Interaction method and system based on semantic recognition

Abstract

The invention is suitable for the technical field of voice interaction, and provides an interaction method and system based on semantic recognition, and the method comprises the following steps: receiving a voice audio, and determining a collection point corresponding to the voice audio, the collection point being a main driving point or a co-driving point; identifying the voice audio to obtain text information, determining a user instruction according to the text information, and determining whether the response display terminal is a central control screen or a co-driver entertainment screen according to the user instruction and the corresponding acquisition point; whether interactive response sound is generated or not is determined, when the interactive response sound is generated, the response type of the generated interactive response sound is judged, and the response type is a main driving demand response, a co-driving demand response or a common demand response; and controlling a corresponding loudspeaker to play the interactive response sound according to the response type. By using the system and the method, it is ensured that each person can hear the interactive response sound which the person wants to hear as far as possible, other passengers cannot be interfered, the intelligent level is high, and the comfort is greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of voice interaction technology, and in particular to an interaction method and system based on semantic recognition. Background Art

[0002] Car voice interaction is an important part of the in-vehicle system. It realizes voice interaction between the driver, passengers and the vehicle through voice recognition and speech synthesis technology. Car voice interaction can improve driving safety and provide convenient operation methods. Voice interaction can provide a more natural and intuitive human-computer interaction method, allowing drivers and co-pilots to control vehicle functions and obtain information more easily. However, there are still some shortcomings in the current car voice interaction. For example, it is impossible to determine whether the sound comes from the driver or the co-pilot, and thus it is impossible to make better targeted interactive responses. For example, when the car computer is playing music, the driver uses voice control to turn on the navigation, and the car speakers will emit navigation sounds, which are easy to understand. The navigation sounds are only useful for the driver, and the navigation sounds will affect passengers listening to music. Therefore, it is necessary to provide an interaction method and system based on semantic recognition to solve the above problems. Summary of the invention

[0003] In view of the deficiencies in the prior art, the purpose of the present invention is to provide an interactive method and system based on semantic recognition to solve the problems existing in the above-mentioned background technology.

[0004] The present invention is implemented in this way: an interaction method based on semantic recognition, the method comprising the following steps:

[0005] Receive voice audio, and determine a collection point corresponding to the voice audio, the collection point being a main driving point or a co-driving point;

[0006] Recognize the voice audio to obtain text information, determine the user command based on the text information, and determine the response display terminal as the central control screen or the co-pilot entertainment screen based on the user command and the corresponding collection point;

[0007] Determining whether an interactive response sound is generated, and when generated, determining a response type of the interactive response sound, the response type being a primary driving demand response, a secondary driving demand response, or a common demand response;

[0008] According to the response type, the corresponding speaker is controlled to play the interactive response sound. When the response type is the main driver's demand response, the main driver's speaker is controlled to play the interactive response sound; when the response type is the co-driver's demand response, the co-driver's speaker is controlled to play the interactive response sound; when the response type is the common demand response, the speakers of the entire vehicle are controlled to play the interactive response sound.

[0009] As a further solution of the present invention: the step of receiving voice audio and determining the collection point corresponding to the voice audio specifically includes:

[0010] Receiving voice audio, wherein the voice audio includes a main driving audio signal and a co-pilot audio signal;

[0011] The RMS values ​​of the main driver audio signal and the co-driver audio signal are calculated respectively;

[0012] Compare the RMS value of the main driver's audio signal and the RMS value of the co-driver's audio signal to determine whether the collection point corresponding to the voice audio is the main driver's point or the co-driver's point.

[0013] As a further solution of the present invention: the step of determining the user instruction according to the text information, and determining the response display terminal as the central control screen or the co-pilot entertainment screen according to the user instruction and the corresponding collection point, specifically includes:

[0014] Perform word segmentation and part-of-speech tagging on text information, and perform semantic analysis through a syntactic analyzer to determine user instructions;

[0015] Matching the user instruction with the execution list library to determine the execution instruction, and determining the terminal information corresponding to the execution instruction, wherein the terminal information is the central control screen and / or the co-pilot entertainment screen;

[0016] When the terminal information is the central control screen, the response display terminal is determined to be the central control screen; when the terminal information is the co-driver entertainment screen, the response display terminal is determined to be the co-driver entertainment screen; when the terminal information is the central control screen and the co-driver entertainment screen, the response display terminal is determined according to the collection point.

[0017] As a further solution of the present invention: the step of determining whether an interactive response sound is generated and, when generated, determining the response type of the interactive response sound specifically comprises:

[0018] Determine whether to generate an interactive response sound according to the responding vehicle computer software;

[0019] When generated, the corresponding vehicle software name is input into the response sound type library, which contains all vehicle software names, and each vehicle software name is marked with a specific response type;

[0020] The corresponding response type is output, and the response sound type library supports modification and editing.

[0021] As a further solution of the present invention: the step of controlling the corresponding speaker to play the interactive response sound according to the response type specifically includes:

[0022] Determine the sound volume according to the response type, the main driving demand response, the co-pilot demand response and the common demand response each corresponding to a sound volume;

[0023] The corresponding speaker is controlled to play the interactive response sound according to the response type and the sound volume.

[0024] As a further solution of the present invention: the method further includes executing regional instructions according to the collection point, and the specific steps are:

[0025] determining whether the execution instruction is a regional instruction, wherein the regional instruction includes a seat function adjustment instruction and an air conditioning light adjustment instruction;

[0026] When the execution instruction is a regional instruction, the regional instruction is executed according to the collection point.

[0027] Another object of the present invention is to provide an interactive system based on semantic recognition, the system comprising:

[0028] A voice and audio receiving module, used to receive voice and audio, and determine a collection point corresponding to the voice and audio, wherein the collection point is a main driving point or a co-driving point;

[0029] A user command determination module is used to identify the voice audio to obtain text information, determine the user command according to the text information, and determine the response display terminal as the central control screen or the co-pilot entertainment screen according to the user command and the corresponding collection point;

[0030] A response type determination module, used to determine whether to generate an interactive response sound, and when it is generated, determine the response type of the interactive response sound, the response type being a primary driving demand response, a secondary driving demand response, or a common demand response;

[0031] The speaker playback control module is used to control the corresponding speaker to play the interactive response sound according to the response type. When the response type is the main driving demand response, the main driving speaker is controlled to play the interactive response sound; when the response type is the co-pilot demand response, the co-pilot speaker is controlled to play the interactive response sound; when the response type is the common demand response, the speakers of the entire vehicle are controlled to play the interactive response sound.

[0032] As a further solution of the present invention: the voice audio receiving module includes:

[0033] A voice and audio receiving unit, used to receive voice and audio, wherein the voice and audio include a main driving audio signal and a co-pilot audio signal;

[0034] An RMS value calculation unit, used to calculate the RMS values ​​of the main driver audio signal and the co-driver audio signal respectively;

[0035] The collection point determination unit is used to compare the RMS value of the main driving audio signal and the RMS value of the co-pilot audio signal, and determine whether the collection point corresponding to the voice audio is the main driving point or the co-pilot point.

[0036] As a further solution of the present invention: the response type determination module includes:

[0037] A response sound determination unit, used to determine whether to generate an interactive response sound according to the responding vehicle computer software;

[0038] The vehicle computer software input unit is used to input the corresponding vehicle computer software name into the response sound type library when it is generated, and the response sound type library contains all vehicle computer software names, and each vehicle computer software name is marked with a specific response type;

[0039] The response type output unit is used to output the corresponding response type, and the response sound type library supports modification and editing.

[0040] As a further solution of the present invention: the speaker playback control module includes:

[0041] A sound volume determination unit, used to determine the sound volume according to the response type, wherein the main driving demand response, the co-pilot demand response and the common demand response each have a corresponding sound volume;

[0042] The sound playing control unit is used to control the corresponding speaker to play the interactive response sound according to the response type and the sound volume.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The present invention determines the collection point corresponding to the voice audio, and the collection point is the main driving point or the co-pilot point; recognizes the voice audio to obtain text information, determines the user instruction according to the text information, and determines the response display terminal as the central control screen or the co-pilot entertainment screen according to the user instruction and the corresponding collection point. For example, the navigation information will be displayed on the central control screen, and the film and television playback will be displayed on the co-pilot entertainment screen. In this way, the driver can focus on driving and the co-pilot can enjoy the fun without mutual interference. Then it will be determined whether an interactive response sound is generated. When it is generated, the response type of the interactive response sound is determined, and the response type is the main driving demand response, the co-pilot demand response or the common demand response; according to the response type, the corresponding speaker is controlled to play the interactive response sound; when the response type is the main driving demand response, it means that the interactive response sound is only what the driver wants to hear, and the main driving speaker will be controlled to play the interactive response sound; when the response type is the co-pilot demand response, it means that the interactive response sound is only what the co-pilot wants to hear, and the co-pilot speaker is controlled to play the interactive response sound; when the response type is the common demand response, it means that the interactive response sound is what everyone in the car wants to hear, and the speakers of the whole car are controlled to play the interactive response sound. In this way, the present invention ensures that the driver and the co-pilot hear the interactive response sounds they want to hear without interfering with each other, has a high level of intelligence, and greatly improves comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flowchart of an interactive method based on semantic recognition.

[0046] Figure 2 The present invention is a flowchart for determining the collection points corresponding to speech audio in an interactive method based on semantic recognition.

[0047] Figure 3 The present invention is a flowchart for determining a response display terminal in an interaction method based on semantic recognition.

[0048] Figure 4 The present invention is a flowchart for determining the response type of an interactive response sound in an interactive method based on semantic recognition.

[0049] Figure 5 The present invention is a flowchart for controlling a speaker to play interactive response sounds in an interactive method based on semantic recognition.

[0050] Figure 6 The present invention is a flowchart for executing regional instructions according to collection points in an interaction method based on semantic recognition.

[0051] Figure 7 A structural diagram of an interactive system based on semantic recognition. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0054] like Figure 1 As shown, an embodiment of the present invention provides an interaction method based on semantic recognition, and the method includes the following steps:

[0055] S100, receiving voice audio, and determining a collection point corresponding to the voice audio, wherein the collection point is a main driving point or a co-driving point;

[0056] S200, recognizing the voice audio to obtain text information, determining the user command according to the text information, and determining the response display terminal as the central control screen or the co-pilot entertainment screen according to the user command and the corresponding collection point;

[0057] S300, determining whether an interactive response sound is generated, and when generated, determining a response type of the interactive response sound, wherein the response type is a primary driving demand response, a secondary driving demand response, or a common demand response;

[0058] S400, controls the corresponding speaker to play the interactive response sound according to the response type. When the response type is the main driver's demand response, controls the main driver's speaker to play the interactive response sound; when the response type is the co-driver's demand response, controls the co-driver's speaker to play the interactive response sound; when the response type is the common demand response, controls the speakers of the entire vehicle to play the interactive response sound.

[0059] It should be noted that there are still some deficiencies in the current car voice interaction, such as the inability to determine whether the sound comes from the driver or the co-driver, and thus the inability to make better targeted interactive responses. For another example, when the car computer is playing music, the driver uses voice control to turn on the navigation, and the car speaker will emit a navigation sound. It is easy to understand that the navigation sound is only useful to the driver and will affect the passengers' listening to music. The embodiments of the present invention are intended to solve the above problems.

[0060] In the embodiment of the present invention, microphones are installed at both the main driving point and the co-pilot point, and the preferred microphones are installed at the headrests of the main driving seat and the co-pilot seat. When the vehicle system obtains voice audio, it will determine the collection point corresponding to the voice audio, and then it can be determined whether the voice is issued by the main driver or the co-pilot. Then the embodiment of the present invention will recognize the voice audio to obtain text information, determine the user instruction according to the text information, and determine the response display terminal as the central control screen or the co-pilot entertainment screen according to the user instruction and the corresponding collection point. For example, the navigation information will be displayed on the central control screen, and the film and television playback will be displayed on the co-pilot entertainment screen. In this way, the driver can focus on driving and the co-pilot can enjoy the fun without mutual interference. In addition, it will also determine whether an interactive response sound is generated. When it is generated, the response type of the interactive response sound is determined, and the response type is the main driving demand response, the co-pilot demand response or the common demand response; finally, according to the response type, the corresponding speaker is controlled to play the interactive response sound. There are multiple speakers installed in the vehicle system. The speaker installed at the main driving position is named the main driving speaker, and the speaker installed at the co-pilot position is named the co-pilot speaker. It is easy to understand that when the response type is main driving demand response, it means that the interactive response sound is only what the driver wants to hear, and the main driving speaker will be controlled to play the interactive response sound; when the response type is co-pilot demand response, it means that the interactive response sound is only what the co-pilot wants to hear, and the co-pilot speaker will be controlled to play the interactive response sound; when the response type is common demand response, it means that the interactive response sound is what everyone in the car wants to hear, and the speakers of the entire car will be controlled to play the interactive response sound. In this way, it is guaranteed as much as possible that everyone hears the interactive response sound they want to hear, and other passengers will not be disturbed. The level of intelligence is high and the comfort is greatly improved.

[0061] like Figure 2 As shown, as a preferred embodiment of the present invention, the step of receiving voice audio and determining the collection point corresponding to the voice audio specifically includes:

[0062] S101, receiving voice audio, where the voice audio includes a driver's audio signal and a co-driver's audio signal;

[0063] S102, respectively calculating the RMS values ​​of the main driver's audio signal and the co-driver's audio signal;

[0064] S103, comparing the RMS value of the main driver's audio signal and the RMS value of the co-driver's audio signal, and determining whether the collection point corresponding to the voice audio is the main driver's point or the co-driver's point.

[0065] In the embodiment of the present invention, it is easy to understand that no matter whether the main driver or the co-driver issues a voice interaction command, the microphones at the main driver point and the co-driver point will collect voice audio, so the voice audio will contain the main driver audio signal and the co-driver audio signal. Then, the RMS values ​​of the main driver audio signal and the co-driver audio signal will be calculated respectively. The RMS value is a statistical measure of the amplitude of the audio signal. It gives the average level of signal strength. When the RMS value is larger, it indicates that the average energy in the audio signal increases, which usually corresponds to an increase in loudness perceived by the human ear. After that, by comparing the size relationship between the RMS value of the main driver audio signal and the RMS value of the co-driver audio signal, it can be determined whether the collection point corresponding to the voice audio is the main driver point or the co-driver point. For example, if the RMS value of the main driver audio signal is greater than the RMS value of the co-driver audio signal, it means that the collection point is the main driver point.

[0066] like Figure 3 As shown, as a preferred embodiment of the present invention, the step of determining the user instruction according to the text information, and determining the response display terminal as the central control screen or the co-pilot entertainment screen according to the user instruction and the corresponding collection point specifically includes:

[0067] S201, performing word segmentation and part-of-speech tagging on the text information, and performing semantic analysis through a syntactic analyzer to determine the user instruction;

[0068] S202, matching the user instruction with an execution list library, determining an execution instruction, and determining terminal information corresponding to the execution instruction, wherein the terminal information is a central control screen and / or a co-pilot entertainment screen;

[0069] S203, when the terminal information is the central control screen, determine that the response display terminal is the central control screen; when the terminal information is the co-pilot entertainment screen, determine that the response display terminal is the co-pilot entertainment screen; when the terminal information is the central control screen and the co-pilot entertainment screen, determine the response display terminal according to the collection point.

[0070] In the embodiment of the present invention, after the voice conversion obtains the text information, the text information will be segmented and POS tagged, specifically, the identified text information will be split into independent vocabulary units (i.e. segmented words). This step is the basis for subsequent processing, which helps the system understand the basic structure of the sentence, and then marks its part of speech (such as noun, verb, adjective, etc.) for each segmented word, and the part of speech tagging helps the system understand the role and function of vocabulary in the sentence, and then through the syntactic analyzer, the results of segmentation and part of speech tagging are combined into a syntactic structure tree, revealing the grammatical relationship between vocabulary (such as subject, predicate, object, attributive, adverbial, complement, etc.), on the basis of syntactic analysis, the semantic information of the sentence will be further analyzed, which includes identifying named entities (such as names, place names, organization names, etc.), understanding the deep meaning of sentences (such as metaphors, irony, etc.), and processing context association and reference resolution, and the goal of semantic analysis is to accurately capture user instructions. Then, the user instruction is matched with the execution list library to determine the execution instruction and the terminal information corresponding to the execution instruction. The terminal information is the central control screen and / or the co-pilot entertainment screen. The execution list library is established in advance and contains all the execution instructions. Each execution instruction is provided with corresponding terminal information. When the terminal information is the central control screen, the response display terminal is determined to be the central control screen; when the terminal information is the co-pilot entertainment screen, the response display terminal is determined to be the co-pilot entertainment screen; when the terminal information is the central control screen and the co-pilot entertainment screen, the response display terminal is determined according to the collection point. For example, if the collection point is the main driving point, the response display terminal is the central control screen, and if the collection point is the co-pilot point, the response display terminal is the co-pilot entertainment screen.

[0071] like Figure 4 As shown, as a preferred embodiment of the present invention, the step of determining whether an interactive response sound is generated and, when generated, determining the response type of the interactive response sound specifically includes:

[0072] S301, determining whether to generate an interactive response sound according to the responding vehicle computer software;

[0073] S302, when generated, inputting the corresponding vehicle software name into a response sound type library, wherein the response sound type library contains all vehicle software names, and each vehicle software name is marked with a specific response type;

[0074] S303, outputting the corresponding response type, wherein the response sound type library supports modification and editing.

[0075] In the embodiment of the present invention, the response type will also be determined. First, it will be determined whether an interactive response sound will be generated according to the corresponding vehicle software, that is, whether the corresponding vehicle software will make a sound when executing the instruction. When it is generated, the corresponding vehicle software name is input into the response sound type library, and the response sound type library contains all vehicle software names, and each vehicle software name is marked with a specific response type; in this way, the corresponding response type will be directly output, and the response sound type library supports user modification and editing. The response type is the main driving demand response, the co-pilot demand response, or the common demand response.

[0076] like Figure 5 As shown, as a preferred embodiment of the present invention, the step of controlling the corresponding speaker to play the interactive response sound according to the response type specifically includes:

[0077] S401, determining a sound volume according to a response type, wherein the primary driving demand response, the secondary driving demand response, and the common demand response each have a corresponding sound volume;

[0078] S402: Control the corresponding speaker to play the interactive response sound according to the response type and the sound volume.

[0079] In the embodiment of the present invention, in order to better perform sound response and avoid mutual interference, the main driving demand response, the co-pilot demand response and the common demand response are each bound to a corresponding sound volume, so that the sound volume can be determined according to the response type, and the corresponding speaker can be controlled to play the interactive response sound according to the response type and the sound volume. For example, the sound volume corresponding to the main driving demand response and the co-pilot demand response can be relatively small, and the sound volume corresponding to the common demand response needs to be relatively large. Of course, the volume of each sound can be set by itself.

[0080] like Figure 6 As shown, as a preferred embodiment of the present invention, the method further includes executing regional instructions according to the collection point, and the specific steps are:

[0081] S501, determining whether the execution instruction is a regional instruction, wherein the regional instruction includes a seat function adjustment instruction and an air conditioning light adjustment instruction;

[0082] S502: When the execution instruction is a regional instruction, execute the regional instruction according to the collection point.

[0083] In the embodiment of the present invention, it is also determined whether the execution instruction is a regional instruction. The regional instruction includes seat function adjustment instructions and air conditioning light adjustment instructions. For example, seat back adjustment, seat front and rear position adjustment and seat ventilation and heating are all seat function adjustment instructions. For example, reading light adjustment and air conditioning adjustment are air conditioning light adjustment instructions. When the execution instruction is a regional instruction, the regional instruction is executed according to the collection point. For example, the content of the execution instruction is to set the air conditioning to 24 degrees, and the collection point is the co-pilot, then the air conditioning at the co-pilot will be automatically adjusted to 24 degrees, which is more intelligent and humane.

[0084] like Figure 7 As shown, an embodiment of the present invention further provides an interactive system based on semantic recognition, the system comprising:

[0085] The voice and audio receiving module 100 is used to receive the voice and audio, and determine the collection point corresponding to the voice and audio, where the collection point is the main driving point or the co-driving point;

[0086] The user instruction determination module 200 is used to identify the voice audio to obtain text information, determine the user instruction according to the text information, and determine whether the response display terminal is the central control screen or the co-pilot entertainment screen according to the user instruction and the corresponding collection point;

[0087] A response type determination module 300 is used to determine whether an interactive response sound is generated, and when generated, determine the response type of the interactive response sound, wherein the response type is a primary driving demand response, a secondary driving demand response, or a common demand response;

[0088] The speaker playback control module 400 is used to control the corresponding speaker to play the interactive response sound according to the response type. When the response type is a main driver demand response, the main driver speaker is controlled to play the interactive response sound; when the response type is a co-driver demand response, the co-driver speaker is controlled to play the interactive response sound; when the response type is a common demand response, the entire vehicle speaker is controlled to play the interactive response sound.

[0089] As a preferred embodiment of the present invention, the voice audio receiving module 100 includes:

[0090] A voice and audio receiving unit, used to receive voice and audio, wherein the voice and audio include a main driving audio signal and a co-pilot audio signal;

[0091] An RMS value calculation unit, used to calculate the RMS values ​​of the main driver audio signal and the co-driver audio signal respectively;

[0092] The collection point determination unit is used to compare the RMS value of the main driving audio signal and the RMS value of the co-pilot audio signal, and determine whether the collection point corresponding to the voice audio is the main driving point or the co-pilot point.

[0093] As a preferred embodiment of the present invention, the response type determination module 300 includes:

[0094] A response sound determination unit, used to determine whether to generate an interactive response sound according to the responding vehicle computer software;

[0095] The vehicle computer software input unit is used to input the corresponding vehicle computer software name into the response sound type library when it is generated, and the response sound type library contains all vehicle computer software names, and each vehicle computer software name is marked with a specific response type;

[0096] The response type output unit is used to output the corresponding response type, and the response sound type library supports modification and editing.

[0097] As a preferred embodiment of the present invention, the speaker playback control module 400 includes:

[0098] A sound volume determination unit, used to determine the sound volume according to the response type, wherein the main driving demand response, the co-pilot demand response and the common demand response each have a corresponding sound volume;

[0099] The sound playing control unit is used to control the corresponding speaker to play the interactive response sound according to the response type and the sound volume.

[0100] The above only describes in detail the preferred embodiments of the present invention, which is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0101] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0102] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0103] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. An interactive method based on semantic recognition, characterized in that: The method comprises the following steps: Receive voice audio, and determine a collection point corresponding to the voice audio, the collection point being a main driving point or a co-driving point; Recognize the voice audio to obtain text information, determine the user command based on the text information, and determine the response display terminal as the central control screen or the co-pilot entertainment screen based on the user command and the corresponding collection point; Determining whether an interactive response sound is generated, and when generated, determining a response type of the interactive response sound, the response type being a primary driving demand response, a secondary driving demand response, or a common demand response; According to the response type, the corresponding speaker is controlled to play the interactive response sound. When the response type is the main driver's demand response, the main driver's speaker is controlled to play the interactive response sound; when the response type is the co-driver's demand response, the co-driver's speaker is controlled to play the interactive response sound; when the response type is the common demand response, the speakers of the entire vehicle are controlled to play the interactive response sound.

2. The interactive method based on semantic recognition according to claim 1, characterized in that: The step of receiving voice audio and determining the collection point corresponding to the voice audio specifically includes: Receiving voice audio, wherein the voice audio includes a main driving audio signal and a co-pilot audio signal; The RMS values ​​of the main driver audio signal and the co-driver audio signal are calculated respectively; Compare the RMS value of the main driver's audio signal and the RMS value of the co-driver's audio signal to determine whether the collection point corresponding to the voice audio is the main driver's point or the co-driver's point.

3. The interactive method based on semantic recognition according to claim 1, characterized in that: The step of determining the user instruction according to the text information, and determining the response display terminal as the central control screen or the co-pilot entertainment screen according to the user instruction and the corresponding collection point specifically includes: Perform word segmentation and part-of-speech tagging on text information, and perform semantic analysis through a syntactic analyzer to determine user instructions; Matching the user instruction with the execution list library to determine the execution instruction, and determining the terminal information corresponding to the execution instruction, wherein the terminal information is the central control screen and / or the co-pilot entertainment screen; When the terminal information is the central control screen, the response display terminal is determined to be the central control screen; when the terminal information is the co-driver entertainment screen, the response display terminal is determined to be the co-driver entertainment screen; when the terminal information is the central control screen and the co-driver entertainment screen, the response display terminal is determined according to the collection point.

4. The interactive method based on semantic recognition according to claim 1, characterized in that: The step of determining whether an interactive response sound is generated and, when generated, determining a response type of the interactive response sound specifically comprises: Determine whether to generate an interactive response sound according to the responding vehicle computer software; When generated, the corresponding vehicle software name is input into the response sound type library, which contains all vehicle software names, and each vehicle software name is marked with a specific response type; The corresponding response type is output, and the response sound type library supports modification and editing.

5. The interactive method based on semantic recognition according to claim 1, characterized in that: The step of controlling the corresponding speaker to play the interactive response sound according to the response type specifically includes: Determine the sound volume according to the response type, the main driving demand response, the co-pilot demand response and the common demand response each corresponding to a sound volume; The corresponding speaker is controlled to play the interactive response sound according to the response type and the sound volume.

6. The interactive method based on semantic recognition according to claim 3, characterized in that: The method further includes executing regional instructions according to the collection point, and the specific steps are: determining whether the execution instruction is a regional instruction, wherein the regional instruction includes a seat function adjustment instruction and an air conditioning light adjustment instruction; When the execution instruction is a regional instruction, the regional instruction is executed according to the collection point.

7. An interactive system based on semantic recognition, characterized in that: The system comprises: A voice and audio receiving module, used to receive voice and audio, and determine a collection point corresponding to the voice and audio, wherein the collection point is a main driving point or a co-driving point; A user command determination module is used to identify the voice audio to obtain text information, determine the user command according to the text information, and determine the response display terminal as the central control screen or the co-pilot entertainment screen according to the user command and the corresponding collection point; A response type determination module, used to determine whether to generate an interactive response sound, and when it is generated, determine the response type of the interactive response sound, the response type being a primary driving demand response, a secondary driving demand response, or a common demand response; The speaker playback control module is used to control the corresponding speaker to play the interactive response sound according to the response type. When the response type is the main driving demand response, the main driving speaker is controlled to play the interactive response sound; when the response type is the co-pilot demand response, the co-pilot speaker is controlled to play the interactive response sound; when the response type is the common demand response, the speakers of the entire vehicle are controlled to play the interactive response sound.

8. The interactive system based on semantic recognition according to claim 7, characterized in that: The voice audio receiving module comprises: A voice and audio receiving unit, used to receive voice and audio, wherein the voice and audio include a main driving audio signal and a co-pilot audio signal; An RMS value calculation unit, used to calculate the RMS values ​​of the main driver audio signal and the co-driver audio signal respectively; The collection point determination unit is used to compare the RMS value of the main driving audio signal and the RMS value of the co-pilot audio signal, and determine whether the collection point corresponding to the voice audio is the main driving point or the co-pilot point.

9. The interactive system based on semantic recognition according to claim 7, characterized in that: The response type determination module includes: A response sound determination unit, used to determine whether to generate an interactive response sound according to the responding vehicle computer software; The vehicle software input unit is used to input the corresponding vehicle software name into the response sound type library when it is generated, and the response sound type library contains all vehicle software names, and each vehicle software name is marked with a specific response type; The response type output unit is used to output the corresponding response type, and the response sound type library supports modification and editing.

10. The interactive system based on semantic recognition according to claim 7, characterized in that: The speaker playback control module includes: A sound volume determination unit, used to determine the sound volume according to the response type, wherein the main driving demand response, the co-pilot demand response and the common demand response each have a corresponding sound volume; The sound playing control unit is used to control the corresponding speaker to play the interactive response sound according to the response type and the sound volume.

Images