Navigation method and related apparatus

Abstract

The application discloses a navigation method and a related device, which are applied to the field of intelligent vehicles. In the application, when a boarding event of a vehicle is detected, first navigation habit information is determined based on boarding scene information and an identification result of a boarding user, and navigation corresponding to the first navigation habit information is initiated. The implementation mode of the application eliminates the cumbersome operation of manual input of a navigation address by a user and actively provides an individualized recommendation service, so that the driving and riding experience of the user is greatly improved.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicle technology, and in particular to navigation methods and related devices. Background Technology

[0002] With the development of automotive intelligence, the functions of intelligent cockpits are becoming increasingly diverse. For example, intelligent cockpits can provide drivers and passengers with various applications, offering a wide range of services such as navigation, audio-visual services, and multimedia services. However, regarding navigation, currently it only supports users manually entering their destination address, which is not conducive to improving the user's driving experience. Summary of the Invention

[0003] This application provides a navigation method and related device that can proactively provide personalized navigation recommendation services to different users, eliminating the tedious operation of manually entering navigation addresses and allowing users to enjoy navigation services immediately, greatly improving the user's driving experience.

[0004] Firstly, this application provides a navigation method, which can be executed by a device with computing power or a component of such a device (such as a chip or module). The following description uses a vehicle control device as the executing entity of this method as an example; however, in actual implementation, the executing entity can be any other name. This navigation method is applied to a vehicle, and the vehicle control device executing the method is located inside the vehicle or has a communication connection with the vehicle. The method includes: upon detecting a vehicle boarding event, determining first navigation habit information based on boarding scene information and the identification result of the boarding user. The first navigation habit information is determined based on at least one piece of behavior data related to using the vehicle, and includes N addresses, where N is an integer greater than or equal to 1. Initiating navigation to the M addresses, where M is a positive integer less than or equal to N. Exemplarily, a vehicle boarding event typically refers to the process by which the vehicle control device senses and identifies the user's entry into the vehicle cabin. For example, the vehicle control device can determine that a boarding event has been detected when it detects one or more of the following operations: unlocking, opening a door, closing a door, sitting down, adjusting a seat, fastening a seatbelt, powering on, or shifting gears. For example, the boarding scenario information includes boarding time information and / or boarding location information. For example, the identification result of the boarding user can be obtained by facial recognition and / or voiceprint recognition, and the identification result of the boarding user can be represented by a user identifier (ID).

[0005] In this application, a proactive recommendation service for personalized navigation is provided based on boarding scenario information and boarding users. This eliminates the need for users to manually input navigation addresses, thereby improving the user's driving and riding experience.

[0006] In another possible implementation of the first aspect, the first navigation habit information includes one or more of the following:

[0007] The information includes the identification of the first driver, the identification of the passengers, the navigation start time, the navigation end time, the latitude and longitude information of the navigation starting point, the latitude and longitude information of the navigation route points, or the latitude and longitude information of the navigation destination.

[0008] Optionally, the first navigation habit information may also include one or more of the following: the identifier of the first navigation habit information, the tolerance deviation information of navigation time, the point of interest (POI) / area of ​​interest (AOI) information corresponding to the starting point of navigation, the POI / AOI information corresponding to the waypoint of navigation, the POI / AOI information corresponding to the destination point of navigation, the number of times the navigation corresponding to the first navigation habit information has been rejected, the time when the first navigation habit information was most recently rejected / cancelled, the time when the first navigation habit information was most recently used, the generation time of the first navigation habit information, the update time of the first navigation habit information, or the clustering results.

[0009] In this implementation, by defining the content included in the navigation habit information, the corresponding navigation habit information can be quickly matched based on the boarding scenario information and the boarding user, which helps to improve the applicability of the solution.

[0010] In another possible implementation of the first aspect, the boarding user includes a first pilot and at least one crew member.

[0011] In this implementation, the navigation habit information is determined jointly by the first driver and the passengers, resulting in more accurate navigation habit information.

[0012] In another possible implementation of the first aspect, the boarding user includes at least a first pilot, and the N addresses include a first address as the destination.

[0013] This implementation defines the navigation requirements for boarding users, including at least the first driver, which helps improve the user's driving experience.

[0014] In another possible implementation of the first aspect, the N addresses further include a second address serving as a waypoint, the second address being the intermediate boarding address of the first crew member.

[0015] This implementation defines the navigation needs of different boarding users, such as temporary stops for boarding (or temporary stops for picking up passengers), which meets the actual navigation needs of users and thus helps to improve the user's driving experience.

[0016] In another possible implementation of the first aspect, the boarding user includes a first pilot and a second crew member, and the N addresses include a first address as a destination and a third address as a transit point, the third address being the disembarkation address of the second crew member.

[0017] This implementation defines the navigation needs of different boarding users, such as those who temporarily stop to drop off passengers (or drop off passengers), which meets the actual navigation needs of users and thus helps to improve the user's driving experience.

[0018] In another possible implementation of the first aspect, determining the first navigation habit information based on boarding scenario information and the identification result of the boarding user includes:

[0019] At least one navigation habit information is determined based on the boarding scenario information;

[0020] The first navigation habit information is determined from the at least one navigation habit information based on the identification result of the boarding user.

[0021] In this implementation, matching the boarding scene information first and then identifying the boarding user can improve navigation recommendation efficiency, because user identification often takes longer than obtaining boarding scene information.

[0022] In another possible implementation of the first aspect, determining the first navigation habit information based on boarding scenario information and the identification result of the boarding user includes:

[0023] At least one navigation habit information is determined based on the identification results of the boarding user;

[0024] The first navigation habit information is determined from the at least one navigation habit information based on the boarding scenario information.

[0025] In this implementation, identifying the boarding user first and then matching the boarding scenario information improves processing performance, such as increasing processing efficiency. This is because if the first driver is a first-time boarder, and no navigation habit information for that driver is found during the user identification phase, the current proactive navigation process can be terminated directly, avoiding further matching of subsequent boarding scenario information. This reduces implementation complexity and improves processing efficiency.

[0026] In another possible implementation of the first aspect, the boarding scenario information includes boarding time information and / or boarding location information.

[0027] In this implementation approach, when the boarding scenario information includes boarding time or boarding location information, it helps reduce implementation complexity. When the boarding scenario information includes both boarding time and boarding location information, it helps improve the accuracy of recommendations.

[0028] In yet another possible implementation of the first aspect, prior to initiating navigation to the M addresses, the method further includes:

[0029] Receive confirmation from the user.

[0030] In this implementation, user confirmation is required before initiating navigation to M addresses, and recommended calibration can be performed, which helps improve the accuracy of navigation.

[0031] In yet another possible implementation of the first aspect, initiating navigation to the M addresses includes:

[0032] If the number of times navigation corresponding to the first navigation habit information is rejected is less than or equal to the first preset number, navigation to the M addresses is initiated.

[0033] In this implementation, when the navigation corresponding to the first navigation habit information is rejected a certain number of times, it indicates that the navigation corresponding to the first navigation habit information is the navigation frequently used by the user. Therefore, when the conditions are met, the navigation corresponding to the first navigation habit information can be proactively initiated, which is beneficial to improving user satisfaction.

[0034] In yet another possible implementation of the first aspect, the method further includes:

[0035] If the number of navigation rejections is greater than 0, reduce the number of navigation rejections.

[0036] In this implementation, if the navigation corresponding to the first navigation habit information is not rejected when the navigation is initiated, and the number of times the navigation corresponding to the first navigation habit information has been rejected is greater than 0, the number of times the navigation corresponding to the first navigation habit information has been rejected can be reduced so that the navigation corresponding to the first navigation habit information can be initiated again in the future.

[0037] In yet another possible implementation of the first aspect, the method further includes:

[0038] If a user denies the navigation request, the number of times the navigation is rejected is increased.

[0039] In this implementation, if a user denies the navigation, the navigation corresponding to the first navigation habit information can be prevented from being initiated, and the number of navigation rejections can be increased to facilitate subsequent decisions on whether to initiate the navigation corresponding to the first navigation habit information.

[0040] In yet another possible implementation of the first aspect, the method further includes:

[0041] If a user initiates navigation habit information that is the same as the first navigation habit information, provided that the boarding scenario information and the boarding user are met, the number of times the navigation is rejected is reduced.

[0042] In this implementation, when a user actively or manually initiates navigation corresponding to the first navigation habit information when the boarding scenario information and boarding user conditions are met, the number of times navigation is rejected can be reduced, so as to facilitate subsequent decisions on whether to initiate navigation corresponding to the first navigation habit information.

[0043] In yet another possible implementation of the first aspect, the method further includes:

[0044] If the number of times navigation is rejected is greater than or equal to a second preset number, and the first navigation habit information has not been used for more than a first time period, the first navigation habit information is deleted.

[0045] In this implementation, when the navigation corresponding to the first navigation habit information is frequently rejected and has not been used for a long time, the first navigation habit information can be deleted to save storage costs.

[0046] In yet another possible implementation of the first aspect, the method further includes:

[0047] Acquire behavioral data of at least one driver using the vehicle, wherein the at least one driver includes a first driver, which is any one of the at least one drivers, and the behavioral data of the first driver using the vehicle includes navigation data and / or parking data;

[0048] Navigation habit information of the at least one driver is generated based on the behavioral data of the at least one driver using the vehicle.

[0049] In this implementation, driver navigation habits are summarized by processing / learning driver vehicle usage data.

[0050] In another possible implementation of the first aspect, any one of the navigation data includes one or more of the following:

[0051] The identification of the first driver, the identification of the passenger, the navigation start time, the navigation end time, the latitude and longitude information of the navigation starting point, the latitude and longitude information of the navigation route points, or the latitude and longitude information of the navigation destination point.

[0052] Optionally, any navigation data may also include one or more of the following information: the identifier of the navigation data, the POI / AOI information corresponding to the starting point of the navigation, the POI / AOI information corresponding to the waypoint of the navigation, the POI / AOI information corresponding to the destination point of the navigation, or the clustering results.

[0053] In this implementation, by defining the content included in the navigation data, corresponding navigation habit information can be summarized based on the navigation data, which helps to improve the applicability of the solution.

[0054] In another possible implementation of the first aspect, any one of the parking data includes one or more of the following:

[0055] The identification of the first driver, the identification of the occupants, the start time of parking, the end time of parking, the latitude and longitude information of the parking location, the parking type, the identification of the seated occupants, the identification of the seated occupants, or the identification of the seated occupants.

[0056] Optionally, any parking data entry may also include one or more of the following information: the identifier of the parking data entry, the POI / AOI information corresponding to the parking location, the door status, or the clustering results.

[0057] In this implementation, by defining the content included in the parking data, corresponding navigation habit information can be summarized based on the parking data, which helps to improve the applicability of the solution.

[0058] In another possible implementation of the first aspect, the parking type is regular parking or temporary parking;

[0059] The method further includes:

[0060] If the first condition is met, the parking type is determined to be regular parking;

[0061] If the second condition is met, the parking type is determined to be temporary parking;

[0062] The first condition includes one or more of the following: detecting P gear, detecting power failure, detecting vehicle lock, or detecting no one inside the vehicle;

[0063] The second condition includes one or more of the following: detecting deceleration to less than the first preset speed and then acceleration to greater than the second preset speed, not detecting power failure, or detecting the addition or reduction of occupants.

[0064] This implementation defines a method for distinguishing between regular parking and temporary parking, which helps improve the accuracy of the judgment.

[0065] In another possible implementation of the first aspect, generating navigation habit information for the at least one driver based on the at least one driver's behavioral data using the vehicle includes:

[0066] If the third condition is met, at least one navigation habit information of the first driver is generated based on the first driver's behavior data using the vehicle, and the at least one navigation habit information includes the first navigation habit information.

[0067] This implementation method proposes that data processing can be performed only when certain conditions (i.e., the third condition) are met, which helps to improve the accuracy of the data processing results.

[0068] In yet another possible implementation of the first aspect, the third condition includes one or more of the following:

[0069] The first driver uses a number of behavioral data points related to the vehicle that are greater than or equal to a preset threshold.

[0070] The time for collecting the first driver's behavior data using the vehicle is less than or equal to a preset time.

[0071] In this implementation, the third condition can be defined, for example, as the collection of enough data and the data being sufficiently recent, which can further improve the accuracy of the data processing results.

[0072] In another possible implementation of the first aspect, the behavioral data of the first driver using the vehicle includes parking data; generating at least one navigation habit information of the first driver based on the behavioral data of the first driver using the vehicle includes:

[0073] Based on the parking data of the first driver, at least two parking habit information of the first driver are determined;

[0074] At least one navigation habit information for the first driver is generated based on the at least two parking habit information.

[0075] In this implementation method, when processing parking data, parking habit information is first summarized based on the parking data, and then navigation habit information is summarized based on the parking habit information, which is highly operable.

[0076] In another possible implementation of the first aspect, any one of the parking habit information items includes one or more of the following:

[0077] The identification of the first driver, the identification of the passenger, the type of the regular parking location, or the latitude and longitude information of the regular parking location.

[0078] Optionally, any parking habit information may also include one or more of the following: parking habit information identifier, latitude and longitude tolerance information, POI information corresponding to the frequently used parking location, AOI information corresponding to the frequently used parking location, the most recent parking time information at the frequently used parking location (e.g., parking start time, parking end time, etc.), the update cycle of the frequently used parking location, the parking start time of the frequently used parking location, the parking end time of the frequently used parking location (i.e., the start time from the frequently used parking location), the parking duration of the frequently used parking location, the parking time period of the frequently used parking location, working hours, working hours, or clustering results.

[0079] In this implementation, by defining the content included in the parking habit information, the corresponding navigation habit information can be summarized based on the parking habit information, which helps to improve the applicability of the solution.

[0080] In yet another possible implementation of the first aspect, the parking habit information includes the type of the frequently used parking location;

[0081] The method further includes:

[0082] Upon receiving confirmation from the user regarding the predicted location type, the predicted location type is determined as the type of the frequently used parking location. The predicted location type is obtained based on clustering the parking data of the first driver.

[0083] In this implementation, the accuracy of the determined predicted location type can be improved by interacting with the user.

[0084] In yet another possible implementation of the first aspect, the method further includes:

[0085] An editing interface is displayed on the screen, and the editing interface includes the type of the frequently stopped location;

[0086] Obtain the user's editing actions;

[0087] The type of the frequently used parking location is updated based on the edit operation.

[0088] In this implementation, providing an editing interface for users to manually modify / adjust the type of permanent parking location facilitates proactive management by users.

[0089] Secondly, this application provides a vehicle control device, which includes an acquisition unit, a processing unit, and an output unit. The acquisition unit is used to acquire data, such as performing the aforementioned acquisition and reception operations. The processing unit is used to process data and perform operations, such as implementing one or more of the aforementioned data processing, execution, control, determination, generation, and decision-making (e.g., judgment). The output unit is used to output information externally, such as one or more of the following: output signals, presented information, and a display interface.

[0090] The vehicle control device is used to implement the method described in the first aspect or any possible implementation of the first aspect.

[0091] Thirdly, this application provides a computing device including a processor and a communication interface. The communication interface is used for outputting and / or outputting data (including instructions), and / or for receiving and / or sending data. When the processor executes program instructions in memory, it implements the method described in the first aspect or any possible embodiment of the first aspect.

[0092] Fourthly, this application provides a computing device, including a processor and a memory. The memory stores a computer program, and the processor invokes the computer program to implement the method described in the first aspect or any possible embodiment of the first aspect.

[0093] Optionally, the computing device described in the third or fourth aspect above includes a chip. This chip can be a single chip or a chip system composed of multiple chips.

[0094] Alternatively, the computing device may be a computing platform.

[0095] Fifthly, this application provides an intelligent cockpit, which is applied to a vehicle, or other human-accommodating transportation or sensing device. The intelligent cockpit includes the vehicle control device described in the second aspect, or the computing device described in the third aspect, or the computing device described in the fourth aspect.

[0096] Sixthly, this application provides a vehicle that includes the vehicle control device described in the second aspect, or the computing device described in the third aspect, or the computing device described in the fourth aspect, or the smart cockpit described in the fifth aspect.

[0097] In a seventh aspect, this application provides a computer program product, including program instructions or executable computer program code, which, when executed by at least one processor, implements the method described in the first aspect or any possible implementation thereof.

[0098] Eighthly, this application provides a computer-readable storage medium storing program instructions that, when executed by a processor, implement the method described in the first aspect or any possible implementation thereof.

[0099] The beneficial effects of the solutions in aspects two through eight of this application can be found in the beneficial effects described in aspect one. Attached Figure Description

[0100] Figure 1 This is a schematic diagram of a vehicle's architecture;

[0101] Figure 2 This is a schematic diagram of a cockpit;

[0102] Figure 3 This is a diagram illustrating vehicle usage scenarios;

[0103] Figure 4 This is a flowchart illustrating a navigation method provided in an embodiment of this application;

[0104] Figure 5 This is a flowchart illustrating the identification results of boarding users provided in an embodiment of this application;

[0105] Figure 6 This is a flowchart illustrating the process of determining first navigation habit information provided in an embodiment of this application;

[0106] Figure 7 This is a schematic diagram illustrating a scenario for obtaining navigation data / parking data provided in an embodiment of this application;

[0107] Figure 8 This is a schematic diagram illustrating a scenario for clustering parking data / navigation data provided in an embodiment of this application;

[0108] Figure 9 This is a schematic diagram of the process for generating navigation habit information provided in an embodiment of this application;

[0109] Figure 10 This is a schematic diagram of a scenario for generating navigation habit information based on parking data, provided in an embodiment of this application.

[0110] Figure 11 This is a schematic diagram of the navigation initiation process provided in the embodiments of this application;

[0111] Figure 12 This is a schematic diagram of a scenario for the navigation method provided in an embodiment of this application;

[0112] Figure 13 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application;

[0113] Figure 14 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application. Detailed Implementation

[0114] This application can be applied to scenarios requiring human-computer interaction, such as smart vehicles, smart homes, smart showrooms, and smart security systems. For example, this application can be applied to electronic devices such as vehicles, televisions, tablets, and conference equipment.

[0115] The following uses a vehicle as an example to illustrate the equipment and scenarios used in the embodiments of this application. For ease of understanding, the following will first summarize... Figure 1 , Figure 2 and Figure 3 This paper introduces an architecture for vehicles to which this application can be applied.

[0116] Please see Figure 1 The vehicle 100 may include a sensing system 11, a computing device 12, and peripheral devices 13. Furthermore, the vehicle 100 can provide seating space for users, for example, it may include a seat or have a large accommodating space to accommodate people. Further, the vehicle 100 also includes other subsystems, such as a mobility system 14, a control system 15, or a power supply (not shown). Each subsystem may include one or more components, and the subsystems or components can be interconnected via wired or wireless means. Figure 1 The functional block diagram shown is for illustrative purposes only. In actual implementation, the vehicle may include more or fewer subsystems, and the types and number of components included in the subsystems may also be designed differently.

[0117] The following is a description of each component of vehicle 100:

[0118] The sensing system 11 may include several sensing devices, or sensors, for sensing information about the environment surrounding or inside the vehicle. Exemplarily, the sensing system 11 may include one or more of the following sensing devices: a camera 111, a microphone 112, a radar 113, a lidar 114, a temperature sensor 115, a humidity sensor 116, a light sensor 117, a positioning system 118, an inertial measurement unit 119, a pressure sensor (not shown), a touch sensor (not shown), etc. The sensing system 11 may also include sensors for sensing the internal environment of the vehicle (e.g., an in-vehicle air quality monitor, a fuel gauge, an oil temperature gauge, etc.). Sensor data from one or more of these sensors can be used to detect the corresponding object and its corresponding characteristics (such as position, shape, orientation, speed, etc.). Some sensing devices are described below as examples.

[0119] The camera 111 is used to collect image data, including images and videos. The camera 111 may include a monocular camera, a binocular camera, a time-of-flight (TOF) camera, a camera from a driver monitoring system (DMS), or a camera from a cockpit monitoring system (CMS), etc. Please see [link to relevant documentation]. Figure 2 The vehicle includes a camera 111 positioned towards the cabin, capable of capturing images within the cabin. The number and location of the cameras 111 can be customized according to actual needs, such as near the A-pillar on the driver's side, near the A-pillar on the passenger side, on the headrest (or backrest) of the front seats, on the front of the cabin roof, or integrated into the central control screen.

[0120] Microphone 112 can collect sound data from the surroundings of the vehicle, such as voice or other audio input from the user. Figure 2 The microphone 112 can be installed in the vehicle's steering wheel or integrated into an in-vehicle display device. For a microphone 112 installed in the vehicle's cabin, it can collect sound data within the cabin. In some solutions, the sound data collected by the microphone 112 can be used for voiceprint recognition to identify the user. For example, some voice control systems require a specific voiceprint from the user to function.

[0121] Radar 113 can use signals such as electromagnetic waves or sound waves to sense objects in the vehicle's surrounding environment and obtain relevant information about the objects. This relevant information may include one or more of the following: distance, angle, speed, direction of travel, reflectivity, color, texture, size, and orientation. LiDAR 114 can use light to sense objects in the vehicle's environment and obtain relevant information about them. Exemplarily, LiDAR 114 may include one or more laser sources, a laser scanner, and one or more detectors, as well as other system components (such as optical elements).

[0122] Other sensors can be found in the relevant prior art, and will not be described in detail here.

[0123] The computing device 12 is a device with computing capabilities. The computing device 12 may include hardware modules with computing capabilities and / or software modules with computing capabilities. Examples are given below based on both hardware and software implementations.

[0124] As an example of hardware implementation, computing device 12 may include at least one processor, which is a module with processing capabilities. In one implementation, the processor may be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor, microcontroller unit (MCU), graphics processing unit (GPU), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits, which may be fixed or reconfigurable. For example, the processor may be a hardware circuit implemented as an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In reconfigurable hardware circuits, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the corresponding function. Furthermore, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. In some implementations, the computing device 12 includes at least one processor integrated as a system-on-chip (SOC), which is commonly referred to as an SOC by those skilled in the art. The SOC may include at least one processor, and when the SOC includes multiple processors, the types of processors can be different, such as including a CPU and an NPU.

[0125] For example, the computing device 12 includes, but is not limited to, a domain controller (DC), a mobile data center (MDC), an electronic control unit (ECU), and a vehicle integrated / integration unit (VIU). The DC may include a cockpit domain controller (CDC).

[0126] As an example of software implementation, computing device 12 may include software functional units. As another example of a software functional unit, computing device 12 may include one or more of the following: an executable computer program, computer code, or computer instructions, where "executable" means capable of running on a processor or computing instance. As yet another example of a software functional unit, computing device 12 may include computing instances, including virtual machines, containers, etc. A virtual machine is a computer system simulated by software, possessing complete hardware system functionality and running in an isolated environment. A container is an isolated environment obtained by packaging applications and their dependencies.

[0127] In some embodiments, some or all of the processors included in the computing device 12 may be located away from the vehicle 100 and be able to transmit information with the vehicle 100.

[0128] Peripheral device 13 is used to provide additional services to the user. In some solutions, peripheral device 13 is used for user interaction. For example, peripheral device 13 may include one or more of the following: communication device 131, screen 132, seat 133, air conditioner 134, speaker 135, fragrance 137, ambient light 138, or car refrigerator 136. Some components are described below by example:

[0129] The communication device 131 can communicate with one or more devices directly or via a communication network, including wired and wireless communication. In some embodiments, the communication device 131 has adjustable functions; for example, the Bluetooth module can support status settings such as turning it on, off, or searching for nearby devices.

[0130] In some solutions, the communication device 131, which supports wireless communication, can receive and / or transmit wireless signals. After being transmitted into the object space, the wireless signal travels through multiple transmission paths to reach the receiving device. The communication device, acting as the receiving device, can sense objects in the object space based on the wave characteristics of the received wireless signal. For example, using the basic Fresnel zone model, the communication device 131 can sense the movement of objects in space based on the waveform of the received wireless signal, thus enabling it to detect users or identify relevant user information, such as movement patterns, height, and respiratory rate. The wireless technologies used by the communication device 131 that supports wireless communication include one or more of the following: SparkLink (or NearLink), wireless local area network (WLAN), Bluetooth, Zigbee, radio frequency identification (RFID), ultra-wideband (UWB) technology, communication technologies based on long term evolution (LTE), 5th generation mobile networks (or 5th generation wireless systems, 5th-Generation, abbreviated as 5G or 5G technology), global system for mobile communications (GSM), general packet radio service (GPRS), or universal mobile telecommunications system (UMTS), etc.

[0131] Screen 132 can display information to the user. Screen 132 includes one or more of the following: physical screen (such as a central control screen, passenger screen, rear screen, etc.), projection system, smart entity, or button panel. Projection system includes, for example, light field screen, head-up display (HUD), or other projection system. Figure 2A central control screen can be installed on the vehicle's center console. This screen is used to display the vehicle's driving route, showcase vehicle functions, or play audio and video content. Besides the central control screen, other types of screens are also installed in the vehicle, allowing passengers in the front passenger seat and rear seats to interact with the vehicle. This application does not strictly limit the number or location of the screens 132 in the applicable scenario. Taking the application of this application in a vehicle as an example, the screens 132 can be located in front of the front passenger seat, on the headrest (or backrest) of the front seats, on the armrests of the seats, on the doors, or on the roof of the cabin, etc.

[0132] Seat 133 is used for the occupants of vehicle 100. In some designs, seat 133 may have a variety of intelligent components, such as backrest angle adjustment components, ventilation components, seat heating components, seat audio components, seat massage components, etc.

[0133] The speaker 135 can output audio to a user inside the vehicle. For example, the speaker 135 can perform voice announcements and / or sound effect playback, such as indicating the current status of a controlled object and providing feedback on the execution of a vehicle control operation. Alternatively, the speaker can play sound effect information, such as expressing information based on the frequency of a "beep" sound. In some embodiments, the speaker 135 can also be a sound wave emitting device, for example, it can serve as the transmitter of an ultrasonic detection system (such as ultrasonic radar). Other peripheral devices 13 can be found in the descriptions in related technologies and will not be described in detail here.

[0134] In some implementations, such as Figure 1 As shown, the vehicle also includes various subsystems. The propulsion system 14 includes components that provide power for the movement of the vehicle 100. Exemplarily, the propulsion system 14 may include an engine 141, an energy source 142, a transmission 143, and wheels 144 (or tires). The control system 15 is a system for controlling the vehicle and its components. Exemplarily, the control system 15 may include a steering system 151, an accelerator 152, or a braking unit 153, etc.

[0135] In some embodiments, the vehicle also includes a memory that may contain instructions (e.g., program logic) that can be executed by a processor to perform various functions of the vehicle 100, including those described above. The memory may also contain additional instructions, including instructions to send data to, receive data from, interact with, and / or control one or more of the mobility system 14, sensing system 11, control system 15, and peripheral devices 13. In addition to instructions, the memory may store data such as road maps, route information, vehicle position, direction, speed, and other such vehicle data, as well as other information. This information may be used by the vehicle 100 and / or computing device 12 during operation of the vehicle in autonomous, semi-autonomous, and / or manual modes.

[0136] With the development of automotive intelligence, the functions of intelligent cockpits are becoming increasingly diverse. For example, intelligent cockpits can provide drivers and passengers with various applications, offering a wide range of services such as navigation, audio-visual services, and multimedia services. Taking navigation as an example, as users demand more intelligent vehicle features, the need for personalized navigation services is becoming more prominent. Currently, navigation only supports preset addresses such as "home" and "work," which can be inconvenient when family members share the vehicle, and the limited range of location options also hinders the improvement of the user's driving experience.

[0137] For example, such as Figure 3 As shown, users can currently manually enter their destination address in the "Home" or "Office" location type field on the map to access navigation services. However, this manual input method is not convenient enough, and the variety of location types is limited, making it impossible to provide personalized navigation services based on different users.

[0138] Based on this, this application provides a navigation method and related apparatus. In this application, by learning from navigation data and parking data of different users, personalized navigation locations (location type prediction) can be proactively generated. Location types include a series of categories such as "home," "company," "school," "shopping mall," "park," "hospital," "gas station," and "charging station." Furthermore, personalized navigation proactive recommendation services are provided based on the time of boarding and the passengers (or boarding users, cabin users, or cabin occupants). This eliminates the need for manual user input and allows for the generation of more location types through intelligent learning. Therefore, during the navigation service phase, personalized recommendation services can be provided based on the results of full cabin recognition, which helps improve the user's driving experience.

[0139] It should be noted that the latitude and longitude information described in the navigation data / parking data / parking habit information / navigation habit information in the following embodiments can be replaced with location information or address information, etc. The location information / address information includes latitude and longitude information, altitude information, etc., and optionally, it may also include location name / location identifier, etc., without limitation.

[0140] The method of this application embodiment is described below. It should be noted that the method is illustrated here using a vehicle scenario as an example. When this method is applied to other devices or systems, it can have similar effects. In this case, the method need not be called a navigation method; it could be called a control method or other methods. It should be understood that the names of the methods, devices, and information can be designed according to the implementation situation, and this application does not strictly limit the names of things.

[0141] Please see Figure 4 , Figure 4 This is a schematic flowchart illustrating a navigation method provided in an embodiment of this application. Optionally, this method is applied to a vehicle, such as... Figure 1 The vehicle 100 shown, for example, is made of Figure 1 The computing device 12 in the vehicle 100 shown executes the method. For ease of description, the following description uses a vehicle control device as the executing entity. Optionally, the vehicle control device may be replaced by the computing device 12, or the computing device 12 may include the vehicle control device.

[0142] like Figure 4 The navigation method shown may include one or more steps from S401 to S402. It should be understood that, for ease of description, the description uses the sequence of S401 to S402, but this embodiment does not limit the order of execution, the execution time, or the number of executions of the above one or more steps. Specifically:

[0143] S401. When the vehicle control device detects a vehicle boarding event, it determines the first navigation habit information based on the boarding scene information and the identification result of the boarding user.

[0144] For example, a vehicle entry event typically refers to the process by which a user's entry into the vehicle cabin is sensed and recognized by the vehicle control device. For instance, the vehicle control device may determine that an entry event has been detected when it detects one or more of the following operations: unlocking, opening the door, closing the door, sitting down, adjusting the seat, fastening the seatbelt, powering on, or shifting gears. Optionally, this application may also define the execution order of the above operations. For example, when it detects that a user sequentially performs the following operations on the vehicle: unlocking → opening the door → closing the door → sitting down → adjusting the seat → fastening the seatbelt → powering on → shifting gears, a vehicle entry event can be determined. The operations and execution order listed above are merely examples. This application does not limit the operations included in the entry event or the execution order of different operations. For example, adjusting the seat is an optional operation, or fastening the seatbelt before adjusting the seat is also possible.

[0145] Optionally, the boarding scenario information described in this application can also be described as boarding environment information. For example, the boarding scenario information includes boarding time information and / or boarding location information. Boarding time information may include, for example, one or more of the following: unlocking time, door opening time, door closing time, seat taking time, seat adjustment time, seatbelt fastening time, power-on time, or gear shifting time. Boarding location information may include, for example, one or more of the following: the name of the boarding location, the latitude and longitude information of the boarding location, etc. Optionally, the boarding location information can also be described as boarding address information, boarding location information, parking location information, parking address information, parking location information, etc., without limitation.

[0146] For example, the boarding user includes at least the driver (hereinafter referred to as the first driver). Optionally, the boarding user may also include at least one occupant. For example, in this application, an occupant can be understood as a person who boards the vehicle other than the driver, such as a person in the front passenger seat or the rear seat. Optionally, the boarding user can also be described as a seated person, and the disembarking user can also be described as a seated person.

[0147] For example, the identification result of the boarding user involved in this application can be represented by a user identifier (ID). In some cases, the identification result of the boarding user can be obtained through facial recognition and / or voiceprint recognition. For example, the user's facial information and voiceprint information can be pre-recorded as personal markers, and a corresponding user ID can be set, such as a user nickname. Subsequently, when facial information and / or voiceprint information are detected, the detected facial information can be matched with facial information pre-stored in the facial feature database, and the detected voiceprint information can be matched with voiceprint information pre-stored in the voiceprint feature database. The matched user ID is then used as the identification result of the boarding user.

[0148] For example, for the user in the driver's seat, since the lighting conditions are better there, facial recognition can be used by default. Conversely, for users in other positions, such as the front passenger seat and rear seats, where lighting conditions may be poorer, both facial recognition and voiceprint recognition can be used simultaneously to improve user identification accuracy. The identification methods described above for users in different positions are merely examples, and this application does not limit the identification methods for users in all positions.

[0149] To make the solution described in this application clearer, the fusion processing of face recognition and voiceprint recognition systems is briefly introduced below. For example, as shown... Figure 5 As shown, it mainly includes ① data input / collection stage, ② feature extraction stage, ③ feature fusion stage, ④ identity matching and decision-making stage, and ⑤ data storage. Among them:

[0150] ① During the data input / acquisition stage: For facial image input, dynamic or static facial images can be captured by a camera; for voice signal input, voice signals can be acquired by a microphone array.

[0151] ② In the feature extraction stage: For facial feature extraction, the facial image can be preprocessed first, such as alignment, normalization, and noise reduction. Then, for the preprocessed facial image, facial key points, such as the coordinates of the eyes, nose, and mouth, are extracted, and a lightweight convolutional network is used to extract facial feature vectors. Finally, the facial feature vectors are output to the feature fusion layer. For voiceprint feature extraction, the speech signal can be preprocessed first, such as frame segmentation, windowing, and noise reduction. Then, for the preprocessed speech signal, Mel-frequency cepstral coefficients (MFCC) features are extracted, and a neural network structure is used to extract voiceprint feature vectors. Finally, the voiceprint feature vectors are output to the feature fusion layer.

[0152] ③ In the feature fusion stage, multimodal feature fusion can be used, such as concatenating or weighting the facial feature vector with the voiceprint feature vector.

[0153] ④ During the identity matching and decision-making stage, when performing face comparison, cosine similarity calculation can be performed between the fused features and the features in the face feature database. When performing voiceprint comparison, probabilistic linear discriminant analysis (PLDA) model is used to calculate voiceprint similarity between the fused features and the features in the voiceprint feature database. When the face and voiceprint similarity of a user (e.g., user 1) in both the face and voiceprint feature databases exceed the threshold, the identity matching is considered successful.

[0154] ⑤ Data storage stage: If no user is matched in the face feature database, the face feature vector obtained this time can be encrypted and stored in the face feature database along with the encrypted face feature vector and ID. The voiceprint feature vector obtained this time can also be encrypted and stored in the voiceprint feature database along with the encrypted voiceprint feature vector and ID.

[0155] For the vehicle control device, upon detecting a vehicle boarding event, it can determine first navigation habit information based on boarding scene information and the identification result of the boarding user. This first navigation habit information is determined based on at least one piece of vehicle usage behavior data. The first navigation habit information includes N addresses, where N is an integer greater than or equal to 1. In this embodiment, the first navigation habit information can be any one piece of navigation habit information from the navigation habit information set / navigation habit information summary table.

[0156] For example, the first navigation habit information includes one or more of the following: the identification of the driver (e.g., the first driver), the identification of the occupants, the navigation start time, the navigation end time, the latitude and longitude information of the navigation start point, the latitude and longitude information of the navigation waypoints, or the latitude and longitude information of the navigation destination.

[0157] Optionally, in addition to the information listed above, the first navigation habit information may also include one or more of the following: the identifier of the first navigation habit information, the tolerance deviation information of navigation time, the POI / AOI information corresponding to the starting point of navigation, the POI / AOI information corresponding to the waypoint of navigation, the POI / AOI information corresponding to the destination point of navigation, the number of times the navigation corresponding to the first navigation habit information has been rejected, the time when the first navigation habit information was most recently rejected / cancelled, the time when the first navigation habit information was most recently used, the generation time of the first navigation habit information, the update time of the first navigation habit information, or the clustering results.

[0158] In some cases, the clustering result contained in any navigation habit information can be understood as the value (or clustering value) of the cluster category to which that navigation habit information belongs. For example, the cluster category can be "going to work" or "getting off work", where the clustering value corresponding to "going to work" is 1, and the clustering value corresponding to "getting off work" is 2, etc.

[0159] In some cases, the above-mentioned navigation time tolerance deviation information can be understood as the tolerance range of the navigation start time. For example, if the navigation time tolerance deviation information is 30 minutes, it can be determined that the half hour before and after the navigation start time is the navigation initiation time corresponding to the first navigation habit information.

[0160] In some cases, the aforementioned POI information refers to location identifiers within a geographic area. These identifiers indicate the government departments, businesses of various industries (gas stations, department stores, supermarkets, restaurants, hotels, convenience stores, hospitals, etc.), tourist attractions (parks, public restrooms, etc.), historical sites, and transportation facilities (various stations, parking lots, speed cameras, speed limit signs, etc.) represented by the location. Each POI includes a name, type, and location information. Location information may include latitude and longitude, altitude, etc., and the type may include catering, accommodation, etc.

[0161] In some cases, the aforementioned AOI information refers to regional geographic entities on a map, such as large states, countries, capital cities, non-capital cities or towns, etc.

[0162] In some cases, the number of times the navigation corresponding to the first navigation habit information is rejected can be understood as the number of times the navigation corresponding to the first navigation habit information is actively initiated and rejected / cancelled / interrupted / exited by the user.

[0163] In some cases, the identifier of the first navigation habit information is used to mark a first navigation habit information. Optionally, the descriptions of "identifier" and "index" in this application can be used interchangeably.

[0164] In some cases, the time when the first navigation habit information was last used can be understood as the time when it was used to initiate navigation corresponding to the first navigation habit information, that is, the time when navigation to M addresses was initiated, where M is a positive integer less than or equal to N, and N addresses are the addresses included in the first navigation habit information. The generation time of the first navigation habit information can be understood as the time when the first navigation habit information was first / initially generated.

[0165] In one usage scenario, the users boarding the cabin include at least a first driver. The first navigation habit information, determined based on the cabin boarding scenario information and the first driver's identification result, includes N addresses, including a first address serving as the destination. Here, the destination can be understood as the first driver's final destination. Optionally, in this usage scenario, the users boarding the cabin may also include at least one passenger, where the first driver and the at least one passenger may share the same destination. For example, in this usage scenario, N can be equal to 1. For instance, assuming on a rest day, the users boarding the cabin in community 1 include a father, a mother, and a child, where the first driver is the father, and the passengers are the mother and the child. The destination of these three users is park 1. As another example, in this usage scenario, N can also be 2, where the two addresses include the address of the departure point (i.e., the address of community 1) and the address of the destination point (i.e., the address of park 1).

[0166] In another use case, the aforementioned N addresses can also include a second address serving as a waypoint, where the second address is the boarding address of the first passenger. For example, in this use case, N can be greater than 1. For instance, taking N=2, suppose the boarding passengers in community 1 include a father, mother, and one child. On their way to park 1, they need to pick up their grandparents in community 2 to go camping together in park 1. Then, the first passengers are the grandparents, and the two addresses can include the address of park 1 and the address of community 2, which serves as a waypoint. As another example, in this use case, N can also be 3, where the three addresses include the address of the departure point (i.e., the address of community 1), the address of the waypoint (i.e., the address of community 2), and the address of the destination point (i.e., the address of park 1).

[0167] In another use case, the boarding users include a first driver and a second passenger. The N addresses can include a first address as the destination and a third address as a transit point. The third address is the second passenger's departure address. For example, suppose on a certain workday, the boarding users in community 1 include a father, a mother, and a child. The first driver is the father, and the passengers are the mother and the child. The father's destination is company 1, the mother's destination is company 2, and the child's destination is school 1. If the father and mother need to take the child to school first, then the father takes the mother to work, and finally the father goes to work alone, then the N addresses can include the address of company 1, the address of company 2, and the address of school 1. Optionally, the N addresses can also include the address of community 1. In this use case, the addresses of company 2 and school 1 are the third addresses as transit points, and the address of company 1 is the first address as the destination.

[0168] In another use case, the scenarios described above can also be combined. For example, N addresses may simultaneously include one or more of the departure address, destination address, intermediate boarding address, and departure address. For instance, suppose on a certain rest day, the boarding users in community 1 include a father and a mother. The father needs to pick up the child from community 2 first, then drop the mother and child off at park 1 before going to work overtime at company 1. In this case, the N addresses could simultaneously include the address of community 1, the address of community 2, the address of park 1, and the address of company 1.

[0169] In one possible implementation (i), the above-mentioned determination of the first navigation habit information based on the boarding scene information and the identification result of the boarding user can be understood as follows: first, at least one navigation habit information is determined based on the boarding scene information, and then the first navigation habit information is determined from the at least one navigation habit information according to the identification result of the boarding user. This implementation method of first matching the boarding scene information and then matching the identification result of the boarding user can improve the efficiency of navigation recommendation, because the time spent on user identification is usually longer than the time spent obtaining the boarding scene information.

[0170] For example, such as Figure 6As shown in (a), when a vehicle boarding event is detected, it first determines whether navigation habit information already exists. If so, it determines at least one navigation habit information from the existing navigation habit information based on the boarding scenario information (or loads at least one navigation habit information that meets the conditions based on the current boarding time information and / or boarding location information). It waits for the boarding user's identification result and then determines the navigation habit information that matches the boarding user's identification result from the determined at least one navigation habit information (hereinafter referred to as the first navigation habit information). Generally, if the boarding user is only the first driver, the first navigation habit information of the first driver is directly matched. If the boarding user includes both the first driver and passengers, the first navigation habit information needs to be matched based on both the first driver and passengers. Further, navigation corresponding to the first navigation habit information can be initiated. Optionally, when passengers are present, there may be a pick-up / drop-off scenario, so multiple navigation segments may need to be initiated, such as picking up / dropping off passengers first and then arriving at the destination / endpoint.

[0171] To further understand the above implementation (I), a specific example is given below. Assume the navigation habit information set (or navigation habit information summary table) includes 5 navigation habit information entries, including 2 entries for user 1 and 3 entries for driver 2. For example, user 1's 2 entries are: 1) navigation habit from residential area 1 to company 1 between 6:00 AM and 9:00 AM on weekdays; and 2) navigation habit from company 1 to residential area 1 between 6:00 PM and 9:00 PM on weekdays. Driver 2's 3 entries are: 3) navigation habit from residential area 1 to residential area 2 between 9:00 AM and 10:00 AM on rest days; 4) navigation habit from residential area 2 to park 1 between 1:00 PM and 2:00 PM on rest days; and 5) navigation habit from park 1 to residential area 1 between 5:00 PM and 6:00 PM on rest days. If this is implementation (I), then:

[0172] When the vehicle control device detects a vehicle boarding event, it can determine at least one navigation habit information as navigation habit information 3 based on the current boarding scene information, such as the boarding time being 9:30 AM on a rest day and the boarding location being community 1. Then, based on the identification result of the boarding user as user 2, it determines the first navigation habit information as navigation habit information 3.

[0173] In one possible implementation (ii), the above-mentioned determination of the first navigation habit information based on the boarding scenario information and the identification result of the boarding user can be understood as follows: first, determine at least one navigation habit information based on the identification result of the boarding user, and then determine the first navigation habit information from the at least one navigation habit information according to the boarding scenario information. This implementation method of first matching the identification result of the boarding user and then matching the boarding scenario information is beneficial to improving processing performance, such as improving processing efficiency. This is because if the first driver is a driver boarding for the first time, then if no navigation habit information for the first driver is matched during the boarding user identification stage, the process of actively initiating navigation can be directly terminated, avoiding the need to continue executing the matching operation of subsequent boarding scenario information. This can reduce implementation complexity and improve processing efficiency.

[0174] For example, such as Figure 6 As shown in (b), when a vehicle boarding event is detected, it first determines whether navigation habit information already exists. If so, it first determines at least one navigation habit information from the existing navigation habit information based on the identification result of the boarding user (or loads at least one navigation habit information that meets the conditions based on the current identification result of the boarding user). Generally, if the boarding user is only the first driver, it directly matches at least one navigation habit information of the first driver. If the boarding user includes both the first driver and passengers, it needs to match at least one navigation habit information based on both the first driver and passengers. Then, based on the boarding scenario information, it determines the navigation habit information that matches the boarding scenario information (hereinafter referred to as the first navigation habit information) from the determined at least one navigation habit information. Further, it can initiate navigation corresponding to the first navigation habit information. Optionally, when there are passengers, there may be a pick-up and drop-off scenario, so it may be necessary to initiate multiple navigation segments, such as picking up and dropping off passengers first, and then arriving at the destination / endpoint.

[0175] To further understand the above implementation (II), a specific example is given below. Assume the navigation habit information set (or navigation habit information summary table) contains 5 navigation habit information entries, including 2 entries for user 1 and 3 entries for driver 2. For example, user 1's 2 entries are: 1) on weekdays from 6:00 AM to 9:00 AM, navigation habit 1 from residential area 1 via company 2 to company 1; and 2) on weekdays from company 1 to residential area 1 from 6:00 PM to 9:00 PM. Driver 2's 3 entries are: 3) on weekends from 9:00 AM to 10:00 AM, navigation habit 3 from residential area 1 to residential area 2; 4) on weekends from 1:00 PM to 2:00 PM, navigation habit 4 from residential area 2 to park 1; and 5) on weekends from 5:00 PM to 6:00 PM, navigation habit 5 from park 1 to residential area 1. If this is implementation (II), then:

[0176] When the vehicle control device detects a boarding event, it can identify at least one navigation habit information as Navigation Habit Information 3, Navigation Habit Information 4, and Navigation Habit Information 5 based on the identification result of the boarding user as User 2. Then, based on the current boarding scenario information, such as the boarding time information as 9:30 am on a rest day and the boarding location information as Community 1, it determines the first navigation habit information as Navigation Habit Information 3.

[0177] The aforementioned at least one navigation habit information / first navigation habit information is determined based on at least one piece of vehicle usage behavior data. For example, vehicle usage behavior data includes navigation data and / or parking data. That is, the vehicle control device can determine navigation habit information based on navigation data and / or parking data.

[0178] The aforementioned navigation data can be obtained, for example, from map software, and the aforementioned parking data can be obtained, for example, from the vehicle's driving records. In this application, the vehicle control device can acquire vehicle usage behavior data of at least one driver, and then generate navigation habit information for that at least one driver based on that vehicle usage behavior data. The vehicle usage behavior data of one of the drivers is used to determine that driver's navigation habit information. For ease of description, the following description primarily uses the first driver among the at least one drivers as an example, where the first driver is any one of the at least one drivers, and the first driver's vehicle usage behavior data includes navigation data and / or parking data.

[0179] For example, any navigation data entry may include one or more of the following information: driver (e.g., first driver) identifier, passenger identifier, navigation start time, navigation end time, latitude and longitude information of the navigation start point, latitude and longitude information of the navigation waypoints, or latitude and longitude information of the navigation destination. Optionally, any navigation data entry may also include one or more of the following information: the identifier of the navigation data entry, the point of interest (POI) / area of ​​interest (AOI) information corresponding to the navigation start point, the POI / AOI information corresponding to the navigation waypoints, the POI / AOI information corresponding to the navigation destination, or clustering results. Optionally, clustering results may be represented by a value or identifier, where one clustering result value / identifier corresponds to one clustering result. In some cases, during the data acquisition / recording phase, the clustering results included in the navigation data are the initial clustering values ​​of the cluster category to which the navigation data entry belongs, such as 0. In some cases, after clustering the navigation data, the clustering values ​​of the cluster category to which the navigation data entry belongs can be updated.

[0180] For ease of understanding, such as Figure 7As shown in Figure (a), this is a schematic diagram of a scenario for obtaining navigation data. Each navigation start and end can be triggered via a callback event through the navigation service, revealing the start and end times of the navigation. The location service can also provide latitude and longitude information and Points of Interest (POI) information. For example, the latitude and longitude information includes the starting point, the route points, and the destination point. POI information includes the POI corresponding to the starting point, the route points, and the destination point. Each navigation data entry needs to be associated with a person (e.g., the driver, passengers). For instance, the perception service can determine seat availability, such as which seats are occupied and which are empty, as well as who entered / exited the seats and the door status (open or closed). Optionally, each navigation data entry may also include an identifier and clustering results.

[0181] For example, any parking data entry may include one or more of the following information: driver (e.g., first driver) identifier, passenger identifier, parking start time, parking end time, latitude and longitude information of the parking location, parking type, identifier of seated passenger, identifier of departing passenger, or identifier of seated passenger. Optionally, any parking data entry may also include one or more of the following information: the identifier of the parking data entry, POI / AOI information corresponding to the parking location, door status, or clustering results. In some cases, during the data collection / recording phase, the clustering results included in the parking data are the initial clustering values ​​of the cluster category to which the parking location belongs, such as 0. In some cases, after clustering the parking data, the clustering values ​​of the cluster category to which the parking data entry belongs can be updated.

[0182] The above parking types include regular parking and temporary parking. Generally speaking, regular parking can be understood as when the car / cabin is unoccupied, the engine is off, and the car is locked. Temporary parking, on the other hand, is when the vehicle is not turned off or the engine is not off, but only when someone gets in or out of the vehicle, and the vehicle will continue to be driven for a short period of time. This is common for picking up or dropping off people, stopping to buy goods, or stopping to retrieve items.

[0183] For example, under certain conditions (hereinafter referred to as the first condition for ease of description), the parking type can be determined to be normal parking (normal_stop). For example, the first condition includes one or more of the following: detecting P gear, detecting power failure, detecting vehicle lock, or detecting no one in the vehicle.

[0184] For example, under certain conditions (hereinafter referred to as the second condition for ease of description), the parking type can be determined to be temporary parking (temporary_stop). For instance, the second condition may include one or more of the following: detecting deceleration to less than a first preset speed followed by acceleration to greater than a second preset speed, no power-off detected, or detection of occupant addition or removal. Optionally, when the parking type is temporary parking, it can be further divided into types such as temporary pick-up (tmp_get_on) and temporary drop-off (tmp_get_off), without limitation. Temporary pick-up typically includes the vehicle stopping, detection of door opening, occupant sitting down, and door closing, while temporary drop-off typically includes the vehicle stopping, detection of door opening, occupant leaving the seat, and door closing. Optionally, temporary pick-up can also be described as temporary pick-up, and temporary drop-off can also be described as temporary drop-off.

[0185] For ease of understanding, such as Figure 7 As shown in Figure (b), this is a schematic diagram of a scenario for acquiring parking data. When the vehicle is detected to be in Park (P), powered off, locked, and unoccupied, the parking type can be determined as regular parking, and parking data can be recorded, such as the first driver's identifier, passenger identifiers, parking start time, parking end time, latitude and longitude of the parking location, parking type, identifiers of seated passengers, identifiers of departing passengers, and identifiers of currently seated passengers. When the vehicle speed is detected to decrease and then increase, the vehicle is not powered off, and the number of passengers added or removed, the parking type can be determined as temporary parking, and parking data can be recorded. In recording parking data, in addition to acquiring the vehicle's own operational data, location services and perception services can also be invoked to obtain parking data.

[0186] Optionally, the following methods can be used to determine the start of a regular parking maneuver: 1) P gear; 2) Vehicle power off; 3) Vehicle locked; 4) No one in the cabin. The following methods can be used to determine the end of a regular parking maneuver: 1) D gear; 2) Vehicle power on; 3) Vehicle speed increases; 4) Someone is in the cabin; 5) There is an incomplete parking record at the same location, i.e., at the same location, there is a parking start time but no parking end time.

[0187] Optionally, the following methods can be used to determine the start of a temporary stop: 1) the vehicle moves from movement to a stop (speed decreases to 0 or very low); 2) a door is opened / closed; 3) there is an increase or decrease in the number of passengers in the cabin; 4) the vehicle is not powered off. The following methods can be used to determine the end of a temporary stop: 1) the vehicle speed increases; 2) there is an incomplete parking record at the same location, i.e., at the same location, there is a parking start time but no parking end time.

[0188] For a vehicle control device, it can generate navigation habit information for at least one driver based on the behavioral data of at least one driver using the vehicle. The following explanation uses the example of a vehicle control device generating at least one navigation habit information for a first driver based on the behavioral data of a first driver using the vehicle as an illustration.

[0189] For example, the vehicle control device can generate at least one navigation habit information of the first driver based on the first driver's vehicle usage behavior data, provided that certain conditions are met (hereinafter referred to as the third condition for ease of description). The third condition could be, for example, that the amount of the first driver's vehicle usage behavior data is greater than or equal to a preset threshold. That is, when the amount of collected first driver vehicle usage behavior data reaches a certain level, at least one navigation habit information of the first driver is generated based on the collected data. Alternatively, the third condition could be that the collection time of the first driver's vehicle usage behavior data is less than or equal to a preset time. That is, when the first driver's vehicle usage behavior data is data collected from the first driver's most recent vehicle use, at least one navigation habit information of the first driver is generated based on the collected data. Optionally, the third condition mentioned above can also be combined. For example, when the collected data is new enough and the data volume is large enough, at least one navigation habit information of the first driver can be generated based on the collected first driver's vehicle usage behavior data. For example, the data collection time span is greater than or equal to 10 working days and the data volume is greater than or equal to 20 records, and it is updated every 7 days thereafter. In addition, only the latest 100 records of the basic data (i.e., vehicle usage behavior data) are retained for clustering.

[0190] In this implementation, clustering algorithms or other machine learning algorithms or large model algorithms can be used to analyze the places a person (e.g., the first driver) frequently visits and the time periods during which this trip is needed, i.e., navigation habit information. Generally speaking, multiple vehicle behavior data are needed to summarize one or a few navigation habit information, meaning that there is a many-to-one relationship between vehicle behavior data and navigation habit information.

[0191] The following example illustrates how clustering algorithms can be used to process the first driver's vehicle usage behavior data to generate at least one navigation habit information for the first driver. For instance, density-based clustering algorithms (such as density-based spatial clustering of applications with noise (DBSCAN)) can be used to cluster parking data into different categories based on the density distribution of parking locations, and / or, navigation data can be clustered into different categories based on the density distribution of navigation start / path / destination points. Figure 8As shown in Figure (a), this is a schematic diagram of clustering parking data. Different parking locations can be clustered into categories based on density, such as homes and companies. Optionally, it may also include clusters for temporary pick-up / drop-off (e.g., schools), hospitals, and shopping malls. For example... Figure 8 As shown in Figure (b), this diagram illustrates the clustering of navigation data. Different starting / path / destination points can be clustered according to density. For example, going to work can be categorized into categories like home, temporary pick-up / drop-off (e.g., school), company, and hospital; leaving get off work can be categorized into categories like company, shopping mall, and home. Regardless of the data type, when using a clustering algorithm, the clustering radius (e.g., 500 meters) and the minimum number of samples within a cluster (e.g., 10; the minimum number of samples within a cluster should be dynamically adjusted based on the total number of samples, for example, the minimum number of samples within a cluster should be greater than 25% of the total number of samples) can be set. This means that data from more than 10 parking locations within a 500-meter radius (e.g., parking locations in parking data, or starting / path / destination points in navigation data) can be grouped into one type / category. Optionally, clustering should also incorporate location and time ranges for multi-dimensional clustering. For example, the time period should be specified to be within 4 hours and support cross-day scenarios to prevent misjudgments of travel records near midnight. Optionally, the clustering radius may be different at different locations. For example, the clustering radius of the starting point may be less than 500 meters, and the clustering radius of the destination point may be less than 100 meters.

[0192] For example, such as Figure 9The diagram illustrates the process of generating navigation habit information. When the vehicle is idle or powered off, the vehicle control unit can read at least one user's vehicle usage behavior data from the database. The data is then grouped according to the user's identifier (e.g., driver's identifier). Subsequent clustering processing focuses only on the vehicle usage behavior data of a specific user (e.g., the first driver) to ensure that the summarized habits clearly belong to that same user and avoid data corruption. Taking the clustering of the first driver's vehicle usage behavior data as an example, before clustering, it's possible to determine if the data volume is sufficient, as clustering algorithms require a certain amount of data for accuracy. It can be agreed that there are more than 20 or 50 instances of vehicle usage behavior data. If the data volume is insufficient, more user vehicle usage behavior data is collected and processed later; if the data volume is sufficient, multi-dimensional clustering is performed. For example, taking parking data clustering as an example, multi-dimensional clustering can refer to clustering according to the latitude and longitude information of the parking location and the start / end time of parking. Similarly, taking navigation data clustering as an example, multi-dimensional clustering can refer to clustering according to the latitude and longitude information of the navigation start / path / destination point and the navigation start / end time. Then, for each clustered category (i.e., the clustering result), auxiliary information is combined, such as POI / AOI information, time period (e.g., whether it is a weekday, commuting time), parking duration, first driver identification, parking type, update cycle, etc., to infer the location type (e.g., home, company, school, shopping mall, etc.). Optionally, commuting time can also be inferred. Finally, navigation habit information is generated and written / recorded / stored / summarized in the database.

[0193] Optionally, when clustering locations (e.g., parking locations, or navigation start / path / destination points), the cluster center can be determined by selecting the point with the most points in the cluster radius during each clustering process. If multiple values ​​exist, the average value is taken. When clustering time points (e.g., parking start / end times, or navigation start / end times), the deviation can be calculated based on the Z-score of an approximately normal distribution. The mean can be calculated by selecting the more concentrated data. Generally, work hours are relatively fixed, while off-get off work times may be variable.

[0194] Optionally, when inferring the location type, inferences can be made by setting conditions through scoring or probability. For example, when inferring the family type, a total score > 1 can be set to consider it a possible family address (the thresholds and corresponding scores set in Table 1 below are just examples; the specific thresholds and scores can be adjusted according to the actual situation, and different thresholds correspond to different levels of inference accuracy).

[0195] Table 1

[0196] POI information Residential other other Score 0.5 0 0 Parking time More than 10 hours 8-10 hours 5-8 hours Score 0.5 0.4 0.3 Update cycle Daily updates More than 3 days Score 0.5 -0.5

[0197] For example, when inferring the type of school pick-up and drop-off, a total score greater than 1 can be set to indicate that it is likely a school address (the thresholds and corresponding scores set in Table 2 below are just examples; the specific thresholds and scores can be adjusted according to the actual situation, and different thresholds correspond to different levels of inference accuracy).

[0198] Table 2

[0199] POI information School Residential other Score 0.5 0.3 0 Parking time Within 1 hour 1-2 hours other Score 0.5 0.4 0 Workday situation yes no Score 0.5 -0.5

[0200] For ease of understanding, let's take the first driver's vehicle usage behavior data, including parking data, as an example. Figure 10 As shown, when the vehicle is idle, the vehicle control device can first determine at least two parking habit information entries for the first driver based on the first driver's parking data (e.g., a parking data record table), and then generate at least one navigation habit information entry for the first driver based on these two parking habit information entries (e.g., a navigation habit information summary table). Generally speaking, the end time of the last parking is the start time of the current trip, and the location information of the last parking location (e.g., latitude and longitude, location name, etc.) is the location information of the starting point corresponding to the current departure. Therefore, navigation habit information can be inferred based on the correlation between multiple parking habit information entries.

[0201] For example, any piece of parking habit information may include one or more of the following: driver (e.g., first driver) identifier, passenger identifier, type of frequently used parking location (e.g., locationtype), or latitude and longitude information of the frequently used parking location. Optionally, any piece of parking habit information may also include one or more of the following: parking habit information identifier, latitude and longitude tolerance information, POI information corresponding to the frequently used parking location, AOI information corresponding to the frequently used parking location, parking time information of the most recent parking at the frequently used parking location (e.g., parking start time, parking end time, etc.), update cycle of the frequently used parking location, parking start time of the frequently used parking location, parking end time of the frequently used parking location (i.e., the start time from the frequently used parking location), parking duration of the frequently used parking location, parking time period of the frequently used parking location, commuting hours, commuting hours, or clustering results.

[0202] In some cases, the clustering result contained in any parking habit information can be understood as the value of the cluster category (or cluster value) to which that parking habit information belongs. For example, the cluster value for home is 3, for company it is 4, for shopping mall it is 5, and for school it is 6, etc. The aforementioned latitude and longitude tolerance deviation information can be understood as the tolerance range of latitude and longitude information for frequently parked locations. For example, latitude and longitude tolerance deviation information includes longitude deviation tolerance value and / or latitude deviation tolerance value. Optionally, both longitude deviation tolerance value and / or latitude deviation tolerance value can be expressed in the form AA°BB′CC.CC″, i.e., AA degrees BB minutes CC.CC seconds.

[0203] The aforementioned frequently visited location type can be a hypothetical location type. That is, in one possible implementation, the hypothesized location type can be directly determined as the frequently visited location type. Optionally, the determination of whether to use the hypothesized location type as the frequently visited location type can also be made through user interaction. For example, upon receiving confirmation from the user regarding the hypothesized location type, the hypothesized location type can be determined as the frequently visited location type. The user's confirmation can be made through a user interface (UI) interaction to confirm the accuracy of the location hypotheses, possibly in the form of a desktop pop-up or a card prompt. Optionally, the determination of whether to use the hypothesized location type as the frequently visited location type can also be made through voice interaction, such as "We noticed you frequently visit this place; would you like to record this location as your company?". Optionally, there can also be a page for presenting and managing the relevant location type hypotheses. Users can manually click to confirm and adjust the frequently visited location type, for example, by displaying an editing interface on the screen. This editing interface includes the frequently visited location type, receives the user's editing actions, and updates the frequently visited location type based on the editing actions.

[0204] For example, taking the logic of inferring the type of frequently parked location as home / office based on parking data as an example, generally speaking, the two addresses with the longest parking time are home and office. On weekdays, the location where the car is started in the morning and parked in the afternoon / evening is generally home, while the location where the car is parked in the morning and started in the afternoon / evening is generally office. In addition, the location where the car stays for a long time during the day on weekdays is generally office. Optionally, another possible logic is that on holidays, the departure point is generally home. If the car is not started throughout the holiday, then the location where the car stays for a long time may also be home (this needs to be combined with POI / AOI information). Optionally, the frequently parked location on holidays is unlikely to be office. Of course, there are also people who drive to work every day and go back to their hometown on holidays, choosing to park their car at office and take a taxi to the station to depart. Therefore, this logic can also be used. Thus, for each category (i.e., clustering result) formed by clustering, combined with the above logic, the type of frequently parked location can be inferred. Optionally, the inferred location type can also be added to the interaction logic for user confirmation.

[0205] S402, The vehicle control unit initiates navigation to M addresses.

[0206] M is a positive integer less than or equal to N. In some cases, when all N addresses are either waypoints or destinations, M can be equal to N. In other cases, when the N addresses also include the address of the starting point, M can be a positive integer less than N.

[0207] Optionally, initiating navigation to M addresses in this embodiment can also be described as initiating navigation corresponding to the first navigation habit information. Initiating navigation can be understood as entering a navigation state and starting navigation, such as planning a route for the user and guiding their movement.

[0208] In one possible implementation, a user confirmation instruction can be received before initiating navigation corresponding to the first navigation habit information. This could involve requiring user confirmation before each proactive initiation of navigation corresponding to the first navigation habit information, or requiring user confirmation only for the first initiation, with subsequent initiations not requiring user confirmation. The user confirmation instruction can be obtained through UI interaction, such as a desktop pop-up or a card prompt. Optionally, voice interaction can also be used to determine whether to initiate navigation.

[0209] In one possible implementation, the vehicle control device can initiate navigation to M addresses if the number of times the navigation corresponding to the first navigation habit information has been rejected is less than or equal to a first preset number. For example, the first preset number is 1 time. That is, if the navigation corresponding to the first navigation habit information has not been rejected, or has only been rejected once, the vehicle control device can continue to actively initiate the navigation corresponding to the first navigation habit information the next day. If the navigation corresponding to the first navigation habit information is rejected twice consecutively, then the vehicle control device will no longer actively initiate the navigation corresponding to the first navigation habit information. In this embodiment, the descriptions such as "cancel," "reject," "exit," and "interrupt" can be interchanged.

[0210] In one possible implementation, when a navigation corresponding to the first navigation habit information is initiated and is not rejected, if the number of times the navigation corresponding to the first navigation habit information has been rejected is greater than 0, then the number of times the navigation corresponding to the first navigation habit information has been rejected can be reduced.

[0211] In one possible implementation, the navigation rejection count is increased upon receiving a user's rejection instruction. Furthermore, when a user's rejection instruction is received, the current navigation will not be initiated, or the current proactive recommendation will be cancelled.

[0212] In one possible implementation, if a user initiates navigation habit information that is identical to the first navigation habit information, provided the user meets the aforementioned boarding scenario information and boarding user conditions, the number of navigation rejections is reduced. In other words, if the user reuses the navigation corresponding to the first navigation habit information (or actively initiates the same navigation), the number of navigation rejections can be reduced. Furthermore, the user can actively initiate the navigation corresponding to the first navigation habit information again the following day; if it is still not rejected, the number of navigation rejections can be reset to 0.

[0213] In one possible implementation, if the number of navigation rejections is greater than or equal to a second preset number, and the first navigation habit information has not been used for a first duration, the first navigation habit information is deleted / cleared / released. For example, when a user moves, changes jobs, or their child changes schools, the corresponding navigation habit information can be deleted.

[0214] Optionally, the first preset number of times and the second preset number of times mentioned above can be the same or different, and the specific values ​​are determined based on actual needs. This application does not limit this. For ease of understanding, the following description will mainly use a first preset number of times of 1, a second preset number of times of 2, and a first duration of 10 days as examples. To make the various situations described above clearer, some specific examples will be used below.

[0215] For example, before the vehicle control device actively initiates navigation corresponding to the first navigation habit information, it can first detect whether the navigation corresponding to the first navigation habit information has been rejected once within a short period of time. If it has not been rejected, it determines whether the number of times the navigation corresponding to the first navigation habit information has been rejected is greater than 0. If so, it reduces the number of times the navigation corresponding to the first navigation habit information has been rejected. If it has been rejected once, it determines whether it will be rejected again. If it is rejected again, it does not initiate this navigation and increases the number of times the navigation corresponding to the first navigation habit information has been rejected. If it is not rejected again, it initiates this navigation and determines whether the number of times the navigation corresponding to the first navigation habit information has been rejected is greater than 0. If so, it reduces the number of times the navigation corresponding to the first navigation habit information has been rejected.

[0216] For another example, when a user initiates navigation (e.g., the user manually enters the navigation destination), the system obtains boarding scene information, the identification result of the boarding user, the current latitude and longitude information, and the latitude and longitude information of the destination. If the navigation habit information corresponding to the user's initiated navigation matches the first navigation habit information (or in other words, it matches the first navigation habit information), the number of times the navigation is rejected is reduced.

[0217] To give another example, if the navigation corresponding to the first navigation habit information is rejected more than twice in a row, and the first navigation habit information has not been used for more than 10 days, then the first navigation habit information will be deleted.

[0218] Optionally, the number of navigation rejections can also be represented by a rejection score, where the rejection score increases by 1 for the first rejection, increases by 2 for consecutive rejections, decreases by 1 when the user actively initiates the same navigation, and decreases by 1 when the vehicle control device actively initiates the same navigation and it is not rejected by the user. To make the various situations described above clearer, some specific examples are given below.

[0219] For example, such as Figure 11 As shown in (a), before the vehicle control device automatically / actively initiates navigation corresponding to the first navigation habit information, the vehicle control device can first detect whether the navigation corresponding to the first navigation habit information has been rejected once within a short period of time. If it has not been rejected, it determines whether the rejection score corresponding to the first navigation habit information is greater than 0. If it is, it decrements the rejection score corresponding to the first navigation habit information by 1. If it has been rejected once, it determines whether it will be rejected again. If it is rejected again, it does not initiate this navigation and adds 2 to the rejection score corresponding to the first navigation habit information; if it is not rejected again, it initiates this navigation and determines whether the rejection score corresponding to the first navigation habit information is greater than 0. If it is, it decrements the rejection score corresponding to the first navigation habit information by 1.

[0220] For another example, please see Figure 11 As shown in (b), when a user initiates navigation (e.g., the user manually enters the navigation destination), the system obtains boarding scene information, the identification result of the boarding user, the current latitude and longitude information, and the latitude and longitude information of the destination. If the navigation habit information corresponding to the navigation initiated by the user matches the first navigation habit information (or in other words, it matches the first navigation habit information), the number of navigation rejections is reduced by 1.

[0221] For example, if the rejection score corresponding to the first navigation habit information is greater than or equal to 3, and the first navigation habit information has not been used for more than 10 days, then the first navigation habit information will be deleted.

[0222] In the embodiments of this application, such as Figure 12 As shown, for users boarding / disembarking, relevant scenario judgments can be made based on vehicle information. When a corresponding scenario event is triggered, such as when someone sits down (detected by the seat gravity sensor), facial recognition and / or voiceprint recognition can be performed, and the correspondence between seat positions and seated personnel can be maintained, i.e., determining who the driver is and which user is sitting in each seat. For example, the driver can use facial recognition results by default, while other positions can combine facial and voiceprint recognition results for comprehensive processing to improve recognition accuracy. In addition, by calling navigation services, parking services, location services, etc., parking data and / or navigation data of different users can be obtained. This data can be learned to generate more location types and navigation habit information stored in the database. In subsequent use, proactive navigation recommendation services can be provided based on boarding scenario information (such as the time and location of boarding) and boarding users (or passengers, cabin users, or cabin personnel). This application's method of generating navigation habit information through intelligent learning enables personalized navigation recommendations to be proactively provided to different users based on the results of full-cabin passenger recognition during the navigation service phase. This eliminates the tedious operation of manually entering navigation addresses, allowing users to immediately enjoy navigation services, thus improving the user's driving experience. Furthermore, this application generates more location types through intelligent learning, including categories such as "home," "company," "school," "shopping mall," "park," "hospital," "gas station," and "charging station." The richer variety of location types allows for the provision of more navigation services, improving the applicability of the solution.

[0223] The foregoing has described the application scenarios and methods provided by the embodiments of this application. The apparatus of the embodiments of this application is provided below. It is understood that the various apparatuses provided in the embodiments of this application, such as interactive devices, computing devices, chips, etc., include hardware structures, software units, or combinations of hardware and software structures to perform the functions described in the above method embodiments. Those skilled in the art should readily recognize that the apparatus and modules within it can be implemented in hardware or a combination of hardware and computer software in conjunction with the various functions described in the embodiments disclosed herein. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different apparatus implementations in different application scenarios to implement the aforementioned method embodiments, and different implementations of the apparatus should not be considered beyond the scope of the embodiments of this application.

[0224] Several possible devices are listed below.

[0225] Please see Figure 13 , Figure 13 This is a schematic diagram of a vehicle control device according to an embodiment of this application. The vehicle control device 130 may include an acquisition unit 1301 and a processing unit 1302, and optionally also includes an output unit 1303. The vehicle control device 130 can be a standalone device, for example... Figure 1 The computing device 12 shown may be Figure 1 ,or Figure 2 ,or Figure 3 The vehicle 100 is shown. Alternatively, the vehicle control unit 130 may also be a software module and / or hardware module in a separate device, such as a chip in the computing device 12.

[0226] The vehicle control device 130 is used to implement the aforementioned navigation method, for example, to implement... Figure 4 The vehicle control device 130 in the illustrated embodiment includes a processing unit 1302 for performing one or more of the aforementioned data processing and instruction execution operations such as determining, adjusting, generating, deciding, and judging. The acquisition unit 1301 is used to perform one or more of the aforementioned operations such as acquiring and receiving. Optionally, the interactive device further includes an output unit 1303, which is used to interact with the user, such as outputting prompts, presenting information, and playing voice messages.

[0227] In one possible design, the vehicle control unit 130 is used to achieve... Figure 4 The navigation method shown.

[0228] In one possible implementation, the processing unit 1302 is configured to determine first navigation habit information based on the boarding scene information and the identification result of the boarding user when a vehicle boarding event is detected. The first navigation habit information is determined based on at least one behavioral data of using the vehicle. The first navigation habit information includes N addresses, where N is an integer greater than or equal to 1. The processing unit 1302 is configured to initiate navigation to the M addresses, where M is a positive integer less than or equal to N.

[0229] In one possible design, the first navigation habit information includes one or more of the following:

[0230] The information includes the identification of the first driver, the identification of the passengers, the navigation start time, the navigation end time, the latitude and longitude information of the navigation starting point, the latitude and longitude information of the navigation route points, or the latitude and longitude information of the navigation destination.

[0231] In one possible design, the boarding users include a first pilot and at least one crew member.

[0232] In one possible design, the boarding user includes at least a first pilot, and the N addresses include a first address as the destination.

[0233] In one possible design, the N addresses also include a second address serving as a waypoint, which is the intermediate boarding address of the first crew member.

[0234] In one possible design, the boarding users include a first pilot and a second crew member, and the N addresses include a first address as the destination and a third address as a waypoint, the third address being the disembarkation address of the second crew member.

[0235] In one possible design, when determining the first navigation habit information based on the boarding scenario information and the identification result of the boarding user, the processing unit 1302 is specifically used for:

[0236] At least one navigation habit information is determined based on the boarding scenario information;

[0237] The first navigation habit information is determined from the at least one navigation habit information based on the identification result of the boarding user.

[0238] In one possible design, when determining the first navigation habit information based on the boarding scenario information and the identification result of the boarding user, the processing unit 1302 is specifically used for:

[0239] At least one navigation habit information is determined based on the identification results of the boarding user;

[0240] The first navigation habit information is determined from the at least one navigation habit information based on the boarding scenario information.

[0241] In one possible design, the boarding scenario information includes boarding time information and / or boarding location information.

[0242] In one possible design, before initiating navigation to the M addresses, the acquisition unit 1301 is used to:

[0243] Receive confirmation from the user.

[0244] In one possible design, when initiating navigation to the M addresses, the processing unit 1302 is specifically used for:

[0245] If the number of times navigation corresponding to the first navigation habit information is rejected is less than or equal to the first preset number, navigation to the M addresses is initiated.

[0246] In one possible design, the processing unit 1302 is further configured to:

[0247] If the number of navigation rejections is greater than 0, reduce the number of navigation rejections.

[0248] In one possible design, the processing unit 1302 is further configured to:

[0249] If a user denies the navigation request, the number of times the navigation is rejected is increased.

[0250] In one possible design, the processing unit 1302 is further configured to:

[0251] If a user initiates navigation habit information that is the same as the first navigation habit information, provided that the boarding scenario information and the boarding user are met, the number of times the navigation is rejected is reduced.

[0252] In one possible design, the processing unit 1302 is further configured to:

[0253] If the number of times navigation is rejected is greater than or equal to a second preset number, and the first navigation habit information has not been used for more than a first time period, the first navigation habit information is deleted.

[0254] In one possible design, the processing unit 1302 is further configured to:

[0255] Acquire behavioral data of at least one driver using the vehicle, wherein the at least one driver includes a first driver, which is any one of the at least one drivers, and the behavioral data of the first driver using the vehicle includes navigation data and / or parking data;

[0256] Navigation habit information of the at least one driver is generated based on the behavioral data of the at least one driver using the vehicle.

[0257] In one possible design, any one of the navigation data points includes one or more of the following:

[0258] The identification of the first driver, the identification of the passenger, the navigation start time, the navigation end time, the latitude and longitude information of the navigation starting point, the latitude and longitude information of the navigation route points, or the latitude and longitude information of the navigation destination point.

[0259] In one possible design, any one of the parking data entries includes one or more of the following:

[0260] The identification of the first driver, the identification of the occupants, the start time of parking, the end time of parking, the latitude and longitude information of the parking location, the parking type, the identification of the seated occupants, the identification of the seated occupants, or the identification of the seated occupants.

[0261] In one possible design, the parking type is either regular parking or temporary parking;

[0262] The method further includes:

[0263] If the first condition is met, the parking type is determined to be regular parking;

[0264] If the second condition is met, the parking type is determined to be temporary parking;

[0265] The first condition includes one or more of the following: detecting P gear, detecting power failure, detecting vehicle lock, or detecting no one inside the vehicle;

[0266] The second condition includes one or more of the following: detecting deceleration to less than the first preset speed and then acceleration to greater than the second preset speed, not detecting power failure, or detecting the addition or reduction of occupants.

[0267] In one possible design, when generating navigation habit information for the at least one driver based on the at least one driver's behavior data using the vehicle, the processing unit 1302 is specifically used for:

[0268] If the third condition is met, at least one navigation habit information of the first driver is generated based on the first driver's behavior data using the vehicle, and the at least one navigation habit information includes the first navigation habit information.

[0269] In one possible design, the third condition includes one or more of the following:

[0270] The first driver uses a number of behavioral data points related to the vehicle that are greater than or equal to a preset threshold.

[0271] The time for collecting the first driver's behavior data using the vehicle is less than or equal to a preset time.

[0272] In one possible design, the first driver uses the vehicle's behavioral data, including parking data; when generating at least one navigation habit information for the first driver based on the vehicle's behavioral data, the processing unit 1302 is specifically used for:

[0273] Based on the parking data of the first driver, at least two parking habit information of the first driver are determined;

[0274] At least one navigation habit information for the first driver is generated based on the at least two parking habit information.

[0275] In one possible design, any one of the parking habit information entries includes one or more of the following:

[0276] The identification of the first driver, the identification of the passenger, the type of the regular parking location, or the latitude and longitude information of the regular parking location.

[0277] In one possible design, the parking habit information includes the type of the frequently used parking location;

[0278] The processing unit 1302 is further configured to:

[0279] Upon receiving confirmation from the user regarding the predicted location type, the predicted location type is determined as the type of the frequently used parking location. The predicted location type is obtained based on clustering the parking data of the first driver.

[0280] In one possible design, the processing unit 1302 is further configured to:

[0281] An editing interface is displayed on the screen, and the editing interface includes the type of the frequently stopped location;

[0282] Obtain the user's editing actions;

[0283] The type of the frequently used parking location is updated based on the edit operation.

[0284] The specific operations performed by the aforementioned vehicle control device 130 can also be found in [reference needed]. Figure 4 The embodiments shown are described below.

[0285] In one possible design, the vehicle control unit 130 is used to achieve... Figure 4 The navigation method shown.

[0286] In one possible implementation, the acquisition unit 1301 is used to acquire input information, and the processing unit 1302 is used to generate first configuration information based on the input information.

[0287] In another possible implementation, the vehicle control device 130 further includes an output unit 1303 for presenting prompts for the first configuration information.

[0288] In another possible implementation, the vehicle control device 130 further includes an output unit 1303, which is used to present a first interface. The first interface includes a programming window, conditional elements, and action elements. The conditional elements describe the execution conditions of the vehicle control operation, and the action elements describe the operation content of the vehicle control operation. The programming window is used to program the conditional elements and action elements. The processing unit 1302 is also used to generate first configuration information based on the instruction information of the target user and the elements programmed in the programming window.

[0289] In another possible implementation, the vehicle control device further includes an output unit 1303, which is used to present a first interface. The first interface includes an arrangement window, conditional elements, and action elements. The conditional elements describe the execution conditions of the vehicle control operation, and the action elements describe the operation content of the vehicle control operation. The conditional elements include user characteristic elements, which describe the user's personal characteristics. The arrangement window is used to arrange the conditional elements, user characteristic elements, and action elements. The processing unit 1302 is also used to generate first configuration information based on the elements arranged in the arrangement window. The elements arranged in the arrangement window include at least one user characteristic element and at least one action element, and the at least one user characteristic element is used to indicate the target user.

[0290] In another possible implementation, the processing unit 1302 is further configured to generate first configuration information based on the target user's vehicle usage scenario information. The target user's vehicle usage scenario information includes the target user's instruction information, the target user's vehicle usage environment information, and the operating information of the vehicle's on-board components.

[0291] In another possible implementation, the processing unit 1302 is further configured to input the target user's vehicle usage scenario information into the first model, and generate first configuration information based on the output of the first model. Further, the first model is trained based on multiple sets of vehicle usage scenario information.

[0292] In another possible implementation, the vehicle control device further includes an output unit 1303 for presenting a second interface for displaying recommended activation of the first configuration information, which is activated upon receiving an input activation instruction for the first configuration information or upon not receiving an input denial activation instruction within a third time period.

[0293] In another possible implementation, the acquisition unit 1301 is further configured to receive an input tag indication for at least one user, the tag indication indicating permission to collect vehicle scenario information of at least one user, the at least one user including a target user, or at least one including a user located in a target location area located inside the vehicle's cabin.

[0294] In another possible implementation, the processing unit 1302 is further configured to update the first configuration information based on the input update instruction for the first configuration information, wherein the update instruction is configured to indicate the update of at least one of the following information: the user associated with the first configuration information, the triggering condition of the first vehicle control operation, and the execution content of the first vehicle control operation.

[0295] The specific operations performed by the aforementioned vehicle control device 130 can also be found in [reference needed]. Figure 4 The embodiments shown are described below.

[0296] Please see Figure 14 , Figure 14 The diagram shown is a structural schematic of a computing device provided in an embodiment of this application. The computing device 12 is a device with computing capabilities. This device can be a physical device, such as a controller, processor, server (e.g., rack server), host, etc., or it can be a virtual device, such as a virtual machine, container, etc. Optionally, the computing device 12 can be included in a vehicle, such as... Figure 1 As shown.

[0297] like Figure 14 As shown, the computing device 12 includes a processor 121 and a memory 122. Optionally, the computing device 12 may also include one or more of a bus 123, a communication interface 124, etc. For example, the processor 121 and the memory 122 communicate with each other via the bus 123. It should be understood that this application does not limit the number of processors and memories in the computing device 12.

[0298] Memory 122 provides storage space, which may optionally store application data, user data, operating system, and computer programs (including the aforementioned instructions). Memory 122 may include volatile memory, such as random access memory (RAM). Memory 122 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0299] Processor 121 is a module for performing computations and may include any one or more of the following: controller (e.g., memory controller), CPU, GPU, microprocessor (MP), DSP, coprocessor (to assist the central processing unit in performing corresponding processing and applications), ASIC, MCU, virtual machine, container, etc.

[0300] The communication interface 124 is used to provide information input or output to at least one processor, such as an in-line interface, an out-line interface, etc.

[0301] And / or, the communication interface 124 can be used to receive data transmitted externally and / or transmit data externally. The communication interface 124 can be a wired link interface, including an Ethernet cable, or a wireless link interface (Wi-Fi, Bluetooth, general wireless transmission, and other wireless communication technologies, etc.). Optionally, the communication interface 124 may also include a transmitter (such as an RF transmitter, antenna, etc.) or a receiver coupled to the interface.

[0302] Bus 123 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 14 The bus 123 is represented by a single line, but this does not mean that there is only one bus or one type of bus. The bus 123 may include a path for transmitting information between various components of the computing device 12 (e.g., memory 122, processor 121, communication interface 124).

[0303] In one possible implementation, memory 122 stores executable instructions, which processor 121 executes to implement the aforementioned navigation method, for example... Figure 4The navigation method in the illustrated embodiment.

[0304] This application also provides a chip, including a processor and a communication interface. The communication interface is used for outputting and / or outputting data (including instructions), and / or for receiving and / or sending data. When the processor executes program instructions in memory, the aforementioned navigation method, for example... Figure 4 The navigation method in the illustrated embodiment.

[0305] As one possible example, the communication interface is used to input voice and gesture information, and the processor is used to determine the controlled object based on the voice information and adjust the state of the controlled object based on the gesture information. Optionally, the communication interface is also used to output at least some information related to various prompts.

[0306] This application provides a computer-readable storage medium storing instructions that, when executed by at least one processor, implement the aforementioned navigation method, for example... Figure 4 The navigation method in the illustrated embodiment.

[0307] The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center that contains one or more available media. Computer-readable storage media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives).

[0308] This application provides a computer program product including computer instructions that, when executed on at least one processor, implement the aforementioned navigation method, for example... Figure 4 The navigation method in the illustrated embodiment.

[0309] Optionally, the computer program product can be a software installation package or an image package. If the aforementioned method is required, the computer program product can be downloaded and executed on a computing device.

[0310] This application provides a vehicle that includes the aforementioned vehicle control device 130, or the aforementioned computing device 12, or the aforementioned chip, or the aforementioned computer storage medium, or the aforementioned computer program product deployed on the vehicle. Exemplarily, the vehicle's architecture may be as follows: Figure 1 As shown.

[0311] In addition, a few additional points need to be made regarding this application:

[0312] 1. Unless otherwise stated, “multiple” means two or more.

[0313] 2. Unless otherwise specified or in case of logical conflict, the terms and / or descriptions in different embodiments of this application are consistent and can be referenced in each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0314] III. The various numerical designations used in this application are merely for descriptive convenience and are not intended to limit the scope of protection of this application. The magnitude of the serial numbers used in this application does not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic. For example, the terms "first," "second," "third," "fourth," and other various terminology (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein.

[0315] Furthermore, any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0316] IV. The terms “comprising” and “having” and any variations thereof are intended to cover non-exclusive inclusion, 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 expressly listed, but may include other steps or units that are not expressly listed or that are inherent to such process, method, product or device.

[0317] V. In this application, "for indicating" can be understood as "enabling". "Enabling" can include direct enabling and indirect enabling. When describing information for enabling A, it can include whether the information directly enables A or indirectly enables A, but it does not mean that the information necessarily carries A.

[0318] The information that enables the information is called the information to be enabled. In the specific implementation process, there are many ways to enable the information to be enabled, such as, but not limited to, directly enabling the information to be enabled, such as the information to be enabled itself or its index. It can also be indirectly enabled by enabling other information, where there is a relationship between the other information and the information to be enabled. It can also enable only a part of the information to be enabled, while the other parts are known or pre-agreed upon. For example, enabling specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing enabling overhead to some extent. Simultaneously, common parts of various pieces of information can be identified and enabled uniformly to reduce the enabling overhead caused by individually enabling the same information.

[0319] VI. In this application, "predefined" may include preconfiguration. For example, predefining certain information means that the information is calculated or received in advance before performing an action that uses the information. The "predefined" can be implemented by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device (e.g., in a controller or vehicle). This application does not limit the specific implementation method.

[0320] VII. The term "storage" or "preservation" in this application can refer to storage in one or more memory devices. These memory devices can be separately configured or integrated into an encoder, decoder, processor, or communication device. Alternatively, some memory devices can be separately configured, while others can be integrated into a decoder, processor, or communication device. The type of memory can be any form of storage medium, and this is not limited.

[0321] 8. In the schematic diagrams in the accompanying drawings of this application, the dashed arrows or boxes indicate optional steps or optional modules.

[0322] 9. Unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can mean A or B. In this application, "and / or" is merely a description of the relationship between the related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

Claims

1. A navigation method, characterized in that, include: When a vehicle boarding event is detected, first navigation habit information is determined based on boarding scene information and the identification result of the boarding user. The first navigation habit information is determined based on at least one behavioral data of using the vehicle. The first navigation habit information includes N addresses, where N is an integer greater than or equal to 1. Initiate navigation to the M addresses, where M is a positive integer less than or equal to N.

2. The method according to claim 1, characterized in that, The first navigation habit information includes one or more of the following: The information includes the identification of the first driver, the identification of the passengers, the navigation start time, the navigation end time, the latitude and longitude information of the navigation starting point, the latitude and longitude information of the navigation route points, or the latitude and longitude information of the navigation destination.

3. The method according to claim 1 or 2, characterized in that, The boarding users include the first pilot and at least one crew member.

4. The method according to any one of claims 1-3, characterized in that, The boarding users include at least the first pilot, and the N addresses include the first address as the destination.

5. The method according to claim 4, characterized in that, The N addresses also include a second address serving as a waypoint, which is the intermediate boarding address of the first crew member.

6. The method according to any one of claims 1-5, characterized in that, The boarding users include a first pilot and a second crew member. The N addresses include a first address as the destination and a third address as a transit point. The third address is the departure address of the second crew member.

7. The method according to any one of claims 1-6, characterized in that, The determination of the first navigation habit information based on boarding scene information and the identification results of boarding users includes: At least one navigation habit information is determined based on the boarding scenario information; The first navigation habit information is determined from the at least one navigation habit information based on the identification result of the boarding user.

8. The method according to any one of claims 1-6, characterized in that, The determination of the first navigation habit information based on boarding scene information and the identification results of boarding users includes: At least one navigation habit information is determined based on the identification results of the boarding user; The first navigation habit information is determined from the at least one navigation habit information based on the boarding scenario information.

9. The method according to any one of claims 1-8, characterized in that, The boarding scenario information includes boarding time information and / or boarding location information.

10. The method according to any one of claims 1-9, characterized in that, Before initiating navigation to the M addresses, the method further includes: Receive confirmation from the user.

11. The method according to any one of claims 1-10, characterized in that, The initiation of navigation to the M addresses includes: If the number of times navigation corresponding to the first navigation habit information is rejected is less than or equal to the first preset number, navigation to the M addresses is initiated.

12. The method according to claim 11, characterized in that, The method further includes: If the number of navigation rejections is greater than 0, reduce the number of navigation rejections.

13. The method according to any one of claims 10-12, characterized in that, The method further includes: If a user denies the navigation request, the number of times the navigation is rejected is increased.

14. The method according to claim 13, characterized in that, The method further includes: If a user initiates navigation habit information that is the same as the first navigation habit information, provided that the boarding scenario information and the boarding user are met, the number of times the navigation is rejected is reduced.

15. The method according to claim 13, characterized in that, The method further includes: If the number of times navigation is rejected is greater than or equal to a second preset number, and the first navigation habit information has not been used for more than a first time period, the first navigation habit information is deleted.

16. The method according to any one of claims 1-15, characterized in that, The method further includes: Acquire behavioral data of at least one driver using the vehicle, wherein the at least one driver includes a first driver, which is any one of the at least one drivers, and the behavioral data of the first driver using the vehicle includes navigation data and / or parking data; Navigation habit information of the at least one driver is generated based on the behavioral data of the at least one driver using the vehicle.

17. The method according to claim 16, characterized in that, Any of the navigation data includes one or more of the following: The identification of the first driver, the identification of the passenger, the navigation start time, the navigation end time, the latitude and longitude information of the navigation starting point, the latitude and longitude information of the navigation route points, or the latitude and longitude information of the navigation destination point.

18. The method according to claim 16 or 17, characterized in that, Any of the parking data entries includes one or more of the following: The identification of the first driver, the identification of the occupants, the start time of parking, the end time of parking, the latitude and longitude information of the parking location, the parking type, the identification of the seated occupants, the identification of the seated occupants, or the identification of the seated occupants.

19. The method according to claim 18, characterized in that, The parking type is either regular parking or temporary parking; The method further includes: If the first condition is met, the parking type is determined to be regular parking; If the second condition is met, the parking type is determined to be temporary parking; The first condition includes one or more of the following: detecting P gear, detecting power failure, detecting vehicle lock, or detecting no one inside the vehicle; The second condition includes one or more of the following: detecting deceleration to less than the first preset speed and then acceleration to greater than the second preset speed, not detecting power failure, or detecting the addition or reduction of occupants.

20. The method according to any one of claims 16-19, characterized in that, The step of generating navigation habit information for at least one driver based on the behavioral data of the at least one driver using the vehicle includes: If the third condition is met, at least one navigation habit information of the first driver is generated based on the first driver's behavior data using the vehicle, and the at least one navigation habit information includes the first navigation habit information.

21. The method according to claim 20, characterized in that, The third condition includes one or more of the following: The first driver uses a number of behavioral data points related to the vehicle that are greater than or equal to a preset threshold. The time for collecting the first driver's behavior data using the vehicle is less than or equal to a preset time.

22. The method according to any one of claims 15-21, characterized in that, The first driver's behavior data using the vehicle includes parking data; generating at least one navigation habit information for the first driver based on the first driver's behavior data includes: Based on the parking data of the first driver, at least two parking habit information of the first driver are determined; At least one navigation habit information for the first driver is generated based on the at least two parking habit information.

23. The method according to claim 22, characterized in that, Any of the parking habit information mentioned includes one or more of the following: The identification of the first driver, the identification of the passenger, the type of the regular parking location, or the latitude and longitude information of the regular parking location.

24. The method according to claim 23, characterized in that, The parking habit information includes the type of the frequently parked location; The method further includes: Upon receiving confirmation from the user regarding the predicted location type, the predicted location type is determined as the type of the frequently used parking location. The predicted location type is obtained based on clustering the parking data of the first driver.

25. The method according to claim 23 or 24, characterized in that, The method further includes: An editing interface is displayed on the screen, and the editing interface includes the type of the frequently stopped location; Obtain the user's editing actions; The type of the frequently used parking location is updated based on the edit operation.

26. A vehicle control device, characterized in that, The vehicle control device includes an acquisition unit, a processing unit, and an output unit. The vehicle control device is used to implement the method according to any one of claims 1-25.

27. A chip, characterized in that, The chip includes a processor and a communication interface, the communication interface being used for inputting and outputting information, and the processor calling a computer program to execute the method described in any one of claims 1-25.

28. A computing device, characterized in that, The computing device includes a processor and a memory, the memory being used to store a computer program, and the processor calling the computer program to perform the method according to any one of claims 1-25.

29. A vehicle, characterized in that, The vehicle includes multiple on-board components, and the vehicle also includes the vehicle control device of claim 26, or the chip of claim 27, or the computing device of claim 28.

30. A computer storage medium, characterized in that, The computer storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1-25.

Images