Navigation information adjustment method and device, storage medium and electronic equipment

Abstract

The invention discloses a navigation information adjustment method and device, a storage medium and electronic equipment. Relates to the technical field of intelligent navigation. The method comprises the steps that under the condition that it is detected that a driver of a target vehicle is in place, identity recognition is conducted on the driver, and target identity information is obtained; acquiring driving environment information of the target vehicle at the current moment to obtain target environment information; based on the target identity information and the target environment information, using a target recommendation model to predict driving planning information of the driver to obtain a prediction result, the target recommendation model including driving planning data of the driver driving a vehicle in a historical time period and driving environment information in the historical time period, training the neural network model to obtain a model; and adjusting navigation information of a navigation system of the target vehicle based on the prediction result. The technical problem that the navigation information of the navigation system needs to be manually adjusted after the driver is replaced and the adjustment efficiency is low in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent navigation technology, and in particular to a navigation information adjustment method, device, storage medium and electronic equipment. Background Art

[0002] At present, whether it is urban commuting or long-distance travel, the in-vehicle navigation system plays a vital role, and its purpose is to bring users a more efficient and comfortable travel experience.

[0003] During vehicle driving, there are many scenarios where the driver needs to be replaced temporarily. For example, when traveling long distances to avoid fatigue driving, the driver needs to be replaced midway, or when the driver has an emergency to deal with. However, different drivers have different driving skills and driving habits. In this case, it is often necessary to re-personalize the navigation system before re-starting navigation.

[0004] In the related art, the driver is required to manually reset the navigation information of the navigation system, and the navigation information adjustment efficiency of the navigation system is extremely low.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiments of the present invention provide a navigation information adjustment method, device, storage medium and electronic device to at least solve the technical problem in the related art that after changing the driver, the navigation information of the navigation system needs to be manually adjusted and the adjustment efficiency is low.

[0007] According to one aspect of an embodiment of the present invention, a navigation information adjustment method is provided, comprising: upon detecting that a driver is seated in the main driving seat of a target vehicle, identifying the driver to obtain target identity information; acquiring driving environment information of the target vehicle at a current moment to obtain target environment information; based on the target identity information and the target environment information, using a target recommendation model to predict the driver's driving plan information to obtain a prediction result, wherein the driving plan information includes at least: the route and destination of the target vehicle, and the target recommendation model includes: a model obtained by training a neural network model based on driving plan data of the driver driving the vehicle in a historical time period and driving environment information of the historical time period; based on the prediction result, adjusting the navigation information of the navigation system of the target vehicle.

[0008] Furthermore, based on the target identity information and the target environment information, a target recommendation model is used to predict the driver's driving plan information to obtain a prediction result, including: based on the target identity information, obtaining the driver's historical planning data, wherein the historical planning data includes: the driving planning data of the driver driving the vehicle within the historical time period; inputting the historical planning data and the target environment information into the target recommendation model, and outputting the prediction result.

[0009] Furthermore, the driver is identified to obtain target identity information, including: collecting biometric information of the driver to obtain target feature information, wherein the biometric information includes at least one of the following: facial features, voiceprint features, and fingerprint features; comparing the target feature information with biometric information in a feature database to obtain a comparison result, and determining the driver's identity information based on the comparison result to obtain the target identity information, wherein the feature database is used to record the mapping relationship between biometric information and identity information.

[0010] Furthermore, in the case where the biometric information is the facial feature, the biometric information of the driver is collected to obtain target feature information, including: using an image acquisition device to collect a facial image of the driver, and preprocessing the facial image of the driver to obtain a target image, wherein the preprocessing method includes at least one of the following: light compensation, grayscale processing, noise reduction processing, and size adjustment; using a feature extraction model to extract facial features in the target image to obtain the target feature information, wherein the feature extraction model includes: a deep learning model for extracting facial features.

[0011] Furthermore, before the driver is identified and the target identity information is obtained, it includes: using a gravity sensor to detect the weight change of the main driver's seat to obtain a detection result; when the detection result indicates that the weight of the main driver's seat has increased, judging whether the increased weight of the main driver's seat exceeds a preset threshold to obtain a judgment result; when the judgment result indicates that the increased weight of the main driver's seat exceeds the preset threshold, determining that the driver is in place on the main driver's seat of the target vehicle.

[0012] Furthermore, the target recommendation model is obtained in the following manner: obtaining the driving planning data of the driver driving the vehicle in multiple historical time periods and the driving environment information of each historical time period to obtain an initial training sample; performing data cleaning on the initial training sample to obtain a target training sample; using the target training sample to perform model training on the neural network model, and in the process of training the neural network model, adjusting the parameters of the neural network model by cross-validation to obtain the target recommendation model.

[0013] Furthermore, after the driver is identified and the target identity information is obtained, it also includes: using multiple sensors pre-deployed in the vehicle to collect driving planning data of the driver driving the target vehicle to obtain target planning data; and adjusting the model parameters of the target recommendation model based on the target planning data.

[0014] According to another aspect of an embodiment of the present invention, a navigation information adjustment device is also provided, including: an identification unit, for identifying the driver when detecting that the driver is in the main driving seat of the target vehicle, and obtaining target identity information; an acquisition unit, for obtaining the driving environment information of the target vehicle at the current moment, and obtaining target environment information; a prediction unit, for predicting the driver's driving plan information based on the target identity information and the target environment information using a target recommendation model, and obtaining a prediction result, wherein the driving plan information at least includes: the driving route and destination of the target vehicle, and the target recommendation model includes: a model obtained by training a neural network model based on the driving plan data of the driver driving the vehicle in a historical time period and the driving environment information of the historical time period; a first adjustment unit, for adjusting the navigation information of the navigation system of the target vehicle based on the prediction result.

[0015] Furthermore, the prediction unit includes: a first acquisition subunit, used to acquire the driver's historical planning data based on the target identity information, wherein the historical planning data includes: driving planning data of the driver driving the vehicle during the historical time period; a first processing subunit, used to input the historical planning data and the target environment information into the target recommendation model and output the prediction result.

[0016] Furthermore, the identification unit includes: a collection subunit, used to collect biometric information of the driver to obtain target feature information, wherein the biometric information includes at least one of the following: facial features, voiceprint features, and fingerprint features; a comparison unit, used to compare the target feature information with the biometric information in a feature database to obtain a comparison result, and determine the identity information of the driver based on the comparison result to obtain the target identity information, wherein the feature database is used to record the mapping relationship between biometric information and identity information.

[0017] Furthermore, in the case where the biometric information is the facial feature, the acquisition subunit includes: a processing module, used to use an image acquisition device to acquire the driver's facial image, and preprocess the driver's facial image to obtain a target image, wherein the preprocessing method includes at least one of the following: light compensation, grayscale processing, noise reduction processing and size adjustment; an extraction module, used to extract facial features in the target image using a feature extraction model to obtain the target feature information, wherein the feature extraction model includes: a deep learning model for feature extraction of facial features.

[0018] Furthermore, the navigation information adjustment device also includes: a detection unit, which is used to use a gravity sensor to detect the weight change of the main driver's seat and obtain a detection result before identifying the driver and obtaining the target identity information; a judgment unit, which is used to judge whether the increased weight of the main driver's seat exceeds a preset threshold and obtain a judgment result when the detection result indicates that the weight of the main driver's seat has increased; and a determination unit, which is used to determine that the driver is in place in the main driver's seat of the target vehicle when the judgment result indicates that the increased weight of the main driver's seat exceeds the preset threshold.

[0019] Furthermore, the target recommendation model is obtained through the following sub-units: a second acquisition sub-unit, used to acquire the driving planning data of the driver driving the vehicle in multiple historical time periods and the driving environment information of each historical time period to obtain an initial training sample; a data cleaning sub-unit, used to perform data cleaning on the initial training sample to obtain a target training sample; a second processing sub-unit, used to perform model training on the neural network model using the target training sample, and in the process of model training the neural network model, adjust the parameters of the neural network model using a cross-validation method to obtain the target recommendation model.

[0020] Furthermore, the navigation information adjustment device also includes: a collection unit, which is used to collect the driving planning data of the driver driving the target vehicle by using multiple sensors pre-deployed in the vehicle after identifying the driver and obtaining the target identity information, so as to obtain target planning data; a second adjustment unit, which is used to adjust the model parameters of the target recommendation model based on the target planning data.

[0021] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above navigation information adjustment methods by executing the executable instructions.

[0022] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, which stores a computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above navigation information adjustment methods.

[0023] In the present invention, when the driver is detected to be in the main driving seat of the target vehicle, the driver is identified to obtain the target identity information; the driving environment information of the target vehicle at the current moment is obtained to obtain the target environment information; based on the target identity information and the target environment information, the driver's driving plan information is predicted using the target recommendation model to obtain the prediction result, wherein the driving plan information at least includes: the driving route and destination of the target vehicle, and the target recommendation model includes: based on the driving plan data of the driver driving the vehicle in the historical time period and the driving environment information of the historical time period, the model obtained by training the neural network model; based on the prediction result, the navigation information of the navigation system of the target vehicle is adjusted. This solves the technical problem in the related art that after changing the driver, the navigation information of the navigation system needs to be manually adjusted, and the adjustment efficiency is low.

[0024] In the present invention, after the driver takes his position, a neural network model is used to predict navigation planning information according to the driver's identity and the current driving environment, and the navigation settings of the navigation system are adjusted, thereby achieving the purpose of automatically adjusting the navigation planning according to the driver's identity, avoiding the manual adjustment of the navigation information of the navigation system in the related art and the low adjustment efficiency, thereby achieving the technical effect of improving the navigation information adjustment efficiency of the navigation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0026] Figure 1 is a flow chart of an optional navigation information adjustment method according to an embodiment of the present invention;

[0027] Figure 2 is a flowchart of an optional face recognition according to an embodiment of the present invention;

[0028] Figure 3 is an optional model training flow chart according to an embodiment of the present invention;

[0029] Figure 4 is a flow chart of an optional navigation information adjustment according to an embodiment of the present invention;

[0030] Figure 5 is a schematic diagram of an optional navigation information adjustment device according to an embodiment of the present invention;

[0031] Figure 6 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] It should be noted that the user information (including but not limited to user device information, user personal information, navigation planning information, etc.), collected information and data (including but not limited to data used for analysis, stored data, displayed data, navigation data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0035] Embodiment 1

[0036] According to an embodiment of the present invention, a method embodiment of an optional navigation information adjustment method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] Figure 1 is a flow chart of an optional navigation information adjustment method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0038] Step S101, when it is detected that the driver is in the main driving seat of the target vehicle, the driver is identified to obtain the target identity information.

[0039] The above-mentioned target identity information may include the identification information of the driver (for example, the driver's ID). In the present embodiment, it is possible to first detect whether there is a driver in the main driver's seat. For example, the main driver's seat gravity sensor may be used to detect whether there is a driver in the main driver's seat of the target vehicle. When it is detected that the driver is in the main driver's seat of the target vehicle, the driver may be identified. For example, the driver may be identified by using biometric identification. For example, the driver's identity may be identified by using biometrics such as face recognition, fingerprint recognition, and voiceprint. The driver's identity may also be identified by collecting the current driver's behavior habits (for example, the driver's operation of the vehicle). A face recognition system may also be used to comprehensively identify the driver's identity through biometrics such as face recognition, voiceprint recognition, or fingerprint recognition, combined with analysis of driving habits (for example, acceleration, braking, steering, etc.), to obtain the target identity information.

[0040] For example, when the gravity sensor of the main driver's seat senses that the driver is in place, the face recognition system will be triggered to comprehensively identify the driver's identity through biometric features such as facial recognition, voiceprint recognition or fingerprint recognition, combined with analysis of driving habits (such as acceleration, braking, steering, etc.).

[0041] Step S102, obtaining the driving environment information of the target vehicle at the current moment, and obtaining the target environment information.

[0042] The above-mentioned driving environment information may include but is not limited to: time, weather, traffic conditions, etc. In this embodiment, the driving environment information of the environment where the target vehicle is located at the current moment can also be obtained to obtain the target environment information.

[0043] Step S103, based on the target identity information and the target environment information, use the target recommendation model to predict the driver's driving plan information to obtain a prediction result, wherein the driving plan information at least includes: the driving route and destination of the target vehicle, and the target recommendation model includes: based on the driving plan data of the driver driving the vehicle in a historical time period and the driving environment information of the historical time period, a model obtained by training a neural network model.

[0044] In this embodiment, a database can be used to store each driver's personal preferences, historical trips, common destinations, driving habits, driving level and other driving planning data, and then the data can be synchronized to the cloud using cloud services to store each driver's driving planning data in the data for sharing among different vehicles.

[0045] When predicting a driver's driving plan information, the driver's historical planning data (i.e., driving planning data for historical time periods) stored in the database can be obtained from the cloud based on the target identity information, and then the driver's driving planning information is predicted based on the historical planning data and target environment information input into the target recommendation model to obtain a prediction result.

[0046] It should be noted that different drivers may correspond to different target recommendation models, that is, each driver may correspond to an independent target recommendation model, thereby improving the accuracy of the prediction results of the target recommendation model.

[0047] Step S104: adjusting the navigation information of the navigation system of the target vehicle based on the prediction result.

[0048] In this embodiment, based on the prediction results, a navigation change suggestion message can be automatically sent to the in-vehicle navigation APP (i.e., navigation information) to adjust the settings of the navigation system, such as the destination, route preference, voice prompts, etc. The recommended route and destination can also be displayed on the navigation interface, and the driver can be allowed to confirm or manually adjust the recommended navigation settings.

[0049] Through the above steps, in this embodiment, after the driver is in place, the navigation planning information is predicted using the neural network model according to the driver's identity and the current driving environment, and the navigation settings of the navigation system are adjusted, so as to achieve the purpose of automatically adjusting the navigation planning according to the driver's identity, avoiding the situation of manually adjusting the navigation information of the navigation system in the related art, and the low adjustment efficiency, thereby achieving the technical effect of improving the navigation information adjustment efficiency of the navigation system. This further solves the technical problem of manually adjusting the navigation information of the navigation system after changing the driver in the related art, and the low adjustment efficiency.

[0050] Through the navigation information adjustment method provided in this embodiment, when changing to a congested narrow road section or an emergency lane on a highway, the corresponding data information can be immediately extracted according to the current driver to update the navigation without manual modification, which can save time and not affect the passage of other vehicles on the congested road section, especially on the highway, which can improve safety. Automatic adjustment is made according to the difference in driving ability of drivers. For example, if the driver is a novice, it can automatically switch to the main road priority to avoid narrow or complex road sections to improve driving safety. In this embodiment, the target recommendation model can perform continuous learning and training optimization to ensure the reliability of navigation information adjustment. For example, the target recommendation model can recognize the improvement of driving skills of novice drivers after a period of time and optimize the navigation plan.

[0051] Optionally, based on the target identity information and the target environment information, a target recommendation model is used to predict the driver's driving plan information to obtain a prediction result, including: based on the target identity information, obtaining the driver's historical planning data, wherein the historical planning data includes: the driving planning data of the driver driving the vehicle within a historical time period; inputting the historical planning data and the target environment information into the target recommendation model, and outputting the prediction result.

[0052] In this embodiment, the target identity information can be used to query the driver's historical driving data from the cloud database, for example, historical itineraries, common destinations, driving habits, driving levels and other data corresponding to the target identity information in the historical time period, and then the historical planning data and target environment information can be input into the target recommendation model, and the prediction results can be output through the target recommendation model.

[0053] For example, the driver's historical planning data can be queried from the cloud database based on the identified driver ID (corresponding to the target identity information), where the driver's historical planning data may include: the driver's personal preferences, such as commonly used navigation settings, commonly used locations, driving style, etc. Combined with the current driving environment (such as time, weather, traffic conditions, etc.) (corresponding to the target environment, it is fresh) and the driver's historical planning data are input into the reasoning engine (corresponding to the target recommendation model). The reasoning engine makes inferences based on these data to predict the driver's possible destination and preferred path, that is, predict the driver's driving planning information. For example, if the current time is 8:00-9:00 in the morning, it can be inferred that the driver may need to buy coffee, and the prediction suggests navigation to a nearby coffee shop. For example, if the current weather is windy and rainy, the prediction suggests avoiding crosswinds, slippery and muddy roads, etc.

[0054] By combining the driver's historical planning data and real-time environmental information and using deep learning models for intelligent prediction, the technical effect of improving the personalization and intelligence level of the in-vehicle navigation system is achieved.

[0055] Optionally, the driver is identified to obtain target identity information, including: collecting biometric information of the driver to obtain target feature information, wherein the biometric information includes at least one of the following: facial features, voiceprint features, and fingerprint features; comparing the target feature information with the biometric information in a feature database to obtain a comparison result, and determining the driver's identity information based on the comparison result to obtain the target identity information, wherein the feature database is used to record the mapping relationship between the biometric information and the identity information.

[0056] The above-mentioned biometric information may include facial features, voiceprint features, fingerprint features, etc. The above-mentioned feature database is a database that stores the biometric information and corresponding identity information of registered drivers, that is, it is used to record the mapping relationship between biometric information and identity information.

[0057] In this embodiment, collecting the biometric information of these drivers may include:

[0058] Facial recognition: The driver’s facial image can be captured through the in-vehicle image acquisition device, focusing on the driver’s facial contour, texture, eye distance and other key features;

[0059] Voiceprint recognition: When the driver interacts with the in-vehicle system (such as voice commands), the driver's voiceprint characteristics, including pitch, speaking speed, timbre, etc., can be recorded and analyzed;

[0060] Fingerprint recognition: Install fingerprint recognition sensors on locations frequently touched by the driver, such as the steering wheel or door handles, to collect the driver's fingerprint information.

[0061] It should be noted that, in this embodiment, deep learning technology can also be used to extract key feature vectors from the driver's facial image, voice, etc. to obtain target feature information.

[0062] After the target feature information is collected, the target feature information can be compared with the information in the feature database, and similarity matching can be performed based on the target feature information and the biometric information in the feature database to identify the driver's identity. For example, the similarity matching results can be used to find the features closest to the driver's target feature information, thereby determining the driver's identity information. Specifically, if the match exceeds a set threshold, it can be determined that the driver's identity has been verified. Otherwise, additional identity authentication operations can be requested for the driver, such as entering a password or collecting biometric information again.

[0063] In this embodiment, the multimodal biometric recognition technology is used to achieve the technical effect of efficiently and accurately identifying the driver's identity.

[0064] Optionally, in the case where the biometric information is facial features, the biometric information of the driver is collected to obtain target feature information, including: using an image acquisition device to capture a facial image of the driver, and preprocessing the facial image of the driver to obtain a target image, wherein the preprocessing method includes at least one of the following: light compensation, grayscale processing, noise reduction processing, and size adjustment; using a feature extraction model to extract facial features in the target image to obtain target feature information, wherein the feature extraction model includes: a deep learning model for extracting facial features.

[0065] The above-mentioned image acquisition device may include but is not limited to: a camera. In this embodiment, the image acquisition device can be used to capture the driver's facial image, and the driver's facial image can be pre-processed such as light compensation, grayscale processing, noise reduction processing, and size adjustment to obtain a target image. In this embodiment, a feature extraction model can also be used to extract facial features in the target image to obtain target feature information.

[0066] For example, driver identification can be mainly divided into steps such as image acquisition equipment (e.g., camera) and face recognition software preparation, real-time monitoring, face positioning and image preprocessing, feature extraction and identity matching.

[0067] Figure 2 is a flowchart of an optional face recognition according to an embodiment of the present invention. Figure 2 The extraction process of feature extraction of the driver's face image is described as follows:

[0068] (1) The system starts, the camera starts, and the face recognition software is ready. The image processing algorithm detects whether there is a face in the picture. If a face is detected, it goes to the next step; otherwise, it continues monitoring.

[0069] (2) Face location and preprocessing: accurately locate key facial areas (such as eyes, nose, and mouth). Preprocess the image, including light compensation, grayscale, noise reduction, size normalization, etc., to optimize the recognition effect.

[0070] (3) Feature extraction: Use a deep learning model (such as a deep neural network) to extract facial feature vectors from the preprocessed image.

[0071] (4) Identity matching: compare the extracted feature vector with the facial feature database of registered users stored on the vehicle, calculate the feature similarity, and determine whether it matches a known user.

[0072] In this embodiment, the feature extraction of the driver's facial image is performed through a deep learning model, thereby achieving the technical effect of improving the accuracy of facial feature extraction and thus improving the accuracy of driver identity recognition.

[0073] Optionally, before identifying the driver and obtaining the target identity information, the method includes: using a gravity sensor to detect the weight change of the main driver's seat to obtain a detection result; when the detection result indicates that the weight of the main driver's seat has increased, judging whether the increased weight of the main driver's seat exceeds a preset threshold to obtain a judgment result; when the judgment result indicates that the increased weight of the main driver's seat exceeds a preset threshold, determining that the driver is in place in the main driver's seat of the target vehicle.

[0074] The gravity sensor can be installed under the main driver's seat or in the seat structure, and can detect the weight distributed on the seat. Before the vehicle is started, the weight baseline of the seat when no one is sitting can be recorded, which is usually a lower value, indicating the weight of the seat itself and its covering. The gravity sensor can continuously monitor the weight change on the seat. For example, once a significant increase in weight is detected and exceeds a preset threshold (corresponding to a preset threshold), it can be determined that the driver is in place.

[0075] In order to avoid false detection, the weight can be monitored for stability over a period of time (such as a few seconds). If the weight remains stable after the weight is increased, it can be determined that the driver is fully in place. If the gravity sensor determines that the driver is in place, a signal can be sent to the vehicle's control unit or a specific system (such as a face recognition system). In the intelligent navigation system, the face recognition system or other biometric detection system can be triggered to confirm the driver's identity.

[0076] Through the above process, the gravity sensor of the main driver's seat can accurately sense whether the driver is in place, thereby triggering the corresponding intelligent system, such as the face recognition system, to achieve automated operation and improve the intelligence level and safety of the vehicle.

[0077] Optionally, the target recommendation model is obtained in the following manner: obtaining driving planning data of the driver driving the vehicle in multiple historical time periods and driving environment information in each historical time period to obtain an initial training sample; performing data cleaning on the initial training sample to obtain a target training sample; using the target training sample to train a neural network model, and in the process of training the neural network model, adjusting the parameters of the neural network model by cross-validation to obtain a target recommendation model.

[0078] In this embodiment, the driving planning data of the driver driving the vehicle in multiple different historical time periods and the driving environment information of each historical time period can also be obtained to obtain an initial training sample. In order to provide the accuracy of model training, the initial training sample can be cleaned. For example, for the initial training sample, outliers and noise can be removed, and normalization and standardization can be performed to ensure the consistency and comparability of data from different sources to obtain a target training sample. The target training sample is used to train the neural network model, and in the process of training the neural network model, the parameters of the neural network model are adjusted by cross-validation. After the neural network model training converges, the target recommendation model is obtained, thereby achieving the technical effect of improving the accuracy of the prediction results of the target recommendation model.

[0079] Optionally, after identifying the driver and obtaining the target identity information, the method further includes: utilizing a variety of sensors pre-deployed in the vehicle to collect the driver's driving planning data of the target vehicle to obtain target planning data; and adjusting the model parameters of the target recommendation model based on the target planning data.

[0080] The above-mentioned various sensors may include but are not limited to: vehicle-mounted sensors, such as an accelerator pedal, a brake pedal, a steering wheel angle sensor, a positioning system, etc.

[0081] After identifying the driver and obtaining the target identity information, the various sensors pre-deployed in the vehicle can be used to continuously collect the driver's driving plan data of the target vehicle from the current moment, obtain the target planning data, and upload the target planning data to the cloud database to update the driver's driving plan data in the database. In order to improve the accuracy of the recommendation results of the target recommendation model, the target recommendation model can also be retrained based on the target planning data, and the parameters of the target recommendation model can be adjusted to make the target recommendation model adapt to the driver's behavioral habits and improve the accuracy of the driving route prediction.

[0082] Figure 3 is an optional model training flow chart according to an embodiment of the present invention, such as Figure 3 As shown, it includes: data collection, data preprocessing (e.g., cleaning data), training construction, model validation (e.g., cross-validation) and optimization, real-time driving habit reasoning (real-time receiving data analysis and reasoning), and continuous learning and updating.

[0083] (1) Data collection: collecting driving behavior data. Through face recognition, heart rate monitoring, etc., the driver's physiological indicators and emotional state and other biological characteristics are collected. The collected data can be used for large-scale model analysis to infer the driver's driving level and behavioral habits.

[0084] (2) Clean the data to remove outliers and noise. Normalize and standardize the data to ensure the consistency and comparability of data from different sources. Feature engineering to extract meaningful features, such as driving speed patterns, acceleration and deceleration frequencies, etc.

[0085] (3) Use deep learning algorithms (e.g., convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory (LSTM), or Transformer, etc.) to build a recommendation model. Use historical driving data (driving planning data in historical time periods) to train the model and learn the driver's driving habits. A large number of samples can be used for iterative training to continuously optimize the model parameters.

[0086] (4) Receive and process new data from sensors in real time. Apply the trained model (corresponding to the target recommendation model) to perform real-time analysis and reasoning on current driving behavior. Identify specific driving habits, such as sudden acceleration, frequent lane changes, and preferred routes.

[0087] (5) The target recommendation model is retrained regularly to incorporate new driving data and adapt to changes in driver habits.

[0088] Figure 4 is a flow chart of an optional navigation information adjustment according to an embodiment of the present invention, such as Figure 4 As shown, the face recognition system can be used to identify the identity information of the driver. For example, after identifying driver A and driver B, the navigation settings of the navigation system can be automatically adjusted for driver A and driver B through the navigation intelligent adaptation system. The behavioral habit information of driver A and driver B can be uploaded to the driver large model learning and reasoning system to regularly train the recommendation model.

[0089] In this embodiment, the combination of identity recognition (for example, face recognition) and large model technology can significantly improve the humanization, automation, and practicality of smart cockpit ecological applications.

[0090] For example, at present, the driving camera in the smart cockpit system is mainly used in the DMS (driver monitoring system) field, and the face recognition capability is also mainly used in smart unlocking and other aspects. In this embodiment, face recognition is applied to a variety of ecological applications of the smart cockpit; multi-source data collection, such as built-in or external sensors in the vehicle (for example, positioning systems, accelerometers, gyroscopes, cameras, etc.) to collect data generated during driving, as well as integrating external data sources such as weather, road conditions, and traffic events.

[0091] It should be noted that in this embodiment, independent driving models (i.e., target recommendation models) can be constructed for different users to avoid the situation where personalized navigation settings are often bound to the account system and the settings need to be manually modified and adjusted according to the actual situation of the individual under the current account. The driving model can continuously learn, train and optimize according to the driver's driving habits and skills improvement, and continuously and automatically adjust the navigation settings. A labeling mechanism can be added to the driving models of different drivers, and driving habits in different time periods can be labeled. The driving data with labels can be used to train classification or regression models to predict driving behavior. For example, if user A has the habit of drinking coffee in the morning, the time segmentation data of the user's driving model can be labeled, and the coffee shop on the way can be automatically pushed when traveling during this period, achieving the technical effect of improving the accuracy of navigation planning.

[0092] Embodiment 2

[0093] Embodiment 2 of the present invention provides an optional navigation information adjustment device, and each implementation unit in the navigation information adjustment device corresponds to each implementation step in Embodiment 1.

[0094] Figure 5 is a schematic diagram of an optional navigation information adjustment device according to an embodiment of the present invention, such as Figure 5 As shown, it includes: an identification unit 51, an acquisition unit 52, a prediction unit 53 and a first adjustment unit 54.

[0095] The identification unit 51 is used to identify the driver and obtain the target identity information when the driver is detected to be in the main driving seat of the target vehicle;

[0096] The acquisition unit 52 is used to acquire the driving environment information of the target vehicle at the current moment, and obtain the target environment information;

[0097] The prediction unit 53 is used to predict the driver's driving plan information based on the target identity information and the target environment information using the target recommendation model to obtain a prediction result, wherein the driving plan information at least includes: the driving route and destination of the target vehicle, and the target recommendation model includes: a model obtained by training a neural network model based on the driving plan data of the driver driving the vehicle in a historical time period and the driving environment information in the historical time period;

[0098] The first adjustment unit 54 is used to adjust the navigation information of the navigation system of the target vehicle based on the prediction result.

[0099] In the navigation information adjustment device provided in the second embodiment of the present invention, when the driver is detected to be in the main driving seat of the target vehicle, the identification unit 51 can identify the driver and obtain the target identity information. The acquisition unit 52 can obtain the driving environment information of the target vehicle at the current moment and obtain the target environment information. The prediction unit 53 uses the target recommendation model to predict the driver's driving plan information based on the target identity information and the target environment information to obtain the prediction result, wherein the driving plan information at least includes: the driving route and destination of the target vehicle, and the target recommendation model includes: a model obtained by training a neural network model based on the driving plan data of the driver driving the vehicle in the historical time period and the driving environment information in the historical time period. The first adjustment unit 54 adjusts the navigation information of the navigation system of the target vehicle based on the prediction result. This solves the technical problem in the related art that the navigation information of the navigation system needs to be manually adjusted after the driver is replaced, and the adjustment efficiency is low.

[0100] In this embodiment, after the driver takes his position, a neural network model is used to predict navigation planning information based on the driver's identity and the current driving environment, and the navigation settings of the navigation system are adjusted, thereby achieving the purpose of automatically adjusting the navigation planning according to the driver's identity, avoiding the manual adjustment of the navigation information of the navigation system and the low adjustment efficiency in the related technology, thereby achieving the technical effect of improving the navigation information adjustment efficiency of the navigation system.

[0101] Optionally, in the navigation information adjustment device provided in Embodiment 2 of the present invention, the prediction unit includes: a first acquisition subunit, used to acquire the driver's historical planning data based on the target identity information, wherein the historical planning data includes: the driving planning data of the driver driving the vehicle within a historical time period; a first processing subunit, used to input the historical planning data and target environment information into a target recommendation model, and output a prediction result.

[0102] Optionally, in the navigation information adjustment device provided in Embodiment 2 of the present invention, the identification unit includes: a collection subunit, used to collect the driver's biometric information to obtain target feature information, wherein the biometric information includes at least one of the following: facial features, voiceprint features, fingerprint features; a comparison unit, used to compare the target feature information with the biometric information in the feature database to obtain a comparison result, and determine the driver's identity information based on the comparison result to obtain target identity information, wherein the feature database is used to record the mapping relationship between the biometric information and the identity information.

[0103] Optionally, in the navigation information adjustment device provided in Embodiment 2 of the present invention, when the biometric information is facial features, the acquisition subunit includes: a processing module, used to acquire a facial image of the driver using an image acquisition device, and preprocess the facial image of the driver to obtain a target image, wherein the preprocessing method includes at least one of the following: light compensation, grayscale processing, noise reduction processing, and size adjustment; an extraction module, used to extract facial features in the target image using a feature extraction model to obtain target feature information, wherein the feature extraction model includes: a deep learning model for extracting facial features.

[0104] Optionally, in the navigation information adjustment device provided in Embodiment 2 of the present invention, the navigation information adjustment device further includes: a detection unit, used to use a gravity sensor to detect the weight change of the main driver's seat and obtain a detection result before identifying the driver and obtaining the target identity information; a judgment unit, used to judge whether the increased weight of the main driver's seat exceeds a preset threshold and obtain a judgment result when the detection result indicates that the weight of the main driver's seat has increased; and a determination unit, used to determine that the driver is in place on the main driver's seat of the target vehicle when the judgment result indicates that the increased weight of the main driver's seat exceeds a preset threshold.

[0105] Optionally, in the navigation information adjustment device provided in the second embodiment of the present invention, the target recommendation model is obtained through the following sub-units: a second acquisition sub-unit, used to obtain the driving planning data of the driver driving the vehicle in multiple historical time periods and the driving environment information of each historical time period to obtain an initial training sample; a data cleaning sub-unit, used to perform data cleaning on the initial training sample to obtain a target training sample; a second processing sub-unit, used to perform model training on the neural network model using the target training sample, and in the process of model training the neural network model, adjust the parameters of the neural network model using a cross-validation method to obtain a target recommendation model.

[0106] Optionally, in the navigation information adjustment device provided in the second embodiment of the present invention, the navigation information adjustment device also includes: a collection unit, which is used to collect the driving planning data of the driver driving the target vehicle by using multiple sensors pre-deployed in the vehicle after identifying the driver and obtaining the target identity information, so as to obtain the target planning data; and a second adjustment unit, which is used to adjust the model parameters of the target recommendation model based on the target planning data.

[0107] The above-mentioned navigation information adjustment device may also include a processor and a memory. The above-mentioned identification unit 51, acquisition unit 52, prediction unit 53 and first adjustment unit 54 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0108] The processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be set, and after the driver is in place, according to the driver's identity and the current driving environment, the navigation planning information is predicted by the neural network model by adjusting the kernel parameters, and the navigation settings of the navigation system are adjusted, so as to achieve the purpose of automatically adjusting the navigation planning according to the driver's identity, avoid the situation of manually adjusting the navigation information of the navigation system in the related technology, and the low adjustment efficiency, thereby achieving the technical effect of improving the navigation information adjustment efficiency of the navigation system.

[0109] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0110] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above navigation information adjustment methods by executing the executable instructions.

[0111] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, which stores a computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above navigation information adjustment methods.

[0112] Figure 6 is a schematic diagram of an electronic device according to an embodiment of the present invention, such as Figure 6 As shown, an embodiment of the present invention provides an electronic device 60, which includes a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, any one of the above navigation information adjustment methods is implemented.

[0113] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0114] In the above embodiments of the present invention, 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.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, 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 interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0116] 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0117] In addition, each functional unit in each embodiment of the present invention 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.

[0118] 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 storage medium. Based on this understanding, the technical solution of the present invention, in essence, 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, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0119] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A navigation information adjustment method, characterized in that: include: When the driver of the target vehicle is detected to be in the main driving seat, the driver is identified to obtain the target identity information; Acquire the driving environment information of the target vehicle at the current moment to obtain the target environment information; Based on the target identity information and the target environment information, a target recommendation model is used to predict the driver's driving plan information to obtain a prediction result, wherein the driving plan information at least includes: a driving route and a destination of the target vehicle, and the target recommendation model includes: a model obtained by training a neural network model based on the driving plan data of the driver driving the vehicle in a historical time period and the driving environment information of the historical time period; Based on the prediction result, navigation information of the navigation system of the target vehicle is adjusted.

2. The navigation information adjustment method according to claim 1, characterized in that: Based on the target identity information and the target environment information, the target recommendation model is used to predict the driver's driving plan information to obtain a prediction result, including: Based on the target identity information, acquiring the driver's historical planning data, wherein the historical planning data includes: the driving planning data of the driver driving the vehicle within the historical time period; The historical planning data and the target environment information are input into the target recommendation model, and the prediction result is output.

3. The navigation information adjustment method according to claim 1, characterized in that: Perform identity recognition on the driver to obtain target identity information, including: Collecting the driver's biometric information to obtain target feature information, wherein the biometric information includes at least one of the following: facial features, voiceprint features, and fingerprint features; The target feature information is compared with the biometric feature information in a feature database to obtain a comparison result, and the identity information of the driver is determined based on the comparison result to obtain the target identity information, wherein the feature database is used to record the mapping relationship between the biometric feature information and the identity information.

4. The navigation information adjustment method according to claim 3, characterized in that: In the case where the biometric feature information is the facial feature, collecting the biometric feature information of the driver to obtain target feature information includes: The driver's facial image is captured by an image acquisition device, and the driver's facial image is preprocessed to obtain a target image, wherein the preprocessing method includes at least one of the following: Light compensation, grayscale processing, noise reduction and size adjustment; The facial features in the target image are extracted using a feature extraction model to obtain the target feature information, wherein the feature extraction model includes: a deep learning model for extracting facial features.

5. The navigation information adjustment method according to claim 1, characterized in that: Before the driver is identified and the target identity information is obtained, the following steps are included: Using a gravity sensor to detect the weight change of the main driver's seat and obtain a detection result; In the case where the detection result indicates that the weight of the main driver's seat has increased, determining whether the increased weight of the main driver's seat exceeds a preset threshold, and obtaining a determination result; When the judgment result indicates that the added weight of the main driver's seat exceeds the preset threshold, it is determined that the driver is in place on the main driver's seat of the target vehicle.

6. The navigation information adjustment method according to claim 1, characterized in that: The target recommendation model is obtained in the following way: Acquire driving planning data of the driver driving the vehicle in multiple historical time periods and driving environment information of each historical time period to obtain an initial training sample; Performing data cleaning on the initial training samples to obtain target training samples; The target training samples are used to perform model training on the neural network model, and during the model training process of the neural network model, the parameters of the neural network model are adjusted by cross-validation to obtain the target recommendation model.

7. The navigation information adjustment method according to claim 1, characterized in that: After the driver is identified and the target identity information is obtained, the method further includes: Using a variety of sensors pre-deployed in the vehicle, the driving planning data of the driver driving the target vehicle is collected to obtain target planning data; The model parameters of the target recommendation model are adjusted based on the target planning data.

8. A navigation information adjustment device, characterized in that: include: An identification unit, configured to identify the driver when a driver is detected to be in the main driving seat of the target vehicle, and obtain target identity information; An acquisition unit, used to acquire the driving environment information of the target vehicle at the current moment, and obtain the target environment information; A prediction unit, configured to predict the driver's driving plan information using a target recommendation model based on the target identity information and the target environment information to obtain a prediction result, wherein the driving plan information at least includes: a driving route and a destination of the target vehicle, and the target recommendation model includes: a model obtained by training a neural network model based on the driving plan data of the driver driving the vehicle in a historical time period and the driving environment information of the historical time period; The first adjustment unit is used to adjust the navigation information of the navigation system of the target vehicle based on the prediction result.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the navigation information adjustment method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the navigation information adjustment method described in any one of claims 1 to 7.

Images