Vehicle voice reply language generation method, electronic equipment and storage medium
By using voice reply configuration files and dynamic templates in the in-vehicle entertainment system, voice reply is generated based on user status and scene information, the problem of fixed voice reply in the prior art is solved and the user experience is improved.
Patent Information
- Application Number
- CN202310492325.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-04
- Publication Date
- 2024-11-12
AI Technical Summary
The voice reply language in the existing in-car entertainment system is fixed and cannot be dynamically adjusted according to user needs or scene changes, resulting in poor user experience.
By setting up the configuration file of the voice reply language in the vehicle, querying the dynamic reply language template based on user status information and scene information, and generating corresponding voice data, thereby realizing personalized and dynamic changes in voice reply.
Improve the user experience, and the dynamically generated voice reply is more in line with the current user status and scene, enhancing the user experience and satisfaction of the user.
Smart Images

Figure CN118942449A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of vehicle technology, and more specifically, to a method for generating vehicle voice response language, an electronic device, and a storage medium. Background Art
[0002] To improve the user experience, current vehicles are usually equipped with voice control functions. During the voice control process, the in-vehicle entertainment system usually needs to play or display different responses in combination with the voice control commands triggered by the user. At present, the voice broadcast responses to voice control commands in the in-vehicle entertainment system are basically fixed terms generated by product design, and different voice prompts are given according to different functions.
[0003] However, current reply prompts are relatively fixed and cannot be changed based on user needs or scenario changes. Summary of the invention
[0004] The embodiments of the present application provide a method for generating a vehicle voice reply, an electronic device, and a storage medium that can at least partially solve the above-mentioned problems or other problems existing in the prior art.
[0005] An embodiment of the present application provides a method for generating vehicle voice reply words, including: in response to receiving voice data, determining a reply word number according to the voice data; querying a dynamic reply word template corresponding to the reply word number in a reply word configuration file according to current user status information and / or current user scenario information, the reply word configuration file including multiple reply word sets corresponding to different user status information and / or different user scenario information; and generating a reply word corresponding to the voice data according to the dynamic reply word template.
[0006] The embodiment of the present application further provides an electronic device, comprising: at least one processor and a memory. The memory is in communication with the at least one processor and stores instructions that can be executed 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 the method for generating a vehicle voice reply as mentioned in the above embodiment.
[0007] The embodiments of the present application also provide a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for generating a vehicle voice reply as mentioned in the above embodiments is implemented.
[0008] According to some embodiments of the present application, the reply language configuration file includes multiple reply language sets corresponding to different user status information and / or different user scenario information, so that the vehicle computer can query the corresponding dynamic reply language template according to the current user status information and / or the current user scenario information, and dynamically generate reply language corresponding to the voice data, thereby making the reply language feedback by the vehicle computer more in line with the current user status and / or the current user scenario, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings, in which:
[0010] Figure 1 is a schematic block diagram of a vehicle computer according to some implementation modes of the present application;
[0011] Figure 2 is a schematic block diagram of an update system according to some embodiments of the present application;
[0012] Figure 3 is a schematic block diagram of a vehicle computer according to some other implementations of the present application;
[0013] Figure 4 is a flow chart of a method for generating a vehicle voice reply according to some embodiments of the present application;
[0014] Figure 5 is a schematic diagram of the interaction between the reply configuration terminal, the cloud server and the vehicle computer during the update process of the configuration file according to some implementation modes of the present application;
[0015] Figure 6 is a schematic diagram of the interaction between the reply configuration terminal, the cloud server and the vehicle in the process of dynamically changing the configuration file according to other embodiments of the present application; and
[0016] Figure 7 is a schematic block diagram of an electronic device according to some embodiments of the present application. DETAILED DESCRIPTION
[0017] In order to better understand the present application, a more detailed description will be made of various aspects of the present application with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application, and are not intended to limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.
[0018] It should also be understood that expressions such as "include", "including", "have", "contain" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present application, "may" is used to mean "one or more embodiments of the present application". And, the term "exemplary" is intended to refer to an example or illustration.
[0019] Unless otherwise specified, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that, unless clearly stated in this application, words defined in common dictionaries should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.
[0020] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. In addition, unless explicitly limited or contradictory to the context, the specific steps included in the method described in the present application are not necessarily limited to the order described, but can be performed in any order or in parallel. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
[0021] In the Internet of Vehicles, related applications that support voice control generally write the corresponding business logic reply language inside each application, and directly follow the App to output the product. After the vehicle is online, it is not possible to dynamically change the voice broadcast TTS (Text To Speech) preset in each installation package through the backend management website configuration method, such as exception prompts / replies, or prompts / replies in classical Chinese for some fixed business scenarios.
[0022] Figure 1 1 is a schematic block diagram of a vehicle computer 130 according to some implementations of the present application. Figure 1 As shown, the in-vehicle entertainment system of the vehicle computer 130 may include a voice engine service module 131 and an entertainment module 133. The vehicle computer 130 may provide users with voice control services for the entertainment module 133 and other components of the vehicle through the voice engine service module 131.
[0023] In some embodiments, the vehicle computer 130 is equipped with an entertainment module 133 supporting voice control. The entertainment module 133 may include, for example, a music module 1331 , a navigation module 1332 , a radio station 1333 and a video module 1334 . The entertainment module 133 may be communicatively connected with the voice engine service module 131 .
[0024] Optionally, entertainment modules 133 such as music module 1331, navigation module 1332, radio station 1333 and video module 1334 can realize their corresponding functions under user operation. For example, music module 1331 can be used to realize music search, play and other functions, navigation module 1332 can be used to provide electronic map and navigation services, radio station 1333 can be used to receive radio signals and play radio programs, and video module 1334 can be used for video search, play and other functions. The functions of the above modules and the implementation methods of the functions can be set as needed, and this application does not limit this.
[0025] In some embodiments, the voice engine service module 131 may include a voice core engine 1311 and a voice broadcast engine 1312. The voice core engine 1311 may be used to determine the reply language to be played according to the configuration file of the reply language, and send the determined reply language to the voice broadcast engine 1312. After receiving the reply language, the voice broadcast engine 1312 may broadcast the received reply language.
[0026] In some embodiments of the present application, the vehicle computer 130 may determine the reply number according to the voice data after receiving the voice data. It is understandable that after the user says "I want to listen to a song" by voice, the voice data may be recognized by the music module 1331 of the vehicle computer 130 and trigger the music play instruction, or may be recognized by the voice core engine 1331 and trigger the music play instruction, which is not limited here.
[0027] In some scenarios, the voice data is recognized by the application corresponding to the voice data (for example, the music module 1331). Taking the music module 1311 as an example, the music module 1331 recognizes and triggers the voice control instruction corresponding to the voice data, and after recognizing the voice control instruction, sends a reply broadcast request to the voice core engine 1311, and the reply broadcast request may include the reply number related to the voice control instruction, so that the voice core engine 1311 can query the dynamic reply template corresponding to the reply number in the reply configuration file, and generate the reply corresponding to the voice data according to the dynamic reply template.
[0028] In other scenarios, the voice data can be identified and triggered by the voice core engine 1311. After the voice core engine 1311 identifies the corresponding voice control instruction, it can query the dynamic reply language template corresponding to the reply language number of the voice control instruction in the reply language configuration file, and generate the reply language corresponding to the voice data according to the dynamic reply language template. It is understandable that the voice core engine 1311 can determine the voice control instruction corresponding to the voice data through online semantic recognition or offline semantic recognition, and this application does not limit this.
[0029] It should be understood that Figure 1 The voice engine service module 131 and the entertainment module 133 are relatively independent for example description, wherein the music module 1331, the navigation module 1332, etc. can be local applications configured when the vehicle computer 130 leaves the factory, or can be third-party applications.
[0030] It is understandable that, without departing from the teachings of this application, when the vehicle computer 130 is installed with a third-party application, the third-party application may also include its own voice engine service module, and the configuration files of the reply language of each third-party application may be different. For example, the vehicle computer 130 can recognize voice data through the voice engine service module of each third-party application, and determine the reply language based on the configuration files of the reply language of each third-party application. This application does not limit the type and existence form of the voice engine service module.
[0031] In some embodiments of the present application, the configuration file of the reply language can be updated in subsequent use. For example, after being powered on, the vehicle computer 130 can request the latest version information of the configuration file of the reply language from the cloud server; in response to the current version information of the configuration file of the reply language used by the vehicle computer being lower than the latest version information, request the latest version of the configuration file of the reply language from the cloud server; and update the configuration file of the reply language fed back by the cloud server to the voice engine service.
[0032] For ease of understanding, the updating process of the configuration file of the reply language in the speech engine service module is exemplarily described below.
[0033] Figure 2 is a schematic block diagram of a vehicle voice response language update system according to some embodiments of the present application. Figure 2 As shown, the vehicle voice reply updating system 100 may include a reply configuration terminal 110 , a cloud server 120 and a vehicle computer 130 .
[0034] In some embodiments of the present application, the reply language configuration terminal 110 may be connected to a cloud server for communication. The administrator may configure the reply language at the reply language configuration terminal 110. The reply language configuration terminal 110 may generate a configuration file of the reply language according to the configuration of the administrator, and upload the generated configuration file of the reply language to the cloud server 120, so that the administrator can manage the reply language configuration in the background.
[0035] In some embodiments of the present application, the cloud server 120 is respectively connected to the reply language configuration terminal 110 and the vehicle computer 130 in communication to receive and issue the latest version of the reply language configuration file. For example, after receiving the new reply language configuration file sent by the reply language configuration terminal 110, the cloud server 120 can save the new configuration file as the latest version of the reply language configuration file and update the latest version information of the reply language configuration file. The cloud server 120 can also feedback the latest version information of the reply language configuration file to the vehicle computer 130 after receiving the configuration file query instruction from the vehicle computer 130. The cloud server 120 can also send the latest version of the reply language configuration file to the vehicle computer 130 after receiving the configuration file download request from the vehicle computer 130. In the above example, the cloud server 130 can update the reply language configuration file based on the new configuration file of the reply language uploaded by the reply language configuration terminal 110, so that it can be updated to the vehicle computer 130 later, so that the configuration of the reply language is decoupled from the upgrade of the in-vehicle entertainment system. The configuration file of the latest version of the reply message can be sent to the vehicle computer 130 in a more timely manner, which facilitates the management of the reply message and improves the user experience of managers and users.
[0036] Optionally, the cloud server 120 may provide a configuration file upload interface to the reply language configuration terminal 110. When the configuration file upload interface is called and a new configuration file is received, the cloud server 120 may compare the version information of the new configuration file with the version information of the locally stored configuration file. If it is determined that the version information of the new configuration file is different from the version information of the locally stored configuration file, the cloud server 120 may save the new configuration file as the latest version of the configuration file of the reply language, and update the latest version information of the configuration file of the reply language. In the above example, the cloud server 120 updates the configuration file after determining that the new configuration file version is different, which can reduce the waste of resources caused by repeated updates of the same configuration file.
[0037] It should be understood that, without departing from the teachings of the present application, when the cloud server 120 compares the version information of the new configuration file with the version information of the locally stored configuration file, if it is determined that the version information of the new configuration file is different from the version information of the locally stored configuration file, it determines whether the version information of the new configuration file is higher than the version information of the locally stored configuration file; if it is, the new configuration file is saved as the latest version of the configuration file of the reply language, and the latest version information of the configuration file of the reply language is updated; if it is determined not to be, no update is performed, or a confirmation instruction is sent to the reply language configuration terminal 110, and the configuration file is updated after the reply language configuration terminal 110 confirms again, so as to reduce the situation of accidental rollback of the configuration file.
[0038] Optionally, the cloud server 120 may send an update notification to the vehicle computer after determining that the version information of the new configuration file is different from the version information of the locally stored configuration file, so that the vehicle computer can update the local configuration file of the vehicle computer in time. In the above example, the cloud server 120 may notify the vehicle computer to update the configuration file when the new configuration file version is higher, which can improve the real-time performance of the configuration file update.
[0039] In some embodiments of the present application, the vehicle computer 130 may be configured to send a configuration file query instruction to the cloud server 120 after power-on to request the latest version information of the configuration file of the reply language. For example, the vehicle computer 130 may query the latest version information of the configuration file from the cloud server 120 by calling the version information interface of the query configuration file. After receiving the latest version information, the vehicle computer may compare the current version information and the latest version information of the configuration file of the reply language. After determining that the current version information of the configuration file of the reply language used by the vehicle computer is lower than the latest version information, the vehicle computer 130 may request the latest version of the configuration file of the reply language from the cloud server 120. After receiving the configuration file of the reply language fed back by the cloud server 120, the vehicle computer 130 may update the configuration file of the reply language fed back by the cloud server 120 to the voice engine service module of the vehicle computer 130. In the above example, after the vehicle computer is powered on, it automatically queries and obtains the latest version of the configuration file of the reply language from the cloud server, so that the configuration of the reply language is decoupled from the upgrade of the in-vehicle entertainment system, and the latest version of the configuration file of the reply language can be sent to the vehicle computer in a more timely manner, which is convenient for implementing the management of the reply language and improving the user experience of managers and users.
[0040] In some embodiments of the present application, the format of the configuration file of the reply message may be in JSON format. Transmitting the configuration file in JSON format makes the file package of the configuration file smaller, which is more conducive to parsing it by the vehicle computer 130.
[0041] It should be understood that Figure 2Taking the vehicle voice reply update system 100 including a reply configuration terminal 110 and a vehicle computer 130 as an example for exemplary description, without departing from the teachings of this application, the number of reply configuration terminals 110 and vehicle computers 130 communicating with the cloud server 120 can be set as needed, and this application does not impose any restrictions on this.
[0042] It should be understood that, without departing from the teachings of this application, the reply configuration terminal 110 may provide a visual reply configuration interface, which may be set as needed. The reply configuration terminal 110 may generate a configuration file based on the user input detected by the interface. The reply configuration terminal 110 may also detect the user input, perform security verification on the configuration file, etc. This application does not limit the settings of the visual interface of the reply configuration terminal 110.
[0043] Optional, Figure 3 is a schematic block diagram of a vehicle computer according to some other embodiments of the present application. Figure 3 As shown, the vehicle computer 130 may also include a data embedding service module 132 and a system control module 134. Among them, the system control module 134 can be used to control the operation of applications such as a music module, a navigation module 1332, a radio station 1333, and a video module 1334 installed on the vehicle computer 130, and can also be used to realize the control of vehicle components, which is not limited in this application. The data embedding service module 132 can collect user behaviors or operation events with the authorization of the user, so as to perform subsequent analysis based on the collected data, which is conducive to subsequent operations such as updating the reply according to the analysis results.
[0044] It is understandable that for ease of understanding, Figure 1 and Figure 3 The communication connection between each module is not drawn, but this does not mean that there is no data communication between the modules.
[0045] It should be understood that, without departing from the teachings of this application, the analysis process of the collected data can be completed in the vehicle computer 130, or can be completed by the cloud server 120 or other servers equipped with a buried point data analysis model, and this application does not impose any restrictions on this.
[0046] Optionally, the vehicle computer 130 can also upload the image data captured by the in-vehicle camera to the data analysis terminal through the data upload module of the vehicle computer 130, so that the data analysis terminal can analyze the current user's age, emotions and other status, and feedback the analysis results to the manager. Based on the analysis results, the manager can determine whether it is necessary to update the dynamic reply template in the configuration file. Among them, the data analysis terminal can be a cloud server 120, or it can be another device independent of the cloud server 120 but connected to the vehicle computer 130 and the reply configuration terminal 110 for communication, and this application does not limit this.
[0047] It should be understood that without departing from the teachings of this application, the configuration file of the reply language may also be updated by other means, for example, writing the new configuration file of the reply language into the upgrade package of the in-vehicle entertainment system, and updating the configuration file of the reply language during the process of updating the in-vehicle entertainment system. This application does not impose any restrictions on this.
[0048] After completing the exemplary description of the updating process of the configuration file of the reply language, the following exemplary description is given of the process of generating the reply language according to the configuration file of the reply language.
[0049] In some embodiments of the present application, Figure 4 FIG. 1 is a flow chart of a method for generating a vehicle voice reply according to some embodiments of the present application. Figure 4 As shown, the method 200 for generating a vehicle voice reply may include the following steps:
[0050] S21, in response to receiving the voice data, determining a reply message number according to the voice data;
[0051] S22, searching for a dynamic reply phrase template corresponding to the reply phrase number in a reply phrase configuration file according to the current user status information and / or the current user scenario information; wherein the reply phrase configuration file includes a plurality of reply phrase sets corresponding to different user status information and / or different user scenario information; and
[0052] S23, generating a reply language corresponding to the voice data according to the dynamic reply language template.
[0053] According to some embodiments of the present application, the reply language configuration file includes multiple reply language sets corresponding to different user status information and / or different user scenario information, so that the vehicle computer can query the corresponding dynamic reply language template according to the current user status information and / or the current user scenario information, and dynamically generate reply language corresponding to the voice data, thereby making the reply language feedback by the vehicle computer more in line with the current user status and / or the current user scenario, thereby improving the user experience.
[0054] For ease of understanding, the method 200 for generating a vehicle voice reply is exemplarily described below.
[0055] In some embodiments of the present application, the configuration file of the reply language includes a plurality of reply language sets corresponding to different user status information and / or different user scenario information. The voice core engine 1311 can determine the reply language set for matching according to the current user status information and / or the current user scenario information, and query the dynamic reply language template corresponding to the reply language number in the determined reply language set. In the above example, since the configuration file of the reply language includes a plurality of reply language sets corresponding to different user status information and / or different user scenario information, the voice core engine 1311 can dynamically play different reply language under different user states and / or user scenarios, realize dynamic playback of reply language, have more personalization and design sense, can make users feel more intimate, and improve user experience.
[0056] For ease of understanding, the process of determining a dynamic reply phrase template is exemplified below in conjunction with the division method of the reply phrase set.
[0057] Example 1
[0058] In some embodiments of the present application, the configuration file of the reply language includes a plurality of reply language sets corresponding to different user status information. The process of the voice core engine 1311 determining the dynamic reply language template may include: determining the reply language set for matching according to the current user status information, and querying the dynamic reply language template corresponding to the reply language number in the determined reply language set. In the above-mentioned embodiment, the voice core engine 1311 can dynamically feedback different reply languages based on the user status information, thereby improving the user experience.
[0059] It should be understood that, without departing from the teachings of this application, user status information may include at least one of user emotional information, user age information, and user holiday information, and may also include other information, which is not limited by this application.
[0060] For ease of understanding, the following is an exemplary description of the method of determining a dynamic reply template in combination with different user status information.
[0061] As an example, the user status information may include one of the user emotion information, user age information, and user holiday information mentioned above. In this example, the voice core engine 1311 can search for an adaptive dynamic reply template in the reply set based on the user status information, thereby improving the user experience.
[0062] In some scenarios, user status information includes user holiday information, and the current user status information may be, for example, the current date. After receiving the reply broadcast request, the voice core engine 1311 obtains the current date and matches the current date with the preset user holiday information. After the match is successful, the dynamic reply template corresponding to the successfully matched user holiday is used as the query result, and a reply is generated based on the dynamic reply template. It is understandable that if the match fails, the voice core engine 1311 may use the specified reply template as the query result and generate a reply accordingly, or may take other measures, which are not limited in this application.
[0063] For example, on the day of the user's birthday, when the user generates a voice control behavior of the vehicle entertainment system in a vehicle with an in-vehicle entertainment system, the dynamic reply language template configured in advance by the administrator on the birthday can be dynamically called to generate a reply language. For example, the user says: "I want to listen to music", and on a date that is not configured with a special holiday, the determined reply language template can be a specified reply language template, such as "XX's "XX" will be played soon". When the user has a birthday, the voice core engine 1311 can obtain the dynamic reply language template configured in advance on the cloud server by the administrator of the in-vehicle entertainment system according to the user's registered birthday and other information to generate a dynamic reply language. For example, the dynamic reply language template can be "Happy birthday, bring you XX's "XX"", "Happy shelling, bring you XX's "XX"", etc., so as to generate more humanized reply language later.
[0064] Optionally, after being turned on, when the vehicle computer 130 receives voice data for the first time, it may match the current date with the user's holiday information and determine a reply based on the matching result. When it is not the first time that voice data is received, a reply may be directly generated based on a specified reply template to reduce the situation where repeated broadcasts of holiday greetings cause user disgust.
[0065] In other scenarios, user status information includes user emotional information. After receiving the reply broadcast request, the voice core engine 1311 obtains the current user emotional information, and searches for a dynamic reply template that matches the current user emotional information in the reply set, and generates a reply based on the dynamic reply template. It is understandable that if the user emotional information fails to be obtained or matched, the voice core engine 1311 can generate a reply based on the specified reply template, or take other measures, which is not limited in this application.
[0066] It is understandable that the current user emotion information can be obtained in a variety of ways without departing from the teachings of this application. For example, after receiving the reply speech broadcast request, the voice core engine 1311 can obtain the current user emotion information determined based on the image data captured by the in-vehicle camera set in the vehicle. For example, the vehicle computer 130 can pre-store an emotion analysis model, and after the image data captured by the in-vehicle camera is input into the emotion analysis model, the current user emotion information can be determined based on the output of the emotion analysis model.
[0067] For another example, when the user uses voice in the car, he often listens to some sad songs. The car machine 130 can collect user behavior data through data embedding, and analyze user behavior through the embedding data analysis model to determine the current user emotional information, for example, determine whether the current user emotional information indicates that the user is in a sad state or a non-sad state. Among them, the embedding data analysis model can be a model trained based on the user's historical behavior data and determines the user's current emotion based on the user behavior data. After determining that the current user emotional information indicates that the user is in a sad state, the voice core engine 1311 can call the dynamic reply language template corresponding to the sad state to generate a reply language. For example, the user says: "I want to listen to a song", the music module 1331 can trigger a music playback instruction, and the configuration file of the reply language can be configured with a dynamic reply language template corresponding to the music playback instruction in the scenario where the user is in a sad state, which is "Don't let sadness flow back into a river, bring you XX's "XX"".
[0068] In other scenarios, the user status information may include the user's age information. After receiving the reply broadcast request, the voice core engine 1311 obtains the age information of the current user, searches for a dynamic reply template matching the age information of the current user in the reply set, and generates a reply based on the dynamic reply template. The age information of the current user can be obtained based on the analysis of the image data captured by the in-vehicle camera, or can be determined by analyzing the language style of the voice data, or can be obtained in other ways, which is not limited in this application.
[0069] It is understandable that if the user's current age information fails to be obtained or matched, the voice core engine 1311 can generate a reply based on a specified reply template, or take other measures, which is not limited in this application.
[0070] For example, a dynamic reply template for children may be configured in the reply set, and the dynamic reply template may end with more erhua sounds. If the character currently using the voice is a child, this type of dynamic reply template may be used to make it childish. For example, if a user says, "I want to listen to BabyBus nursery rhymes," if the user is not a child, the dynamic reply template may be "OK," and if the user is a child, the dynamic reply template may be "OK," to add a childish touch.
[0071] As another example, the user status information may include at least two types of information, for example, at least two of the user emotion information, user age information, and user holiday information mentioned above. In this example, the voice core engine 1311 searches for an adaptive dynamic reply template in the reply set in combination with a variety of user status information, thereby improving the user experience.
[0072] In some scenarios, the user status information includes user emotion information and user age information, and the voice core engine 1311 determines the dynamic reply template in a manner that may include but is not limited to manner one and manner two.
[0073] Method 1
[0074] In some embodiments, the reply word set includes a plurality of first sets corresponding to different user ages and a plurality of second sets corresponding to different user emotions, and the first set includes one or more interjections. The process of determining the reply word set for matching according to the current user status information may include: in response to the determined user status information including user age information and user emotion information, the first set corresponding to the user age information and the second set corresponding to the user emotion information are determined as the reply word set for matching. The process of querying the dynamic reply word template corresponding to the reply word number in the determined reply word set may include: querying the dynamic reply word template corresponding to the reply word number in the determined second set, and selecting at least one interjection for combination from the determined first set. After the dynamic reply word template is determined in the above manner, the process of generating the reply word corresponding to the voice data according to the dynamic reply word template may include: combining the dynamic reply word template and the selected interjection according to the preset first combination rule to obtain a combined dynamic reply word template, and generating the reply word corresponding to the voice data according to the combined dynamic reply word template.
[0075] As an example, a plurality of first sets corresponding to different user ages may include a first interjection set corresponding to children such as "Yeah", "Ah", "La", etc., and a second interjection set corresponding to adults such as "Of" or a blank character, and a plurality of second sets corresponding to different user emotions may include a first template set corresponding to happy emotions such as "Have fun when you are happy", and a second template set corresponding to sad emotions such as "Don't let sadness flow into a river". The preset first combination rule may be, for example, to combine the dynamic reply language template and the interjection in the form of "dynamic reply language template" + "interjection". If it is determined that the user age is a child and the current emotion is happy, the voice core engine 1311 may determine that the reply language set for matching is the first interjection set and the first template set. If the dynamic reply language template queried in the first template set is "Have fun when you are happy", and the selected interjection is "Yeah", the combined dynamic reply language template obtained by combination is "Have fun when you are happy". If it is determined that the user is an adult and the current emotion is happy, the voice core engine 1311 can determine that the response language set for matching is the first exclamation word set and the first template set. If the dynamic response language template queried in the first template set is "When you are happy, you should be happy", and the selected exclamation word is an empty character, the combined dynamic response language template obtained is "When you are happy, you should be happy". When the user is of other age groups and the current emotion is other emotions, the method of obtaining the combined dynamic response language template can be referred to above and will not be repeated here.
[0076] It is worth mentioning that in the above example, the administrator can configure the user age and user emotion separately, and the voice core engine 1311 combines them, which can reduce the workload of the administrator.
[0077] Method 2
[0078] In some embodiments, any reply word set corresponds to at least one user age information and at least one user emotion information. The voice core engine 1311 can jointly determine the reply word set for matching based on the current user age information and the current user emotion information, and query the dynamic reply word template corresponding to the reply word number in the determined reply word set. For example, the administrator can set the reply word set based on different user ages and different user emotions in the configuration file. For example, the configuration file may include a data table about the correspondence between age, emotion and reply word set. The data table may be shown in Table 1, for example. Through the data table, the voice core engine 1311 can jointly determine the reply word set for matching based on the current user age information and the current user emotion information.
[0079] Table 1
[0080] age mood Reply Collection Children (0-12) sad Collection J11 Adults (13-40) sad Collection J21 Elderly (41-100) sad Collection J31 Children (0-12) Happy Collection J12 Adults (13-40) Happy Collection J22 Elderly (41-100) Happy Collection J32 …… …… ……
[0081] It is understandable that the division of age groups and emotions in Table 1 is for exemplary purposes only. In other implementations, the division of age groups and emotions may be adaptively adjusted, which is not limited here.
[0082] It is understandable that the correspondence between age, emotion and reply word set may also be stored in the configuration file in other forms, and this application does not impose any limitation on this.
[0083] In other scenarios, the user status information includes user holiday information, user emotion information and / or user age information, the reply word set includes at least one third set corresponding to each user holiday, and multiple first sets corresponding to different user ages and / or multiple second sets corresponding to different user emotions, and the current user status information includes the current date. The voice core engine 1311 determines the reply word set for matching according to the current user status information, which may include: in response to the first receipt of voice data, matching the current date with the preset user holiday information; and in response to a successful match, determining the third set corresponding to the successfully matched user holiday as the reply word set for matching; in response to non-first receipt of voice data, or a failed match, determining the reply word set for matching according to the current user emotion information and / or the current user age information. Among them, the process of determining the reply word set according to the current user emotion information and / or the current user age information can refer to the above-mentioned method 1 and method 2, which will not be repeated here.
[0084] It should be understood that without departing from the teachings of this application, the user status information may also include other information. If the user status information includes multiple information, the configuration method of the dynamic reply template in the configuration file and the method of determining the dynamic reply template by the voice core engine 1311 may refer to the above method one and method two, and other methods may also be adopted, which are not limited here.
[0085] Example 2
[0086] In some embodiments of the present application, the multiple reply language sets in the reply language configuration file include reply language sets corresponding to different user scenarios. The voice core engine 1311 can dynamically determine and feedback the reply language according to the current user scenario to improve the user experience.
[0087] As an example, user scenarios may be defined based on different time periods, and the configuration file may be configured with a set of reply words for different time periods. For example, the configuration file may include a set of reply words configured for daytime and a set of reply words configured for nighttime.
[0088] As another example, the user scenario can be defined based on the operating state of the vehicle computer, and the configuration file can be configured with a set of reply words for normal state and a set of reply words for abnormal state. For example, for the network state in the operating state, a dynamic reply word template corresponding to the network abnormality can be configured in the configuration file. For example, the user says: "I want to listen to Jay Chou's song", if the current network is not good, a dynamic reply word template can be selected from the set of reply words for abnormal network. For example, the dynamic reply word template can be "The network is not good, and my IQ can't keep up."
[0089] It is understandable that if the administrator wants to change this dynamic reply template, the administrator can configure it in advance on the reply configuration terminal and modify the dynamic reply template. When the vehicle computer is powered on next time, based on the update method mentioned above, the vehicle computer will check the current version information of the local configuration file to update the local reply configuration file, so as to achieve the purpose of the administrator dynamically changing the dynamic reply template.
[0090] It should be understood that, without departing from the teachings of this application, each reply word set mentioned in the above embodiments may include dynamic reply word templates with multiple reply word numbers. The dynamic reply word templates with the same reply word number in different reply word sets may be the same or different, which is not limited here.
[0091] Example 3
[0092] In some embodiments of the present application, multiple reply word sets in the configuration file of the reply word are divided into reply word set groups corresponding to different user scenario information, and each reply word set group includes a reply word set corresponding to different user status information. The voice core engine 1311 determines the reply word set for matching according to the current user status information and the current user scenario information, which may include: determining the reply word set group for matching according to the current user scenario information; and determining the reply word set for matching from the determined reply word set group according to the current user status information. For example, the manager can set the reply word set for different user status information respectively for different user scenarios. In the process of the voice core engine 1311 determining the reply word based on the configuration file, the matching reply word set group can be first screened out from the multiple reply word set groups based on the current user scenario, and then the reply word set for matching can be screened out based on the user status information, and finally the reply word is determined based on the screened reply word set. Among them, the process of determining the reply word based on the screened reply word set can refer to the relevant description in Example 1, which is not repeated here.
[0093] It is worth mentioning that the above example enables the car computer to dynamically respond to the user based on the current user scenario and user status, making the response more in line with the environment that triggers the voice control command, thereby improving the user experience.
[0094] After completing the exemplary description of determining a dynamic reply language template, the following exemplary description is given of generating a reply language corresponding to voice data according to the dynamic reply language template.
[0095] In some embodiments of the present application, the dynamic reply template in the reply configuration file is a complete reply template, for example, the above-mentioned "Happy birthday, I bring you XX's "XX"", "Happy birth, I bring you XX's "XX"", etc. In this case, the voice core engine 1311 can directly bring the music information or other information to be played into the dynamic reply template to generate a reply.
[0096] In some other embodiments of the present application, the dynamic reply language template in the configuration file of the reply language includes the part of the complete reply language template that will change according to the current user status information and / or the current user scenario information, and the part that does not change with the current user status information and / or the current user scenario information is configured as a fixed reply language template. In this case, the voice core engine 1311 determines the dynamic reply language template according to the current user status information and / or the current user scenario information, and the reply language number, and determines the fixed reply language template according to the reply language number. Afterwards, the voice core engine 1311 can generate a reply language corresponding to the voice data in combination with the dynamic reply language template and the fixed reply language template according to the preset second combination rule. Among them, the second combination rule can, for example, indicate that the dynamic reply language template and the fixed reply language template are generated according to the mode of dynamic reply language template + fixed reply language template. In the above example, setting the fixed reply part of the voice control instruction as a fixed template can reduce the parameters that need to be edited in the reply language template setting, reducing the workload of the administrator.
[0097] For example, a fixed reply template corresponding to playing music may include "Bring you XX's "XX"", and a dynamic reply template may include "Happy Birthday", "Don't let sadness flow into a river", etc. By combining the dynamic reply template and the fixed reply template, multiple replies such as "Happy Birthday, bring you XX's "XX"", "Don't let sadness flow into a river, bring you XX's "XX"" can be obtained.
[0098] It should be understood that without departing from the teachings of the present application, the combination of the dynamic reply language template and the fixed reply language template can be set as needed. For example, the second combination rule can, for example, indicate that a reply language is generated according to the pattern of the first part of the dynamic reply language template + the fixed reply language template + the second part of the dynamic reply language template. The present application does not impose any restrictions on this.
[0099] For ease of understanding, the following Figure 5 and Figure 6The example interaction process among the reply configuration terminal 110 , the cloud server 120 and the vehicle computer 130 exemplifies the updating process of the configuration file and the generating process of the reply.
[0100] Figure 5 1 is a schematic diagram of the interaction between the reply configuration terminal 110, the cloud server 120 and the vehicle computer 130 during the update process of the configuration file in some embodiments of the present application. Figure 5 As shown, the update process of the configuration file of the reply language may include the following steps:
[0101] S41, the reply configuration terminal 110 changes the dynamic reply template and generates a new reply configuration file.
[0102] For example, the dynamic reply template can be changed by the administrator. For example, after confirming that the administrator has successfully logged in, the reply configuration terminal 110 provides a visual interface for the administrator to configure the dynamic reply template, and generates a new configuration file after detecting that the administrator clicks the upload control.
[0103] Optionally, the manager can design some single reply words in the early stage design to speed up the early development progress. If the manager wants to change the voice reply words, he can configure it on the reply word configuration terminal 110 after the vehicle goes online, and add multiple dynamic reply word templates for dynamic broadcast.
[0104] S42 , the reply language configuration terminal 110 sends the new reply language configuration file and the version information of the new reply language configuration file to the cloud server 120 .
[0105] S43, the cloud server 120 saves the configuration file of the new reply language. The process of the cloud server 120 saving the configuration file of the new reply language can be referred to the above related description, which will not be repeated here.
[0106] S44, after the vehicle computer 130 is powered on, the voice core engine 1311 requests the cloud server 130 for the latest version information of the configuration file of the reply speech.
[0107] For example, when the vehicle leaves the factory, the voice core engine 1311 can configure an initial reply configuration file and the version number of the configuration file. When the vehicle computer 130 is powered off and then powered on, the latest version information of the configuration file can be actively queried to confirm whether the reply configuration file needs to be updated.
[0108] S45, the cloud server 130 returns the latest version information of the configuration file of the reply message.
[0109] S46, the voice core engine 1311 compares the latest version information of the configuration file with the current version information. For example, if the current version information is lower than the latest version information, step S471 can be executed, otherwise, the original reply configuration file can continue to be used without updating.
[0110] S471, the voice core engine 1311 requests the cloud server 120 for the latest version of the reply language configuration file.
[0111] S472, the cloud server 120 returns the configuration file of the latest version of the reply language.
[0112] S473, the voice core engine 1311 uses the latest version of the reply language configuration file to update the local reply language configuration file, and updates the current version information of the reply language configuration file.
[0113] S48, the music module 1331 in the entertainment module 133 detects that the user's voice data indicates that the user needs to listen to music, and sends a reply message broadcast request to the voice core engine 1311. The reply message broadcast request may include a reply message number related to the start of music playback.
[0114] S49, the voice core engine 1311 searches for and generates a reply word corresponding to the reply word number in the local reply word configuration file. The process of the voice core engine 1311 searching and generating the reply word can be referred to the above related description, which will not be repeated here.
[0115] S50, the voice core engine 1311 sends the determined reply language to the voice broadcast engine 1312.
[0116] S51, after receiving the reply, the voice broadcast engine 1312 may broadcast the received reply.
[0117] Through the above implementation, after the car computer is powered on, it automatically queries the cloud server and obtains the latest version of the reply language configuration file, so that the configuration of the reply language is decoupled from the upgrade of the in-vehicle entertainment system. The latest version of the reply language configuration file can be sent to the car computer in a more timely manner, which facilitates the management of reply language and improves the user experience of managers and users. In addition, the car computer can query the corresponding dynamic reply language template based on voice data to realize dynamic voice reply, which improves the user experience. Managers can more easily realize the dynamic change of reply language in different scene modes more conveniently and easily, giving users a more humane experience.
[0118] Figure 61 is a schematic diagram of the interaction between the reply configuration terminal 110, the cloud server 120 and the vehicle in the process of dynamically changing the configuration file in some embodiments of the present application. For example, the vehicle includes a vehicle computer 130, an in-vehicle camera 140 and a data upload module 150. The vehicle computer 130 includes a voice engine service module 131 and an entertainment module 133. The voice engine service module 131 may include a voice core engine 1311 and a voice broadcast engine 1312. Figure 6 As shown, the update process of the configuration file of the reply language may include the following steps:
[0119] S61, the in-vehicle camera 140 captures image data of the interior of the vehicle.
[0120] S62, the in-car camera 140 determines detection data based on the image data, and sends the detection data to the data upload module 150. For example, the in-car camera 140 can directly use the image data as detection data, or can detect the user status information of the in-car user based on the image data as detection data. The user status information may include user emotional information and user age information. It should be understood that the in-car camera 140 can directly send the detection data to the data upload module 150 after obtaining it, or can send it to the data upload module 150 after determining that the user status information has changed, and this application does not limit this.
[0121] S63 , the data uploading module 150 transmits the detection data transmitted by the in-vehicle camera 140 to the cloud server 130 .
[0122] S64, the cloud server 130 can determine whether there is new user status information based on the detection data. For example, there is user age information or user emotion information that does not match the current configuration file. If it is determined to be yes, step S65 is executed, otherwise, the detection data can be deleted.
[0123] It should be understood that without departing from the teachings of this application, the cloud server 130 may also directly execute step S65, and the administrator may determine whether the configuration needs to be updated, and this application does not impose any restrictions on this.
[0124] S65, the cloud server 130 sends the detection data to the reply configuration terminal 110, so that the administrator can determine whether to update the configuration. If the administrator determines that the configuration needs to be updated, the configuration file of the reply can be modified or re-edited at the reply configuration terminal 110.
[0125] S66, the reply configuration terminal 110 generates and sends a new reply configuration file to the cloud server 130 based on the administrator's editing. Afterwards, the configuration file will be updated to the vehicle computer 130. The update process can be referred to Figure 5 , I will not go into details here.
[0126] S67, after the vehicle computer 130 detects that the user controls the entertainment module 133 with voice, it initiates a voice recognition request to the cloud server 130 through the voice core engine 1311.
[0127] S68, the voice core engine 1311 receives the voice recognition result returned by the cloud server.
[0128] S691, the voice core engine 1311 sends corresponding voice control instructions to the entertainment module 133 according to the voice recognition result.
[0129] S692, the voice core engine 1311 determines a reply word based on the triggered voice control instruction, and sends the determined reply word to the voice broadcast engine 1312 so that the voice broadcast engine 1312 performs voice broadcast.
[0130] It should be understood that step S691 and step S692 may be executed simultaneously or one after the other, and this application does not impose any limitation on this.
[0131] S70, the entertainment module 133 executes the received voice control instruction.
[0132] Through the above implementation, the administrator can more easily and conveniently realize the dynamic change of reply words in different scene modes, giving users a more humane experience.
[0133] It should be noted that in the technical solution of this application, the acquisition, storage and application 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. It should also be noted that the information in this embodiment is obtained after the user authorizes it to provide (that is, with the consent of the user himself). In addition, the information / data obtained is not intended to represent a specific type of user, and therefore cannot reflect the personal information of a specific type of user.
[0134] The step division of the above methods is only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this patent.
[0135] The embodiment of the present application also provides an electronic device, such as Figure 7As shown, the electronic device 800 may include: at least one processor and a memory, the memory is communicatively connected to the at least one processor and stores instructions that can be executed 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 the above-mentioned method 200 for generating vehicle voice reply language.
[0136] As an example, the electronic device 800 may be a vehicle computer 130, and its processor may execute the method 200 for generating vehicle voice response language mentioned in the above embodiment.
[0137] One embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, a method 200 for generating a vehicle voice reply is implemented.
[0138] Figure 7 8 is a schematic block diagram of an electronic device 800 according to some embodiments of the present application. Figure 7 As shown, the electronic device 800 includes a processor 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a memory 808 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The processor 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.
[0139] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, such as buttons and touch screens of the vehicle computer; an output unit 807, connected to, for example, various types of displays, speakers, etc., to output various forms of signals; a memory 808, including any medium for storing computer executable programs; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through, for example, a local area network or other wireless communication networks.
[0140] The processor 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 801 performs the various methods and processes described above, such as the method 200 for generating a vehicle voice reply. For example, in some embodiments, the method 200 for generating a vehicle voice reply may be implemented as a computer software program, which is tangibly contained in a computer-readable storage medium, such as a memory 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the processor 801, one or more steps of the method 200 for generating a vehicle voice reply described above may be performed. Alternatively, in other embodiments, the processor 801 may be configured to execute the method 200 for generating a vehicle voice reply in any other appropriate manner (eg, by means of firmware).
[0141] Various aspects of the present application are described herein with reference to the flowcharts and / or timing diagrams of the methods, devices (systems), and computer program products according to the exemplary embodiments of the present application. It should be understood that each step of the flowchart and / or timing diagram and the combination of the steps in the flowchart and / or timing diagram can be implemented by computer-readable program instructions.
[0142] These computer-readable program instructions can be provided to a processor in an electronic device, a general-purpose computer, a special-purpose computer, or a processing unit of other programmable data processing devices, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / steps specified in one or more steps in the flowchart and / or timing diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / steps specified in one or more steps in the flowchart and / or timing diagram.
[0143] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / steps specified in one or more steps in the flowchart and / or timing diagram.
[0144] The flowchart and timing diagram in the accompanying drawings show the possible architecture, functions and operations of the equipment, methods and computer program products according to multiple embodiments of the present application. In this regard, each step in the flowchart or timing diagram can represent a part of a module, a program segment or an instruction, and a part of the module, a program segment or an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative embodiments, the functions marked in the steps can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each step in the timing diagram and / or the flowchart, and the combination of the steps in the timing diagram and / or the flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0145] The above description is only an implementation method of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of protection involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the technical concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in this application.
Claims
1. A method for generating a vehicle voice reply, characterized in that: include: In response to receiving the voice data, determining a reply speech number according to the voice data; According to the current user status information and / or the current user scenario information, querying the dynamic reply phrase template corresponding to the reply phrase number in the reply phrase configuration file, wherein the reply phrase configuration file includes a plurality of reply phrase sets corresponding to different user status information and / or different user scenario information; as well as Generate a reply language corresponding to the voice data according to the dynamic reply language template.
2. The method according to claim 1, wherein: The querying of the dynamic reply language template corresponding to the reply language number in the reply language configuration file according to the current user status information and / or the current user scenario information includes: Determining a set of reply words for matching according to current user status information and / or current user scenario information; and The dynamic reply phrase template corresponding to the reply phrase number is searched in the determined reply phrase set.
3. The method according to claim 2, wherein: The plurality of reply word sets are divided into reply word set groups corresponding to different user scenario information, and each reply word set group includes a reply word set corresponding to different user status information; Wherein, determining a set of reply words for matching according to the current user state information and the current user scenario information includes: Determining a response language set for matching according to the current user scenario information; and According to the current user status information, a reply word set for matching is determined from the determined reply word set group.
4. The method according to claim 2, wherein: The user status information includes at least one of user emotion information, user age information and user holiday information.
5. The method according to claim 4, wherein: The reply word set includes a plurality of first sets corresponding to different user ages and a plurality of second sets corresponding to different user emotions, wherein the first set includes one or more interjections; The step of determining a set of reply words for matching according to the current user status information includes: In response to determining that the user state information includes the user age information and the user emotion information, determining a first set corresponding to the user age information and a second set corresponding to the user emotion information as the reply language set for matching; The step of searching the determined reply statement set for a dynamic reply statement template corresponding to the reply statement number includes: Searching the determined second set for a dynamic reply language template corresponding to the reply language number, and selecting at least one interjection for combination from the determined first set; Generating a reply language corresponding to the voice data according to the dynamic reply language template includes: Combining the dynamic reply template and the selected interjection word according to a preset first combination rule to obtain a combined dynamic reply template; and A reply language corresponding to the voice data is generated according to the combined dynamic reply language template.
6. The method according to claim 4, wherein: Any of the reply word sets corresponds to at least one of the user age information and at least one of the user emotion information; The step of determining a set of reply words for matching according to the current user status information includes: The reply language set for matching is jointly determined according to the current user age information and the current user emotion information.
7. The method according to claim 4, wherein: The reply word set includes at least one third set corresponding to user festivals, and a plurality of first sets corresponding to different user ages and / or a plurality of second sets corresponding to different user emotions, and the current user festival information includes the current date; The step of determining a set of reply words for matching according to the current user status information includes: In response to receiving the voice data for the first time, matching the current date with the user holiday information; and In response to a successful match, a third set corresponding to the successfully matched user festivals is determined as the reply language set for matching.
8. The method according to any one of claims 1 to 7, wherein: The method further comprises: Querying the fixed reply phrase template corresponding to the reply phrase number in the configuration file of the reply phrase; Generating a reply language corresponding to the voice data according to the dynamic reply language template includes: According to a preset second combination rule, the dynamic reply language template and the fixed reply language template are combined to generate a reply language corresponding to the voice data.
9. The method according to claim 1, wherein: The method further comprises: In response to the vehicle computer being powered on, requesting the cloud server for the latest version information of the configuration file of the reply message; In response to the current version information of the configuration file of the reply language used by the vehicle computer being lower than the latest version information, requesting the cloud server for the latest version of the configuration file of the reply language; and The configuration file of the reply language fed back by the cloud server is updated to the speech engine service.
10. An electronic device, characterized in that: include: at least one processor; as well as, A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can execute the method for generating a vehicle voice reply as described in any one of claims 1 to 9.
11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for generating a vehicle voice response language according to any one of claims 1 to 9 is implemented.
