Location-based activation of voice control without the use of a specific activation term

Abstract

The present disclosure relates to a device and a computer-implemented method for voice control of a motor vehicle, and to a corresponding motor vehicle. The device (1100) has an interface (1110) which is designed to communicate information for actuation to at least one specific vehicle component (1200) of the motor vehicle (1000) and further has a control module (1120). The control module 1120 is designed to detect (100) spoken words (110); to analyse (200) detected (100) spoken words (110) with respect to a relevant term (210), wherein the relevant term (210) constitutes a key term for actuating the specific motor vehicle component (1200); to identify (300) a relevant vehicle state (310) based on the analysed (200) relevant term (210); to determine (400) a common context (410) between the analysed (200) relevant term (210) and the relevant vehicle state (310); and to actuate (500) the specific vehicle component (1200) based on the determined (400) common context (410).

Description

[0001] Description

[0002] Location-based activation of voice control without using a specific activation term

[0003] The present invention relates to voice controls in motor vehicles.

[0004] Before each voice command, an activation action (SDS button or activation word) must be performed to start the voice command. Traditionally, voice dialog systems are activated using so-called wake-up words, such as "Hello Volkswagen," followed by the voice command, or by using hot words. When hot words are used, the voice dialog system responds to a minimal set of commands, such as "Skip Track" for media control, without the specific activation of the voice command. The latter is popular in Asia. The disadvantage is the very limited set of commands available with hot words. The risk of false activation due to recognized terms within the wrong conversation context increases with the number of usable terms.

[0005] WO 2021 199 707 A1 discloses a device and a method for activating a virtual personal assistant in a motor vehicle using a user's voice. The embodiments enable calibration of one or more devices for recognizing a keyword for activating the virtual personal assistant with corresponding values ​​of operating parameters of these devices that depend on the recognized user. This allows adjustment of the sensitivity of the activation keyword recognition according to a setting associated with the identified user, thus improving the recognition performance of the activation keyword spoken by any user of the vehicle.

[0006] EP 3 654 329 A1 discloses an in-vehicle device comprising a first speech recognition unit configured to recognize, by speech recognition, from a first voice data input to the in-vehicle device, a word indicative of the in-vehicle device and a word indicative of a first instruction type. The first instruction type is one of the instruction types for operating the in-vehicle device.The in-vehicle device further comprises a second voice recognition unit configured to recognize, in response to the word indicative of the in-vehicle device recognized from the first voice data by the first voice recognition unit, a word indicative of a second instruction type by means of the voice recognition from a second voice data input to the in-vehicle device, wherein the second voice data input occurs after the first voice data input, and wherein the second instruction type is one of the instruction types for operating the in-vehicle device.

[0007] It is therefore desirable to provide improved voice control for motor vehicles.

[0008] This is done by means of a voice control device for a motor vehicle, a method for voice control for a motor vehicle and by means of a related motor vehicle.

[0009] The voice control device for a motor vehicle has an interface configured to communicate control information with at least one specific vehicle component of the motor vehicle, and a control module. The control module is configured to recognize spoken words, analyze recognized spoken words for a relevant term, wherein the relevant term represents a key term for controlling the specific motor vehicle component, identify a relevant vehicle state based on the analyzed relevant term, determine a common context between the analyzed relevant term and the relevant vehicle state, and control the specific vehicle component based on the determined common context.

[0010] A voice control device according to the present invention refers to a device for recognizing human spoken language. The voice control device can be located entirely within the vehicle interior, thus locally, but parts of the voice control of the voice control device can also be connected externally to the vehicle, for example, via a backend, a cloud, or the like, in which speech recognition and / or speech processing can be performed. For this purpose, it may be necessary for the motor vehicle to establish a wireless communication connection to the backend in order to send the perceived speech, which is converted into data, to the backend and to receive its evaluation. However, the voice control device can also be implemented entirely locally, so that no external data connection for evaluating the perceived speech is required.

[0011] Speech refers to the sounds or words spoken by a vehicle user that are to be perceived and evaluated.

[0012] A relevant term within the meaning of the invention refers to a word or a combination of words that are evaluated for meaningfulness within the context for which the speech recognition device is configured. Meaningfulness refers to terms, each consisting of a corresponding word or a corresponding combination of words, that are indicative of a vehicle user's desire to operate at least one part of the motor vehicle accordingly. Thus, to instruct the voice control device to execute a command for operating and / or controlling at least one vehicle component.

[0013] A key term within the meaning of the invention means a term that can be stored in a command set for a specific vehicle component and that, when used and recognized, can operate and / or control at least part of the specific vehicle component accordingly.

[0014] A relevant vehicle state refers to a state of the motor vehicle and / or at least one corresponding component of the motor vehicle, which can be stored in a vehicle state set to define which types of states of the motor vehicle can be addressed, thus operable and / or controlled via a voice command. These can, for example, be states that are indicative of a current vehicle position at a so-called point of interest (POI), such as a gas station, a car wash, the area in front of one's garage, a drive-in movie theater, a section of road in a forest, and the like.

[0015] A common context within the meaning of the invention means a defined relationship between the relevant term and the relevant vehicle state, which, when combined with one another and thus placed in a common context, can address and accordingly control a limited number of defined controllable vehicle components. The common context must be unambiguous to avoid misinterpretations. For example, if the vehicle is at a car wash directly next to a drive-in open-air cinema and the motor vehicle is a convertible, it is important to be able to clearly determine whether the common context means controlling vehicle components to prepare the motor vehicle for a car wash or for an open-air evening at the cinema.In this case, the convertible top is also one of the vehicle components that can be addressed and can be opened in good weather in the second case, but it is better to close it in the first case.

[0016] According to the invention, more than one vehicle component can be addressed and thus controlled based on the common context.

[0017] Thus, by combining hot words with additional triggers, such as the user's location, contextual references can be established and false triggers minimized. For example, if the system detects that the user is at a car wash, the additional hot word "Car Wash Mode On" could be activated within the system and recognized by the system in a context-related manner without having to activate the voice system beforehand. A GPS sensor can be used for location determination, and the loudspeaker or display can be used to output information to the vehicle user.

[0018] This has the advantage that the user dialogue becomes more human, i.e. more natural, through context-based language interaction without the use of an additional activation action.

[0019] According to a further aspect of the invention, a method for voice control of a motor vehicle is provided, the method comprising: recognizing spoken words; analyzing recognized spoken words for a relevant term, wherein the relevant term represents a key term for controlling at least one specific motor vehicle component; identifying a relevant vehicle state based on the analyzed relevant term; determining a common context between the analyzed relevant term and the relevant vehicle state; and controlling at least one part of the motor vehicle based on the determined common context.

[0020] For this purpose, corresponding technical means can be provided, such as a speech recognition means for recognizing spoken words; an analysis means for analyzing recognized spoken words for a relevant term; an identification means for identifying a relevant vehicle state based on the analyzed relevant term; a determination means for determining a common context between the analyzed relevant term and the relevant vehicle state; and a control means for controlling a part of the motor vehicle and / or at least one vehicle component based on the determined common context.

[0021] This has the advantage of providing a way to make the user dialogue more human / natural based on rules and thus to be carried out by means of a control module or a computer device.

[0022] According to yet another aspect of the invention, a motor vehicle is provided which has a voice control device according to the invention.

[0023] This has the advantage that a motor vehicle can be provided in which the user dialogue becomes more human / natural based on rules and the vehicle user can therefore communicate with the vehicle in a more relaxed and natural manner.

[0024] According to yet another aspect of the invention, a computer program product is provided, comprising program code for carrying out a method according to the invention for voice control for a motor vehicle when the computer program product is executed on a computing unit, device or system according to the invention.

[0025] This has the advantage of providing a way to make the user dialogue more human / natural based on rules and thus to be carried out automatically.

[0026] According to a first embodiment, the control module of the voice control device is further configured to select, based on the relevant term, that vehicle state from a plurality of vehicle states which is most probable for the relevant term.

[0027] This has the advantage that the context options can be meaningfully restricted at an early stage. This makes it even easier to prevent operating errors, and the voice control system can also process and analyze the information more efficiently and thus more quickly. According to a further embodiment, the voice control device is further configured to determine the relevant vehicle state from a vehicle state type group. The vehicle state type group includes an external spatial situation of the motor vehicle and / or a current interior situation of the motor vehicle.

[0028] This has the advantage that context options can be further and more effectively restricted at an early stage. This makes it even easier to prevent operating errors, and voice control can also process and analyze information more efficiently and thus more quickly.

[0029] According to a further embodiment, the external spatial situation of the motor vehicle comprises: a current geographical location of the motor vehicle; a current point-of-interest location of the motor vehicle; an inclination situation of the motor vehicle, and / or a vehicle surroundings situation, in particular with regard to the lighting conditions and / or visibility conditions in the surroundings of the motor vehicle.

[0030] This has the advantage that context options can be further and more effectively restricted at an early stage. This makes it even easier to prevent operating errors, and voice control can also process and analyze information more efficiently and thus more quickly.

[0031] According to a further embodiment, the current interior situation of the motor vehicle comprises: a setting of a seat position for a vehicle seat of the motor vehicle; a setting of a lighting source of the interior of the motor vehicle; a setting of a window position, roof position and / or door position of the motor vehicle; a setting of an air conditioning system for at least one interior area of ​​the motor vehicle, and / or a sound and / or video setting of an entertainment device of the motor vehicle.

[0032] This has the advantage that context options can be further and more effectively restricted at an early stage. This makes it even easier to prevent operating errors, and voice control can also process and analyze information more efficiently and thus more quickly.

[0033] According to a further embodiment, the voice control device is further configured such that the control module is permanently activated; thus, without a fixed key term activating the control module, so that the control module begins to analyze recognized spoken words for a relevant term.

[0034] The voice control device can be configured to immediately remove irrelevant terms from the memory and thus to process only those terms that may be relevant for controlling the motor vehicle or its components.

[0035] According to a further embodiment, the control module of the voice control device is further configured to recognize spoken words in the interior of the motor vehicle and / or in the surroundings of the motor vehicle.

[0036] This has the advantage that the voice control can also be accessed from outside and thus the vehicle can also be controlled by voice from outside, i.e. outside the interior.

[0037] Various aspects of the present disclosure relate to an apparatus comprising one or more processors and one or more memory devices configured to perform the method presented above.

[0038] Various aspects of the present disclosure relate to a program having program code for the previously presented method when the program code is executed on a computer, a processor, a control module or a programmable hardware component.

[0039] The following describes the features of the method, the corresponding device, a corresponding computer program, and the vehicle in relation to the method. Features described in connection with the method can also be incorporated into the corresponding device, the corresponding computer program, and the corresponding vehicle.

[0040] Various aspects of the present disclosure relate to a computer-implemented method for controlling one or more settings of a vehicle, as well as to a corresponding device and a corresponding computer program. The method, the device and the computer program can be used to adapt (i.e., change) the one or more settings based on the following criteria. Not all vehicle settings are equally suitable for the present concept. In particular, the present concept is suitable for one or more settings that can be changed by the one or more occupants of the vehicle via a user interface (of the vehicle), i.e., settings that can also be changed by the users themselves without this requiring a change to the hardware or software of the vehicle.A possible restriction to such settings also has the advantage that the actions of the occupants, i.e., the changes in settings by the occupants, can be recorded and used to train the machine learning model. Consequently, the method can include recording a change in settings by the occupants, along with corresponding environmental indicators. For example, the one or more vehicle settings can relate to functions of an interior of the vehicle, such as comfort functions of the vehicle. These can, for example, be one or more vehicle settings, at least one of an air conditioning setting of the vehicle, a seat setting of the vehicle, a lighting setting of the vehicle, or a windshield wiper setting of the vehicle.However, the vehicle's suspension settings can also be included, such as switching between a comfort and a sport suspension setting. Other settings are also conceivable.

[0041] Some examples will now be described in more detail with reference to the accompanying figures. However, other possible examples are not limited to the features of these detailed embodiments. These may include modifications of the features, as well as equivalents and alternatives to the features. Furthermore, the terminology used herein to describe specific examples is not intended to be limiting of other possible examples.

[0042] Throughout the description of the figures, identical or similar reference numerals refer to identical or similar elements or features, which may be implemented identically or in a modified form while providing the same or a similar function. Furthermore, the thickness of lines, layers, and / or regions in the figures may be exaggerated for clarity.

[0043] When two elements A and B are combined using "or", this should be understood to mean that all possible combinations are disclosed, that is, only A, only B, and A and B, unless explicitly defined otherwise in a specific case. As an alternative formulation for the same combinations, "at least one of A and B" or "A and / or B" can be used. This applies equivalently to combinations of more than two elements. If a singular form, e.g. "a" and "the", is used and the use of only a single element is neither explicitly nor implicitly defined as mandatory, further examples may also use multiple elements to implement the same function. If a function is described below as being implemented using multiple elements, further examples may implement the same function using a single element or a single processing entity.It is further understood that the terms "comprises", "comprising", "has" and / or "having" when used herein describe the presence of the specified features, integers, steps, operations, processes, elements, components and / or a group thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, processes, elements, components and / or a group thereof.

[0044] Some examples of devices and / or methods are explained in more detail below with reference to the accompanying figures. They show:

[0045] Fig. 1 shows a block diagram of an example of a voice control device for a motor vehicle according to the invention;

[0046] Fig. 2 shows a flowchart of an example of a method for voice control for a motor vehicle according to the invention; and

[0047] Fig. 3 shows a schematic example of a motor vehicle according to the invention with a voice control device.

[0048] Fig. 1 shows a block diagram of an example of a voice control device 1100 according to the invention for a motor vehicle 1000. The voice control device has an interface 1110 configured to communicate control information with at least one specific vehicle component 1200 of the motor vehicle 1000, and a control module 1120.The control module 1120 is configured to recognize 100 spoken words 110; analyze 200 recognized 100 spoken words 110 for a relevant term 210, wherein the relevant term 210 represents a key term for controlling the specific motor vehicle component 1200; identify 300 a relevant vehicle state 310 based on the analyzed 200 relevant term 210; determine 400 a common context 410 between the analyzed 200 relevant term 210 and the relevant vehicle state 310; and control 500 the specific vehicle component 1200 based on the determined 400 common context 410.

[0049] Fig. 2 shows a flowchart of an example of a method according to the invention for voice control of a motor vehicle 1000. The method comprises: recognizing 100 spoken words 110; analyzing 200 recognized 100 spoken words 110 for a relevant term 210, wherein the relevant term 210 represents a key term for controlling at least one specific motor vehicle component 1200; identifying 300 a relevant vehicle state 310 based on the analyzed 200 relevant term 210; determining 400 a common context 410 between the analyzed 200 relevant term 210 and the relevant vehicle state 310; and controlling 500 at least one part of the motor vehicle 1000 based on the determined 400 common context 410.

[0050] Fig. 3 shows a schematic example of the invention of a motor vehicle 1000 with a voice control device 1100. The motor vehicle 1000 has a voice control device 1100 according to the invention, as shown or explained, for example, in Fig. 1.

[0051] The aim of the invention is therefore to provide a simplified voice control system for a motor vehicle that does not require dedicated activation commands such as "Hello Volkswagen", "Hello Siri" and the like, and is also capable of establishing a context between the spoken instruction and a current situation in the motor vehicle in order to control the motor vehicle based on this context. This contributes to making verbal interaction with the motor vehicle more natural for a user and also preventing incorrect control of the motor vehicle. Because the context already limits which instructions can actually be useful, the processing speed of the voice control system is also increased, since fewer evaluation options have to be taken into account. This can also facilitate the learning of vehicle user profiles.

[0052] The aspects and features described in connection with a particular one of the previous examples can also be combined with one or more of the further examples in order to replace an identical or similar feature of that further example or to additionally introduce the feature into the further example. Examples can further be or relate to a (computer) program with program code for carrying out one or more of the above methods when the program is executed on a computer, a processor or other programmable hardware component. Steps, operations or processes of various of the methods described above can therefore also be carried out by programmed computers, processors or other programmable hardware components. Examples can also include program storage devices, e.g.Digital data storage media that are machine-, processor-, or computer-readable and encode or contain machine-executable, processor-executable, or computer-executable programs and instructions. The program storage devices may include or be, for example, digital memories, magnetic storage media such as magnetic disks and magnetic tapes, hard disk drives, or optically readable digital data storage media.Further examples may also cover computers, processors, control units, field-programmable logic arrays ((F)PLAs = (Field) Programmable Logic Arrays), field-programmable gate arrays ((F)PGA = (Field) Programmable Gate Arrays), graphics processor units (GPU = Graphics Processor Unit), application-specific integrated circuits (ASIC = application-specific integrated circuit), integrated circuits (IC = Integrated Circuit) or system-on-a-chip (SoC = System-on-a-Chip) programmed to perform the steps of the methods described above.

[0053] It is further understood that the disclosure of multiple steps, processes, operations, or functions disclosed in the specification or claims should not be construed as necessarily being in the described order, unless explicitly stated in the individual case or technically required. Therefore, the foregoing description does not limit the performance of multiple steps or functions to any particular order. Furthermore, in further examples, a single step, function, process, or operation may include and / or be broken down into multiple sub-steps, functions, processes, or operations.

[0054] If some aspects in the preceding sections were described in connection with a device or system, these aspects are also to be understood as a description of the corresponding method. For example, a block, a device, or a functional aspect of the device or system can correspond to a feature, such as a method step, of the corresponding method. Accordingly, aspects described in connection with a method are also to be understood as a description of a corresponding block, a corresponding element, a property, or a functional feature of a corresponding device or system.

[0055] The following claims are hereby incorporated into the Detailed Description, each claim being understood to stand on its own as a separate example. It should also be noted that although a dependent claim in the claims refers to a particular combination with one or more other claims, other examples may include a combination of the dependent claim with the subject matter of any other dependent or independent claim. Such combinations are hereby explicitly contemplated unless it is specifically stated that a particular combination is not intended. Furthermore, features of a claim for any other independent claim are also intended to be included, even if that claim is not directly defined as dependent on that other independent claim.

[0056] List of reference symbols

[0057] 100 spoken word recognition

[0058] 110 spoken words

[0059] 200 analyze recognized spoken words

[0060] 210 relevant term

[0061] 300 identify a relevant vehicle condition

[0062] 310 relevant vehicle condition

[0063] 400 determining a common context between relevant term and relevant vehicle condition

[0064] 410 common context between relevant term and relevant

[0065] Vehicle condition

[0066] 500 control at least part of the motor vehicle

[0067] 1000 motor vehicles

[0068] 1100 Voice control device

[0069] 1110 interface

[0070] 1120 Control module

[0071] 1200 specific vehicle components

Claims

A voice control device (1100) for a motor vehicle (1000), the device comprising: An interface (1110) configured to communicate control information with at least one specific vehicle component (1200) of the motor vehicle (1000), a control module (1120) configured to: o recognize (100) spoken words (110), o analyze (200) recognized (100) spoken words (110) for a relevant term (210), wherein the relevant term (210) represents a key term for controlling the specific motor vehicle component (1200), o identify (300) a relevant vehicle state (310) based on the analyzed (200) relevant term (210), o determine (400) a common context (410) between the analyzed (200) relevant term (210) and the relevant vehicle state (310), and o control the specific vehicle component (1200) based on the determined (400) common context (410) (500).The voice control device (1100) according to claim 1, wherein the control module is further configured to select, based on the relevant term, the vehicle state from a plurality of vehicle states that is most likely for the relevant term. The voice control device (1100) according to claim 1 or 2, wherein the relevant vehicle state is ascertainable from a vehicle state type group, the vehicle state type group comprising:. An external spatial situation of the motor vehicle, and / or a current interior situation of the motor vehicle. The voice control device (1100) according to claim 3, wherein the external spatial situation of the motor vehicle comprises: A current geographical location of the motor vehicle, a current point-of-interest location of the motor vehicle, a tilt situation of the motor vehicle, and / or a vehicle environment situation, in particular with regard to the lighting conditions and / or visibility conditions in the environment of the motor vehicle. The voice control device (1100) according to claim 3 or 4, wherein the current interior situation of the motor vehicle comprises: A setting of a seat position for a vehicle seat of the motor vehicle, a setting of a lighting source of the interior of the motor vehicle, a setting of a window position, roof position, and / or door position of the motor vehicle, a setting of an air conditioning system for at least one interior area of ​​the motor vehicle, and / or a sound and / or video setting of an entertainment device of the motor vehicle. The voice control device (1100) according to any one of the preceding claims, wherein the control module is permanently activated without a fixed keyword activating the control module, so that the control module begins to analyze recognized spoken words for a relevant term.The voice control device (1100) according to any one of the preceding claims, wherein the control module is further configured to recognize spoken words in the interior of the motor vehicle and / or in the surroundings of the motor vehicle. A method for voice control for a motor vehicle (1000), the method comprising:. Recognizing (100) spoken words (110), analyzing (200) recognized (100) spoken words (110) for a relevant term (210), wherein the relevant term (210) represents a key term for controlling at least one specific motor vehicle component (1200), identifying (300) a relevant vehicle state (310) based on the analyzed (200) relevant term (210), determining (400) a common context (410) between the analyzed (200) relevant term (210) and the relevant vehicle state (310), and controlling (500) at least a part of the motor vehicle (1000) based on the determined (400) common context (410). A motor vehicle (1000) comprising a voice control device (1100) according to any one of the preceding claims 1 to 7. A computer program product with program code for carrying out the method according to claim 8, when the computer program product is executed on a computing unit or a device according to any one of claims 1 to 7.

Images