Vehicle-mounted voice interaction method and device, electronic equipment and storage medium
By differentiating and guiding user voice commands, the problem of semantic ambiguity or intent ambiguity in in-vehicle voice systems has been solved, achieving precise voice vehicle control services and improving the accuracy and efficiency of user interaction.
Patent Information
- Application Number
- CN202411086023.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-11-15
AI Technical Summary
Existing in-vehicle voice systems lack precise interactive guidance and cannot provide accurate voice vehicle control services. In particular, when faced with user voice commands that are semantically ambiguous or have unclear intentions, they cannot accurately identify the user's intentions and execute the corresponding control actions.
By distinguishing user voice commands and determining whether they are semantically ambiguous or intent-ambiguous, prompts are output to guide the user to input specific intents or perform corresponding control actions. This includes converting user voice commands, semantic recognition, and intent judgment, and adopting different guidance strategies for different types of commands.
It achieves accurate recognition and guidance of user voice commands, allowing users to control corresponding functions through somewhat imprecise and vague commands, providing the voice vehicle control service that truly meets their needs and improving the accuracy and efficiency of user interaction.
Smart Images

Figure CN118968984A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle technology, and in particular to a vehicle-mounted voice interaction method, device, electronic equipment and storage medium. Background Art
[0002] With the continuous advancement of artificial intelligence and voice recognition technology, and the interactive characteristics of in-vehicle voice such as zero level, high efficiency and convenience, and no need to distract driving attention, in-vehicle voice is becoming one of the important and commonly used interaction methods in vehicles. In-vehicle voice can not only help users control the vehicle efficiently, but also help drivers drive the vehicle more attentively and safely.
[0003] However, existing in-vehicle voice systems usually adopt fixed fallback solutions and mandatory logical definitions, lack precise interactive guidance and a process for soliciting users' true intentions, and are unable to provide users with accurate voice vehicle control services. Summary of the invention
[0004] The problem solved by the present invention is how to provide accurate voice vehicle control service.
[0005] In order to solve the above problems, the present invention provides a vehicle-mounted voice interaction method, device, electronic device and storage medium.
[0006] In a first aspect, the present invention provides a vehicle-mounted voice interaction method, comprising:
[0007] Distinguishing user voice commands to determine the type of the user voice commands;
[0008] When the type of the user voice command is a semantically ambiguous command, outputting prompt information according to the type of the semantically ambiguous command to guide the user to input a specific intention or perform a corresponding control action, wherein the semantically ambiguous command refers to at least one of a lack of action, an ambiguous action, and an action mismatch in the user intention corresponding to the user voice command;
[0009] When the type of the user voice command is an intention-ambiguous command, prompt information is output to guide the user to input a specific intention, and a corresponding control action is performed according to the user's specific intention, wherein the intention-ambiguous command means that the user intention corresponding to the user voice command cannot point to the specific intention.
[0010] Optionally, the distinguishing the user voice command to determine the type of the user voice command includes:
[0011] Converting the user's voice command into text data, performing semantic recognition on the text data, and determining the user's intention based on the semantic recognition result;
[0012] When the user intention is semantically ambiguous, determining the type of the user voice instruction is the semantically ambiguous instruction;
[0013] When the user intention is ambiguous, the type of the user voice instruction is determined to be the intention ambiguous instruction.
[0014] Optionally, when the user intention is semantically ambiguous, after determining that the type of the user voice instruction is the semantically ambiguous instruction, the method further includes:
[0015] When the user intention lacks an action, determining the type of the semantically ambiguous instruction is an action-lacking instruction;
[0016] When the user intends to perform an ambiguous action, determining that the type of the semantically ambiguous instruction is an action-ambiguous instruction;
[0017] When there is a mismatch between the user intention and the semantically ambiguous instruction, the type of the semantically ambiguous instruction is determined to be an instruction to be matched.
[0018] Optionally, when the type of the user voice instruction is a semantically ambiguous instruction, outputting prompt information according to the type of the semantically ambiguous instruction to guide the user to input a specific intention or perform a corresponding control action includes:
[0019] When the type of the semantically ambiguous instruction is the action lacking instruction, outputting prompt information corresponding to the action lacking instruction according to the state of the entity to be controlled, so as to guide the user to input the specific intention;
[0020] When the type of the semantic fuzzy instruction is the action fuzzy instruction, outputting prompt information corresponding to the action fuzzy instruction according to the correspondence between the function of the entity to be controlled and the fuzzy action, so as to guide the user to input the specific intention, or to execute the control action corresponding to the action fuzzy instruction;
[0021] When the type of the semantically ambiguous instruction is the instruction to be matched, prompt information corresponding to the instruction to be matched is output to guide the user to input the specific intention.
[0022] Optionally, when the type of the semantic fuzzy instruction is the action fuzzy instruction, outputting prompt information corresponding to the action fuzzy instruction according to the correspondence between the function of the entity to be controlled and the fuzzy action to guide the user to input the specific intention, or executing the control action corresponding to the action fuzzy instruction includes:
[0023] When the function of the entity to be controlled corresponds to the fuzzy action, executing the control action corresponding to the action fuzzy instruction;
[0024] When the function of the entity to be controlled does not correspond to the fuzzy action, prompt information corresponding to the action fuzzy instruction is output to guide the user to input the specific intention.
[0025] Optionally, when the user intention has an ambiguous intention, determining the type of the user voice instruction as the intention ambiguous instruction includes:
[0026] When the user voice command satisfies the preset fuzzy intention command and the voice active triggering precondition, it is determined that the user intention has fuzzy intention, wherein the voice active triggering precondition includes: the entity function to be controlled in the user voice command is triggered and other functions of the same type as the entity function to be controlled are not triggered.
[0027] Optionally, before distinguishing the user voice command, the in-vehicle voice interaction method further includes:
[0028] Enable the voice interaction function according to the wake-up voice command.
[0029] In a second aspect, the present invention provides a vehicle-mounted voice interaction device, comprising:
[0030] A distinguishing module, used to distinguish the user voice command to determine the type of the user voice command;
[0031] a semantic fuzzy module, configured to output prompt information according to the type of the semantic fuzzy instruction to guide the user to input a specific intention or perform a corresponding control action when the type of the user voice instruction is a semantic fuzzy instruction, wherein the semantic fuzzy instruction refers to at least one of a lack of action, an ambiguous action, and an action mismatch in the user intention corresponding to the user voice instruction;
[0032] An intention fuzzy module is used to output prompt information to guide the user to input a specific intention when the type of the user voice instruction is an intention fuzzy instruction, and perform corresponding control actions according to the user's specific intention, wherein the intention fuzzy instruction means that the user intention corresponding to the user voice instruction cannot point to the specific intention.
[0033] In a third aspect, the present invention provides an electronic device, including a memory and a processor;
[0034] The memory is used to store computer programs;
[0035] The processor is used to implement the in-vehicle voice interaction method as described in the first aspect when executing the computer program.
[0036] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the in-vehicle voice interaction method as described in the first aspect is implemented.
[0037] The beneficial effect of the in-vehicle voice interaction method of the present invention is: by distinguishing the types of user voice commands, different guidance strategies are determined for different user voice commands. For example, when the type of user voice command is a semantically ambiguous command (for example, the corresponding user intention has at least one of a lack of action, ambiguous action and mismatched action), prompt information can be output to guide the user to input a specific intention, or when the entity function to be controlled corresponds to the fuzzy action, the corresponding control action can be executed, so that the user can achieve corresponding function control through less precise action fuzzy instructions; for example, when the type of user voice command is an intention fuzzy command, since the user intention corresponding to the user voice command cannot point to a specific intention, prompt information can be output to guide the user to input a specific intention, and the corresponding control action can be executed according to the user's specific intention, guiding the user to express the voice command correctly and efficiently, and providing the user with the voice vehicle control service that he really wants and needs. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 A schematic diagram of a flow chart of a vehicle-mounted voice interaction method according to an embodiment of the present invention;
[0039] Figure 2 A schematic diagram of a flow chart of determining the type of a user voice command according to an embodiment of the present invention;
[0040] Figure 3 A schematic diagram of a flow chart for distinguishing types of semantically ambiguous instructions according to an embodiment of the present invention;
[0041] Figure 4 A flowchart of a guidance strategy corresponding to a semantically ambiguous instruction according to an embodiment of the present invention;
[0042] Figure 5 It is a flow chart of the corresponding guidance strategy of the entity function to be controlled and the fuzzy action according to the embodiment of the present invention;
[0043] Figure 6 A system architecture diagram of a vehicle-mounted voice interaction device according to an embodiment of the present invention;
[0044] Figure 7 4 is a system architecture diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0045] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be interpreted as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.
[0046] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.
[0047] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to"; the term "based on" means "based at least in part on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0048] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0049] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.
[0050] like Figure 1 As shown, an in-vehicle voice interaction method provided by an embodiment of the present invention includes:
[0051] S100: Differentiate user voice instructions to determine the type of the user voice instructions.
[0052] Specifically, the user voice commands are differentiated, for example, the user voice commands are differentiated into semantically ambiguous commands and intentionally ambiguous commands.
[0053] S200: When the type of the user voice command is a semantically ambiguous command, a prompt message is output according to the type of the semantically ambiguous command to guide the user to input a specific intention or perform a corresponding control action, wherein the semantically ambiguous command refers to the user intention corresponding to the user voice command having at least one of a lack of action, ambiguous action and mismatched action.
[0054] Specifically, when the type of user voice command is a semantically ambiguous command, the corresponding guidance strategy is determined according to the type of semantically ambiguous command. For example, prompt information can be output to the user to guide the user to input a specific intention, or corresponding control actions can be executed to achieve refined guidance of the user. Among them, the semantically ambiguous command refers to the user intention corresponding to the user voice command having at least one of the following situations: lack of action, ambiguous action and action mismatch.
[0055] S300: When the type of the user voice command is an intention-ambiguous command, a prompt message is output to guide the user to input a specific intention, and a corresponding control action is performed according to the user's specific intention, wherein the intention-ambiguous command means that the user intention corresponding to the user voice command cannot point to the specific intention.
[0056] Specifically, when the type of the user voice command is an intention fuzzy command (i.e., the user intention corresponding to the user voice command cannot point to a specific intention), the corresponding guidance strategy is determined, and prompt information can be output to the user to guide the user to input a specific intention, and then the corresponding control action is performed according to the user's specific intention. In the prior art, the voice system usually adopts a fixed bottom-line solution and a mandatory logical definition, wherein the fixed bottom-line solution refers to refusing to recognize or bottom-line broadcast the fuzzy command provided by the user (for example, the user command is "air conditioning"), and will not guide the user to set the function; and the mandatory logical definition will not solicit the user's specific intention, for example, when the air conditioning wind direction is only turned on to blow the face, the user issues a command to turn off the blowing on the face, and the system will forcibly switch to blowing the feet, instead of soliciting the user's intention to switch the wind direction or turn off the air conditioning. In this embodiment, by distinguishing the types of user voice commands, different guidance strategies are determined for different user voice commands, guiding users to correctly and efficiently express voice commands, and providing users with the voice car control services they really want.
[0057] In this embodiment, by distinguishing the types of user voice commands, different guidance strategies are determined for different user voice commands. For example, when the type of user voice command is a semantically ambiguous command (for example, the corresponding user intention has at least one of the following situations: lack of action, ambiguous action, and action mismatch), prompt information can be output to guide the user to input a specific intention, or when the entity function to be controlled corresponds to the fuzzy action, the corresponding control action can be executed, so that the user can achieve corresponding function control through less precise action fuzzy instructions; for example, when the type of user voice command is an intention fuzzy command, since the user intention corresponding to the user voice command cannot point to a specific intention, prompt information can be output to guide the user to input a specific intention, and the corresponding control action can be executed according to the user's specific intention, guiding the user to express the voice command correctly and efficiently, and providing the user with the voice vehicle control service that they really want and need.
[0058] Optionally, the distinguishing the user voice command to determine the type of the user voice command includes:
[0059] S110: Convert the user voice instruction into text data, perform semantic recognition on the text data, and determine the user intention according to the semantic recognition result.
[0060] Specifically, combined Figure 2 As shown, the user's speaking content (i.e., user voice) is obtained through a microphone or other device, and the user's voice (usually audio data) is converted into text data through voice recognition technology. After obtaining the text data, natural language processing technology is used to perform semantic recognition on the text data to understand the semantics of the text information and the conversation intention, thereby determining the user's intention.
[0061] S120: When there is semantic ambiguity in the user intention, determine that the type of the user voice instruction is the semantically ambiguous instruction.
[0062] Specifically, combined Figure 2 As shown, the complete user voice command can be divided into three parts: entity + sub-function + action / parameter. According to user habits, semantic ambiguity usually includes lack of action, existence of ambiguous action and existence of mismatch. When the above situation occurs, the type of user voice command is semantically ambiguous command.
[0063] S130: When the user intention is ambiguous, determine the type of the user voice instruction as the intention ambiguous instruction.
[0064] Specifically, combined Figure 2 As shown, when the user voice command corresponds to multiple potential intentions, the user intention is ambiguous, and the type of the user voice command is an intention ambiguous command.
[0065] In this optional embodiment, by accurately determining the type of user voice commands, it is helpful to subsequently determine the corresponding user guidance means, guide users to correctly and efficiently express voice commands, and provide users with the voice vehicle control services they really want and need.
[0066] Optionally, when the user intention is semantically ambiguous, after determining that the type of the user voice instruction is the semantically ambiguous instruction, the in-vehicle voice interaction method further includes:
[0067] S121: When the user intention lacks action, determining the type of the semantically ambiguous instruction is an action-lacking instruction.
[0068] Specifically, combined Figure 3 As shown, the user intention lacks action, including two cases, one is only entities but no actions / parameters, such as "air conditioning", "HUD", "seats" and "windows", etc., the other is only entities + sub-functions but no actions / parameters, such as "air conditioning temperature", "air conditioning volume" and "seat height", etc. In these two cases, the type of semantically ambiguous instructions is action-lacking instructions.
[0069] S122: When the user intends to perform an ambiguous action, determining that the type of the semantically ambiguous instruction is an action-ambiguous instruction.
[0070] Specifically, combined Figure 3 As shown, there are two cases where the user's intention involves fuzzy actions. One is entity + fuzzy action, such as "open the window a little" and "the seat is higher", and the other is entity + sub-function + fuzzy action, such as "higher air conditioning temperature" and "larger air conditioning volume". In these two cases, the type of semantic fuzzy instruction is action fuzzy instruction.
[0071] S123: When there is a mismatch between the user intention and the instruction, determine that the type of the semantically ambiguous instruction is an instruction to be matched.
[0072] Specifically, combined Figure 3 As shown, there are many cases where user intentions do not match. One is entity + mismatched action, such as "adjust the air conditioner up" and "open the seat", etc. The second is entity + sub-function + mismatched action, such as "turn on the air conditioner temperature" and "adjust the air conditioner height forward", etc. In addition, there are cases where the entity and the sub-function do not match, such as "adjust the air conditioner height higher", "seat wind direction to the left" and "increase the fragrance air volume".
[0073] In this optional embodiment, the types of semantically ambiguous instructions are further subdivided to achieve refined guidance for users, guiding users to express voice instructions correctly and efficiently, and providing users with the voice vehicle control services they really want and need.
[0074] Optionally, when the type of the user voice instruction is a semantically ambiguous instruction, outputting prompt information according to the type of the semantically ambiguous instruction to guide the user to input a specific intention or perform a corresponding control action includes:
[0075] S210: When the type of the semantically ambiguous instruction is the action-lacking instruction, outputting prompt information corresponding to the action-lacking instruction according to the state of the entity to be controlled, so as to guide the user to input the specific intention.
[0076] Specifically, combined Figure 4 As shown, for example, when the semantically fuzzy instruction is "air conditioning", it is necessary to determine whether the "air conditioning" is turned on. If the "air conditioning" is turned on, a prompt message can be output to the user, that is, asking the user: "The air conditioning" is turned on early, what do you need to help you adjust? If the "air conditioning" is not turned on, you can ask the user: what do you need to help you adjust about the "air conditioning"? For example, when the semantically fuzzy instruction is "air conditioning air volume", it is necessary to determine whether the "air conditioning air volume" is turned on. If the "air conditioning air volume" is turned on, you can ask the user: "The air conditioning air volume" is turned on early, what do you need to help you adjust? If the "air conditioning air volume" is not turned on, you can ask the user: what do you need to help you adjust about the "air conditioning air volume".
[0077] S220: When the type of the semantic fuzzy instruction is the action fuzzy instruction, prompt information corresponding to the action fuzzy instruction is output according to the correspondence between the entity function to be controlled and the fuzzy action, so as to guide the user to input the specific intention, or execute the control action corresponding to the action fuzzy instruction.
[0078] Specifically, combined Figure 4 As shown, when the semantic fuzzy instruction is entity + fuzzy action or entity + sub-function + fuzzy action, the type is action fuzzy instruction. At this time, it is necessary to determine whether to ask the user to obtain the user's specific intention or to execute the corresponding control action based on the correspondence between the entity function to be controlled and the fuzzy action. The specific content is shown below.
[0079] S230: When the type of the semantically ambiguous instruction is the instruction to be matched, output prompt information corresponding to the instruction to be matched to guide the user to input the specific intention.
[0080] Specifically, combined Figure 4 As shown, for example, when the semantically ambiguous instruction is "adjust the air conditioner up" or "move the seat height forward", "air conditioner" and "adjust up" do not match, and "seat", "height" and "forward" do not match. Therefore, it is necessary to ask the user to obtain the user's specific intention, for example: I don't understand, try another way of saying it.
[0081] In this optional embodiment, the corresponding guidance strategy is determined according to the type of semantically ambiguous instructions, so as to achieve refined guidance for users, guide users to express voice instructions correctly and efficiently, and provide users with the voice vehicle control services they really want and need.
[0082] Optionally, when the type of the semantic fuzzy instruction is the action fuzzy instruction, outputting prompt information corresponding to the action fuzzy instruction according to the correspondence between the function of the entity to be controlled and the fuzzy action to guide the user to input the specific intention, or executing the control action corresponding to the action fuzzy instruction includes:
[0083] S221: When the function of the entity to be controlled corresponds to the fuzzy action, execute the control action corresponding to the action fuzzy instruction.
[0084] Specifically, combined Figure 5 As shown, when the entity function to be controlled corresponds to the fuzzy action, for example, the entity function to be controlled "temperature" corresponds to the fuzzy action "a little higher", the action fuzzy instruction "a little higher temperature" composed of the two can trigger the corresponding control action, such as raising it by 1 degree, and at the same time provide feedback to the user that the action is completed.
[0085] S222: When the entity function to be controlled does not correspond to the fuzzy action, output prompt information corresponding to the action fuzzy instruction to guide the user to input the specific intention.
[0086] Specifically, combined Figure 5 As shown, when the function of the entity to be controlled does not correspond to the fuzzy action, for example, the function of the entity to be controlled "temperature" does not correspond to the fuzzy action "comfort", the action fuzzy instruction "temperature comfort" composed of the two cannot trigger the corresponding control action. At this time, you can ask the user: What value do you need to help you adjust the "temperature" to, so as to guide the user to enter specific intentions.
[0087] In this optional embodiment, the corresponding guidance strategy is determined according to the correspondence between the entity function to be controlled and the fuzzy action, so as to achieve refined guidance for the user, guide the user to express voice commands correctly and efficiently, and provide the user with the voice vehicle control service that he really wants and needs.
[0088] Optionally, when the user intention has an ambiguous intention, determining the type of the user voice instruction as the intention ambiguous instruction includes:
[0089] When the user voice command satisfies the preset fuzzy intention command and the voice active triggering precondition, it is determined that the user intention has fuzzy intention, wherein the voice active triggering precondition includes: the entity function to be controlled in the user voice command is triggered and other functions of the same type as the entity function to be controlled are not triggered.
[0090] Specifically, a voice fuzzy intention instruction library is formed by pre-defining voice fuzzy intention instructions. When the user voice instruction hits the preset fuzzy intention instruction and satisfies the voice active triggering precondition, it is determined that the user intention has a fuzzy intention, and the user is actively triggered to obtain the user's specific intention. Among them, the voice active triggering precondition includes: the entity function to be controlled in the user voice instruction is triggered and other functions of the same type as the entity function to be controlled are not triggered. For example, the user voice instruction "turn off the air conditioner to blow on the face" hits the preset fuzzy intention instruction. At this time, if the air conditioner only turns on the face blowing function, the voice active triggering precondition is met, and it is determined that the user intention has a fuzzy intention, and it is necessary to further obtain the specific intention from the user. At this time, if the air conditioner turns on the face blowing function and the foot blowing function at the same time, the voice active triggering precondition is not met. At this time, the user intention is clear, and the air conditioner face blowing function can be directly turned off according to the user intention. In this embodiment, it can be preliminarily determined whether the user intention has a fuzzy intention based on the relationship between the user voice instruction and the preset fuzzy intention instruction, and at the same time, the voice active triggering precondition is combined to achieve accurate judgment of the fuzzy intention, and the user intention is closely associated with the state of the entity function to be controlled, which effectively improves the accuracy of the judgment of the user voice instruction.
[0091] In this optional embodiment, by designing the judgment logic of fuzzy intentions, the user's specific intentions can be obtained, and the user can be guided to express voice commands correctly and efficiently, providing the user with the voice vehicle control service that he or she really wants and needs.
[0092] Optionally, before distinguishing the user voice command, the in-vehicle voice interaction method further includes:
[0093] Enable the voice interaction function according to the wake-up voice command.
[0094] Specifically, before recognizing the user intention according to the user voice, if the voice interaction function is not turned on, the user needs to first generate a wake-up voice instruction by issuing a wake-up voice (for example, XiaoXiaoX or Hello, XX), and turn on the voice interaction function according to the wake-up voice instruction.
[0095] In this optional embodiment, a wake-up voice is added to the voice interaction function, which can be turned on or off according to user needs.
[0096] like Figure 6 As shown, an in-vehicle voice interaction device 600 provided by an embodiment of the present invention includes:
[0097] A distinguishing module 610, configured to distinguish user voice commands to determine the type of the user voice commands;
[0098] The semantic fuzzy module 620 is used for, when the type of the user voice command is a semantic fuzzy command, outputting prompt information according to the type of the semantic fuzzy command to guide the user to input a specific intention or perform a corresponding control action, wherein the semantic fuzzy command refers to at least one of a lack of action, an ambiguous action, and an action mismatch in the user intention corresponding to the user voice command;
[0099] The intention fuzzy module 630 is used to output prompt information to guide the user to input a specific intention when the type of the user voice instruction is an intention fuzzy instruction, and perform corresponding control actions according to the user's specific intention, wherein the intention fuzzy instruction means that the user intention corresponding to the user voice instruction cannot point to the specific intention.
[0100] like Figure 7 As shown, an electronic device 700 provided by an embodiment of the present invention includes a memory 710 and a processor 720; the memory 710 is used to store a computer program; the processor 720 is used to implement the in-vehicle voice interaction method as described above when executing the computer program.
[0101] In other words, an electronic device 700 includes a memory 710 and a processor 720 coupled to the memory 710; the memory 710 is configured to store a computer program; and the processor 720 is configured to perform the following operations when executing the computer program:
[0102] Distinguishing user voice commands to determine the type of the user voice commands;
[0103] When the type of the user voice command is a semantically ambiguous command, outputting prompt information according to the type of the semantically ambiguous command to guide the user to input a specific intention or perform a corresponding control action, wherein the semantically ambiguous command refers to at least one of a lack of action, an ambiguous action, and an action mismatch in the user intention corresponding to the user voice command;
[0104] When the type of the user voice command is an intention-ambiguous command, prompt information is output to guide the user to input a specific intention, and a corresponding control action is performed according to the user's specific intention, wherein the intention-ambiguous command means that the user intention corresponding to the user voice command cannot point to the specific intention.
[0105] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the in-vehicle voice interaction method as described above is implemented.
[0106] In other words, a non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor performs the following operations:
[0107] Distinguishing user voice commands to determine the type of the user voice commands;
[0108] When the type of the user voice command is a semantically ambiguous command, outputting prompt information according to the type of the semantically ambiguous command to guide the user to input a specific intention or perform a corresponding control action, wherein the semantically ambiguous command refers to at least one of a lack of action, an ambiguous action, and an action mismatch in the user intention corresponding to the user voice command;
[0109] When the type of the user voice command is an intention-ambiguous command, prompt information is output to guide the user to input a specific intention, and a corresponding control action is performed according to the user's specific intention, wherein the intention-ambiguous command means that the user intention corresponding to the user voice command cannot point to the specific intention.
[0110] An electronic device 700 that can be used as a server or client of the present invention will now be described, which is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device 700 is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 700 can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the present invention described herein and / or required.
[0111] The electronic device 700 includes a computing unit, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) or a computer program loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for the operation of the device can also be stored. The computing unit, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.
[0112] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc. In the present application, the unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present invention. In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
[0113] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.
Claims
1. A vehicle-mounted voice interaction method, It is characterized in that include: Distinguishing user voice commands to determine the type of the user voice commands; When the type of the user voice command is a semantically ambiguous command, outputting prompt information according to the type of the semantically ambiguous command to guide the user to input a specific intention or perform a corresponding control action, wherein the semantically ambiguous command refers to at least one of a lack of action, an ambiguous action, and an action mismatch in the user intention corresponding to the user voice command; When the type of the user voice command is an intention-ambiguous command, prompt information is output to guide the user to input a specific intention, and a corresponding control action is performed according to the user's specific intention, wherein the intention-ambiguous command means that the user intention corresponding to the user voice command cannot point to the specific intention.
2. The vehicle-mounted voice interaction method according to claim 1, It is characterized in that The distinguishing the user voice command to determine the type of the user voice command includes: Converting the user's voice command into text data, performing semantic recognition on the text data, and determining the user's intention based on the semantic recognition result; When the user intention is semantically ambiguous, determining the type of the user voice instruction is the semantically ambiguous instruction; When the user intention is ambiguous, the type of the user voice instruction is determined to be the intention ambiguous instruction.
3. The vehicle-mounted voice interaction method according to claim 2, It is characterized in that When the user intention is semantically ambiguous, after determining that the type of the user voice instruction is the semantically ambiguous instruction, the method further includes: When the user intention lacks an action, determining the type of the semantically ambiguous instruction is an action-lacking instruction; When the user intends to perform an ambiguous action, determining that the type of the semantically ambiguous instruction is an action-ambiguous instruction; When there is a mismatch between the user intention and the semantically ambiguous instruction, the type of the semantically ambiguous instruction is determined to be an instruction to be matched.
4. The vehicle-mounted voice interaction method according to claim 3, It is characterized in that When the type of the user voice instruction is a semantically ambiguous instruction, outputting prompt information according to the type of the semantically ambiguous instruction to guide the user to input a specific intention or perform a corresponding control action includes: When the type of the semantically ambiguous instruction is the action lacking instruction, outputting prompt information corresponding to the action lacking instruction according to the state of the entity to be controlled, so as to guide the user to input the specific intention; When the type of the semantic fuzzy instruction is the action fuzzy instruction, outputting prompt information corresponding to the action fuzzy instruction according to the correspondence between the function of the entity to be controlled and the fuzzy action, so as to guide the user to input the specific intention, or to execute the control action corresponding to the action fuzzy instruction; When the type of the semantically ambiguous instruction is the instruction to be matched, prompt information corresponding to the instruction to be matched is output to guide the user to input the specific intention.
5. The vehicle-mounted voice interaction method according to claim 4, It is characterized in that When the type of the semantic fuzzy instruction is the action fuzzy instruction, outputting prompt information corresponding to the action fuzzy instruction according to the correspondence between the function of the entity to be controlled and the fuzzy action to guide the user to input the specific intention, or executing the control action corresponding to the action fuzzy instruction includes: When the function of the entity to be controlled corresponds to the fuzzy action, executing the control action corresponding to the action fuzzy instruction; When the function of the entity to be controlled does not correspond to the fuzzy action, prompt information corresponding to the action fuzzy instruction is output to guide the user to input the specific intention.
6. The vehicle-mounted voice interaction method according to claim 2, It is characterized in that When the user intention has an ambiguous intention, determining the type of the user voice instruction is the intention ambiguous instruction includes: When the user voice command satisfies the preset fuzzy intention command and the voice active triggering precondition, it is determined that the user intention has fuzzy intention, wherein the voice active triggering precondition includes: the entity function to be controlled in the user voice command is triggered and other functions of the same type as the entity function to be controlled are not triggered.
7. The in-vehicle voice interaction method according to any one of claims 1 to 6, It is characterized in that Before distinguishing the user's voice command, the method further includes: Enable the voice interaction function according to the wake-up voice command.
8. A vehicle-mounted voice interaction device, It is characterized in that include: A distinguishing module, used to distinguish the user voice command to determine the type of the user voice command; a semantic fuzzy module, configured to output prompt information according to the type of the semantic fuzzy instruction to guide the user to input a specific intention or perform a corresponding control action when the type of the user voice instruction is a semantic fuzzy instruction, wherein the semantic fuzzy instruction refers to at least one of a lack of action, an ambiguous action, and an action mismatch in the user intention corresponding to the user voice instruction; An intention fuzzy module is used to output prompt information to guide the user to input a specific intention when the type of the user voice instruction is an intention fuzzy instruction, and perform corresponding control actions according to the user's specific intention, wherein the intention fuzzy instruction means that the user intention corresponding to the user voice instruction cannot point to the specific intention.
9. An electronic device, It is characterized in that including memory and processor; The memory is used to store computer programs; The processor is used to implement the in-vehicle voice interaction method as described in any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, It is characterized in that The storage medium stores a computer program, and when the computer program is executed by the processor, the in-vehicle voice interaction method as described in any one of claims 1 to 7 is implemented.
Citation Information
Cited By
Human-computer interaction method, device, equipment and medium
CN120071971A
