Voice control method and device, storage medium and electronic equipment

Abstract

The present disclosure provides a voice control method, device, storage medium and electronic equipment, the method comprising: in response to a received first voice request, determining a vehicle model corresponding to the first voice request and a vehicle control object; in response to the vehicle model existing in configuration information matching the configuration object of the vehicle control object, and the configuration object supporting voice control, determining a control instruction; in response to the control instruction, performing voice control on the vehicle machine. In the technical solution provided by the present disclosure, configuration information is stored in advance, and a set of configuration information can be adapted to multiple vehicle models, thereby realizing quick adaptation of voice functions for each vehicle model, without the need for manual configuration for different vehicle models, which is efficient, time-saving, low in labor cost and high in accuracy.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle communication technology, and more specifically, to voice control methods, devices, storage media, and electronic devices. Background Technology

[0002] With the continuous development of intelligent technology, there are more and more voice scenarios in vehicles. Vehicle manufacturers usually have many product lines, and the configurations of each product line are different. Therefore, when configuring voice functions for vehicles, it is necessary to manually match the voice functions one by one. The configuration of voice functions is time-consuming and inefficient. Summary of the Invention

[0003] This disclosure provides voice control methods, devices, computer-readable storage media, and electronic devices to address the technical problem of low configuration efficiency of existing vehicle voice functions.

[0004] Firstly, a voice control method is provided, which specifically includes the following steps:

[0005] In response to the received first voice request, determine the vehicle model and vehicle control object corresponding to the first voice request;

[0006] In response to the existence of a configuration object matching the vehicle control object for the vehicle model mentioned in the configuration information, and the configuration object supporting voice control, a control command is determined;

[0007] In response to the control command, the vehicle's infotainment system is controlled by voice.

[0008] Secondly, a voice control device is provided, specifically including the following modules:

[0009] The request processing module is configured to respond to a received first voice request by determining the vehicle model and vehicle control object corresponding to the first voice request.

[0010] The instruction determination module is configured to determine a control instruction in response to the existence of a configuration object that matches the vehicle control object in the configuration information and the configuration object supports voice control.

[0011] The control processing module is configured to perform voice control of the vehicle system in response to the control command.

[0012] Thirdly, a computer-readable storage medium is provided, the storage medium storing a computer program for executing the above-described voice control method.

[0013] Fourthly, an electronic device is provided, the electronic device comprising:

[0014] processor;

[0015] Memory used to store the processor's executable instructions;

[0016] The processor is configured to read the executable instructions from the memory and execute the instructions to implement the above-described voice control method.

[0017] Compared with the prior art, the voice control method, apparatus, computer-readable storage medium, and electronic device provided in this disclosure have at least the following beneficial effects:

[0018] The technical solution provided in this disclosure receives a first voice request. Different first voice requests may correspond to different user intentions, and thus to different vehicle models and different vehicle control objects. Therefore, in response to receiving a first voice request, the vehicle model and vehicle control object corresponding to the first voice request are determined. The vehicle model and vehicle control object are compared with pre-configured configuration information. If a configuration object matching the vehicle control object exists under the vehicle model in the configuration information, and the configuration object supports voice control, a control command can be determined, and the configuration object of the vehicle system can be voice-controlled using the control command. In the technical solution provided in this disclosure, configuration information is pre-stored. One set of configuration information can be adapted to multiple vehicle models, thereby realizing rapid adaptation of voice function for each vehicle model. There is no need for manual configuration for different vehicle models, resulting in high configuration efficiency, short time, low labor costs, and high accuracy. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of this disclosure, the accompanying drawings used in the description of this disclosure will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a voice control method provided in an exemplary embodiment of this disclosure. Figure 1 ;

[0021] Figure 2 This is a flowchart illustrating a voice control method provided in an exemplary embodiment of this disclosure. Figure 2 ;

[0022] Figure 3 This is a flowchart illustrating a voice control method provided in an exemplary embodiment of this disclosure. Figure 3 ;

[0023] Figure 4 This is a schematic diagram of the structure of a voice control device provided in an exemplary embodiment of the present disclosure;

[0024] Figure 5 This is a structural diagram of an electronic device provided in an exemplary embodiment of this disclosure. Detailed Implementation

[0025] The technical solutions of this disclosure will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the embodiments of this disclosure.

[0026] Exemplary methods

[0027] Figure 1 This is a flowchart illustrating an exemplary embodiment of the voice control method provided in this disclosure. The voice control method can be applied to an in-vehicle system or a server, where the server can be a cloud server. Specifically, it includes the following steps:

[0028] Step S11: In response to the received first voice request, determine the vehicle model and vehicle control object corresponding to the first voice request.

[0029] The first voice request is the command issued by the user for voice control. The vehicle model corresponds to the coding information of the vehicle the user intends to control; different vehicle models have different coding information, used to distinguish vehicle types. The vehicle control object is the in-vehicle device that the user intends to control via voice.

[0030] In one possible implementation, the first voice request includes voice content and model parameters. The voice content is the user's speech, and the model parameters are parameters other than the voice content carried when sending the first voice request, used to determine the vehicle model.

[0031] In one possible application scenario, the method provided in this embodiment is applied to a cloud server. When a user drives vehicle A, he says "open the sunroof". The voice acquisition device inside the vehicle collects the voice signal and sends a first voice request with the voice content "open the sunroof" to the cloud server through the vehicle's infotainment system. The first voice request not only carries the voice content but also the model parameter. Therefore, when the first voice request is obtained, the model parameter is read to determine the vehicle model of vehicle A. Furthermore, the vehicle control object is determined based on the voice content of the first voice request. In the case that the voice content is "open the sunroof", the vehicle control object is the sunroof.

[0032] In one possible implementation, the voice content of the first voice request includes the vehicle model and the vehicle control object.

[0033] In one possible application scenario, the method provided in this embodiment is applied to a cloud server. When a user is driving vehicle A, he says "Open the sunroof of A1 (a vehicle model)". The voice acquisition device inside the vehicle collects the voice signal and sends a first voice request with the voice content "Open the sunroof of A1" to the cloud server. Based on the first voice request, the vehicle model is determined to be A1 and the vehicle control object is the sunroof.

[0034] In one possible implementation, the voice content of the first voice request includes the vehicle model and the vehicle control object, and the first voice request also carries a model parameter. In this case, it can be configured to use the carried model parameter as the standard to avoid situations where the user speaks an incorrect vehicle model.

[0035] In one possible implementation, the method provided in this embodiment is applied to an in-vehicle infotainment system, where model parameters are pre-stored within the system. Specifically, after the in-vehicle voice acquisition device acquires a voice signal, it generates a first voice request. If the determined voice content of the first voice request is "open the sunroof," the vehicle control object is determined to be the sunroof based on the voice content, and the pre-stored model parameters are read as the vehicle model.

[0036] In some embodiments, determining the vehicle control object corresponding to the first voice request in step S11 includes:

[0037] Step S111: Determine the semantic recognition result corresponding to the first voice request.

[0038] Step S112: In response to the semantic recognition result belonging to the vehicle control vertical domain, determine the vehicle control object corresponding to the semantic recognition result.

[0039] Specifically, vertical domains are pre-defined, such as a vehicle control domain for controlling the vehicle and a music domain for analyzing music. Upon receiving a first voice request, in response to the first voice request, semantic recognition is performed to determine the semantic recognition result. For example, a semantic recognition model is pre-trained, the first voice request is input into the semantic recognition model, and the semantic recognition result output by the model is determined. Further, it is determined whether the semantic recognition result belongs to the vehicle control domain. If the semantic recognition result belongs to the vehicle control domain, it indicates that the user intends to control the vehicle via voice, thus determining the vehicle control object corresponding to the semantic recognition result; if the semantic recognition result does not belong to the vehicle control domain, it indicates that the user does not intend to control the vehicle via voice, thus ending the current process without further steps. In this embodiment, by dividing the vertical domains, refined management of voice control is achieved, ensuring the accuracy of voice control and the effectiveness of vehicle control object confirmation.

[0040] In some embodiments, said step S112 comprises:

[0041] Step S1121, in response to the semantic recognition result belonging to the vehicle control vertical domain and the semantic recognition result including a preset interrogative word semantics, invoking a pre-stored knowledge base for query to determine the vehicle control object corresponding to the semantic recognition result.

[0042] Wherein, the preset interrogative word semantics refer to preset words with interrogative word properties, for example, zen, zenme, zenyang, zenmeyang, zenmezhuo, ruhe, weishenme etc. A large amount of content for semantic determination is stored in the knowledge base, for example, knowledge content related to the vehicle control vertical domain is stored. According to the content in the knowledge base, the user intent can be determined more accurately, ensuring the accuracy of determining the vehicle control object.

[0043] Specifically, it is determined whether the semantic recognition result belongs to the vehicle control vertical domain; if the semantic recognition result belongs to the vehicle control vertical domain, it is determined whether the semantic recognition result includes the preset interrogative word semantics; if the semantic recognition result includes the preset interrogative word semantics, it indicates that the vehicle control object may not be determined through the voice content of the first voice request, therefore a pre-stored knowledge base is invoked for query, and the vehicle control object corresponding to the semantic recognition result is queried.

[0044] In a possible application scenario, if the voice content of the first voice request is "how to open the sunroof", after semantic recognition is performed on the voice content, it is determined that the semantic recognition result belongs to the vehicle control vertical domain, and the semantic recognition result includes the preset interrogative word semantics "how", therefore the knowledge base is invoked to determine that the vehicle control object corresponding to the semantic recognition result is "sunroof". If the voice content of the first voice request is "how to quickly lower the in-vehicle temperature", after semantic recognition is performed on the voice content, it is determined that the semantic recognition result belongs to the vehicle control vertical domain, and the semantic recognition result includes the preset interrogative word semantics "how", therefore the knowledge base is invoked to determine that the vehicle control object corresponding to the semantic recognition result is "air conditioner".

[0045] Step S1122, in response to the semantic recognition result belonging to the vehicle control vertical domain and the semantic recognition result not including the preset interrogative word semantics, extracting the vehicle control object from the semantic recognition result.

[0046] Specifically, when determining whether the semantic recognition result includes the preset interrogative word semantics, if the semantic recognition result does not include the preset interrogative word semantics, it indicates that the user may directly issue a voice instruction for a certain vehicle control object, such as "open the sunroof", "turn on the air conditioner", etc., therefore the vehicle control object can be extracted according to the semantic recognition result, that is, "sunroof" in "open the sunroof", and "air conditioner" in "turn on the air conditioner".

[0047] In one possible implementation, if the vehicle control object cannot be extracted from the semantic recognition result, a pre-stored knowledge base can be called to query and determine the vehicle control object corresponding to the semantic recognition result.

[0048] It should be noted that, of course, in response to the semantic recognition result belonging to the vehicle control domain, a pre-stored knowledge base can be directly called for querying to determine the vehicle control object corresponding to the semantic recognition result, so as to ensure the accuracy of the vehicle control object determination.

[0049] In this embodiment, when the semantic recognition result belongs to the vehicle control domain, different processing is applied depending on whether the semantic recognition result includes preset interrogative words. When the preset interrogative words are included, it may not be possible to directly extract the vehicle control object from the semantic recognition result, or the extracted object may not be the in-vehicle device that the user intends to control. Therefore, to ensure the accuracy of vehicle control object determination, the vehicle control object is accurately determined based on a pre-stored knowledge base. When the semantic recognition result does not include preset interrogative words, the vehicle control object can be quickly extracted from the semantic recognition result, ensuring the efficiency of vehicle control object determination and saving computing resources.

[0050] Step S12: In response to the existence of a configuration object matching the vehicle control object for the vehicle model in the configuration information, and the configuration object supporting voice control, a control command is determined.

[0051] The configuration information includes vehicle configurations for different vehicle models and their voice control information, meaning one set of configuration information can be applied to multiple vehicle models. The configuration information can be a vehicle configuration table. For example, the table could contain: A1 (vehicle model): sunroof, 360° panoramic camera, reversing camera, etc.; A2 (vehicle model): panoramic sunroof, reversing camera; A3 (vehicle model): sunroof, reversing camera. Voice control is supported for sunroof, panoramic sunroof, and panoramic camera, allowing the configuration table to be applied to A1, A2, and A3 simultaneously, avoiding manual configuration for each model individually. It's worth noting that when product iterations are needed, the configuration information can be updated without OTA (Over-The-Air) version upgrades, resulting in efficient upgrades.

[0052] Specifically, after determining the vehicle model and the vehicle control object, it is determined whether there is a configuration object matching the vehicle control object under the vehicle model in the configuration information. If there is a configuration object matching the vehicle control object, it is determined whether the configuration object supports voice control. If the configuration object supports voice control, a control command is determined, and the configuration object can be controlled through the control command.

[0053] In one possible application scenario, a user driving an A1 vehicle says "Open the sunroof," meaning the initial voice request is "Open the sunroof," carrying the model parameter A1. This identifies the vehicle model as A1 and the vehicle control object as the sunroof. The configuration information is read, and it's determined that the A1 model has a sunroof. Therefore, the configuration information contains a matching object for the vehicle control object: sunroof, and the sunroof supports voice control. Thus, the control command "Open the sunroof" is determined, and this command is used to open the vehicle's sunroof.

[0054] In some embodiments, prior to step S12, the method further includes:

[0055] Step S14: In response to the existence of the vehicle control object in the configuration information for the vehicle model, the configuration information shows that there is a configuration object matching the vehicle control object for the vehicle model.

[0056] Specifically, after obtaining the vehicle model and the vehicle control object, it is determined whether there is a vehicle control object under the vehicle model in the configuration information. If there is a vehicle control object in the configuration information, it is determined that there is a configuration object matching the vehicle control object for the vehicle model in the configuration information.

[0057] For example, if the vehicle model is A1, the vehicle control object is the sunroof, the configuration information stores A1, and A1 is configured with a sunroof, then the sunroof is the matching configuration object. In this case, the vehicle control object and the configuration object are consistent.

[0058] Step S15: In response to the fact that the vehicle model in the configuration information does not exist, a conversion control object that corresponds to the vehicle control object is determined.

[0059] Step S16: In response to the existence of the conversion control object for the vehicle model in the configuration information, the configuration information contains a configuration object that matches the vehicle control object for the vehicle model.

[0060] In steps S15 and S16, the correspondence between different in-vehicle devices is preset, such as the correspondence between sunroof and panoramic sunroof. This means setting the correspondence between in-vehicle devices that have similar functions but different levels. The difference in level often manifests as the difference between high-configuration and low-configuration.

[0061] Specifically, if there is no vehicle control object for the vehicle model in the configuration information, a conversion control object that corresponds to the vehicle control object is further identified. If there is a conversion control object in the configuration information, the conversion control object is a configuration object that matches the vehicle control object. At this time, the vehicle control object and the configuration object are not consistent.

[0062] For example, the correspondence between sunroof and sunroof canopy can be pre-defined. If the first voice request is "Open sunroof," and the vehicle model is identified as A2, the vehicle control object is the sunroof, and the configuration information stores A2, which has a sunroof, meaning there is no sunroof control object in the configuration information, then the corresponding conversion control object is determined to be the sunroof. Since the configuration information for A2 contains the conversion control object sunroof, it can be determined that the vehicle model in the configuration information has a matching configuration object. Therefore, control commands related to the sunroof can be further generated, such as adjusting the sunroof transmittance to the highest level. After controlling the sunroof using this command, further voice feedback can be provided, such as "This car doesn't have a sunroof yet, I've adjusted the sunroof transmittance to the highest level for you." Compared to directly receiving voice feedback "This function is not currently supported," the method provided in this embodiment can more deeply analyze the user's intent and provide clear feedback prompts, allowing the user to better understand the vehicle and facilitating future voice control.

[0063] In this embodiment, by configuring in-vehicle devices with corresponding relationships, the configured objects can be accurately controlled even when the user cannot accurately grasp the in-vehicle devices, thus providing convenience for the user.

[0064] Step S13: In response to the control command, perform voice control on the vehicle system.

[0065] Specifically, after determining the control command, the vehicle's infotainment system is controlled by voice using the control command. When the method provided in this disclosure is applied to an in-vehicle infotainment system, the system is directly controlled after the control command is generated. When the method provided in this disclosure is applied to a cloud server, the control command is returned to the in-vehicle infotainment system after it is generated. After receiving the control command returned by the cloud server, the in-vehicle infotainment system controls the configured object.

[0066] The technical solution provided in this embodiment receives a first voice request. Different first voice requests may correspond to different user intentions, and thus to different vehicle models and different vehicle control objects. Therefore, in response to receiving a first voice request, the vehicle model and vehicle control object corresponding to the first voice request are determined. The vehicle model and vehicle control object are compared with pre-configured configuration information. If a configuration object matching the vehicle control object exists under the vehicle model in the configuration information, and the configuration object supports voice control, a control command can be determined, and the configuration object of the vehicle system can be voice-controlled using the control command. In the technical solution provided in this disclosure, configuration information is pre-stored. One set of configuration information can be adapted to multiple vehicle models, thereby realizing rapid adaptation of voice function for each vehicle model. There is no need for manual configuration for different vehicle models, resulting in high configuration efficiency, short time, low labor costs, and high accuracy.

[0067] In some embodiments, the method further includes:

[0068] Step S17: In response to the existence of a configuration object matching the vehicle control object in the configuration information and the configuration object not supporting voice control, determine the interface information corresponding to the configuration object.

[0069] Step S18: In response to the interface information indicating that the configuration object has a control interface, determine the interface jump instruction.

[0070] Step S19: In response to the interface jump command, control the vehicle system to jump to the control interface.

[0071] The interface information indicates whether the configuration object has a control interface, which refers to the display interface used to control the configuration object inside the vehicle.

[0072] Specifically, when the vehicle model has a matching configuration object in the configuration information, it is determined whether the configuration object supports voice control. If voice control is not supported, meaning the configuration object cannot be directly controlled by voice, a preset voice message such as "XXX cannot be controlled by voice" is often returned. In this embodiment, if voice control is not supported, the interface information corresponding to the configuration object is determined. If the interface information indicates that the configuration object has a control interface, an interface jump command is determined. Using this interface jump command, the vehicle system is controlled to jump to the control interface. The user can control the configuration object through the jump control interface, providing convenience for the user.

[0073] In some embodiments, after the step of controlling the vehicle's infotainment system to switch to the control interface, the method further includes:

[0074] Step S20: Obtain the text information corresponding to the operation buttons in the control interface;

[0075] Step S21: In response to the received second voice request matching the target information in the text information, perform a virtual click operation on the target operation button corresponding to the target information.

[0076] The operation buttons are used to control the configuration interface, such as increasing or decreasing. The system retrieves the text information corresponding to the operation buttons in the control interface and responds to the received second voice request, i.e., the content spoken by the user again. When the second voice request matches the target information in the text information, such as the second voice request being "increase" and corresponding to the "increase" button in the control interface, a virtual click operation can be performed on the target operation button corresponding to the target information, such as a virtual click on the "increase" button. This allows the target operation button to be operated using voice, providing convenience for the user.

[0077] In some embodiments, the method further includes:

[0078] Step S22: In response to the interface information indicating that the configuration object does not have a control interface, determine the first voice information;

[0079] Step S23: Control the vehicle's infotainment system to play the first voice message.

[0080] Specifically, when the configuration object does not support voice control, the interface information corresponding to the configuration object is further determined. If the interface information indicates that the configuration object does not have a control interface, a first voice message is determined, such as "Voice control is not yet supported; please operate manually." In this embodiment, when the configuration object neither supports voice control nor has a control interface, a fallback voice message is determined to provide feedback to the user, allowing the user to understand the voice control progress in a timely manner.

[0081] For example, if the reversing camera does not support voice control, and the first voice request is "turn on the reversing camera", the configuration target is determined to be the reversing camera. Since the reversing camera does not support voice control, it is determined whether the reversing camera has a control interface. If a control interface exists, an interface jump command is generated to control the vehicle's system to jump to the reversing camera's control interface. If no control interface exists, the first voice message is generated and played.

[0082] In one possible implementation, such as Figure 2 As shown, the cloud server includes a gateway control center, control services, a voice learning platform, and capability services. Control services include vehicle control and system control. The gateway control center initiates requests to the control services for all received requests. Once a request is found in any of the control services, it queries either the capability service or the voice learning platform. The voice learning platform queries the knowledge base service; if a relevant command is found, it returns it directly to the control skill; otherwise, it calls the capability service. Depending on its configuration, the capability service may call back commands from the control services to the voice learning platform.

[0083] Specifically, such as Figure 3 As shown, the user initiates the first voice request: "How do I open the canopy?", and the gateway control receives this first voice request. Figure 3 1), used to initiate requests to control services; if a request is hit, the vehicle control service ( Figure 3 (1.1) indicates that the semantic recognition result corresponding to the first voice request belongs to the vehicle control vertical domain, and the vehicle control service processes the semantic related to the interrogative word in the semantic recognition result corresponding to the first voice request. Figure 3 (1.1.1) If there are preset question word semantics, enter the school results query ( Figure 3 (1.1.12) Utilize the Voice Learning Platform to query the knowledge base service to determine the vehicle control object. If the vehicle configuration table is stored in the knowledge base, further determine whether the vehicle control object has a configuration object in the vehicle configuration table based on the knowledge base. If a matching configuration object exists, determine whether the configuration object supports voice control. Based on whether voice control is supported, determine whether there is a command. Based on whether there is a command, decide whether to request the capability. Figure 3 (1.1.2.1) If voice control is supported, there will be control command related content, meaning the control command can be returned directly. If voice control is not supported, there will be no command related content, and a command definition will be requested from the capability service. The capability service will decide whether to request a callback to the system control interface based on the configuration. Figure 3 (1.1.2.2.1), if a control interface exists, then request system control interface commands ( Figure 3 (1.1.2.2.2), System control service processing standard script instructions ( Figure 3 (1.1.2.2.2.1), and return the interface command result, i.e., the interface jump command ( Figure 3 The final result is returned to the client, i.e., the vehicle's infotainment system.

[0084] In some embodiments, the method further includes:

[0085] Step S24: In response to the fact that there is no configuration object matching the vehicle control object for the vehicle model in the configuration information, determine the second voice information;

[0086] Step S25: Control the vehicle's infotainment system to play the second voice message.

[0087] In this embodiment, when there is no matching configuration object for the vehicle model in the configuration information, a second voice message is determined, such as "I don't have what you're talking about," and the vehicle system is controlled to play the second voice message so that the user can understand the voice control process in a timely manner and gain a further understanding of the vehicle based on the second voice message, which is beneficial for the user's subsequent voice control.

[0088] In one possible application scenario, a vehicle configuration table is pre-set and stored on a cloud server. Upon receiving the first voice request, the cloud server determines whether there is a matching configuration object for the vehicle model corresponding to the first voice request, based on the vehicle configuration table. If no configuration object is found, it announces, "I don't have what you're referring to." If a configuration object is found, it further checks whether the configuration object supports voice control. If it does, it generates control commands to control the vehicle's infotainment system via voice. If it does not support voice control, it checks whether the configuration object has a control interface. If it does, it generates an interface navigation command to redirect the vehicle's infotainment system to the configuration object's control interface, allowing the user to control the configuration object. If there is no control interface, it announces, "Voice control is not yet supported; please operate manually."

[0089] Exemplary device

[0090] Based on the same concept as the embodiments of the method disclosed herein, such as Figure 4 As shown in the embodiments of this disclosure, a voice control device is also provided, specifically including the following modules:

[0091] Request processing module 41 is configured to, in response to a received first voice request, determine the vehicle model and vehicle control object corresponding to the first voice request;

[0092] The instruction determination module 42 is configured to determine a control instruction in response to the existence of a configuration object that matches the vehicle control object in the configuration information and the configuration object supports voice control.

[0093] The control processing module 43 is configured to perform voice control on the vehicle system in response to the control command.

[0094] In some embodiments, the apparatus further includes:

[0095] The interface determination module is configured to determine the interface information corresponding to the configuration object in response to the existence of a configuration object that matches the vehicle control object in the configuration information and the configuration object does not support voice control.

[0096] The jump determination module is configured to determine an interface jump instruction in response to the interface information indicating that the configuration object has a control interface;

[0097] The jump control module is configured to control the vehicle system to jump to the control interface in response to the interface jump command.

[0098] In some embodiments, the apparatus further includes:

[0099] The first voice determination module is configured to determine first voice information in response to the interface information indicating that the configuration object does not have a control interface;

[0100] The first voice playback module is configured to control the vehicle's infotainment system to play the first voice information.

[0101] In some embodiments, the apparatus further includes:

[0102] The text acquisition module is configured to acquire the text information corresponding to the operation buttons in the control interface;

[0103] The virtual operation module is configured to perform a virtual click operation on the target operation button corresponding to the target information in the text information in response to a received second voice request matching the target information in the text information.

[0104] In some embodiments, the apparatus further includes:

[0105] The first object determination module is configured to respond to the existence of the vehicle control object in the configuration information, where the vehicle model in the configuration information contains a configuration object that matches the vehicle control object;

[0106] The second object determination module is configured to determine a conversion control object that corresponds to the vehicle control object in response to the fact that the vehicle model in the configuration information does not exist.

[0107] The third object determination module is configured to respond to the existence of the conversion control object for the vehicle model in the configuration information, wherein the vehicle model in the configuration information has a configuration object that matches the vehicle control object.

[0108] In some embodiments, the apparatus further includes:

[0109] The second voice determination module is configured to determine second voice information in response to the fact that there is no configuration object matching the vehicle control object in the configuration information for the vehicle model.

[0110] The second voice playback module is configured to control the vehicle's infotainment system to play the second voice message.

[0111] In some embodiments, the request processing module includes:

[0112] The semantic recognition unit is configured to determine the semantic recognition result corresponding to the first voice request;

[0113] The object determination unit is configured to determine the vehicle control object corresponding to the semantic recognition result in response to the semantic recognition result belonging to the vehicle control vertical domain.

[0114] In some embodiments, the object determination unit includes:

[0115] The query processing sub-unit is configured to, in response to the semantic recognition result belonging to the vehicle control vertical domain and the semantic recognition result including preset question word semantics, call the pre-stored knowledge base to perform a query to determine the vehicle control object corresponding to the semantic recognition result;

[0116] The object extraction subunit is configured to extract the vehicle control object in response to the semantic recognition result belonging to the vehicle control vertical domain and the semantic recognition result not including preset interrogative words.

[0117] Exemplary electronic devices

[0118] Figure 5 A block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0119] like Figure 5 As shown, the electronic device 50 includes one or more processors 51 and memory 52.

[0120] The processor 51 may be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and may control other components in the electronic device 50 to perform desired functions.

[0121] The memory 52 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 51 may execute the program instructions to implement the voice control methods of the various embodiments of this disclosure described above and / or other desired functions.

[0122] In one example, the electronic device 50 may also include an input device 53 and an output device 54, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0123] Of course, for the sake of simplicity, Figure 5 Only some of the components of the electronic device 50 relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 50 may include any other suitable components depending on the specific application.

[0124] Exemplary computer program products and computer-readable storage media

[0125] In addition to the methods and apparatus described above, embodiments of this disclosure may also be computer program products comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps of the voice control methods according to various embodiments of this disclosure as described in the "Exemplary Methods" section of this specification.

[0126] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the vehicle owner's computing device, partially on the vehicle owner's device, as a standalone software package, partially on the vehicle owner's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0127] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the steps of the voice control methods according to various embodiments of this disclosure as described in the "Exemplary Methods" section above.

[0128] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0129] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details of the invention described above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details.

[0130] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0131] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.

[0132] The above description of aspects of the invention is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features of the invention herein.

[0133] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms of the invention herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A voice control method, characterized in that, Specifically, the steps include the following: In response to the received first voice request, determine the vehicle model and vehicle control object corresponding to the first voice request; In response to the existence of a configuration object matching the vehicle control object for the vehicle model mentioned in the configuration information, and the configuration object supporting voice control, a control command is determined; In response to the control command, the vehicle's infotainment system can be controlled by voice. The method further includes: In response to the existence of a configuration object matching the vehicle control object for the vehicle model in the configuration information, and the configuration object not supporting voice control, the interface information corresponding to the configuration object is determined; In response to the interface information indicating that the configuration object has a control interface, a screen navigation instruction is determined; In response to the interface jump command, the vehicle system is controlled to jump to the control interface; After the step of controlling the vehicle's infotainment system to switch to the control interface, the method further includes: Obtain the text information corresponding to the operation buttons in the control interface; In response to the received second voice request matching the target information in the text information, a virtual click operation is performed on the target operation button corresponding to the target information.

2. The method according to claim 1, further comprising: In response to the interface information indicating that the configuration object does not have a control interface, the first voice information is determined; Control the vehicle's infotainment system to play the first voice message.

3. The method according to claim 1, prior to the step of responding to the existence of a configuration object matching the vehicle control object in the configuration information, the method further includes: In response to the existence of the vehicle control object for the vehicle model in the configuration information, the configuration information contains a configuration object that matches the vehicle control object for the vehicle model. In response to the fact that the vehicle model in the configuration information does not exist in the vehicle control object, a conversion control object that has a corresponding relationship with the vehicle control object is determined; In response to the existence of the conversion control object for the vehicle model in the configuration information, the configuration information contains a configuration object that matches the vehicle control object for the vehicle model.

4. The method according to claim 1, further comprising: In response to the fact that no configuration object matching the vehicle control object exists for the vehicle model in the configuration information, the second voice information is determined; Control the vehicle's infotainment system to play the second voice message.

5. The method according to claim 1, wherein determining the vehicle control object corresponding to the first voice request includes: Determine the semantic recognition result corresponding to the first voice request; In response to the semantic recognition result belonging to the vehicle control vertical domain, the vehicle control object corresponding to the semantic recognition result is determined.

6. The method according to claim 5, wherein determining the vehicle control object corresponding to the semantic recognition result in response to the semantic recognition result belonging to the vehicle control vertical domain includes: In response to the semantic recognition result belonging to the vehicle control vertical domain and the semantic recognition result including preset question word semantics, a pre-stored knowledge base is called to query and determine the vehicle control object corresponding to the semantic recognition result; In response to the semantic recognition result belonging to the vehicle control vertical domain and the semantic recognition result not including preset interrogative semantics, the vehicle control object is extracted from the semantic recognition result.

7. A voice control device, characterized in that, Specifically, it includes the following modules: The request processing module is configured to respond to a received first voice request by determining the vehicle model and vehicle control object corresponding to the first voice request. The instruction determination module is configured to determine a control instruction in response to the existence of a configuration object that matches the vehicle control object in the configuration information and the configuration object supports voice control. The control processing module is configured to perform voice control of the vehicle system in response to the control command. The device further includes: The interface determination module is configured to determine the interface information corresponding to the configuration object in response to the existence of a configuration object that matches the vehicle control object in the configuration information and the configuration object does not support voice control. The jump determination module is configured to determine an interface jump instruction in response to the interface information indicating that the configuration object has a control interface; The jump control module is configured to control the vehicle system to jump to the control interface in response to the interface jump command; The device further includes: The text acquisition module is configured to acquire the text information corresponding to the operation buttons in the control interface; The virtual operation module is configured to respond to a received second voice request by matching the target information in the text information with the target information, and to perform a virtual click operation on the target operation button corresponding to the target information.

8. A computer-readable storage medium storing a computer program for performing the voice control method according to any one of claims 1-6.

9. An electronic device, the electronic device comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the voice control method according to any one of claims 1-6.

Images