returned from the cloud as the target notes, since the second AI model is a larger-scale model, the accuracy of the target notes can be guaranteed. When the notes returned from the cloud are not obtained through the vehicle computer, the first AI model deployed locally on the vehicle computer is used to generate the target notes, which can ensure reliability. Therefore, the target notes are obtained through the first AI model and the second AI model, which can improve accuracy and reliability.
[0123] Figure 7 It is a schematic diagram according to the fifth embodiment of the present disclosure. This embodiment provides a voice data processing device, and the device 700 includes: a recording module 701, an acquisition module 702 and a display module 703.
[0124] The recording module 701 is used to record the voice data collected by the vehicle computer; the acquisition module 702 is used to obtain the target notes corresponding to the voice data, and the target notes are generated after processing the voice data using an AI model; the display module 703 is used to display the target notes in response to the note display instruction.
[0125] In this embodiment, voice data is recorded and notes corresponding to the voice data are obtained through an AI model. This eliminates the need for users to record voice content, thereby ensuring driving safety. Important information can be screened out through notes, thereby improving the effectiveness of the recorded voice content.
[0126] In some embodiments, the acquisition module 702 is further used to:
[0127] Using a specially trained model for generating the target note as the AI model, and using the specially trained model for generating the target note to process the text data corresponding to the voice data to obtain the target note; or,
[0128] The large language model is used as the AI model, and the text data corresponding to the voice data is processed based on the prompt information to obtain the target notes.
[0129] In this embodiment, note generation based on a specially trained model can improve targeting and processing efficiency; obtaining target notes based on LLM can utilize the excellent text generation capability of LLM to improve the accuracy of the target notes.
[0130] In some embodiments, the acquisition module 702 is further used to:
[0131] The voice data is processed using a first AI model locally deployed in the vehicle computer and / or a second AI model deployed in the cloud to obtain the target notes.
[0132] In this embodiment, obtaining target notes through the first AI model and / or the second AI model can improve processing flexibility.
[0133] In some embodiments, the acquisition module 702 is further used to:
[0134] Performing speech recognition on the speech data to obtain text data corresponding to the speech data; and processing the text data using the first AI model to obtain the target note; or
[0135] Receive the target notes sent by the cloud, where the target notes are obtained after the cloud uses the second AI model to process the text data corresponding to the voice data.
[0136] In this embodiment, the target notes are obtained through the first AI model. Since the first AI model is located in the vehicle computer, the target notes can be generated locally on the vehicle computer, thereby improving processing efficiency. The target notes are obtained through the second AI model. Since the second AI model is located in the cloud, it usually has better performance and can improve processing accuracy.
[0137] In some embodiments, the acquisition module 702 is further used to:
[0138] Sending the voice data or the text data corresponding to the voice data to the cloud, so that the cloud uses the second AI model to process the text data corresponding to the voice data;
[0139] If the notes obtained by the second AI model are obtained, the notes obtained by the second AI model are used as the target notes;
[0140] If the notes obtained by the second AI model are not obtained, the first AI model is used to process the text data corresponding to the voice data to obtain the target notes;
[0141] The model parameter amount of the first AI model is smaller than the model parameter amount of the second AI model.
[0142] In this embodiment, by giving priority to the notes returned from the cloud as the target notes, since the second AI model is a larger-scale model, the accuracy of the target notes can be guaranteed. When the notes returned from the cloud are not obtained through the vehicle computer, the first AI model deployed locally on the vehicle computer is used to generate the target notes, which can ensure reliability. Therefore, the target notes are obtained through the first AI model and the second AI model, which can improve accuracy and reliability.
[0143] Figure 8It is a schematic diagram according to the sixth embodiment of the present disclosure. This embodiment provides a voice data processing device. The device 800 includes: an acquisition module 801, a processing module 802 and a sending module 803.
[0144] The acquisition module 801 is used to obtain the text data corresponding to the voice data collected by the vehicle computer; the processing module 802 is used to process the text data based on the AI model to obtain the target notes; the sending module 803 is used to send the target notes to the vehicle computer, so that the vehicle computer displays the target notes after receiving the note display instruction.
[0145] In this embodiment, voice data is recorded and notes corresponding to the voice data are obtained through an AI model. This eliminates the need for users to record voice content, thereby ensuring driving safety. Important information can be screened out through notes, thereby improving the effectiveness of the recorded voice content.
[0146] In some embodiments, the acquisition module 801 is further used to:
[0147] receiving voice data sent by the vehicle computer, and performing voice recognition on the voice data to obtain the text data; or,
[0148] Receive text data sent by the vehicle computer, where the text data is obtained after the vehicle computer performs voice recognition on the voice data.
[0149] In this embodiment, the cloud can receive the voice data sent by the vehicle computer and perform voice recognition on the voice data to obtain text data, which can improve processing accuracy; or, the cloud can directly receive the text data sent by the vehicle computer, which can improve processing efficiency.
[0150] In some embodiments, the processing module 802 is further configured to:
[0151] Using a large language model as the AI model, the text data is processed based on the prompt information sent by the vehicle computer to obtain the target note; or,
[0152] The text data is processed using an AI model specially trained for generating the target note to obtain the target note.
[0153] In this embodiment, note generation based on a specially trained model can improve targeting and processing efficiency; obtaining target notes based on LLM can utilize the excellent text generation capability of LLM to improve the accuracy of the target notes.
[0154] It can be understood that in the embodiments of the present disclosure, the same or similar contents in different embodiments can be referenced to each other.
[0155] It can be understood that the “first”, “second”, etc. in the embodiments of the present disclosure are only used for distinction and do not indicate the degree of importance, time sequence, etc.
[0156] It is understandable that unless there is any special limitation on the sequence of steps in the process, it means that the timing relationship between these steps is not limited.
[0157] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0158] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
[0159] Fig. 9 A schematic block diagram of an example electronic device 900 that can be used to implement an embodiment of the present disclosure is shown. The electronic device 900 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.
[0160] like Fig. 9 As shown, the electronic device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.
[0161] Multiple components in the electronic device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the electronic device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0162] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above, such as a voice data processing method. For example, in some embodiments, the voice data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 900 via ROM 902 and / or a communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the voice data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the voice data processing method in any other appropriate manner (e.g., by means of firmware).
[0163] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0164] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable task processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0165] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0166] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0167] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.
[0168] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.
[0169] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.
[0170] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.
Claims
1. A method for processing speech data, comprising: Record the voice data collected by the vehicle computer; Obtaining a target note corresponding to the voice data, where the target note is generated after processing the voice data using an artificial intelligence (AI) model; In response to the note display instruction, the target note is displayed.
2. The method according to claim 1, wherein: The obtaining of the target note corresponding to the voice data includes: Using a specially trained model for generating the target note as the AI model, and using the specially trained model for generating the target note to process the text data corresponding to the voice data to obtain the target note; or, The large language model is used as the AI model, and the text data corresponding to the voice data is processed based on the prompt information to obtain the target notes.
3. The method according to claim 1, wherein: The obtaining of the target note corresponding to the voice data includes: The voice data is processed using a first AI model locally deployed in the vehicle computer and / or a second AI model deployed in the cloud to obtain the target notes.
4. The method according to claim 3, wherein: The first AI model locally deployed in the vehicle and / or the second AI model deployed in the cloud are used to process the voice data to obtain the target note, including: Performing speech recognition on the speech data to obtain text data corresponding to the speech data; and processing the text data using the first AI model to obtain the target note; or Receive the target notes sent by the cloud, where the target notes are obtained after the cloud uses the second AI model to process the text data corresponding to the voice data.
5. The method according to claim 3, wherein: The using of the first AI model locally deployed in the vehicle computer and / or the second AI model deployed in the cloud to process the voice data to obtain the note includes: Sending the voice data or the text data corresponding to the voice data to the cloud, so that the cloud uses the second AI model to process the text data corresponding to the voice data; If the notes obtained by the second AI model are obtained, the notes obtained by the second AI model are used as the target notes; If the notes obtained by the second AI model are not obtained, the first AI model is used to process the text data corresponding to the voice data to obtain the target notes; The model parameter amount of the first AI model is smaller than the model parameter amount of the second AI model.
6. A method for processing speech data, comprising: Obtain text data corresponding to the voice data collected by the vehicle computer; Processing the text data based on an artificial intelligence (AI) model to obtain target notes; The target note is sent to the vehicle computer, so that the vehicle computer displays the target note after receiving the note display instruction.
7. The method according to claim 6, wherein: The step of obtaining text data corresponding to the voice data collected by the vehicle computer includes: receiving voice data sent by the vehicle computer, and performing voice recognition on the voice data to obtain the text data; or, Receive text data sent by the vehicle computer, where the text data is obtained after the vehicle computer performs voice recognition on the voice data.
8. The method according to claim 6, wherein: The processing of the text data based on the AI model to obtain the target note includes: Using a large language model as the AI model, the text data is processed based on the prompt information sent by the vehicle computer to obtain the target note; or, The text data is processed using an AI model specially trained for generating the target note to obtain the target note.
9. A speech data processing device, comprising: Recording module, used to record voice data collected by the vehicle computer; An acquisition module, used to acquire a target note corresponding to the voice data, wherein the target note is generated after processing the voice data using an AI model; The display module is used to display the target note in response to the note display instruction.
10. The device according to claim 9, wherein: The acquisition module is further used for: Using a specially trained model for generating the target note as the AI model, and using the specially trained model for generating the target note to process text data corresponding to the voice data to obtain the target note; or, The large language model is used as the AI model, and the text data corresponding to the voice data is processed based on the prompt information to obtain the target notes.
11. The device according to claim 9, wherein: The acquisition module is further used for: The voice data is processed using a first AI model locally deployed in the vehicle computer and / or a second AI model deployed in the cloud to obtain the target notes.
12. The device according to claim 11, wherein The acquisition module is further used for: Performing speech recognition on the speech data to obtain text data corresponding to the speech data; and processing the text data using the first AI model to obtain the target note; or Receive the target notes sent by the cloud, where the target notes are obtained after the cloud uses the second AI model to process the text data corresponding to the voice data.
13. The device according to claim 11, wherein: The acquisition module is further used for: Sending the voice data or the text data corresponding to the voice data to the cloud, so that the cloud uses the second AI model to process the text data corresponding to the voice data; If the notes obtained by the second AI model are obtained, the notes obtained by the second AI model are used as the target notes; If the notes obtained by the second AI model are not obtained, the first AI model is used to process the text data corresponding to the voice data to obtain the target notes; The model parameter amount of the first AI model is smaller than the model parameter amount of the second AI model.
14. A speech data processing device, comprising: An acquisition module is used to acquire text data corresponding to the voice data collected by the vehicle computer; A processing module, used for processing the text data based on an AI model to obtain a target note; The sending module is used to send the target note to the vehicle computer, so that the vehicle computer displays the target note after receiving the note display instruction.
15. The device according to claim 14, wherein: The acquisition module is further used for: receiving voice data sent by the vehicle computer, and performing voice recognition on the voice data to obtain the text data; or, Receive text data sent by the vehicle computer, where the text data is obtained after the vehicle computer performs voice recognition on the voice data.
16. The device according to claim 14, wherein: The processing module is further configured to: Using a large language model as the AI model, the text data is processed based on the prompt information sent by the vehicle computer to obtain the target note; or, The text data is processed using an AI model specially trained for generating the target note to obtain the target note.
17. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.
18. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-8.
19. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 8.