Navigation route planning method and device based on multi-modal interaction

Abstract

The application relates to the field of intelligent navigation, and provides a navigation route planning method and device based on multi-modal interaction. The method comprises the following steps: determining a first expected travel time period and a first travel preference corresponding to each starting position, and a second expected travel time period and a second travel preference corresponding to each destination position; acquiring first historical traffic flow data of a first driving route section from a current position of a vehicle to each starting position in the first expected travel time period; acquiring second historical traffic flow data of a second driving route section from the current position of the vehicle to each destination position in the second expected travel time period; and performing navigation route planning based on the first expected travel time period, the first travel preference, the first historical traffic flow data, the second expected travel time period, the second travel preference and the second historical traffic flow data. The application can meet the efficient and convenient travel requirements of each user in a multi-user multi-destination / starting position scenario, and improve the satisfaction of users to the navigation service and the travel efficiency.

Description

Technical Field

[0001] This application relates to the field of intelligent navigation, and in particular to a navigation route planning method and apparatus based on multimodal interaction. Background Technology

[0002] With the rapid development of technology, intelligent navigation has become an indispensable part of people's daily travel.

[0003] Existing navigation systems can meet the requirements of efficient and convenient travel for a single user with a single destination, but they are unable to meet the requirements of efficient and convenient travel for multiple users with multiple destinations / departure points (for example, multiple users traveling from the same departure point to different destinations, or multiple users traveling from different departure points to different destinations, or multiple users traveling from different departure points to the same destination). Summary of the Invention

[0004] In view of this, embodiments of this application provide a navigation route planning method and apparatus based on multimodal interaction to solve the problem that the existing technology is unable to meet the requirements of efficient and convenient travel for each user in navigation scenarios with multiple users and multiple destinations / departure points.

[0005] A first aspect of this application provides a navigation route planning method based on multimodal interaction, comprising:

[0006] Create a navigation location group, which includes the vehicle's current location and multiple different departure locations and a common destination location, or includes the vehicle's current location and a common departure location and multiple different destination locations;

[0007] Determine the first desired travel time and first travel preference corresponding to each departure location, and the second desired travel time and second travel preference corresponding to each destination location;

[0008] For each departure location, obtain the first historical traffic flow data of the first travel segment from the vehicle's current location to the departure location during the first expected travel time.

[0009] For each destination location, obtain the second historical traffic flow data of the second travel segment from the vehicle's current location to the destination location during the second expected travel time period;

[0010] Navigation route planning is performed based on the first desired travel time, the first travel preference, the first historical traffic flow data, the second desired travel time, the second travel preference, and the second historical traffic flow data, and the target navigation route is output.

[0011] A second aspect of this application provides a navigation route planning device based on multimodal interaction, comprising:

[0012] The creation module is configured to create a navigation location group, which includes the vehicle's current location and multiple different departure locations and a common destination location, or includes the vehicle's current location and a common departure location and multiple different destination locations, or includes the vehicle's current location and multiple different departure locations and multiple different destination locations.

[0013] The determination module is configured to determine the first expected travel time and first travel preference corresponding to each departure location, and the second expected travel time and second travel preference corresponding to each destination location;

[0014] The first acquisition module is configured to acquire, for each departure location, the first historical traffic flow data of the first travel segment from the current location of the vehicle to the departure location during the first expected travel time.

[0015] The second acquisition module is configured to acquire, for each destination location, the second historical traffic flow data of the second travel segment from the current location of the vehicle to the destination location during the second expected travel time.

[0016] The navigation planning module is configured to plan navigation routes based on the first desired travel time, the first travel preference, the first historical traffic flow data, the second desired travel time, the second travel preference, and the second historical traffic flow data, and output the target navigation route.

[0017] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0018] A fourth aspect of this application provides a readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0019] Compared with the prior art, the beneficial effects of this application embodiment include at least the following: by creating a navigation location group and comprehensively considering the first expected travel time and first travel preference corresponding to each departure location in the navigation location group, the second expected travel time and second travel preference corresponding to each destination location, as well as the first historical traffic flow data of the first driving segment from the current vehicle location to each departure location, and the second historical traffic flow data of the second driving route from the current vehicle location to each destination location, a navigation route that can meet the efficient and convenient travel requirements of each user in a multi-user, multi-destination / departure scenario can be planned, thereby improving user satisfaction with the navigation service and effectively improving travel efficiency. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the first navigation application scenario provided in the embodiments of this application;

[0022] Figure 2 This is a schematic diagram of the second navigation application scenario provided in the embodiments of this application;

[0023] Figure 3 This is a schematic diagram of the third navigation application scenario provided in the embodiments of this application;

[0024] Figure 4 This is a flowchart illustrating a navigation route planning method provided in an embodiment of this application;

[0025] Figure 5 This is a schematic diagram of the structure of a multimodal interaction system provided in an embodiment of this application;

[0026] Figure 6 This is a schematic diagram of another multimodal interaction system provided in an embodiment of this application;

[0027] Figure 7 This is a schematic diagram of the structure of a navigation route planning system provided in an embodiment of this application;

[0028] Figure 8 This is a schematic diagram of the fourth navigation application scenario provided in the embodiments of this application;

[0029] Figure 9 This is a flowchart illustrating a method for calculating the single-source shortest path provided in an embodiment of this application;

[0030] Figure 10 This is a schematic diagram of the fifth navigation application scenario provided in the embodiments of this application;

[0031] Figure 11 This is a schematic diagram of the structure of a navigation route planning device based on multimodal interaction provided in an embodiment of this application;

[0032] Figure 12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0033] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0034] A navigation route planning method and apparatus according to embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0035] Figure 1 This is a schematic diagram of the first navigation application scenario provided in this application embodiment. The application scenario may include vehicle 101, first users 102, 103 and 104, and server 105.

[0036] Users 102, 103, and 104 can be users located at different departure locations (departure addresses), wanting to go to the same destination location (destination address), and waiting for vehicle 101 to pick them up.

[0037] Figure 2 This is a schematic diagram of a second navigation application scenario provided in this application embodiment. The application scenario may include vehicle 101, server 105, and second users 106, 107, and 108.

[0038] Among them, the second users 106, 107 and 108 can be users who are located at the same departure location (departure address), want to go to different destination locations (destination addresses) and are waiting for vehicle 101 to pick them up.

[0039] Figure 3 This is a schematic diagram of a third navigation application scenario provided in this application embodiment. The application scenario may include vehicle 101, server 105, and third users 109, 110, and 111.

[0040] Among them, the third users 109, 110 and 111 can be users who are located at different departure locations (departure addresses), want to go to different destination locations (destination addresses), and are waiting for vehicle 101 to pick them up.

[0041] Vehicle 101 can be a new energy vehicle. New energy vehicles refer to vehicles that use new energy sources (non-traditional petroleum and diesel energy) and possess advanced technologies. These vehicles employ new power systems that can effectively reduce vehicle emissions, minimize environmental impact, and improve energy efficiency. The new energy vehicles in this application include, but are not limited to, the following types of vehicles: electric vehicles (EVs), battery electric vehicles (BEVs), fuel cell electric vehicles (FCEVs), plug-in hybrid electric vehicles (PHEVs), and hybrid electric vehicles (HEVs).

[0042] Server 105 can be a server that provides various services. For example, it can be a single server, a server cluster consisting of several servers, or a cloud computing service center. This application embodiment does not limit this.

[0043] It should be noted that the specific types, quantities, and combinations of vehicles 101, first users 102, 103 and 104, second users 106, 107 and 108, third users 109, 110 and 111, and server 105 can be adjusted according to the actual needs of the application scenario, and this application embodiment does not impose any restrictions on this.

[0044] Currently, existing navigation systems can handle navigation tasks for a single user traveling to a single destination. However, when faced with multiple users and multiple destinations / departure points, drivers typically need to manually input each destination / departure point and determine the navigation order based on experience. However, drivers have limited knowledge of factors such as the distance between different destinations and departure points (e.g., the vehicle's current location), road accessibility, traffic congestion between destinations, and the efficiency of different road segments at different times. Therefore, the navigation order they determine based on experience is inaccurate. They may need to repeatedly compare and adjust the navigation order to determine a more efficient route with better road conditions. This process is very time-consuming and requires a high level of understanding of the geographical locations of each destination / departure point, impacting the user experience and resulting in relatively low travel efficiency.

[0045] In view of this, this application provides a navigation route planning method. By integrating advanced multimodal interaction technology and AI (Artificial Intelligence) optimization algorithms, it realizes intelligent planning of navigation routes for multi-user, multi-destination / departure scenarios. It can comprehensively consider various factors such as the user's expected travel time, traffic conditions, and user preferences to provide the user with the optimal travel plan (navigation route). This innovation not only improves the user's travel efficiency and experience, but also injects new vitality into the development of smart travel.

[0046] Furthermore, this application embodiment also provides a navigation route planning method. By creating a navigation location group and comprehensively considering the first expected travel time and first travel preference corresponding to each departure location in the navigation location group, the second expected travel time and second travel preference corresponding to each destination location, as well as the first historical traffic flow data of the first driving segment from the current vehicle location to each departure location, and the second historical traffic flow data of the second driving route from the current vehicle location to each destination location, a navigation route that can meet the efficient and convenient travel requirements of each user in a multi-user, multi-destination / departure scenario can be planned. This can improve user satisfaction with navigation services and effectively improve travel efficiency.

[0047] Figure 4 This is a flowchart illustrating a navigation route planning method provided in an embodiment of this application. Figure 3 The navigation route planning method can be derived from Figures 1-3 The server 105 executes. For example... Figure 4 As shown, this navigation route planning method specifically includes the following steps:

[0048] Step S401: Create a navigation location group. The navigation location group includes the vehicle's current location and multiple different departure locations and a common destination location, or includes the vehicle's current location and a common departure location and multiple different destination locations, or includes the vehicle's current location and multiple different departure locations and multiple different destination locations.

[0049] Figure 5 This is a schematic diagram of the structure of a multimodal interaction system provided in an embodiment of this application.

[0050] Please see Figure 5The multimodal interaction system of this application embodiment includes a cockpit software system 501, a T-BOX (Telematics Service Provider) 502, a TSP (Telematics Service Provider) 503, a cloud information platform 504, a map navigation system 505, a GPS positioning system 506, and a smart voice assistant 507. The cockpit software system 501, T-BOX 502, TSP 503, map navigation system 505, GPS positioning system 506, and smart voice assistant 507 can be deployed in a vehicle 101. The cockpit software system 501, T-BOX 502, TSP 503, map navigation system 505, GPS positioning system 506, smart voice assistant 507, and cloud information platform 504 can communicate with each other via a CAN (Controller Area Network) bus. The vehicle 101 can establish a communication connection with a server 105 through the cloud information platform 504.

[0051] Users (such as drivers) can turn the multi-destination / departure point intelligent navigation function (mode) on or off through the cockpit software system 501 of vehicle 101, and bind the multi-destination / departure point intelligent navigation function (mode) to the vehicle system account of vehicle 101.

[0052] The current location of vehicle 101 can be collected by GPS positioning system 506 and transmitted to map navigation system 505 via CAN bus.

[0053] As an example, please refer to Figure 1 and Figure 5 When multiple users (such as users 102, 103, and 104) are all inside vehicle 101, they can input their desired destination via touchscreen operation on the central control screen of the vehicle 101's cockpit software system 501, or via voice interaction using the vehicle 101's intelligent voice assistant 507. Both the cockpit software system 501 and the intelligent voice assistant 507 support multiple users simultaneously inputting different destinations.

[0054] Figure 6 This is a schematic diagram of another multimodal interaction system provided in the embodiments of this application.

[0055] As an example, please refer to Figure 6Users (such as drivers) can activate the multi-destination / departure point intelligent navigation mode through the cockpit software system 501 of vehicle 101, and establish a communication connection with the cloud information platform 504 through the T-BOX 502 or TSP 503 of vehicle 101. User devices (such as smartphones) can establish a communication connection with the cloud information platform 504 through 4G / 5G networks. Each user can use their user device to input their desired destination / departure location, which is then transmitted to vehicle 101 via T-BOX 502 or TSP 503 through the cloud information platform 504. Vehicle 101 then transmits the received destination / departure location to the cockpit software system 501 and map navigation system 505 via the CAN bus.

[0056] As an example, in a scenario where multiple users travel from the same starting point to different destinations, the driver can create a multi-destination navigation trip by using the touchscreen of the cockpit software system 501 in vehicle 101 or by voice interaction through the intelligent voice assistant 507. The cockpit software system 501 generates a QR code based on this multi-destination navigation trip and displays it on the central control screen. Each user in the vehicle (such as the first user 102, 103, and 104) can scan the QR code using their respective user devices (such as smartphones) and input their desired destination location (address) on the information entry page that appears after scanning the QR code. Alternatively, they can share location information from other software (such as WeChat, QQ, or other instant messaging software) containing their desired destination location to the information entry page.

[0057] As another example, in scenarios where multiple users are traveling from different departure points to different destinations or the same destination, the driver can remotely share a QR code of a multi-destination navigation trip created in the cockpit software system 501 with each user. In this way, each user can remotely input their departure location and desired destination by scanning the QR code shared by the driver.

[0058] Figure 7 This is a schematic diagram of the structure of a navigation route planning system provided in an embodiment of this application.

[0059] Please see Figure 7 The navigation route planning system of this application embodiment includes a map navigation system 505 and a map cloud database 701. The map navigation system 505 can communicate with the map cloud database 701 via a 4G / 5G network to transmit the collected current vehicle location, the departure location of each first user, and the destination location of each second user to the map cloud database 701. The map cloud database 701 can be deployed in a server 105, wherein the server 105 can be a cloud server.

[0060] The departure location (departure address) and destination location (destination address) mentioned above can be saved to the address database of the map navigation system 505 of vehicle 101, and the address database can be bound to the vehicle system account of vehicle 101 for easy access when needed later.

[0061] Before creating a navigation location group, preliminary processing can be performed on each departure and destination location to ensure data accuracy and validity. This preliminary processing mainly includes data cleaning, format conversion, and verification. Specifically, this can involve address extraction, administrative region parsing, address structuring, address error correction and completion, address standardization, address anomaly detection, multi-address similarity assessment, and latitude / longitude lookup and coordinate system conversion for the aforementioned departure and destination locations.

[0062] For origin and destination locations input in text form, Named Entity Recognition (NER) algorithms and deep learning-based NER models, such as BiLSTM-CRF (Bidirectional Long Short-Term Memory Network with Conditional Random Field), can be used to identify address entities in the text. Slot filling techniques can be used to identify and classify the various components of the address, such as province, city, and district. Spelling correction algorithms (such as Levenshtein distance (edit distance) or BK-Tree (Inverted Keyword Tree) algorithm) can be used to identify and correct spelling errors in the origin and destination locations.

[0063] In supervised learning, a classification algorithm (Support Vector Machine (SVM) or neural network) trained on a dataset can be used to identify anomalous addresses in the destination and departure locations. In unsupervised learning, clustering algorithms (such as K-means or DBSCAN) can be used to identify anomalous patterns in the input destination and departure locations.

[0064] Geocoding technology is used to convert the input destination and departure locations into latitude and longitude geographic coordinates; Dynamic Time Warping (DTW) and Hidden Markov Model (HMM) are used for map matching to ensure correct matching between GPS track points and road network maps.

[0065] The aforementioned algorithms and intelligent large models can learn geospatial data through deep learning (such as convolutional neural networks (CNN) and recurrent neural networks (RNN)) and can be optimized through reinforcement learning and other methods.

[0066] Step S402: Determine the first expected travel time and first travel preference corresponding to each departure location, and the second expected travel time and second travel preference corresponding to each destination location.

[0067] The first desired travel time indicates the time period during which the user expects the pick-up vehicle to arrive at the provided departure location.

[0068] The second desired travel time indicates the time period during which the user expects a ride-hailing vehicle to take them to their provided destination location.

[0069] First and second travel preferences indicate a user's daily travel habits, such as avoiding toll roads or preferring highways. Collaborative filtering methods can be used to learn user travel preferences by analyzing their historical travel behavior. Matrix factorization methods (such as SVD) can be used to predict user preferences for different routes.

[0070] As an example, users can use their smartphones to scan the QR code of a multi-destination / departure navigation trip shared by the driver, and enter the departure location, first desired travel time and first travel preference on the redirected page; then enter the destination location, second desired travel time and second travel preference.

[0071] Step S403: For each departure location, obtain the first historical traffic flow data of the first travel segment from the vehicle's current location to the departure location during the first expected travel time.

[0072] Figure 8 This is a schematic diagram illustrating the fourth navigation application scenario provided in this application. Please refer to... Figure 8 In a scenario where multiple users (including first users 102, 103, and 104) travel from different starting points to the same destination, assuming that the starting point provided by first user 102 is point B, the starting point provided by first user 103 is point C, the starting point provided by first user 104 is point D, the current position of vehicle 101 is point A, and the destination that first users 102, 103, and 104 want to go to is point E. Then, server 105 can interact with the traffic management system to obtain the first historical traffic flow data 1 of the first travel segment 1 (i.e., A→B) of vehicle 101 from point A to point B provided by the first user 102 during the first expected travel time (e.g., T1) of the first user 102; obtain the first historical traffic flow data 2 of the first travel segment 2 (i.e., A→C) of vehicle 101 from point A to point C provided by the first user 103 during the first expected travel time (e.g., T2) of the first user 103; and obtain the first historical traffic flow data 3 of the first travel segment 3 (i.e., A→D) of vehicle 101 from point A to point D provided by the first user 104 during the first expected travel time (e.g., T3) of the first user 104.

[0073] The first historical traffic flow data includes road congestion, traffic accidents, construction information, etc., on the first travel segment within the first expected time period.

[0074] Step S404: For each destination location, obtain the second historical traffic flow data of the second travel segment from the vehicle's current location to the destination location during the second expected travel time.

[0075] Specifically, the second historical traffic flow data for each second travel segment during the second expected travel period can be obtained using the same method as the first historical traffic flow data mentioned above, which will not be elaborated here.

[0076] Step S405: Based on the first desired travel time, the first travel preference, the first historical traffic flow data, the second desired travel time, the second travel preference, and the second historical traffic flow data, a navigation route is planned, and the target navigation route is output.

[0077] The technical solution provided in this application creates a navigation location group and comprehensively considers the first expected travel time and first travel preference corresponding to each departure location in the navigation location group, the second expected travel time and second travel preference corresponding to each destination location, as well as the first historical traffic flow data of the first driving segment from the current vehicle location to each departure location and the second historical traffic flow data of the second driving route from the current vehicle location to each destination location. This allows for the planning of navigation routes that can meet the efficient and convenient travel requirements of users in multi-user, multi-destination / departure scenarios, thereby improving user satisfaction with navigation services and effectively increasing travel efficiency.

[0078] In some embodiments, navigation route planning is performed based on a first desired travel time, a first travel preference, first historical traffic flow data, a second desired travel time, a second travel preference, and second historical traffic flow data, and the target navigation route is output, including:

[0079] Based on the first historical traffic flow data of each first driving segment, predict the first traffic congestion status of each first driving segment during the first expected time period.

[0080] Based on the second historical traffic flow data of each second driving segment, predict the second traffic congestion status of each second driving segment during the second expected travel time.

[0081] Based on the first traffic congestion status and the first travel preference, the departure locations are sorted to obtain the first navigation sequence;

[0082] Based on the second traffic congestion status and the second travel preference, the destination locations are sorted to obtain the second navigation sequence;

[0083] Navigation route planning is performed based on the first and second navigation sequences, and the target navigation route is output.

[0084] As an example, please refer to Figure 8 Taking the first travel segment 1 (A (starting point) → B (ending point)) as an example, assuming the first expected travel time T1 corresponding to the first travel segment 1 is 9:00 to 10:00, the map cloud database 701 of server 105 can retrieve the first historical traffic flow data corresponding to the first expected travel time T1 of the previous w days (w is an integer ≥ 1). Then, the first historical traffic flow data of the previous w days is input into a pre-trained prediction model (which can be a convolutional neural network model or other deep learning network model), and outputs the first traffic congestion state of the first travel segment 1 in the first expected travel time T1. The first traffic congestion state includes m forward travel paths (m is an integer ≥ 1) from the starting point (point A) to the ending point (point B), n reverse travel paths from the ending point (point B) to the starting point (point A), and information such as vehicle flow, path node topology, and travel distance (Euclidean distance) corresponding to each forward travel path and each reverse travel path.

[0085] The above method can be used to predict the traffic congestion status of the first travel segment 2 (A (starting point) → C (end point)), the first travel segment 3 (A (starting point) → D (end point)), and each of the second travel segments during the second expected travel time. These will not be elaborated further here.

[0086] In some embodiments, based on a first traffic congestion state and a first travel preference, the departure locations are sorted to obtain a first navigation sequence, including:

[0087] For each departure location, based on the first traffic congestion status and the first travel preference, determine the first shortest travel path from the vehicle's current location to the departure location; wherein, the first shortest travel time of the first shortest travel path is within the first desired travel time period;

[0088] The starting positions are sorted based on the first shortest travel time to obtain the first navigation sequence.

[0089] As an example, please refer to Figure 8Taking the first travel segment 1 (A(starting point) → B(end point)) as an example, assuming that the first user 102's first travel preference is to prefer fast routes and avoid toll roads, we can first search for k forward candidate travel paths from the m travel paths from A(starting point) to B(end point) that satisfy the first user 102's first travel preference, and g reverse candidate travel paths from the n travel paths from B(end point) to A(starting point) that satisfy the first user 102's first travel preference, where k≤m and g≤n. We then remove overlapping candidate travel paths from the k forward candidate travel paths and the g reverse candidate travel paths, obtaining s candidate travel paths. Then, based on the first traffic congestion state, we calculate the travel time for each of the s target candidate travel paths, and determine the target candidate travel path with the shortest travel time within the first expected travel time period as the first shortest travel path 1 for the first travel segment 1 (A(starting point) → B(end point)).

[0090] By combining user travel preferences to search for forward candidate routes from origin to destination, and simultaneously searching for reverse candidate routes from destination to origin, overlapping candidate routes between forward and reverse routes are eliminated. Furthermore, by combining the first traffic congestion status and the user's expected travel time for route filtering, the system can find the globally optimal route that matches the user's travel preferences and expected travel time in the shortest possible time, thereby improving the user's experience with navigation services.

[0091] Figure 9 This is a flowchart illustrating a method for calculating the shortest path from a single source, as provided in an embodiment of this application.

[0092] Please see Figure 9 First, the starting path node, intermediate path node, and ending path node of each target candidate driving route can be determined based on the first traffic congestion state. Then, the following steps are executed: Figure 9 The process shown determines the first shortest travel path 1 for the first travel segment 1 (A (starting point) → B (ending point)).

[0093] Specifically, step S901: Initialize the distance of all vertices (including intermediate and final path nodes) to infinity. Step S902: Set the distance of the source node (e.g., the starting path node) to zero. Step S903: Create a priority queue and add the source node. Step S904: Check if the priority queue is empty. If the priority queue is empty, end the process. If the priority queue is not empty, jump to step S905: Pop vertex U and its distance from the priority queue. Step S906: Check if all neighbors V of vertex U have been traversed. If yes, return to step S904. If not, jump to step S907: Iterate over each neighbor V of the vertex. Step S908: Calculate the distance from the source node to neighbor V. Step S909: Check if the newly calculated distance from the source node to neighbor V is less than the known distance of neighbor V. If not, return to step S906. If so, proceed to step S910 and update the distance to neighbor V. S911: Add neighbor V and the new distance to the priority queue and return to step S906.

[0094] The first shortest travel path 2 for the first travel segment 2 (A (starting point) → C (ending point)) and the first shortest travel path 3 for the first travel segment 3 (A (starting point) → D (ending point)) can be calculated using a similar method.

[0095] Next, based on the first shortest travel time corresponding to the first shortest travel path 1, the first shortest travel path 2, and the first shortest travel path 3, the starting positions are sorted to obtain the first navigation sequence.

[0096] As an example, assuming that the shortest travel times corresponding to the first shortest travel path 1, the first shortest travel path 2, and the first shortest travel path 3 are arranged in ascending order as follows: first shortest travel path 3 < first shortest travel path 1 < first shortest travel path 2, then the first navigation sequence is [D, B, C], which means that the order in which vehicle 101 arrives at the starting positions provided by the first users 102, 103, and 104 is D→B→C.

[0097] Furthermore, starting from D, we can calculate the second shortest travel time 1 from D to B and the second shortest travel time 2 from D to C. If the second shortest travel time 1 > the second shortest travel time 2, then the first navigation sequence can be adjusted to obtain the adjusted first navigation sequence [D,C,B].

[0098] A similar approach can be used to sort the destination locations based on the second traffic congestion status and the second travel preference to obtain the second navigation sequence, which will not be elaborated here.

[0099] Please see Figure 8Based on the above example, assuming the first navigation sequence obtained through the above steps is [D,C,B] and the second navigation sequence is [E], then the target navigation route obtained by planning the navigation route based on the first and second navigation sequences is [A,D,C,B,E]. This means that the pick-up and drop-off order of vehicle 101 arriving at the departure position provided by the first users 102, 103, and 104 and taking them to the destination position is A→D→C→B→E.

[0100] The above implementation method, in the process of navigation route planning, can take into account the user's travel preferences, expected time of day, and traffic congestion status from the vehicle's current location to each departure / destination location, so that the obtained navigation route can meet the requirements of efficient and convenient travel for each user in a multi-user, multi-destination / departure scenario as much as possible, thereby improving user satisfaction with navigation services and effectively improving overall travel efficiency.

[0101] In some embodiments, determining the first shortest travel time for a first travel segment from the vehicle's current location to its starting location, based on a first traffic congestion state and a first travel preference, includes:

[0102] Determine the navigation application scenario;

[0103] Based on navigation application scenarios, determine the weight of the first preference for the first trip.

[0104] Based on the first preference weight and the first traffic congestion state, navigation route planning is performed to obtain the optimal driving trajectory for the first driving segment;

[0105] Calculate the first shortest travel time based on the optimal travel trajectory and vehicle speed.

[0106] Navigation application scenarios include, but are not limited to, urban commuting scenarios, long-distance travel scenarios, and short-distance hitchhiking scenarios.

[0107] For urban commuting, users generally prioritize minimizing commute time and avoiding congested areas. For long-distance travel, users typically prioritize factors such as distance, fuel consumption, and rest stops along the way. For short-distance ridesharing, users generally prioritize speed and convenience.

[0108] In view of this, the embodiments of this application pre-set the correspondence between the general user preferences and their weight factors corresponding to different navigation application scenarios, and store the correspondence in the map cloud database 701 of the server 105.

[0109] As an example, the correspondence between navigation application scenarios, common user preferences, and weighting factors is shown in Table 1.

[0110] Table 1. Correspondence between navigation application scenarios, common user preferences, and weighting factors.

[0111]

[0112] Figure 10 This is a schematic diagram illustrating the fifth navigation application scenario provided in this application. Please refer to... Figure 2 and Figure 10 In a scenario where multiple users (such as users 106, 107, and 108) travel from the same starting point to different destinations, assuming that users 106, 107, and 108 all provide starting point A, vehicle 101's current location is also point A, user 106 wants to go to point F, user 107 wants to go to point G, and user 108 wants to go to point H, and server 105 identifies the current navigation application scenario as a short-distance hitchhiking scenario. Therefore, firstly, based on the short-distance hitchhiking scenario, the first preference weights of the first travel preferences of users 106, 107, and 108 are determined.

[0113] The following is a detailed explanation of the first preference weight for determining the first travel preference of the second user 106 based on a short-distance ride-sharing scenario.

[0114] Assuming that the first travel preference of the second user 106 is to prefer fast routes and avoid toll roads, and the current navigation application scenario is a short-distance hitchhiking scenario, according to Table 1 above, the general user preferences for short-distance hitchhiking scenarios are fast arrival and convenience. Comparison shows that the second user 106's first travel preference is basically consistent with the general user preferences for short-distance hitchhiking scenarios. Based on the weight factors corresponding to Fac_short_1 and Fac_short_2, the weight of the second user 106's first travel preference can be determined to be 1.

[0115] After determining the first preference weight of the second user 106, navigation route planning is performed based on the first preference weight of the second user 106 and the first traffic congestion status of the first travel segment (A→F). (Specifically, ant colony algorithm, genetic algorithm, etc. can be used for navigation route planning) to obtain the optimal travel trajectory of the first travel segment (A→F). Finally, based on the travel distance of the optimal travel trajectory and the vehicle's travel speed, the first shortest travel time of the first travel segment (A→F) is calculated.

[0116] The above implementation method, by combining navigation application scenarios and users' travel preferences to plan navigation routes, can maximize the travel efficiency of all passengers and the satisfaction of users with navigation services while taking into account the different travel preferences of each user as much as possible.

[0117] In some embodiments, navigation route planning is performed based on a first navigation sequence and a second navigation sequence, and a target navigation route is output, including:

[0118] Obtain the first navigation requirement for the departure location and the second navigation requirement for the destination location;

[0119] Based on the first navigation requirement and the second navigation requirement, the first navigation sequence and the second navigation sequence are adjusted to obtain a combined navigation sequence; wherein, the combined navigation sequence includes the vehicle's current position, as well as each departure position and each destination position;

[0120] Generate the target navigation route based on the combined navigation sequence and output the target navigation route.

[0121] The first navigation requirement could be the user's requirement for the order in which vehicles arrive at the provided starting point.

[0122] The second navigation requirement could be the user's requirement for the order in which the vehicle arrives at the provided destination.

[0123] Users can input their first navigation requirement and second navigation requirement while entering their departure location / destination location.

[0124] As an example, please refer to Figure 10 Assuming the first navigation sequence obtained according to the above implementation method is [A], the second navigation sequence is [G,H,F], and the second navigation requirement is "request to reach destination location F first", then the map cloud database 701 of server 105 can first verify whether navigation sequences [F,G,H] and [F,H,G] can meet the travel preferences and expected travel times of each user. If both can be met, then the estimated total travel time of navigation sequences [F,G,H] and [F,H,G] is further compared, and the navigation sequence with the shortest estimated total travel time is determined as the adjusted second navigation sequence. For example, if both navigation sequences [F,G,H] and [F,H,G] can meet the travel preferences and expected travel times of each user, and the estimated total travel time of [F,G,H] is the shortest, then [F,G,H] can be determined as the adjusted second navigation sequence.

[0125] The first navigation sequence [A] and the adjusted second navigation sequence [F,G,H] are combined to obtain the combined navigation sequence [A,F,G,H]. Finally, based on the combined navigation sequence [A,F,G,H], the target navigation route A→F→G→H is generated and output to the map navigation system 505 of vehicle 101.

[0126] The above implementation method, by adjusting the first navigation sequence and the second navigation sequence in combination with the user's navigation needs, can make the obtained navigation route better meet the travel needs and actual conditions of each user, thereby further improving the user's satisfaction with the navigation service.

[0127] In some embodiments, the above method further includes:

[0128] Show the user the target navigation route;

[0129] Obtain the user's modification instructions for the target navigation route;

[0130] The target navigation route is modified according to the modification instructions to obtain the modified navigation route, and the modified navigation route is output.

[0131] Modification commands can instruct users to avoid specific areas or choose specific paths.

[0132] As an example, the map cloud database 701 of server 105 can transmit the calculated target navigation route to the map navigation system 505 of vehicle 101. The map navigation system 505's central control screen displays the target navigation route to the user, or the map navigation system 505 can share the target navigation route with the user's device, allowing the user to view the target navigation route and enter modification commands on the user device. Specifically, the user can use the vehicle 101's cockpit software system 501 for touch operation, use the intelligent voice assistant 507 for voice interaction, or enter modification commands through the user device.

[0133] After receiving a user's modification instruction for the target navigation route, the map navigation system 505 transmits the modification instruction to the map cloud database 701. The map cloud database 701 recalculates and modifies the target navigation route based on the modification instruction, obtains the modified navigation route, and returns the modified navigation route to the map navigation system 505.

[0134] The above implementation method can adjust the target navigation route once or multiple times based on the user's modification instructions, so that the obtained navigation route can meet the personalized needs of each user as much as possible, thereby improving the user's satisfaction with the navigation service.

[0135] In some embodiments, the above method further includes:

[0136] Obtain real-time traffic data for the target navigation route, as well as the vehicle's current energy consumption information;

[0137] Based on real-time traffic data and current vehicle energy consumption information, the target navigation route is optimized to obtain an optimized navigation route.

[0138] Real-time traffic data, including but not limited to road gradient, curvature, traffic light distribution, and real-time traffic congestion information for each segment of the target navigation route.

[0139] The vehicle's current energy consumption information indicates the vehicle's current fuel consumption / electricity status and power performance, etc.

[0140] As an example, the map cloud database 701 of server 105 can interact with the traffic management system to obtain real-time traffic data for the target navigation route; and interact with vehicle 101 to obtain the vehicle's current energy consumption information. Then, based on the obtained real-time traffic data and vehicle current energy consumption information, the map cloud database 701 optimizes the target navigation route to minimize fuel consumption or electricity usage while ensuring driving safety. For example, in a congested urban commuting scenario, the map cloud database 701 can switch congested sections of the target navigation route to relatively uncongested but longer sections to avoid frequent stops and starts, thereby reducing fuel or electricity consumption.

[0141] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0142] In summary, the technical solutions provided in this application have at least the following beneficial effects:

[0143] 1) By integrating advanced AI algorithms and comprehensively considering user travel preferences, real-time traffic conditions, distance, congestion, and user's desired travel time, it can significantly improve travel efficiency and greatly enhance user satisfaction with navigation services.

[0144] 2) It supports multiple interaction methods such as voice and touch screen, broadcasts driving information in real time to ensure driving safety, and allows passengers to adjust their destination during the trip, enhancing flexibility and interactivity.

[0145] 3) It can intelligently and automatically adjust the route planning strategy according to the navigation application scenario (such as urban commuting scenario, long-distance travel scenario, short-distance hitchhiking scenario), thereby meeting the personalized needs of each user and improving the system's adaptability.

[0146] 4) It can optimize vehicle fuel / electricity usage during navigation, reduce resource consumption, reduce human planning costs, and save time costs.

[0147] 5) It can ensure the system's efficiency in processing big data and complex calculations, update traffic information in real time, and provide accurate navigation services.

[0148] 6) Through intelligent and personalized route planning and multimodal interaction, we bring users an efficient, convenient and personalized travel experience.

[0149] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0150] Figure 11 This is a schematic diagram of the structure of a navigation route planning device based on multimodal interaction provided in an embodiment of this application. Figure 11 As shown, the navigation route planning device based on multimodal interaction includes:

[0151] Module 1101 is configured to create a navigation location group, which includes the vehicle's current location and multiple different departure locations and a common destination location, or includes the vehicle's current location and a common departure location and multiple different destination locations, or includes the vehicle's current location and multiple different departure locations and multiple different destination locations.

[0152] The determination module 1102 is configured to determine the first expected travel time and first travel preference corresponding to each departure location, and the second expected travel time and second travel preference corresponding to each destination location;

[0153] The first acquisition module 1103 is configured to acquire, for each departure location, the first historical traffic flow data of the first travel segment from the current location of the vehicle to the departure location during the first expected travel time.

[0154] The second acquisition module 1104 is configured to acquire, for each destination location, the second historical traffic flow data of the second travel segment from the current location of the vehicle to the destination location during the second expected travel time.

[0155] The navigation planning module 1105 is configured to plan navigation routes based on the first desired travel time, the first travel preference, the first historical traffic flow data, the second desired travel time, the second travel preference, and the second historical traffic flow data, and output the target navigation route.

[0156] In some embodiments, the navigation planning module 1105 described above includes:

[0157] The first prediction unit is configured to predict the first traffic congestion status of each first travel segment during the first expected time period based on the first historical traffic flow data of each first travel segment.

[0158] The second prediction unit is configured to predict the second traffic congestion status of each second travel segment during the second expected travel time based on the second historical traffic flow data of each second travel segment.

[0159] The first sorting unit is configured to sort each departure location based on the first traffic congestion state and the first travel preference to obtain the first navigation sequence;

[0160] The second sorting unit is configured to sort the destination locations based on the second traffic congestion status and the second travel preference to obtain the second navigation sequence;

[0161] The planning output unit is configured to plan a navigation route based on the first navigation sequence and the second navigation sequence, and output the target navigation route.

[0162] In some embodiments, the first sorting unit described above includes:

[0163] The route determination component is configured to determine, for each departure location, a first shortest travel route from the vehicle's current location to the departure location based on a first traffic congestion state and a first travel preference; wherein the first shortest travel time of the first shortest travel route is within a first desired travel time period.

[0164] The location sorting component is configured to sort each departure location based on a first shortest travel time to obtain a first navigation sequence.

[0165] In some embodiments, the path determination component described above may be specifically configured as follows:

[0166] Determine the navigation application scenario;

[0167] Based on navigation application scenarios, determine the weight of the first preference for the first trip.

[0168] Based on the first preference weight and the first traffic congestion state, navigation route planning is performed to obtain the optimal driving trajectory for the first driving segment;

[0169] Calculate the first shortest travel time based on the optimal travel trajectory and vehicle speed.

[0170] In some embodiments, the planning output unit described above includes:

[0171] The requirement retrieval component is configured to retrieve the first navigation requirement for the departure location and the second navigation requirement for the destination location.

[0172] The adjustment component is configured to adjust the first navigation sequence and the second navigation sequence based on the first navigation requirement and the second navigation requirement to obtain a combined navigation sequence; wherein, the combined navigation sequence includes the vehicle's current position, as well as each departure position and each destination position;

[0173] The output component is configured to generate a target navigation route based on the combined navigation sequence and output the target navigation route.

[0174] In some embodiments, the above-described apparatus further includes:

[0175] The display module is configured to show the user the target navigation route;

[0176] The instruction acquisition module is configured to acquire user instructions to modify the target navigation route;

[0177] The route modification module is configured to modify the target navigation route according to the modification command, obtain the modified navigation route, and output the modified navigation route.

[0178] In some embodiments, the above-described apparatus further includes:

[0179] The information acquisition module is configured to acquire real-time traffic data of the target navigation route, as well as the vehicle's current energy consumption information;

[0180] The route optimization module is configured to optimize the target navigation route based on real-time traffic data and the vehicle's current energy consumption information, thereby obtaining an optimized navigation route.

[0181] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0182] Figure 12 This is a schematic diagram of the electronic device 12 provided in an embodiment of this application. Figure 12 As shown, the electronic device 12 of this embodiment includes: a processor 1201, a memory 1202, and a computer program 1203 stored in the memory 1202 and executable on the processor 1201. When the processor 1201 executes the computer program 1203, it implements the steps in the various method embodiments described above. Alternatively, when the processor 1201 executes the computer program 1203, it implements the functions of each module / unit in the various device embodiments described above.

[0183] Electronic device 12 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 12 may include, but is not limited to, processor 1201 and memory 1202. Those skilled in the art will understand that... Figure 12This is merely an example of electronic device 12 and does not constitute a limitation on electronic device 12. It may include more or fewer components than shown, or different components.

[0184] The processor 1201 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0185] The memory 1202 can be an internal storage unit of the electronic device 12, such as a hard disk or RAM of the electronic device 12. The memory 1202 can also be an external storage device of the electronic device 12, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, FlashCard, etc., equipped on the electronic device 12. The memory 1202 can also include both internal and external storage units of the electronic device 12. The memory 1202 is used to store computer programs and other programs and data required by the electronic device.

[0186] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0187] If integrated modules / units are implemented as software functional units and sold or used as independent products, they can be stored in a readable storage medium (e.g., a computer-readable storage medium). Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0188] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A navigation route planning method based on multimodal interaction, characterized in that, include: Create a navigation location group, which includes the vehicle's current location and multiple different departure locations and a common destination location, or includes the vehicle's current location and a common departure location and multiple different destination locations, or includes the vehicle's current location and multiple different departure locations and multiple different destination locations; Determine the first desired travel time and first travel preference corresponding to each departure location, and the second desired travel time and second travel preference corresponding to each destination location; The first expected travel time period indicates the time period during which the user expects the pick-up vehicle to arrive at the departure location provided by the user, and the second expected travel time period indicates the time period during which the user expects the drop-off vehicle to take them to the destination location provided by the user. For each departure location, obtain the first historical traffic flow data of the first travel segment from the vehicle's current location to the departure location during the first expected travel time period; For each destination location, obtain the second historical traffic flow data of the second travel segment from the vehicle's current location to the destination location during the second expected travel time period; Based on the first historical traffic flow data of each first driving segment, predict the first traffic congestion status of each first driving segment during the first expected time period. Based on the second historical traffic flow data of each second travel segment, predict the second traffic congestion status of each second travel segment during the second expected travel time. Based on the first traffic congestion status and the first travel preference, the departure locations are sorted to obtain the first navigation sequence; Based on the second traffic congestion status and the second travel preference, the destination locations are sorted to obtain a second navigation sequence; Navigation route planning is performed based on the first navigation sequence and the second navigation sequence, and the target navigation route is output.

2. The method according to claim 1, characterized in that, Based on the first traffic congestion status and the first travel preference, the departure locations are sorted to obtain a first navigation sequence, including: For each departure location, based on the first traffic congestion status and the first travel preference, a first shortest travel path is determined from the vehicle's current location to the departure location; wherein, the first shortest travel time of the first shortest travel path is within the first desired travel time period; The departure locations are sorted based on the first shortest travel time to obtain a first navigation sequence.

3. The method according to claim 2, characterized in that, Based on the first traffic congestion status and the first travel preference, determine the first shortest travel time for the first travel segment from the vehicle's current location to its starting location, including: Determine the navigation application scenario; Based on the navigation application scenario, determine the first preference weight of the first travel preference; Based on the first preference weight and the first traffic congestion state, navigation route planning is performed to obtain the optimal driving trajectory for the first driving segment. Calculate the first shortest travel time based on the optimal travel trajectory and vehicle speed.

4. The method according to claim 1, characterized in that, Based on the first navigation sequence and the second navigation sequence, a navigation route is planned and the target navigation route is output, including: Obtain the first navigation requirement for the departure location and the second navigation requirement for the destination location; Based on the first navigation requirement and the second navigation requirement, the first navigation sequence and the second navigation sequence are adjusted to obtain a combined navigation sequence; wherein, the combined navigation sequence includes the vehicle's current position, as well as each of the departure positions and each of the destination positions; Generate a target navigation route based on the combined navigation sequence, and output the target navigation route.

5. The method according to claim 1, characterized in that, The method further includes: Show the user the target navigation route; Obtain the user's modification instructions for the target navigation route; The target navigation route is modified according to the modification instruction to obtain the modified navigation route, and the modified navigation route is output.

6. The method according to claim 1, characterized in that, The method further includes: Obtain real-time traffic data for the target navigation route, as well as the vehicle's current energy consumption information; Based on the real-time traffic data and the vehicle's current energy consumption information, the target navigation route is optimized to obtain an optimized navigation route.

7. A navigation route planning device based on multimodal interaction, characterized in that, include: The creation module is configured to create a navigation location group, which includes the vehicle's current location and multiple different departure locations and a common destination location, or includes the vehicle's current location and a common departure location and multiple different destination locations, or includes the vehicle's current location and multiple different departure locations and multiple different destination locations. The determination module is configured to determine a first desired travel time and a first travel preference corresponding to each of the departure locations, and a second desired travel time and a second travel preference corresponding to each of the destination locations; The first acquisition module is configured to acquire, for each of the departure locations, the first historical traffic flow data of the first travel segment from the current location of the vehicle to the departure location during the first expected travel time period. The second acquisition module is configured to acquire, for each of the destination locations, the second historical traffic flow data of the second travel segment from the current location of the vehicle to the destination location during the second expected travel time period. The navigation planning module is configured to predict the first traffic congestion status of each of the first driving segments during the first expected time period based on the first historical traffic flow data of each of the first driving segments; and to predict the second traffic congestion status of each of the second driving segments during the second expected travel time based on the second historical traffic flow data of each of the second driving segments. Based on the first traffic congestion status and the first travel preference, the departure locations are sorted to obtain the first navigation sequence; Based on the second traffic congestion status and the second travel preference, the destination locations are sorted to obtain a second navigation sequence; Navigation route planning is performed based on the first navigation sequence and the second navigation sequence, and the target navigation route is output.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6.

9. A readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images