Vehicle navigation man-machine interaction method and system, electronic equipment and storage medium

Abstract

The invention provides a vehicle-mounted navigation man-machine interaction method and system, electronic equipment and a storage medium, and relates to the technical field of vehicle-mounted navigation, and the method comprises the steps: collecting sound signals in a vehicle through a microphone array which comprises a plurality of microphones and is used for collecting sound signals in different directions; preprocessing the in-vehicle sound signal by using a noise reduction algorithm to obtain a to-be-recognized voice signal; recognizing the to-be-recognized voice signal by using a deep learning model to obtain target text information; analyzing the target text information to obtain an analysis result; under the condition that the analysis result comprises a target interaction instruction, the vehicle-mounted navigation responds to the target interaction instruction according to a preset preference configuration file, and the target interaction instruction is used for representing an instruction for interaction with the vehicle-mounted navigation. By implementing the technical scheme provided by the invention, the effect of improving the user experience is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle-mounted navigation, and in particular to a vehicle-mounted navigation human-computer interaction method, system, electronic device and storage medium. Background Art

[0002] With the improvement of automobile intelligence, the in-vehicle navigation system has become one of the standard features of vehicles. It plays an important role in guiding drivers in driving directions and avoiding congested roads. Most of the mainstream in-vehicle navigation systems on the market currently have basic map display, route planning and other functions, which greatly facilitate people's travel. However, the existing in-vehicle navigation systems still have some shortcomings in human-computer interaction. They are greatly disturbed by noise, resulting in low voice recognition accuracy, and the navigation system's response method is relatively simple, which affects the user experience. Summary of the invention

[0003] In order to solve the above technical problems, the present application provides a vehicle-mounted navigation human-computer interaction method, system, electronic device and storage medium.

[0004] In a first aspect, the present application provides a method for human-computer interaction of in-vehicle navigation, comprising: collecting in-vehicle sound signals through a microphone array, wherein the microphone array includes multiple microphones for collecting sound signals in different directions; preprocessing the in-vehicle sound signals using a noise reduction algorithm to obtain a voice signal to be recognized; using a deep learning model to recognize the voice signal to be recognized to obtain target text information; parsing the target text information to obtain a parsing result; when the parsing result includes a target interaction instruction, the in-vehicle navigation responds to the target interaction instruction according to a preset preference profile, wherein the target interaction instruction is used to represent an instruction for interacting with the in-vehicle navigation.

[0005] By adopting the above technical solution, multiple microphones are used to collect sound signals from different directions, so as to capture the sound environment in the car more comprehensively and reduce omissions caused by single-point collection; the sound signals in the car are preprocessed to remove background noise, thereby improving the accuracy of speech recognition; the preprocessed speech signals are recognized using advanced deep learning technology, further improving the accuracy and robustness of speech recognition; by parsing the recognized target text information, it is ensured that the system can correctly understand the user's intention; then based on the preset preference profile, the in-vehicle navigation can respond to the user's interactive instructions more personalized, improving the user experience and satisfaction. In summary, this technical solution not only solves the problem of speech recognition of existing in-vehicle navigation systems under noise interference, but also greatly improves the user's overall driving experience through intelligent analysis and personalized response.

[0006] Optionally, when the parsing result includes target interaction instructions, the in-vehicle navigation responds to the target interaction instructions according to a preset preference profile, including: comparing the parsing result with a preset instruction library; when the parsing result includes any instruction in the preset instruction library, determining that the parsing result includes the target interaction instruction; the in-vehicle navigation responds to the target interaction instruction according to preset interaction rules or user preferences, wherein the preference profile includes interaction rules and user preferences.

[0007] By adopting the above technical solution, the voice recognition accuracy and response speed of the vehicle navigation system can be significantly improved. Specifically, by comparing the analysis results with the preset instruction library, it is possible to quickly determine whether a valid target interaction instruction is included, thereby avoiding misjudgment; when the analysis results contain any instruction in the preset instruction library, the system can accurately identify the target interaction instruction and respond accordingly according to the preset interaction rules or user preferences, thereby improving the intelligence of the system and user experience. The preset preference profile includes not only the interaction rules, but also the user's personalized preferences, so that the system can better adapt to the needs of different users and improve the naturalness and convenience of human-computer interaction.

[0008] Optionally, the above method also includes: when the analysis result does not include any instruction in the preset instruction library, determining that the analysis result does not include the target interaction instruction, and the vehicle navigation does not respond to the in-vehicle sound signal.

[0009] By adopting the above technical solution, when the parsing result does not include any instruction in the preset instruction library, it is determined that the parsing result does not include the target interaction instruction, and the in-vehicle navigation does not respond to the in-vehicle sound signal, which helps to avoid misoperation and improve the stability and reliability of the system.

[0010] Optionally, the preference profile is obtained in the following ways: collecting the user's biometric information when using the vehicle for the first time and building a personal profile of the user; continuously recording each interaction event of the user during use; building a user behavior pattern database through iterative training, and establishing a preference profile that matches the user, wherein the preference profile is used to dynamically adjust the vehicle-mounted interface layout and response method.

[0011] By adopting the above technical solutions, the user's biometric information is collected when used for the first time to build a personal profile, which can ensure that the system has a unique recognition ability for each user and improve the user experience; it continuously records each interaction event of the user during use, and builds a user behavior pattern database through iterative training, so that the system can better understand and predict user needs, thereby providing more intelligent navigation services; the preference profile is used to dynamically adjust the layout and response mode of the vehicle interface, so that the system can automatically optimize according to the user's habits and preferences, further improving the convenience and comfort of human-computer interaction. By dynamically adjusting the interface layout and response mode, the system can better adapt to the user's usage habits and improve operational efficiency and satisfaction.

[0012] Optionally, when the parsing result includes a target interaction instruction, the in-vehicle navigation responds to the target interaction instruction according to a preset preference profile, including: when the parsing result includes the target interaction instruction, searching the local cache for a navigation result that matches the target interaction instruction, wherein a target navigation data set is pre-stored in the local cache, the target navigation data set including common destinations and route data; when it is determined that a navigation result that matches the target interaction instruction exists in the local cache, the in-vehicle navigation calls the navigation result from the local cache and responds according to the preset preference profile.

[0013] By adopting the above technical solution, when the parsing result includes the target interaction instruction, the local cache is searched for navigation results that match the target interaction instruction, so that commonly used destinations and route data can be quickly located, reducing system query time. When it is determined that there are navigation results that match the target interaction instruction in the local cache, the in-vehicle navigation can directly call the corresponding navigation results from the local cache and respond according to the preset preference profile, avoiding repeated calculations and network delays, and improving the user experience. By pre-storing commonly used navigation data sets in the local cache, services can be provided quickly even in poor network conditions, significantly improving the response speed of the in-vehicle navigation system.

[0014] Optionally, when the parsing result includes target interaction instructions, the in-vehicle navigation responds to the target interaction instructions according to a preset preference profile, including: acquiring a target image, and recognizing the target image to obtain an image recognition result, wherein the target image is captured by a vehicle-mounted camera; when the parsing result includes target interaction instructions, judging the validity of the target interaction instructions based on the image recognition result; when it is determined that the target interaction instruction is a valid instruction, the in-vehicle navigation responds to the target interaction instruction according to the preset preference profile.

[0015] By adopting the above technical solution, the target image captured by the vehicle camera is used for recognition to ensure the validity of the target interaction instructions in the parsing results. This not only improves the accuracy of the system's understanding of user intentions, but also reduces invalid operations caused by misjudgment, thereby improving the user experience. After determining that the target interaction instruction is a valid instruction, the vehicle navigation responds according to the preset preference profile, further enhancing the system's personalized service capabilities and enabling the navigation system to better adapt to the usage habits and needs of different users.

[0016] Optionally, the above method also includes: perceiving the user's current emotional state based on the voice intonation and facial expressions of the in-car sound signal, wherein the in-car sound signal includes the user's voice signal, and the image recognition result includes the recognition result of the facial expression; the in-car navigation adjusts the navigation voice according to the voice broadcast method matching the current emotional state in the preference profile to respond to the target interaction command.

[0017] By adopting the above technical solution, the user's current emotional state can be accurately perceived by analyzing the voice intonation and facial expressions of the sound signal in the car; the in-vehicle navigation system can select a voice broadcast method that matches the perceived emotional state for navigation response, thereby improving the user experience and making the interaction more natural and humane; this method can achieve more accurate emotion perception and personalized navigation voice adjustment.

[0018] In the second aspect of the present application, a vehicle-mounted navigation human-computer interaction system is also provided, including: an acquisition module for acquiring in-vehicle sound signals; a noise reduction processing module for preprocessing the in-vehicle sound signals using a noise reduction algorithm to obtain a voice signal to be recognized; a voice recognition module for using a deep learning model to recognize the voice signal to be recognized to obtain target text information; a parsing module for parsing the target text information to obtain a parsing result; and a response module for, when the parsing result includes a target interaction instruction, the vehicle-mounted navigation responds to the target interaction instruction according to a preset preference profile, wherein the target interaction instruction is used to represent an instruction for interacting with the vehicle-mounted navigation.

[0019] In a third aspect of the present application, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, any of the above method steps is implemented.

[0020] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the above method steps is performed.

[0021] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: 1. Improved the accuracy of voice recognition. Based on the preset preference profile, the in-vehicle navigation can respond to the user's interactive instructions more personalized, improving the user experience and satisfaction; 2. The preference profile is used to dynamically adjust the layout and response mode of the vehicle interface, so that the system can be automatically optimized according to the user's habits and preferences, further improving the convenience and comfort of human-computer interaction; 3. By pre-storing commonly used navigation data sets in the local cache, services can be provided quickly even in poor network conditions, significantly improving the response speed of the in-vehicle navigation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of a vehicle navigation human-computer interaction method provided by an embodiment of the present application; Figure 2 It is a structural block diagram of a vehicle navigation human-computer interaction system provided in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application.

[0023] Description of reference numerals: 300 - electronic device; 301 - processor; 302 - communication bus; 303 - user interface; 304 - network interface; 305 - memory. DETAILED DESCRIPTION

[0024] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0025] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0026] In the description of the embodiments of the present application, the term "plurality" means two or more. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0027] The following is combined with Figure 1-Figure 3 The embodiments of the present application are described.

[0028] This application provides a vehicle navigation human-computer interaction method, referring to Figure 1 , Figure 1 : is a flow chart of a vehicle navigation human-computer interaction method provided by an embodiment of the present application, the method comprising: Step S101, collecting in-vehicle sound signals through a microphone array, wherein the microphone array includes a plurality of microphones for collecting sound signals from different directions; Step S102, preprocessing the in-vehicle sound signal using a noise reduction algorithm to obtain a speech signal to be recognized; Step S103, using a deep learning model to recognize the speech signal to be recognized to obtain target text information; Step S104, parsing the target text information to obtain a parsing result; Step S105: when the parsing result includes the target interaction instruction, the in-vehicle navigation responds to the target interaction instruction according to a preset preference configuration file, wherein the target interaction instruction is used to represent an instruction for interacting with the in-vehicle navigation.

[0029] Through the above steps, by collecting sound signals from different directions through multiple microphones, the sound environment inside the car can be captured more comprehensively, reducing omissions caused by single-point collection; preprocessing the sound signals inside the car to remove background noise, thereby improving the accuracy of speech recognition; using advanced deep learning technology to recognize the preprocessed speech signals, further improving the accuracy and robustness of speech recognition; by parsing the recognized target text information, ensure that the system can correctly understand the user's intentions; then based on the preset preference profile, the in-vehicle navigation can respond to the user's interactive instructions more personalized, improving user experience and satisfaction. In summary, the method of this embodiment not only solves the problem of speech recognition of existing in-vehicle navigation systems under noise interference, but also greatly improves the user's overall driving experience through intelligent analysis and personalized response.

[0030] The microphone array is used to collect the sound signals in the car, which can effectively collect the sound signals from different directions, and the noise reduction algorithm is used for preprocessing, which can effectively remove the background noise. For example, the adaptive filter algorithm can effectively suppress the wind noise and engine noise from inside and outside the car, making the driver's voice clearer and improving the accuracy of speech recognition. The accuracy of speech recognition is significantly improved, and the recognition problem caused by noise interference in the existing technology is effectively solved. The preprocessed speech signal is recognized by a deep learning model (such as GRU, LSTM, etc.), which can more accurately obtain the target text information. The target text information can be parsed by natural language processing technology to extract the instructions and intentions therein. When the parsing result contains the target interaction instruction, the in-vehicle navigation responds according to the preset preference profile, realizing a personalized interaction method and meeting the diverse needs of different users. For example, the parsing result includes the instruction to go to the XX destination. The in-vehicle navigation can call the in-vehicle map data for route planning or related information retrieval based on the instruction, and quickly feedback to the user. The preference profile can be customized and updated according to the user's personal habits and preferences, improving the flexibility and personalization of human-computer interaction, avoiding the problem that the in-vehicle navigation system in the related art can only interact in a fixed way, or there may be navigation systems in the related art that need to manually adjust the interaction method, which affects the user's experience. This embodiment significantly improves the accuracy of speech recognition and reduces the number of misidentifications through noise reduction algorithms and deep learning models; provides personalized navigation services based on the user's preference profile to improve user satisfaction.

[0031] In an optional embodiment, when the parsing result includes a target interaction instruction, the in-vehicle navigation responds to the target interaction instruction according to a preset preference profile, including: comparing the parsing result with a preset instruction library; when the parsing result includes any instruction in the preset instruction library, determining that the parsing result includes the target interaction instruction; the in-vehicle navigation responds to the target interaction instruction according to preset interaction rules or user preferences, wherein the preference profile includes interaction rules and user preferences.

[0032] In the above embodiment, the voice recognition accuracy and response speed of the vehicle navigation system can be significantly improved. Specifically, by comparing the analysis results with the preset instruction library, it is possible to quickly determine whether a valid target interaction instruction is included, thereby avoiding misjudgment; when the analysis results contain any instruction in the preset instruction library, the system can accurately identify the target interaction instruction and respond accordingly according to the preset interaction rules or user preferences, thereby improving the intelligence of the system and user experience. The preset preference profile includes not only the interaction rules, but also the user's personalized preferences, so that the system can better adapt to the needs of different users and improve the naturalness and convenience of human-computer interaction.

[0033] First, by comparing the parsing results with the preset instruction library, it is determined whether it contains valid target interaction instructions. If there is a match, it is identified as the target interaction instruction, and actions are taken according to the interaction rules or user preferences specified in the preference profile. This step ensures that the system only responds to valid instructions and avoids misoperation. Secondly, when it is determined that the target interaction instruction is included, the system responds according to the preset interaction rules or user preferences. The interaction rules may include the execution order and priority of the instructions, while the user preferences may involve the selection of navigation paths, the method of voice prompts, etc. By combining the interaction rules and user preferences, the system can provide more personalized and intelligent navigation services. Through the instruction matching mechanism, the system ensures accurate recognition of valid instructions and avoids misoperation caused by misidentification. By combining the interaction rules and user preferences, the response method is diversified and personalized, which improves the flexibility of the system and user satisfaction. Through personalized services, more intelligent navigation services are provided according to the user's preference profile to enhance user satisfaction.

[0034] The target interaction instructions may be route planning instructions, destination search instructions, route modification instructions, or navigation auxiliary function instructions. Interaction rules are rules for the system to respond to after receiving user instructions. They may be pre-set rules, for example, they may include multiple instruction processing rules. For complex multi-step instructions, the system will execute them step by step. For example, if the user says "navigate to ** first, then find nearby restaurants", the system will first start the navigation function, and after arriving at **, search for nearby restaurants. For example, the navigation guidance rules. During the navigation process, the system will update the vehicle position in real time and provide navigation instructions such as turning and distance. For example, when the vehicle approaches a turning point, the system will issue a voice prompt in advance, "Turn right 50 meters ahead; there are also route optimization rules. If there is traffic congestion, the system will automatically re-plan the route and notify the user. For example, the system will say "The road ahead is congested, and the route has been re-planned for you." User preferences may include: navigation path preferences, such as the option to avoid highways, give priority to free roads, and avoid congestion; voice prompt preferences. Users can set the volume, speed, tone, and content of voice prompts (such as only prompting turning information, not distance); language selection preferences, such as Chinese, English, or dialects; screen display preferences. Users can adjust screen brightness, contrast, display mode (such as day mode, night mode), and map zoom ratio; broadcast channel preferences. Users can choose default broadcast channels, such as news channels, music channels, etc.; safety assistance preferences, such as fatigue driving reminders. Users can set the interval time for fatigue driving reminders, such as reminding once every 2 hours.

[0035] In an optional embodiment, the method further includes: when the parsing result does not include any instruction in the preset instruction library, determining that the parsing result does not include the target interaction instruction, and the in-vehicle navigation does not respond to the in-vehicle sound signal.

[0036] In the above embodiment, when the analysis result does not include any instruction in the preset instruction library, it is determined that the analysis result does not include the target interaction instruction, and the vehicle navigation does not respond to the in-vehicle sound signal, which helps to avoid misoperation and improve the stability and reliability of the system.

[0037] When the parsing result does not include any instruction in the preset instruction library, the in-vehicle navigation does not respond to the sound signal in the car, which can avoid invalid interaction and the safety risks that may be caused by performing incorrect operations. Optionally, when the parsing result does not include any instruction in the preset instruction library, the in-vehicle navigation can give a clear error prompt, for example, it can be a voice prompt or an information prompt through the in-vehicle screen; through this embodiment, when the system cannot recognize the user's instruction, by not giving any response or giving a clear error prompt, the user can know that the system did not understand his or her instruction, thereby avoiding user confusion or dissatisfaction.

[0038] In an optional embodiment, the preference profile is obtained in the following manner: collecting the user's biometric information when using the vehicle for the first time and building a personal profile of the user; continuously recording each interaction event of the user during use; through iterative training, building a user behavior pattern database, and establishing a preference profile that matches the user, wherein the preference profile is used to dynamically adjust the vehicle-mounted interface layout and response mode.

[0039] In the above embodiment, the user's biometric information is collected when used for the first time to build a personal profile, which can ensure that the system has a unique recognition ability for each user and improve the user experience; each interaction event of the user during use is continuously recorded, and the user's behavior pattern database is built through iterative training, so that the system can better understand and predict the user's needs, thereby providing a more intelligent navigation service; the preference profile is used to dynamically adjust the layout and response mode of the vehicle interface, so that the system can automatically optimize according to the user's habits and preferences, and further improve the convenience and comfort of human-computer interaction. By dynamically adjusting the interface layout and response mode, the system can better adapt to the user's usage habits and improve operational efficiency and satisfaction. From collecting biometric information to establish a personal profile when used for the first time, to recording each interaction event, to using these data for iterative training to build a behavior pattern database, and finally forming a personalized preference profile, the entire process is a closed-loop learning and optimization process; this method not only takes into account the personalized settings for the first use, but also emphasizes the adaptability and improvement in long-term use, ensuring that the system can continuously optimize the user experience over time.

[0040] When a user uses the in-vehicle navigation system for the first time, the system will collect his / her biometric information (e.g., facial recognition through a camera or fingerprint scanning through a touch screen) and create a personal profile; as the user uses it daily, the system will record all interactive events, including but not limited to voice commands, touch operations, destination selection, etc.; using these accumulated data, the system can iteratively train through a machine learning algorithm and gradually build a database that reflects the user's behavior patterns; based on the above-mentioned behavior pattern database, the system establishes a preference profile for each user, which is used to guide the system on how to dynamically adjust the interface layout and response mode according to the user's habits. Through this embodiment, a personal profile is constructed through the user's biometric information and interactive behavior, and the interface layout and response mode of the in-vehicle navigation system are dynamically adjusted by continuously learning the user's behavior pattern. By dynamically adjusting the interface layout and response mode, the system can better adapt to the user's usage habits and improve operational efficiency and satisfaction; as the understanding of the user's behavior pattern deepens, the system can make a more intelligent and appropriate response, making the interaction more natural and smooth; a system that can "understand" and adapt to user needs is more likely to win the trust and love of users, thereby increasing the market competitiveness of the product.

[0041] In an optional embodiment, when the parsing result includes a target interaction instruction, the in-vehicle navigation responds to the target interaction instruction according to a preset preference profile, including: when the parsing result includes a target interaction instruction, searching the local cache for a navigation result that matches the target interaction instruction, wherein a target navigation data set is pre-stored in the local cache, the target navigation data set including common destinations and route data; when it is determined that a navigation result that matches the target interaction instruction exists in the local cache, the in-vehicle navigation calls the navigation result from the local cache and responds according to the preset preference profile.

[0042] In the above embodiment, when the parsing result includes the target interaction instruction, searching the local cache for navigation results that match the target interaction instruction can quickly locate commonly used destinations and route data, reducing system query time. When it is determined that there are navigation results that match the target interaction instruction in the local cache, the in-vehicle navigation can directly call the corresponding navigation results from the local cache and respond according to the preset preference profile, avoiding repeated calculations and network delays, and improving the user experience. By pre-storing commonly used navigation data sets in the local cache, services can be provided quickly even in poor network conditions, significantly improving the response speed of the in-vehicle navigation system.

[0043] In order to solve the problem of slow response to instructions during human-computer interaction, the in-vehicle navigation system can cache frequently used geographic data locally, such as common locations, road information, etc., so that services can be provided quickly even in poor network conditions. Specifically, when the parsing results include target interaction instructions, the in-vehicle navigation system first checks whether there is a navigation result matching the target interaction instruction in the local cache; the local cache pre-stores the target navigation data set, including common destinations and route data, which are used to accelerate the generation of navigation results; if there is a matching navigation result in the local cache, the in-vehicle navigation system will call the result from the cache and respond according to the preset preference profile, such as adjusting the display mode of the navigation interface, the style of voice prompts, etc. The local cache storing common destination and route data in the in-vehicle navigation system can speed up the generation of navigation results and improve user experience; as well as reduce the number of remote data accesses, it can reduce network burden and energy consumption and improve the overall efficiency of the system.

[0044] In an optional embodiment, when the analysis result includes a target interaction instruction, the vehicle navigation responds to the target interaction instruction according to a preset preference profile, including: acquiring a target image, and recognizing the target image to obtain an image recognition result, wherein the target image is taken by a vehicle-mounted camera; when the analysis result includes a target interaction instruction, judging the validity of the target interaction instruction based on the image recognition result; when it is determined that the target interaction instruction is a valid instruction, the vehicle navigation responds to the target interaction instruction according to the preset preference profile.

[0045] In the above embodiment, the target image captured by the vehicle camera is used for recognition to ensure the validity of the target interaction instruction in the analysis result, which not only improves the accuracy of the system's understanding of the user's intention, but also reduces invalid operations caused by misjudgment, thereby improving the user experience. After determining that the target interaction instruction is a valid instruction, the vehicle navigation responds according to the preset preference profile, further enhancing the system's personalized service capabilities and enabling the navigation system to better adapt to the usage habits and needs of different users.

[0046] The target image is captured by a vehicle camera. For example, the target image may be a user's gesture, facial expression or other image. The captured target image is identified to obtain an image recognition result. The result is used to assist in determining the validity of the user interaction instruction. When the analysis result includes the target interaction instruction, the image recognition result is combined to determine whether the instruction is valid. For example, if the image recognition result shows that the user is making a specific gesture and the gesture is consistent with the interaction instruction, the instruction is determined to be valid; when the target interaction instruction is determined to be a valid instruction, the vehicle navigation responds according to the preset preference profile, such as adjusting the navigation path, playing music or performing other user-defined operations. This embodiment can significantly reduce the probability of misidentification and improve the accuracy of the system by combining the image recognition result to determine the validity of the interaction instruction; using image recognition technology as an auxiliary identity authentication method can enhance the security of the system and prevent unauthorized operations; by introducing image recognition technology, more interaction methods are provided for the vehicle navigation system, such as gesture control, etc., which increases the flexibility and fun of the system, and responds according to the preset preference profile, which can meet the personalized needs of users and improve user experience.

[0047] In an optional embodiment, the above method also includes: perceiving the user's current emotional state based on the voice intonation and facial expressions of the in-car sound signal, wherein the in-car sound signal includes the user's voice signal, and the image recognition result includes the recognition result of the facial expression; the in-car navigation adjusts the navigation voice according to the voice broadcast method matching the current emotional state in the preference profile to respond to the target interaction command.

[0048] In the above embodiment, by analyzing the voice intonation and facial expressions of the sound signal in the car, the user's current emotional state can be accurately perceived; the in-vehicle navigation system can select a voice broadcast method that matches the perceived emotional state for navigation response, thereby improving the user experience and making the interaction more natural and humane; this method can achieve more accurate emotional perception and personalized navigation voice adjustment.

[0049] The user's facial expression is collected by the vehicle camera and the user's voice signal is collected by the microphone, and the user's emotional state is perceived by using image recognition and voice emotion recognition technology. For example, the user's facial expression is captured by the vehicle camera, and the facial features are extracted by a deep learning model (such as a convolutional neural network) to identify the user's emotional state. The user's voice signal is collected by the microphone, and the user's emotional state is identified by feature extraction (such as MFCCs and PLP-CC) and classifier (such as SVM). For example, by analyzing the voice intonation features (such as pitch, sound intensity, rhythm, etc.) in the sound signal emitted by the user, the system can preliminarily estimate the user's emotional state; according to the perceived emotional state, the vehicle navigation system adjusts the navigation voice broadcasting mode according to the preset preference profile. For example, if the user is depressed, the system can use a soft tone for broadcasting; if the user is excited, the system can use a more energetic tone for broadcasting. In this embodiment, by perceiving the user's emotional state and adjusting the voice broadcasting mode, the system can provide a more intimate and personalized interactive experience and improve user satisfaction; by adjusting the voice broadcasting mode, the system can reduce the user's emotional fluctuations and improve driving safety. If the system can sense negative emotions such as driver stress or fatigue, it can take appropriate measures, such as suggesting a break or playing soothing music, thereby helping to improve driving safety.

[0050] Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application will be described in detail below in conjunction with specific embodiments.

[0051] For example, in a specific application scenario, when the driver issues a voice command of "go to the downtown museum", the in-vehicle navigation system first receives the sound signal through the microphone array located under the steering wheel, and then the system uses an adaptive filter algorithm to effectively suppress wind noise, engine noise, etc. from inside and outside the car, making the driver's voice clearer. After preprocessing, the voice signal is sent to a pre-trained deep neural network model, which accurately identifies the driver's intention. The system immediately searches and calculates the best route to the downtown museum from the cloud database, and informs the driver of the estimated arrival time and the turn instructions ahead in voice form. The entire interactive process is smooth and efficient, greatly improving the driving experience.

[0052] Furthermore, in order to solve the problem of slow response to commands during human-computer interaction, a fast response mechanism is used to reduce system response time by increasing local cache and optimizing cloud service request strategies. Specifically, the in-vehicle navigation system can cache frequently used geographic data locally, such as common locations, road information, etc., so that services can be provided quickly even in poor network conditions. At the same time, for functions that require remote data support, such as weather forecasts and real-time traffic updates, the system uses intelligent prediction algorithms to preload potentially useful information in advance to avoid response delays caused by network delays.

[0053] To further enhance the user experience, a personalized customization function is added, so that the navigation system can automatically adjust the interface layout and voice broadcast style according to the habits of different drivers. Specifically, the system forms a personalized user profile by learning user behavior patterns, such as frequently used destinations, preferred route types (fastest or most scenic), and preferred language style of navigation voice. Each time the navigation is started, the system automatically calls these settings, so that each journey can be tailored to personal preferences, thereby improving satisfaction and loyalty.

[0054] The present application also provides a vehicle-mounted navigation human-computer interaction system, such as Figure 2 As shown, Figure 2 : is a structural block diagram of a vehicle navigation human-computer interaction system provided in an embodiment of the present application, the system comprising: The acquisition module 201 is used to acquire the sound signal inside the vehicle; The noise reduction processing module 202 is used to pre-process the in-vehicle sound signal using a noise reduction algorithm to obtain a speech signal to be recognized; The speech recognition module 203 is used to use a deep learning model to recognize the speech signal to be recognized to obtain target text information; The parsing module 204 is used to parse the target text information and obtain the parsing result; The response module 205 is used for, when the parsing result includes a target interaction instruction, the in-vehicle navigation responds to the target interaction instruction according to a preset preference configuration file, wherein the target interaction instruction is used to represent an instruction for interacting with the in-vehicle navigation.

[0055] In an optional embodiment, the above-mentioned response module 205 includes: a comparison unit, used to compare the parsing result with a preset instruction library; a first determination unit, used to determine that the parsing result includes a target interaction instruction when the parsing result includes any instruction in the preset instruction library; a first response unit, used for the in-vehicle navigation to respond to the target interaction instruction according to preset interaction rules or user preferences, wherein the preference profile includes interaction rules and user preferences.

[0056] In an optional embodiment, the system further includes: a second determination unit, configured to determine that the parsing result does not include the target interaction instruction, and the vehicle navigation does not respond to the in-vehicle sound signal when the parsing result does not include any instruction in the preset instruction library.

[0057] In an optional embodiment, the above-mentioned preference profile is obtained in the following manner: collecting the user's biometric information when using for the first time and building a personal profile of the user; continuously recording each interaction event of the user during use; through iterative training, building a user's behavior pattern database, and establishing a preference profile matching the user, wherein the preference profile is used to dynamically adjust the vehicle-mounted interface layout and response mode.

[0058] In an optional embodiment, the response module 205 includes: a search unit, used to search in the local cache whether there is a navigation result matching the target interaction instruction when the parsing result includes the target interaction instruction, wherein a target navigation data set is pre-stored in the local cache, and the target navigation data set includes common destinations and route data; a calling unit, used to call the navigation result from the local cache when it is determined that there is a navigation result matching the target interaction instruction in the local cache, and the in-vehicle navigation responds according to a preset preference profile.

[0059] In an optional embodiment, the above-mentioned response module 205 includes: an acquisition unit, used to acquire a target image, and identify the target image to obtain an image recognition result, wherein the target image is taken by a vehicle-mounted camera; a judgment unit, used to judge the validity of the target interaction instruction according to the image recognition result when the analysis result includes the target interaction instruction; a second response unit, used to respond to the target interaction instruction according to a preset preference profile by the vehicle-mounted navigation when it is determined that the target interaction instruction is a valid instruction.

[0060] In an optional embodiment, the system further includes: a perception module, used to perceive the user's current emotional state based on the voice intonation and facial expressions of the in-car sound signal, wherein the in-car sound signal includes the user's voice signal, and the image recognition result includes the recognition result of the facial expression; an adjustment module, used for the in-car navigation to adjust the navigation voice according to the voice broadcast method matching the current emotional state in the preference profile, so as to respond to the target interaction command.

[0061] The specific interactive control method of the above system is the same as the interactive control method in the aforementioned embodiment, and will not be repeated here.

[0062] The present application also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed, any one of the method steps described above is executed.

[0063] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0064] The present application also discloses an electronic device. Figure 3 As shown, Figure 3 The electronic device 300 may include: at least one processor 301 , at least one communication bus 302 , a user interface 303 , at least one network interface 304 , and a memory 305 .

[0065] The communication bus 302 is used to realize the connection and communication between these components.

[0066] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0067] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0068] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts of the entire electronic device (such as a server), and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0069] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a vehicle navigation human-computer interaction method.

[0070] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call an application program of a vehicle navigation human-computer interaction method stored in the memory 305, and when executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0071] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0072] In the several implementation modes provided in this application, it should be understood that the disclosed device or system can be implemented in other ways. For example, the device or system embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0073] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0074] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0075] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0076] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification, those skilled in the art will easily think of other embodiments of the present disclosure.

[0077] This application is intended to cover any modifications, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field not recorded in the present disclosure.

Claims

1. A vehicle navigation human-computer interaction method, characterized in that: include: Collecting in-vehicle sound signals through a microphone array, wherein the microphone array includes a plurality of microphones for collecting sound signals from different directions; Preprocessing the in-vehicle sound signal using a noise reduction algorithm to obtain a speech signal to be recognized; Using a deep learning model to recognize the speech signal to be recognized to obtain target text information; Parsing the target text information to obtain a parsing result; In a case where the parsing result includes a target interaction instruction, the in-vehicle navigation responds to the target interaction instruction according to a preset preference configuration file, wherein the target interaction instruction is used to represent an instruction for interacting with the in-vehicle navigation.

2. The method according to claim 1, characterized in that: In the case where the parsing result includes the target interaction instruction, the in-vehicle navigation responds to the target interaction instruction according to a preset preference configuration file, including: Comparing the analysis result with a preset instruction library; When the parsing result includes any instruction in the preset instruction library, determining that the parsing result includes the target interaction instruction; The in-vehicle navigation responds to the target interaction instruction according to preset interaction rules or user preferences, wherein the preference configuration file includes the interaction rules and the user preferences.

3. The method according to claim 2, characterized in that The method further comprises: When the analysis result does not include any instruction in the preset instruction library, it is determined that the analysis result does not include the target interaction instruction, and the in-vehicle navigation does not respond to the in-vehicle sound signal.

4. The method according to claim 1, characterized in that The preference profile is obtained by: Collecting the user's biometric information upon first use to build a personal profile of the user; Continuously record each interaction event of the user during use; Through iterative training, a behavior pattern database of the user is constructed, and a preference profile matching the user is established, wherein the preference profile is used to dynamically adjust the interface layout and response mode of the vehicle.

5. The method according to claim 1, characterized in that In the case where the parsing result includes the target interaction instruction, the in-vehicle navigation responds to the target interaction instruction according to a preset preference configuration file, including: In the case where the parsing result includes the target interaction instruction, searching in a local cache whether there is a navigation result matching the target interaction instruction, wherein a target navigation data set is pre-stored in the local cache, and the target navigation data set includes common destination and route data; When it is determined that the navigation result matching the target interaction instruction exists in the local cache, the in-vehicle navigation calls the navigation result from the local cache and responds according to the preset preference profile.

6. The method according to claim 1, characterized in that In the case where the parsing result includes the target interaction instruction, the in-vehicle navigation responds to the target interaction instruction according to the preset preference configuration file, including: Acquiring a target image, and recognizing the target image to obtain an image recognition result, wherein the target image is taken by using a vehicle-mounted camera; In the case where the analysis result includes a target interaction instruction, judging the validity of the target interaction instruction according to the image recognition result; When it is determined that the target interaction instruction is a valid instruction, the in-vehicle navigation responds to the target interaction instruction according to the preset preference profile.

7. The method according to claim 6, characterized in that The method further comprises: Perceiving the current emotional state of the user according to the voice intonation and facial expression of the in-vehicle sound signal, wherein the in-vehicle sound signal includes the voice signal of the user, and the image recognition result includes the recognition result of the facial expression; The in-vehicle navigation adjusts the navigation voice according to the voice broadcast mode in the preference configuration file that matches the current emotional state to respond to the target interaction instruction.

8. A vehicle-mounted navigation human-computer interaction system, characterized in that: include: A collection module, used for collecting sound signals inside the vehicle; A noise reduction processing module, used to pre-process the in-vehicle sound signal using a noise reduction algorithm to obtain a speech signal to be recognized; A speech recognition module, used to use a deep learning model to recognize the speech signal to be recognized to obtain target text information; A parsing module, used to parse the target text information to obtain a parsing result; A response module is used for, when the parsing result includes a target interaction instruction, the vehicle navigation responds to the target interaction instruction according to a preset preference configuration file, wherein the target interaction instruction is used to represent an instruction for interacting with the vehicle navigation.

9. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images