A cloud server-based vehicle-mounted intelligent voice system training method and device

Abstract

The application discloses a kind of based on cloud server's vehicle-mounted intelligent voice system training method and device, the method includes: applied to vehicle-mounted intelligent voice system, vehicle-mounted intelligent voice system is connected with cloud server, method includes: obtaining voice instruction issued by user, and determine whether voice instruction is in the instruction set of vehicle-mounted intelligent voice system;When judging that voice instruction is not in the instruction set of vehicle-mounted intelligent voice system, determine whether voice instruction is trainable instruction;When judging that voice instruction is trainable instruction, receive the training operation of user to vehicle-mounted intelligent voice system to train vehicle-mounted intelligent voice system;Training data obtained by training vehicle-mounted intelligent voice system to voice instruction is uploaded to cloud server.The application solves the problem that user experience is not good due to the great limitation of vehicle-mounted intelligent voice system in the prior art.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a training method and apparatus for an in-vehicle intelligent voice system based on a cloud server. Background Technology

[0002] Nowadays, in-vehicle voice systems are one of the important interaction methods in the cockpit. Intelligent voice is an important part of the future digital cockpit, and more intelligent in-vehicle voice systems are what users expect.

[0003] Currently, in-vehicle intelligent voice systems rely on a limited number of technical personnel for generalization, data collection, training, testing, optimization, and iteration. When faced with user content that exceeds their own generalization resource library, they can only provide feedback such as "cannot answer" or "still need to learn." In-vehicle intelligent voice systems have significant limitations, resulting in a poor user experience. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a training method and device for an in-vehicle intelligent voice system based on a cloud server, which aims to solve the problem that the user experience is poor due to the large limitations of the in-vehicle intelligent voice system in the prior art.

[0005] The embodiments of the present invention are implemented as follows: A training method for an in-vehicle intelligent voice system based on a cloud server is provided, applicable to an in-vehicle intelligent voice system connected to a cloud server. The method includes: The system acquires voice commands issued by the user and determines whether the voice commands are within the instruction set of the in-vehicle intelligent voice system. When it is determined that the voice command is not in the instruction set of the vehicle intelligent voice system, it is determined whether the voice command is a trainable command. When it is determined that the voice command is a trainable command, the system receives the user's training operation on the in-vehicle intelligent voice system to train the in-vehicle intelligent voice system. The system acquires training data obtained by training the in-vehicle intelligent voice system in response to the voice commands, and uploads the training data to the cloud server.

[0006] Furthermore, the above-mentioned training method for an in-vehicle intelligent voice system based on a cloud server further includes, after the step of acquiring training data obtained from training the in-vehicle intelligent voice system based on the voice command and uploading the training data to the cloud server: Search the cloud server for a target voice command whose similarity to the voice command is within a preset threshold range; Obtain target response information corresponding to the target voice command, and adjust the training data based on the target response information.

[0007] Furthermore, in the above-mentioned training method for an in-vehicle intelligent voice system based on a cloud server, after the step of determining whether the voice command is a trainable command when it is determined that the voice command is not in the instruction set of the in-vehicle intelligent voice system, the method further includes: When it is determined that the voice command is an untrainable command, the voice command is pushed to the technician through the cloud server; After the technician provides feedback on the voice command, the cloud server receives the technician's feedback information on the voice command. Furthermore, the above-mentioned training method for an in-vehicle intelligent voice system based on a cloud server further includes, after the step of acquiring training data obtained from training the in-vehicle intelligent voice system based on the voice command and uploading the training data to the cloud server: Obtain the model number of the in-vehicle intelligent language system, and set up multiple training data storage sub-databases on the cloud server according to the model number of the in-vehicle intelligent language system; The training data is categorized according to the model of the in-vehicle intelligent language system, and then stored in the training data storage sub-database according to preset rules.

[0008] Furthermore, in the above-mentioned training method for an in-vehicle intelligent voice system based on a cloud server, the step of storing the training data into the training data storage sub-database according to preset rules after classification includes: Semantic analysis is performed on the first training data within a preset time period, and the training data is decomposed into multiple semantic fields; Obtain the unique identifier code and the number of segments of the semantic field of the training data storage sub-database respectively; The encryption key for the training data storage sub-database is determined based on the unique identifier code, semantic field, and the number of segments in the semantic field; The training data within the preset time period is stored in the training data storage sub-database according to the encryption key.

[0009] Furthermore, in the above-mentioned training method for an in-vehicle intelligent voice system based on a cloud server, the step of determining the encryption key for the training data storage sub-database based on the unique identifier code, semantic fields, and the number of segments in the semantic fields includes: The number of encrypted elements extracted from each semantic field is determined based on the number of segments in the semantic field. The encrypted element is selected from each of the semantic fields and assigned to the unique identifier code to determine the encryption key.

[0010] Furthermore, the above-mentioned training method for an in-vehicle intelligent voice system based on a cloud server further includes: When it is determined that the voice command is not in the command set of the in-vehicle intelligent voice system, the voice command is searched for in the cloud server, and after the voice command is found, the corresponding response data is determined and fed back through the in-vehicle voice system.

[0011] Another aspect of the present invention is to provide a cloud server-based training device for an in-vehicle intelligent voice system, which is applied in an in-vehicle intelligent voice system connected to a cloud server. The device includes: The acquisition module is used to acquire the voice commands issued by the user and determine whether the voice commands are in the instruction set of the vehicle intelligent voice system. The judgment module is used to determine whether the voice command is a trainable command when it is determined that the voice command is not in the instruction set of the vehicle intelligent voice system. The receiving module is used to receive the user's training operation on the vehicle intelligent voice system to train the vehicle intelligent voice system when it is determined that the voice command is a trainable command. The upload module is used to acquire training data obtained by training the in-vehicle intelligent voice system in response to the voice commands, and upload the training data to the cloud server.

[0012] Another object of the present invention is to provide a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0013] Another object of the present invention is to provide an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method described above.

[0014] This invention acquires voice commands issued by the user and determines whether the voice command is within the instruction set of the in-vehicle intelligent voice system. If the voice command is not within the instruction set, it determines whether the voice command is a trainable command. If the voice command is trainable, it receives the user's training operation on the in-vehicle intelligent voice system to train the system. It acquires the training data obtained from training the in-vehicle intelligent voice system based on the voice commands and uploads the training data to a cloud server. By using the voice commands generated by the user's daily needs to train the in-vehicle intelligent voice system's AI through self-learning, and with the support of cloud data, it can continuously provide users with more intelligent and user-responsive in-vehicle intelligent voice services. This solves the problem of poor user experience caused by the limitations of existing in-vehicle intelligent voice systems. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the structure of a vehicle-mounted intelligent voice system training system based on a cloud server in one embodiment of the present invention; Figure 2 This is a flowchart of the training method for an in-vehicle intelligent voice system based on a cloud server in the first embodiment of the present invention; Figure 3 This is a structural block diagram of the vehicle-mounted intelligent voice system training device based on a cloud server in the third embodiment of the present invention.

[0016] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0017] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0018] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0020] Please see Figure 1 The diagram shows a schematic representation of a cloud server-based training system for an in-vehicle intelligent voice system according to an embodiment of the present invention. The system includes an in-vehicle intelligent voice system and a cloud server communicatively connected to the in-vehicle intelligent voice system, wherein: The in-vehicle intelligent voice system receives voice commands from the user and identifies whether the command is in the preset command set, i.e., whether it can accurately provide feedback data. Moreover, even when the voice command is not in the preset command set, the system can be trained by the user through a predetermined process. The cloud server receives the training data and sends it to the corresponding in-vehicle intelligent voice system training system. It can also provide data to the user for training and provide positive feedback support. Technicians can learn from and process the training data, and maintain the training data and cloud data.

[0021] It should be pointed out that, Figure 1 The structure shown does not constitute a limitation on the cloud server-based in-vehicle intelligent voice system training system. In other embodiments, the cloud server-based in-vehicle intelligent voice system training system may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0022] The following will describe in detail how to improve the user experience of in-vehicle intelligent voice systems, with reference to specific embodiments and accompanying drawings.

[0023] Example 1 Please see Figure 1 The image shows a cloud server-based training method for an in-vehicle intelligent voice system according to the first embodiment of the present invention. The method is applied to an in-vehicle intelligent voice system connected to a cloud server and includes steps S10 to S13.

[0024] Step S10: Obtain the voice command issued by the user and determine whether the voice command is in the command set of the vehicle intelligent voice system.

[0025] Among them, the AI-powered in-vehicle intelligent voice system responds to the user's voice commands. Specifically, it determines whether the user's voice command is within the command set, that is, whether the current in-vehicle intelligent voice system can accurately respond to the voice command. Step S11: When it is determined that the voice command is not in the command set of the vehicle intelligent voice system, determine whether the voice command is a trainable command.

[0026] Among them, instructions not in the instruction set are distinguished by AI according to safety principles and relevant norms and regulations, and are divided into trainable instructions and non-trainable instructions. Trainable instructions refer to instructions that users can train the in-vehicle intelligent voice system, that is, to inform in advance what information needs to be fed back after receiving the voice instruction, so that accurate feedback can be given after receiving the voice instruction again.

[0027] Untrainable instructions refer to instructions that users cannot train the intelligent voice system through a predetermined process. When the voice instruction is determined to be untrainable, it will be pushed to the technical personnel through the cloud server. After the technician provides feedback on the voice command, the cloud server receives the technician's feedback information on the voice command.

[0028] Untrainable instructions are fed back to the cloud for unified review by backend technical staff, and this logic is further improved by post-training technical staff.

[0029] Step S12: When it is determined that the voice command is a trainable command, the user's training operation on the vehicle intelligent voice system is received to train the vehicle intelligent voice system. Among them, those classified as trainable instructions allow AI to guide users through a predetermined process to train the intelligent voice system.

[0030] In addition, in some optional embodiments of the present invention, during training, a target voice instruction whose similarity to the voice instruction is within a preset threshold range is searched in the cloud server. Obtain target response information corresponding to the target voice command, and adjust the training data based on the target response information.

[0031] Specifically, it calls upon all similar operation cases in the cloud to provide positive feedback support to the in-vehicle intelligent voice system, thereby providing users with more personalized services.

[0032] Step S13: Obtain training data obtained by training the in-vehicle intelligent voice system for the voice command, and upload the training data to the cloud server.

[0033] The intelligent voice system uploads its training data to the cloud after training. Specifically, the training data includes at least voice commands and their corresponding accurate feedback responses.

[0034] Furthermore, after the training data is uploaded to the cloud server, if it is determined that the voice command is not in the command set of the in-vehicle intelligent voice system, the voice command is searched for in the cloud server. Once the voice command is found, the corresponding response data is determined and fed back through the in-vehicle voice system. This provides cloud data support for the in-vehicle intelligent voice system so that when other users encounter the same or similar voice commands, they can prepare a response based on the data stored in the cloud.

[0035] In summary, the cloud-based in-vehicle intelligent voice system training method in the above embodiments of the present invention acquires voice commands issued by the user and determines whether the voice commands are within the instruction set of the in-vehicle intelligent voice system. If the voice commands are not within the instruction set of the in-vehicle intelligent voice system, it determines whether the voice commands are trainable commands. If the voice commands are trainable commands, it receives the user's training operation on the in-vehicle intelligent voice system to train the in-vehicle intelligent voice system. It acquires the training data obtained from training the in-vehicle intelligent voice system based on the voice commands and uploads the training data to the cloud server. By using the voice commands generated by the user's daily needs to train the in-vehicle intelligent voice system through its AI self-learning and with the support of cloud data, it can continuously provide users with more intelligent and user-friendly in-vehicle intelligent voice services, solving the problem of poor user experience caused by the limitations of in-vehicle intelligent voice systems in the prior art.

[0036] Example 2 This embodiment also proposes a cloud server-based training method for an in-vehicle intelligent voice system. The difference between the cloud server-based training method for an in-vehicle intelligent voice system in this embodiment and the cloud server-based training method for an in-vehicle intelligent voice system in Embodiment 1 is as follows: Step S13 and the following steps include: Obtain the model number of the in-vehicle intelligent language system, and set up multiple training data storage sub-databases on the cloud server according to the model number of the in-vehicle intelligent voice system; The training data is categorized according to the model of the in-vehicle intelligent voice system, and then stored in the training data storage sub-database according to preset rules.

[0037] After uploading the training data to the cloud server, it is necessary to store and manage the data. To facilitate management, multiple different training data storage sub-databases are set up in the cloud server. According to the model of the in-vehicle intelligent voice system, the training data generated by different models of in-vehicle intelligent voice systems are stored in different training data storage sub-databases.

[0038] In addition, in some optional embodiments of the invention, the step of storing the training data according to preset rules into the training data storage sub-database after classification includes: Semantic analysis is performed on the first training data within a preset time period, and the training data is decomposed into multiple semantic fields; Obtain the unique identifier code and the number of segments of the semantic field of the training data storage sub-database respectively; The encryption key for the training data storage sub-database is determined based on the unique identifier code, semantic field, and the number of segments in the semantic field; The training data within the preset time period is stored in the training data storage sub-database according to the encryption key.

[0039] Furthermore, to enhance data storage security, data is encrypted within different time periods, and the encryption key is dynamically modified for each preset time period. The preset time periods can be set according to actual conditions, such as one day or one week. Typical training data includes text information corresponding to voice commands. Semantic analysis is performed on the training data, decomposing it into multiple semantic fields. Analysis can be performed based on pause marks; for example, semantic analysis of "OK, now play music for you" yields the fields "OK" and "now play music for you." The unique identifier code of the training data storage sub-database and the number of segments in the semantic fields are then obtained. Each training data storage sub-database is configured with a unique identifier code, primarily composed of numbers and letters, and the number of segments in the semantic fields is obtained, such as the "2" segments mentioned above. Based on these encryption elements, a corresponding encryption key is generated; this encryption key is the encryption key for the sub-database within the current time period.

[0040] Specifically, the number of encrypted elements extracted from each semantic field is determined based on the number of segments in the semantic field; The encrypted element is selected from each of the semantic fields and assigned to the unique identifier code to determine the encryption key.

[0041] Based on the determined segment number "2", it is determined that two encryption elements need to be extracted from the semantic field. Specifically, the encryption elements can be the letters involved in the semantic field. Two letters are extracted from the pinyin of the text in the semantic field and randomly assigned to the unique identifier code to determine the encryption key.

[0042] In summary, the cloud-based in-vehicle intelligent voice system training method in the above embodiments of the present invention acquires voice commands issued by the user and determines whether the voice commands are within the instruction set of the in-vehicle intelligent voice system. When it is determined that the voice commands are not within the instruction set of the in-vehicle intelligent voice system, it determines whether the voice commands are trainable commands. When it is determined that the voice commands are trainable commands, it receives the user's training operation on the in-vehicle intelligent voice system to train the in-vehicle intelligent voice system. It acquires the training data obtained by training the in-vehicle intelligent voice system based on the voice commands and uploads the training data to the cloud server. By using the voice commands generated by the user's daily needs to train the in-vehicle intelligent voice system through self-learning of the AI, and with the support of cloud data, it can continuously provide users with more intelligent in-vehicle intelligent voice services that better meet user needs. This solves the problem of poor user experience caused by the significant limitations of in-vehicle intelligent voice systems in the prior art.

[0043] Example 3 Please see Figure 3 The image shows a cloud server-based training device for an in-vehicle intelligent voice system proposed in the third embodiment of the present invention. This device is applied to an in-vehicle intelligent voice system connected to a cloud server. The device includes: The acquisition module 100 is used to acquire the voice command issued by the user and determine whether the voice command is in the instruction set of the vehicle intelligent voice system. The judgment module 200 is used to determine whether the voice command is a trainable command when it is determined that the voice command is not in the instruction set of the vehicle intelligent voice system. The receiving module 300 is used to receive the user's training operation on the vehicle intelligent voice system to train the vehicle intelligent voice system when it is determined that the voice command is a trainable command. The upload module 400 is used to acquire training data obtained by training the in-vehicle intelligent voice system in response to the voice commands, and upload the training data to the cloud server.

[0044] Furthermore, in the aforementioned cloud-server-based in-vehicle intelligent voice system training device, after the step of acquiring training data obtained from training the in-vehicle intelligent voice system based on the voice commands and uploading the training data to the cloud server, the device further includes: Search the cloud server for a target voice command whose similarity to the voice command is within a preset threshold range; Obtain target response information corresponding to the target voice command, and adjust the training data based on the target response information.

[0045] Furthermore, in the aforementioned cloud-server-based in-vehicle intelligent voice system training device, after the step of determining whether the voice command is a trainable command when it is determined that the voice command is not in the instruction set of the in-vehicle intelligent voice system, the device further includes: When it is determined that the voice command is an untrainable command, the voice command is pushed to the technician through the cloud server; After the technician provides feedback on the voice command, the cloud server receives the technician's feedback information on the voice command. Furthermore, in the aforementioned cloud-server-based in-vehicle intelligent voice system training device, after the step of acquiring training data obtained from training the in-vehicle intelligent voice system based on the voice commands and uploading the training data to the cloud server, the device further includes: Obtain the model number of the in-vehicle intelligent voice system, and set up multiple training data storage sub-databases on the cloud server according to the model number of the in-vehicle intelligent voice system; The training data is categorized according to the model of the in-vehicle intelligent voice system, and then stored in the training data storage sub-database according to preset rules.

[0046] Furthermore, in the aforementioned cloud-server-based in-vehicle intelligent voice system training device, the step of classifying and storing the training data according to preset rules into the training data storage sub-database includes: Semantic analysis is performed on the first training data within a preset time period, and the training data is decomposed into multiple semantic fields; Obtain the unique identifier code and the number of segments of the semantic field of the training data storage sub-database respectively; The encryption key for the training data storage sub-database is determined based on the unique identifier code, semantic field, and the number of segments in the semantic field; The training data within the preset time period is stored in the training data storage sub-database according to the encryption key.

[0047] Furthermore, in the aforementioned cloud-server-based in-vehicle intelligent voice system training device, the step of determining the encryption key for the training data storage sub-database based on the unique identifier code, semantic fields, and the number of segments in the semantic fields includes: The number of encrypted elements extracted from each semantic field is determined based on the number of segments in the semantic field. The encrypted element is selected from each of the semantic fields and assigned to the unique identifier code to determine the encryption key.

[0048] Furthermore, the aforementioned cloud server-based in-vehicle intelligent voice system training device further includes; The feedback module is used to search for the voice command from the cloud server when it is determined that the voice command is not in the command set of the vehicle intelligent voice system, and to determine the corresponding response data to be fed back through the vehicle voice system after the voice command is found.

[0049] The functions or operation steps implemented by the above modules are largely the same as those in the above method embodiments, and will not be repeated here.

[0050] Example 4 In another aspect, the present invention provides a readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the steps of the method described in any one of the above embodiments one to two.

[0051] Example 5 In another aspect, the present invention provides an electronic device, the electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any one of the methods described in embodiments one to two above.

[0052] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0053] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable instructions for implementing logical functions, and can be embodied in any computer-readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable storage medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0054] More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable storage media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0055] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0056] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0057] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A training method for an in-vehicle intelligent voice system based on a cloud server, characterized in that, The method, applied in an in-vehicle intelligent voice system connected to a cloud server, includes: The system acquires voice commands issued by the user and determines whether the voice commands are within the instruction set of the in-vehicle intelligent voice system. When it is determined that the voice command is not in the instruction set of the vehicle intelligent voice system, it is determined whether the voice command is a trainable command. When it is determined that the voice command is a trainable command, the system receives the user's training operation on the in-vehicle intelligent voice system to train the in-vehicle intelligent voice system. Acquire training data obtained by training the in-vehicle intelligent voice system in response to the voice commands, and upload the training data to the cloud server; After the step of acquiring training data obtained from training the in-vehicle intelligent voice system for the voice command and uploading the training data to the cloud server, the method further includes: Obtain the model number of the in-vehicle intelligent voice system, and set up multiple training data storage sub-databases on the cloud server according to the model number of the in-vehicle intelligent voice system; The training data is classified according to the model of the vehicle-mounted intelligent voice system, and after classification, the training data is stored in the training data storage sub-database according to preset rules. The step of classifying the training data and storing it in the training data storage sub-database according to preset rules includes: Semantic analysis is performed on the first training data within a preset time period, and the training data is decomposed into multiple semantic fields; Obtain the unique identifier code and the number of segments of the semantic field of the training data storage sub-database respectively; The encryption key for the training data storage sub-database is determined based on the unique identifier code, semantic field, and the number of segments in the semantic field; The training data within the preset time period is stored in the training data storage sub-database according to the encryption key; The step of determining the encryption key for the training data storage sub-database based on the unique identifier code, semantic field, and the number of segments in the semantic field includes: The number of encrypted elements extracted from each semantic field is determined based on the number of segments in the semantic field. The encrypted element is selected from each of the semantic fields and assigned to the unique identifier code to determine the encryption key.

2. The training method for an in-vehicle intelligent voice system based on a cloud server according to claim 1, characterized in that, After the step of acquiring training data obtained from training the in-vehicle intelligent voice system for the voice command and uploading the training data to the cloud server, the method further includes: Search the cloud server for a target voice command whose similarity to the voice command is within a preset threshold range; Obtain target response information corresponding to the target voice command, and adjust the training data based on the target response information.

3. The training method for an in-vehicle intelligent voice system based on a cloud server according to claim 1, characterized in that, After determining that the voice command is not in the instruction set of the in-vehicle intelligent voice system, the step of determining whether the voice command is a trainable command further includes: When it is determined that the voice command is an untrainable command, the voice command is pushed to the technician through the cloud server; After the technician provides feedback on the voice command, the cloud server receives the technician's feedback information on the voice command.

4. The training method for an in-vehicle intelligent voice system based on a cloud server according to any one of claims 1 to 3, characterized in that, The method further includes; When it is determined that the voice command is not in the command set of the in-vehicle intelligent voice system, the voice command is searched for in the cloud server, and after the voice command is found, the corresponding response data is determined and fed back through the in-vehicle voice system.

5. A training device for an in-vehicle intelligent voice system based on a cloud server, characterized in that, The device is applied to an in-vehicle intelligent voice system, wherein the in-vehicle intelligent voice system is connected to a cloud server, and is used to implement the cloud server-based in-vehicle intelligent voice system training method according to any one of claims 1 to 4, wherein the device comprises: The acquisition module is used to acquire the voice commands issued by the user and determine whether the voice commands are in the instruction set of the vehicle intelligent voice system. The judgment module is used to determine whether the voice command is a trainable command when it is determined that the voice command is not in the instruction set of the vehicle intelligent voice system. The receiving module is used to receive the user's training operation on the vehicle intelligent voice system to train the vehicle intelligent voice system when it is determined that the voice command is a trainable command. The upload module is used to acquire training data obtained by training the in-vehicle intelligent voice system in response to the voice commands, and upload the training data to the cloud server.

6. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1 to 4.

7. A vehicle, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the method as described in any one of claims 1 to 4.

Images