Planned path generation method and device, medium and equipment

Abstract

The invention discloses a planned path generation method and device, a medium and equipment. The method comprises the steps of obtaining an input instruction of a user in a vehicle; analyzing the input instruction to obtain navigation key information for path planning and implicit passing point constraint conditions; generating an initial planning path based on the navigation key information; determining a first implicit passing point based on an implicit passing point constraint condition; and generating a fused planned path of the vehicle based on the first implicit waypoint and the initial planned path. According to the scheme, the input instruction can be analyzed to obtain the implicit pass point constraint condition, so that the potential intention of the user can be understood, and the first implicit pass point screened based on the implicit pass point constraint condition can meet the personalized requirement of the user; therefore, the fusion planning path generated based on the first implicit passing point and the initial planning path can solve the problem of multi-constraint condition processing in navigation planning in a complex scene, so that the navigation efficiency and the user experience are improved.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, specifically to a method, apparatus, medium, and device for generating a planned path. Background Technology

[0002] With the increasing diversification of users' travel needs, navigation systems have become an important auxiliary tool for users' travel. At present, vehicle navigation systems mainly provide route planning with preset modes, such as the shortest distance and avoiding highways, which makes navigation technology have significant limitations.

[0003] However, in actual travel scenarios, users' needs are quite complex. For example, when traveling to Nanjing, a user might expect a route with beautiful scenery along the way and a total travel time of less than 4 hours. However, navigation technologies can only provide preset routes with the shortest distance or that avoid highways, failing to meet the user's diverse personalized preferences and resulting in a poor user experience.

[0004] Therefore, there is an urgent need for a method to generate planned routes to meet users' diverse personalized preferences. Summary of the Invention

[0005] To address the aforementioned technical issues, this disclosure provides a method, apparatus, medium, and device for generating planned paths, in order to meet users' diverse personalized preferences and improve user experience.

[0006] One aspect provides a method for generating planned paths, including:

[0007] Obtain input commands from users inside the vehicle;

[0008] The input instructions are parsed to obtain key navigation information and implicit waypoint constraints for path planning;

[0009] Based on the aforementioned key navigation information, an initial planned path is generated;

[0010] Based on the implicit waypoint constraints, the first implicit waypoint is determined;

[0011] Based on the first implicit waypoint and the initial planned path, a fusion planned path for the vehicle is generated.

[0012] In another aspect, a path planning generation apparatus is provided, comprising:

[0013] The first acquisition module is used to acquire input commands from users inside the vehicle;

[0014] The first parsing module is used to parse the input command to obtain key navigation information and implicit waypoint constraints for path planning;

[0015] The first planning module is used to generate an initial planned path based on the navigation key information;

[0016] The first determining module is used to determine the first implicit path point based on the implicit path point constraint conditions;

[0017] The second planning module is used to generate a fusion planning path for the vehicle based on the first implicit waypoint and the initial planning path.

[0018] In another aspect, the embodiments propose a computer program product that, when the instruction processor in the computer program product is executed, performs the path planning generation method proposed in the above embodiments of this disclosure.

[0019] In another aspect, an electronic device is proposed, comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the above-described method for generating a planned path.

[0020] The path generation method provided in this disclosure can parse the user's input commands to obtain key navigation information and implicit waypoint constraints for path planning. Based on the key navigation information, an initial planned path is generated, and based on the implicit waypoint constraints, a first implicit waypoint is determined. Then, based on the first implicit waypoint and the initial planned path, a fusion planned path for the vehicle is generated. This solution, by parsing the input commands to obtain implicit waypoint constraints, can understand the user's underlying intent. This allows the first implicit waypoint selected based on the implicit waypoint constraints to meet the user's personalized needs. Therefore, the fusion planned path generated based on the first implicit waypoint and the initial planned path can solve the problem of handling multiple constraints in navigation planning in complex scenarios, thus improving navigation efficiency and user experience. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the structure of a path planning system provided in an exemplary embodiment of this disclosure.

[0022] Figure 2 This is a flowchart illustrating a method for generating a planned path provided in an exemplary embodiment of this disclosure.

[0023] Figure 3 This is a flowchart illustrating a method for generating a planned path provided in an exemplary embodiment of this disclosure.

[0024] Figure 4 This is a flowchart illustrating a method for generating a planned path provided in an exemplary embodiment of this disclosure.

[0025] Figure 5 This is a flowchart illustrating a method for generating a planned path provided in an exemplary embodiment of this disclosure.

[0026] Figure 6 This is a flowchart illustrating a method for generating a planned path provided in an exemplary embodiment of this disclosure.

[0027] Figure 7 This is a flowchart illustrating a method for generating a planned path provided in an exemplary embodiment of this disclosure.

[0028] Figure 8 This is a flowchart illustrating a method for generating a planned path provided in an exemplary embodiment of this disclosure.

[0029] Figure 9 This is a schematic diagram of the structure of a path planning generation apparatus provided in an exemplary embodiment of this disclosure.

[0030] Figure 10 This is a structural diagram of an electronic device provided in an exemplary embodiment of this disclosure. Detailed Implementation

[0031] To explain this disclosure, exemplary embodiments of the disclosure will now be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the disclosure, and not all of them. It should be understood that the disclosure is not limited to exemplary embodiments.

[0032] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0033] Application Overview

[0034] Currently, in related technologies, vehicle navigation systems rely on specific algorithms or preset modes to plan navigation routes. For example, distance-first algorithms find the shortest path between two points, but because this approach is solely distance-oriented, it ignores road conditions, scenery, and the user's personalized needs. Another example is using a route-avoiding mode, which is only suitable for users who want to avoid highway tolls or have concerns about high-speed driving, but not for users with other needs. Therefore, when faced with the challenge of handling multiple constraints in navigation planning in complex scenarios, existing navigation systems cannot meet the diverse personalized preferences of users, resulting in a poor user experience.

[0035] To address the aforementioned problems, this disclosure provides a method for generating a planned path. This method parses user input commands to obtain key navigation information and implicit waypoint constraints for path planning. Based on the key navigation information, an initial planned path is generated. Based on the implicit waypoint constraints, a first implicit waypoint is determined. Then, based on the first implicit waypoint and the initial planned path, a fusion planned path for the vehicle is generated. This solution, by parsing the input commands to obtain implicit waypoint constraints, understands the user's underlying intent. This allows the first implicit waypoint selected based on the implicit waypoint constraints to meet the user's personalized needs. Therefore, the fusion planned path generated based on the first implicit waypoint and the initial planned path solves the problem of handling multiple constraints in navigation planning in complex scenarios, thus improving navigation efficiency and user experience.

[0036] Exemplary System

[0037] Figure 1 This is a schematic diagram of the structure of a path planning system provided in an exemplary embodiment of this disclosure.

[0038] In some examples, such as Figure 1 As shown, the above-mentioned route planning system can perform the following steps when planning a route:

[0039] (1) Instruction parsing stage:

[0040] In some embodiments, the user's input command is obtained, and the large language model is guided to parse the input command using preset basic navigation prompt words to obtain key navigation information; and the large language model is guided to parse the input command using preset waypoint constraint prompt words to obtain implicit waypoint constraint conditions.

[0041] (2) Determine the main path framework:

[0042] In some embodiments, after obtaining the navigation key information, since the navigation key information includes the navigation start point and the navigation end point, and may also include at least one explicit waypoint, an initial planned path can be generated based on the navigation start point, the navigation end point and at least one explicit waypoint, that is, the main path is obtained.

[0043] (3) Pre-screening of search scope

[0044] In some embodiments, after obtaining the implicit waypoint constraints, a feasible search range can be determined based on the distance constraints, the initial planned path, and real-time traffic data in the implicit waypoint constraints; then, based on other constraints in the implicit waypoint constraints, the feasible search range is filtered to obtain a set of candidate waypoints; wherein, other constraints may include time constraints, type constraints, and may also include price constraints and / or user rating constraints, etc.

[0045] (4) Determine implicit path points

[0046] In some embodiments, after obtaining the above-mentioned candidate path point set, the comprehensive score of multiple candidate implicit path points included in the candidate path point set can be calculated, and the first implicit path point can be determined based on the comprehensive score of multiple candidate implicit path points.

[0047] (5) Integration Planning Path

[0048] In some embodiments, after obtaining the first implicit waypoint, a fusion planning path can be generated based on the first implicit waypoint and the initial planning path described above.

[0049] For the specific implementation of each of the above steps, please refer to the detailed description in the following method embodiments. The embodiments disclosed herein will not be repeated here.

[0050] The technical solution provided in this disclosure can parse the input command to obtain implicit waypoint constraints, thus understanding the user's potential intentions. This allows the first implicit waypoint selected based on the implicit waypoint constraints to meet the user's personalized needs. As a result, the fusion planning path generated based on the first implicit waypoint and the initial planning path can solve the problem of handling multiple constraints in navigation planning in complex scenarios, thereby improving navigation efficiency and user experience.

[0051] Exemplary methods

[0052] Figure 2 This is a flowchart illustrating a method for generating a planned path according to an exemplary embodiment of this disclosure. This embodiment can be applied to electronic devices, such as... Figure 2 As shown, it includes the following steps:

[0053] Step 201: Obtain input commands from the user inside the vehicle.

[0054] In some examples, the input instructions can be voice commands or text commands entered by the user. These input instructions can include multiple constraints under navigation planning, or they can include only a single navigation planning constraint (i.e., ordinary input instructions for route planning); for example, the input instruction could be "Tomorrow morning at 10:00, I will leave home for the company, find a restaurant with a rating of at least 4.5 and an average cost of 30-50 yuan per person for lunch, avoiding Zhongshan Road."

[0055] In some embodiments, voice commands are used as an example of input instructions. When a user needs to plan a route, they can initiate a voice command, which is then collected by audio sensors within the vehicle. For example, the audio sensors could be a microphone array located within the vehicle's cabin.

[0056] In other embodiments, the input command is a text command entered by the user. When the user needs to plan a route, the user can trigger the vehicle's navigation system on the display screen of the in-vehicle terminal and enter a text command on the display screen of the in-vehicle terminal, so that the vehicle can receive the text command through the navigation system.

[0057] Step 202: Parse the input command to obtain key navigation information and implicit waypoint constraints for path planning.

[0058] In some embodiments, the aforementioned navigation key information is basic information used for route planning, meaning that the navigation key information may include at least the navigation start point and the navigation destination. The navigation key information may also include information such as explicit waypoints, avoidance areas, and avoidance roads; wherein, explicit waypoints refer to the waypoints that the user explicitly specifies the vehicle needs to pass through before reaching the navigation destination in the route planning process.

[0059] In some embodiments, the implicit waypoint constraints described above are constraints used to determine implicit waypoints. Implicit waypoint constraints may include multi-dimensional constraints. Implicit waypoints refer to waypoints that the vehicle needs to pass through before reaching the navigation destination in the route planning process, and which are not explicitly specified by the user.

[0060] In some examples, the input command is a voice command. One possible approach is to first convert the voice command into text information using Automatic Speech Recognition (ASR) technology, and then use Natural Language Processing (NLP) techniques, such as Named Entity Recognition (NER) and syntactic analysis, to analyze, understand, and process the text information corresponding to the voice command in order to extract key navigation information. Another approach is to use a large model to parse the input command to obtain key navigation information. For details, please refer to the detailed description in the following embodiments, which will not be repeated here.

[0061] In some examples, a large model can be used to parse the input instructions to obtain implicit waypoint constraints. Specific details can be found in the following embodiments, which will not be elaborated upon here. Implicit waypoint constraints may include multi-dimensional constraints, such as distance constraints, type constraints, time constraints, price constraints, and user rating constraints.

[0062] Step 203: Generate an initial planned path based on key navigation information.

[0063] In some embodiments, a preset route planning strategy can be obtained, and a route search algorithm can be used to generate an initial planned route based on navigation key information, the route planning strategy, and real-time traffic data (such as road congestion index, speed limits, traffic restrictions, etc.). The route planning strategy can be either the default setting of the navigation system or a user-defined setting. For example, the route search algorithm can be a heuristic search algorithm (A-Star Algorithm, A) or the shortest path Dijkstra's algorithm; the route planning strategy can prioritize speed or avoid highways, etc.

[0064] In some examples, if the navigation key information only includes the navigation start point and navigation end point, then an initial planned path of "navigation start point → navigation end point" is directly generated based on the navigation start point and navigation end point. If the navigation key information includes the navigation start point, navigation end point, and at least one explicit waypoint, then an initial planned path from the navigation start point → explicit waypoint → navigation end point can be generated directly in one go based on the navigation start point, navigation end point, and at least one explicit waypoint. Alternatively, an initial planned path of "navigation start point → navigation end point" can be generated first based on the navigation start point and navigation end point, and then at least one explicit waypoint can be directly inserted between the navigation start point and navigation end point to obtain an initial planned path of "navigation start point → explicit waypoint → navigation end point".

[0065] Step 204: Determine the first implicit path point based on the implicit path point constraint.

[0066] In some embodiments, the implicit pathpoint constraints may include multiple constraints; the search range of implicit pathpoints can be determined based on a portion of the constraints, and then filtered within that search range based on another portion of the constraints to obtain the first implicit pathpoint. For details, please refer to the detailed descriptions in the following embodiments; the embodiments disclosed herein will not be repeated here.

[0067] Step 205: Generate the vehicle's fused planning path based on the first implicit waypoint and the initial planned path.

[0068] In some embodiments, a first implicit waypoint can be inserted into the initial planned path based on a preset path search algorithm to obtain the vehicle's fused planned path; wherein the starting node and ending node in the fused planned path are the same as the starting node and ending node in the initial planned path, and the node position of the first implicit waypoint in the fused planned path is determined based on the path search algorithm, that is, the node position of the first implicit waypoint can be any position in the fused planned path other than the navigation starting point and navigation ending point.

[0069] For example, taking the initial planned path as A→B→C and the first implicit waypoint as D as an example, inserting the first implicit waypoint into the initial planned path, the resulting fused planned path for the vehicle can be either A→B→D→C or A→D→B→C.

[0070] The path generation method provided in this disclosure can parse the user's input commands to obtain key navigation information and implicit waypoint constraints for path planning. Based on the key navigation information, an initial planned path is generated, and based on the implicit waypoint constraints, a first implicit waypoint is determined. Then, based on the first implicit waypoint and the initial planned path, a fusion planned path for the vehicle is generated. This solution, by parsing the input commands to obtain implicit waypoint constraints, can understand the user's underlying intent. This allows the first implicit waypoint selected based on the implicit waypoint constraints to meet the user's personalized needs. Therefore, the fusion planned path generated based on the first implicit waypoint and the initial planned path can solve the problem of handling multiple constraints in navigation planning in complex scenarios, thus improving navigation efficiency and user experience.

[0071] like Figure 3 As shown above, in the above Figure 2 Based on the illustrated embodiment, step 204 may include the following steps:

[0072] Step 2041: Based on the implicit waypoint constraints, obtain the candidate waypoint set.

[0073] In some examples, the implicit waypoint constraints mentioned above include a first constraint, which may include time constraints, distance constraints, and type constraints, etc.

[0074] In some embodiments, the implicit waypoint constraint condition mentioned above includes a first constraint condition; step 2041 may specifically include the following steps (a) to (d):

[0075] Step (a): Based on the distance constraint in the first constraint and the initial planned path, perform implicit waypoint search to obtain the basic search area.

[0076] In some examples, since the initial planned path is used as the main path, the aforementioned distance constraint refers to the range within which implicit waypoints are searched along the initial planned path; that is, the distance constraint is used to constrain the distance between implicit waypoints and the initial planned path. When the distance constraint includes the main path distance constraint value D, a buffer zone called "main path distance constraint D" is formed by extending to both sides of the initial planned path as the axis, which serves as the basic search area. The distance constraint value D can be determined based on a preset distance constraint value Dc or a user-provided distance constraint value Du. If the user's input command includes the distance constraint value Du, then the distance constraint value Du is used as the main path distance constraint value D; otherwise, if the user's input command does not include the distance constraint value Du, then the preset distance constraint value Dc is used as the main path distance constraint value D.

[0077] Step (b): Determine the remaining time required for vehicle route planning, and determine the drivable range of the vehicle based on the remaining time required and the vehicle's speed.

[0078] In some examples, the remaining time required for vehicle path planning can be calculated based on the current time and the time constraint in the first constraint. Then, the maximum travel range of the vehicle within the remaining time can be calculated based on the remaining time and the vehicle's speed. Of course, when calculating the travel range, real-time traffic data (such as road congestion) can also be combined with the remaining time and the vehicle's speed.

[0079] For example, the time constraint is to arrive before 18:00, the current time is 17:00, and the remaining time is 60 minutes; based on the remaining time and the vehicle's speed, the vehicle's travel range within the remaining time is calculated to be 50 kilometers.

[0080] Step (c): Determine the feasible search range based on the drivable range and the basic search area.

[0081] In some examples, the drivable range and the basic search area intersect, so the feasible search range can be obtained by taking the intersection of the drivable range and the basic search area.

[0082] Step (d): Based on the time constraint and type constraint in the first constraint, search for implicit path points in the feasible search range to obtain a set of candidate path points.

[0083] In some examples, time constraints are used to limit the time reserved for implicit waypoints; type constraints are used to constrain the type of implicit waypoints. Using R-tree spatial indexing, all implicit waypoints satisfying the type constraints can be searched from the feasible search range. Then, based on the time constraints, implicit waypoints that do not meet the time constraints are removed from all implicit waypoints. This yields at least one implicit waypoint that simultaneously satisfies both the time and type constraints. The set of these at least one implicit waypoints is the candidate waypoint set.

[0084] For example, consider a time constraint of arriving before 18:00 and a type constraint of "restaurant". Using R-tree spatial indexing, all restaurants can be searched from the feasible search range based on the type constraint. Then, based on the distance of each restaurant from the initial planned path and the vehicle's speed, the vehicle's travel time and dwell time at each restaurant are calculated. If the sum of the travel time and the dwell time at a particular restaurant (e.g., 70 minutes) exceeds the time constraint (e.g., 60 minutes remaining), that restaurant can be removed, thus obtaining a set of candidate waypoints.

[0085] Based on the above embodiments, since implicit waypoint search is performed based on the distance constraint in the first constraint and the initial planned path to obtain the basic search area, and the drivable range of the vehicle is determined based on the remaining required time and driving speed of the vehicle path planning, and then implicit waypoints are searched in the feasible search range determined based on the drivable range and the basic search area based on the time constraint and the type constraint in the first constraint to obtain the candidate waypoint set, the candidate implicit waypoints in the obtained candidate waypoint set have satisfied the distance, time and type constraints, thereby solving the problem of handling multiple constraints in navigation planning in complex scenarios.

[0086] In some embodiments, the implicit waypoint constraint further includes a second constraint; the second constraint includes, but is not limited to, at least one of the following: a price constraint, a user rating constraint; the above step (d) may specifically include: filtering the candidate waypoint set based on the second constraint to obtain an updated candidate waypoint set.

[0087] In some examples, when the second preset condition only includes price constraints, the actual prices of all candidate waypoints in the candidate waypoint set can be obtained from a third-party platform. Based on the price constraints, candidate implicit waypoints whose actual prices do not meet the price constraints are filtered out from the candidate waypoint set to obtain an updated candidate waypoint set. That is, all candidate implicit waypoints in the updated candidate waypoint set meet the price constraints.

[0088] In other examples, when the second preset condition includes both price constraints and user rating constraints, the following steps can be taken: First, based on the price constraints, filter out candidate implicit pathways from the candidate pathway set whose actual prices do not meet the price constraints. Then, obtain the actual user ratings of the remaining candidate implicit pathways from the third-party platform, and based on the user rating constraints, filter out candidate implicit pathways from the remaining candidate implicit pathways whose actual user ratings do not meet the user rating constraints. This results in an updated candidate pathway set, where all candidate implicit pathways in the updated candidate pathway set simultaneously meet both price constraints and user rating constraints.

[0089] For example, taking a price constraint of 30-50 yuan and a user rating constraint of greater than or equal to 4.5 points as an example, based on the price constraint and the user rating constraint, implicit candidate waypoints with user ratings less than 4.5 points and prices exceeding 50 yuan are filtered from the candidate waypoint set to obtain an updated candidate waypoint set.

[0090] It should be noted that the above embodiments are merely illustrative examples of second constraints including price constraints and / or user rating constraints. In actual use, the above second constraints may also include other constraints, and this disclosure does not limit this.

[0091] Based on the above embodiments, since the implicit waypoint constraint also includes a second constraint, the candidate waypoint set can be filtered based on the second constraint to obtain an updated candidate waypoint set. Therefore, under the premise of satisfying the distance, time and type constraints, the updated candidate waypoint set can also satisfy the user rating constraint and / or price constraint, thereby satisfying the user's personalized needs in different dimensions.

[0092] In some embodiments, after step (d) above, the method for generating a planned path provided in this disclosure may further include the following steps (e) or (f):

[0093] Step (e): In response to the fact that the candidate waypoint set does not include candidate implicit waypoints, the implicit waypoint constraints are adjusted; based on the adjusted implicit waypoint constraints, the candidate waypoint set is determined.

[0094] When the candidate path point set does not include candidate implicit path points, i.e., the candidate path point set is empty, it is necessary to adjust the implicit path point constraints to ensure the generation of a valid candidate path point set. Therefore, by adjusting at least some of the implicit path point constraints, adjusted implicit path point constraints are obtained, and the candidate path point set can be re-determined based on the adjusted implicit path point constraints. For the re-determining of the candidate path point set based on the adjusted implicit path point constraints, please refer to the detailed description in the above embodiments; this disclosure will not repeat it here.

[0095] In some examples, when adjusting implicit waypoint constraints, you can adjust only the first constraint or the second constraint, or both the first constraint and the second constraint.

[0096] For example, the distance constraint in the first constraint can be changed from "less than or equal to 2 kilometers" to "less than or equal to 3 kilometers"; another example is to change the user rating constraint in the second constraint from "greater than or equal to 4.5 points" to "greater than or equal to 4 points".

[0097] Step (f): In response to the fact that the candidate waypoint set does not include candidate implicit waypoints, output the first prompt message.

[0098] The first prompt message is used to inform the user that no implicit path point that meets the user's needs has been found.

[0099] In some examples, the aforementioned first prompt information can be a voice prompt or a text prompt. When the first prompt information is a text prompt, outputting the first prompt information includes: displaying the text prompt information on the vehicle's display screen (e.g., the central control screen); when the first prompt information is a voice prompt, outputting the first prompt information includes: playing the voice prompt information through the vehicle's microphone.

[0100] In some examples, if the candidate waypoint set does not include candidate implicit waypoints, i.e. the candidate waypoint set is empty, a first prompt message can be output to inform the user that no implicit waypoint that meets the user's needs has been found. Therefore, the vehicle can directly navigate based on the initial planned path.

[0101] Based on the above embodiments, when the candidate path point set does not include candidate implicit path points, the user experience in complex scenarios is improved because the implicit path point constraints can be adjusted to ensure the generation of a valid candidate set, or a prompt message can be output to indicate to the user that no implicit path point that meets the user's needs has been found.

[0102] Step 2042: Determine the first implicit waypoint based on the set of candidate waypoints.

[0103] In some examples, when the candidate path point set includes only one implicit path point, that one implicit path point is determined as the first implicit path point; when the candidate path point set includes multiple implicit path points, any one of the multiple implicit path points can be determined as the first implicit path point, or a specific implicit path point among the multiple implicit path points can be determined as the first implicit path point. The determination of the specific implicit path point can be referred to the detailed description in the following embodiments.

[0104] In some embodiments, step 2042 above may include the following steps:

[0105] Step 2042A: In response to the candidate path point set including multiple candidate implicit path points, calculate the comprehensive score of each of the multiple candidate implicit path points.

[0106] In some examples, the scores of each candidate implicit pathpoint across multiple dimensions can be calculated separately. Then, the scores of each dimension and their corresponding weight coefficients are summed to obtain the comprehensive score of each candidate implicit pathpoint. The multiple dimensions can be determined based on the implicit pathpoint constraints.

[0107] For example, if the implicit waypoint constraint includes distance and time constraints, then multiple dimensions can include distance and time dimensions; as another example, if the implicit waypoint constraint includes distance, time, user rating, and price constraints, then multiple dimensions can include distance, time, user rating, and price dimensions.

[0108] For example, consider multiple dimensions including distance, time, user rating, and price. First, set the score range for each dimension to 0-k points (e.g., k=5), then calculate the score for each dimension. For instance, to calculate the distance dimension score Sd, obtain the actual distance d between the candidate implicit waypoint and the initial planned path. Let D be the distance threshold for the distance constraint. The distance score Sd = k*(Dd) / D, where D is greater than or equal to d. Similarly, the scores St for the time dimension, Se for the user rating dimension, and Sp for the price dimension can be calculated. The comprehensive score S for the candidate implicit waypoint is S = a*Sd + b*Se + c*Sp + d*St, where a, b, c, and d are the weight coefficients for each dimension, and the sum of a, b, c, and d equals 1. The weight coefficients for each dimension can be preset or user-defined.

[0109] Understandably, within the distance constraint, the closer a candidate implicit waypoint is to the initial planned path, the higher its distance dimension score; the shorter the dwell time of a candidate implicit waypoint, the higher its time dimension score; the higher the actual user rating of a candidate implicit waypoint, the higher its user rating dimension score; and within the price constraint, the lower the price of a candidate implicit waypoint, the higher its price dimension score.

[0110] Step 2042B: Determine the first implicit path point based on the comprehensive score of multiple candidate implicit path points.

[0111] In some examples, after calculating the comprehensive score of multiple candidate implicit path points, the candidate implicit path points can be sorted in descending order based on their comprehensive scores, and the candidate implicit path point ranked first can be determined as the first implicit path point; alternatively, the candidate implicit path points can be sorted in ascending order based on their comprehensive scores, and the candidate implicit path point ranked last can be determined as the first implicit path point. It can be understood that the first implicit path point is the candidate implicit path point with the highest comprehensive score among the multiple candidate implicit path points.

[0112] The technical solution provided in this disclosure, after obtaining a set of candidate path points based on implicit path point constraints, can calculate the comprehensive score of multiple candidate implicit path points and determine the first implicit path point based on the comprehensive score of multiple candidate implicit path points. Therefore, the obtained first implicit path point can not only meet the user's multi-dimensional potential needs, but also automatically evaluate the candidate implicit path points in the candidate set to select the optimal solution without requiring the user to make a manual selection, thereby improving the efficiency of path planning and user satisfaction.

[0113] like Figure 4 As shown above, in the above Figure 2 Based on the illustrated embodiment, step 202 above may include the following steps:

[0114] Step 2021: Obtain the preset basic navigation prompts.

[0115] In some examples, the basic navigation prompts mentioned above can be set at the vehicle's factory or customized by the user. Basic navigation prompts can guide the large model to parse user input commands to obtain key navigation information. Basic navigation prompts can include at least the fields for navigation start point, navigation destination, and explicit waypoints, and may also include other fields such as avoidance areas or avoidance roads.

[0116] For example, the following is an exemplary basic navigation prompt provided by an embodiment of this disclosure:

[0117] You are a navigation route planner, transcribing user input commands into the following format:

[0118] {

[0119] "fromAndTo": "starting point; ending point";

[0120] "mode": Path planning strategy (integer, default 0 means speed priority);

[0121] "passedByPOIs":["passed by POI1","passed by POI2",...];

[0122] "avoidPolygons":["Avoidance Zone 1","Avoidance Zone 2",...];

[0123] "avoidRoad": "Avoid the name of the road".

[0124] }

[0125] It should be noted that the above basic navigation prompts are merely an illustrative example, and this disclosure does not limit them.

[0126] Step 2022: Using basic navigation prompts, guide the first language model to parse the input command and obtain key navigation information.

[0127] The key navigation information includes at least the navigation start point and the navigation destination.

[0128] In some examples, the primary language model mentioned above can be GPT, Deepseek, or other large language models. The key navigation information mentioned above may also include explicit waypoints, avoidance zones, and avoidance roads.

[0129] For example, suppose a user inputs the following command at 10:00 AM from Xinjiekou: "I want to get to Zhongshan Wharf at 1:00 PM, passing through Laomendong, and find a restaurant with a rating of at least 4.5 and an average cost of 30-50 yuan per person for lunch." The primary language model is Deepseek. When guiding the Deepseek model to parse the input command using basic navigation prompts, both the basic navigation prompts and the input command can be input into the Deepseek model. The Deepseek model then outputs key navigation information, which is as follows:

[0130] {

[0131] "fromAndTo":"Xinjiekou; Zhongshan Wharf";

[0132] "mode":0;

[0133] "passedByPOIs":"Laomendong";

[0134] "avoidPolygons": "";

[0135] "avoidRoad": "";

[0136] }

[0137] The technical solution provided in this disclosure can obtain preset basic navigation prompts and use these prompts to guide the first language model to parse the input command and obtain key navigation information. Therefore, it can improve the efficiency and accuracy of parsing the input command and reduce the user interaction threshold, thereby improving navigation accuracy and user experience.

[0138] like Figure 5 As shown above, in the above Figure 2 Based on the illustrated embodiment, step 202 above may include the following steps:

[0139] Step 2023: Obtain the preset waypoint constraint prompts.

[0140] In some examples, the waypoint constraint prompts mentioned above can be set at the vehicle factory or can be user-defined. The waypoint constraint prompts are used to guide the large model to parse the user's input commands to obtain implicit waypoint constraints.

[0141] For example, when setting waypoint constraint prompts, multi-dimensional attribute information of implicit waypoints can be considered. The aforementioned waypoint constraint prompts can include at least two of the following: type information, geospatial information, and time information, and may also include fields such as quality information, cost information, and facilities and services information. Type information refers to the type of implicit waypoint, common types include attractions, restaurants, gas stations, hospitals, shopping malls, and schools. Different types of implicit waypoints correspond to different user needs; when planning a travel route, users will focus on attractions, while during long-distance driving, they will be more interested in gas stations. Quality information reflects the overall quality of the current implicit waypoint and can include at least one of the following: user ratings, number of reviews, and reputation tags. Geospatial information controls the rationality and convenience of route planning and can include at least one of the following: distance from the starting point, destination, or main route, geographical location, and region. Time information can include at least one of the following: operating hours, arrival time, and length of stay. Cost information can include average per capita consumption price or charging standards. Facilities and services information can include supporting facilities and services.

[0142] For example, the following is an exemplary waypoint constraint prompt provided in an embodiment of this disclosure:

[0143] {

[0144] "fromAndTo":"starting point; ending point",

[0145] "mode": Path planning strategy (integer, default 0 means speed priority),

[0146] "passedByPOIs":[

[0147] {

[0148] "name":"Pathway Name",

[0149] "type":"Type of waypoint (e.g., tourist attractions, gas stations, hospitals, etc.)",

[0150] "rating":"rating requirement (e.g., ≥4.5)",

[0151] "distance":"Distance requirement from the main route (e.g., ≤2 km)",

[0152] "opening Hours": "Business hours requirements (e.g., 09:00-18:00)",

[0153] "priceRange": "Price range requirement (e.g., 50-100 yuan per person)"

[0154] }],

[0155] "avoidPolygons":["Avoidance Zone 1","Avoidance Zone 2",...],

[0156] "avoidRoad": "Avoid the name of the road".

[0157] }

[0158] It should be noted that the above-mentioned waypoint constraint prompts are merely illustrative examples and are not intended to limit the scope of this disclosure.

[0159] Step 2024: Using the path constraint prompts, guide the second language model to parse the input instructions and obtain the implicit path constraint conditions.

[0160] In some examples, the second large language model mentioned above may be the same as or different from the first large language model. The second large language model may be a Generative Pre-trained Transformer (GPT) large model, a Deepseek large model, or other large language models.

[0161] For example, suppose a user inputs the following command at 10:00 AM from Xinjiekou: "I want to get to Zhongshan Wharf at 1:00 PM, passing through Laomendong, and find a restaurant with a rating of at least 4.5 and an average cost of 30-50 yuan per person for lunch." The second largest language model is GPT-4. When guiding the GPT-4 model to parse the input command using the waypoint constraint prompts, the waypoint constraint prompts and the input command can be combined and input into the GPT-4 model. The GPT-4 model then outputs implicit waypoint constraints, which are as follows:

[0162] {

[0163] "fromAndTo":"Xinjiekou; Zhongshan Wharf",

[0164] "mode":0,

[0165] "passedByPOIs":[

[0166] {

[0167] "name":"",

[0168] "type":"restaurant",

[0169] "rating":"≥4.5",

[0170] "distance":"≤2 kilometers",

[0171] "opening Hours":"10:00-13:00",

[0172] "priceRange": "30-50 yuan per person"

[0173] }],

[0174] "avoidPolygons":[],

[0175] "avoidRoad": "Zhongshan Road"

[0176] }

[0177] It should be noted that when using waypoint constraint prompts to guide the second language model in parsing the input command, if the specific value of a certain field in the waypoint constraint prompt is not parsed from the input command, the preset value of that field in the waypoint constraint prompt can be used as the threshold of the corresponding field in the implicit waypoint constraint condition. For example, in the above example, the input command does not specify a distance constraint condition, so the preset value of the distance constraint field "≤2 km" in the waypoint constraint prompt can be used as the threshold "≤2 km" for the distance constraint condition "distance" in the implicit waypoint constraint condition.

[0178] The technical solution provided in this disclosure can obtain preset pathpoint constraint prompts and use these prompts to guide the second language model to parse the input command and obtain implicit pathpoint constraint conditions. Therefore, while improving the parsing efficiency and accuracy of the input command, it can both understand the user's hidden intentions and ensure that the parsed pathpoint constraint conditions are personalized and in line with user preferences. This makes the implicit pathpoints obtained based on the implicit pathpoint constraint conditions more in line with user needs.

[0179] In some embodiments, the initial planned path includes a navigation start point, a navigation end point, and at least one explicit waypoint; such as Figure 6 As shown above, in the above Figure 2 Based on the illustrated embodiment, step 205 above may include the following steps:

[0180] Step 2051: Based on a preset algorithm, determine the arrangement order of at least one explicit waypoint and the first implicit waypoint.

[0181] In some examples, the above-mentioned preset algorithm is a greedy algorithm (Traveling Salesman Problem Greedy Algorithm, TSP). First, obtain the path point sequence of at least one explicit waypoint and the first implicit waypoint. Then, based on the TSP greedy algorithm, starting from the vehicle's current starting point, calculate the distance to all waypoints in the path point sequence, select the closest waypoint as the next waypoint, and repeat the above process until all waypoints in the path point sequence have been traversed. This yields the arrangement of at least one explicit waypoint and the first implicit waypoint. This arrangement is the driving order of the vehicle through each waypoint in the path point sequence, thus ensuring that the total driving distance of the vehicle through at least one explicit waypoint and the first implicit waypoint is minimized.

[0182] In some embodiments, step 2051 may specifically include: in response to a user specifying the order priority of at least one explicit waypoint, determining the arrangement order of at least one explicit waypoint and a first implicit waypoint based on a preset algorithm and the order priority of at least one explicit waypoint.

[0183] In some examples, since the order priority of the explicit waypoints specified by the user is higher than the system-optimized order, the order of at least one explicit waypoint can be determined based on the order priority of at least one explicit waypoint specified by the user. Without changing the order of at least one explicit waypoint, the first implicit waypoint can be sorted based on the TSP greedy algorithm. That is, the first implicit waypoint can be inserted based on the order of at least one explicit waypoint, and finally the order of at least one explicit waypoint and the first implicit waypoint can be obtained.

[0184] For example, taking at least one explicit waypoint including Xinjiekou and Laomendong, and the first implicit waypoint being Kexiang, when the user specifies the priority of the explicit waypoints as "from Xinjiekou to Laomendong", the order of the explicit waypoints is determined to be "Xinjiekou → Laomendong" based on the priority of the explicit waypoints. Based on the TSP greedy algorithm, it is calculated that the distance from Xinjiekou to Laomendong is shorter than the distance from Xinjiekou to Kexiang in Laomendong. Therefore, the implicit waypoint "Kexiang" can be arranged after Laomendong, thus obtaining the order of at least one explicit waypoint and the first implicit waypoint as "Xinjiekou → Laomendong → Kexiang".

[0185] Based on the above embodiments, when the user specifies the order priority of at least one explicit waypoint, the arrangement order of at least one explicit waypoint and the first implicit waypoint can be determined based on a preset algorithm and the order priority of at least one explicit waypoint. Therefore, it can not only meet the user's needs, but also avoid detour problems caused by random arrangement, thereby saving vehicle travel time.

[0186] Step 2052: Generate a fusion planning path based on the arrangement of at least one explicit waypoint and the first implicit waypoint, the navigation start point, and the navigation end point.

[0187] In some examples, a complete set of waypoints can be established, including at least one explicit waypoint, a first implicit waypoint sequence, a navigation start point, and a navigation end point. First, the order of the at least one explicit waypoint, the first implicit waypoint sequence, the navigation start point, and the navigation end point is determined. Then, based on this order, all waypoints in the complete set are concatenated to obtain the merged planned path. Afterward, this merged planned path can be converted into standard navigation interface parameters.

[0188] For example, the following is an exemplary standard navigation interface parameter:

[0189] List <latlonpoint>waypoints=new ArrayList<>();

[0190] waypoints.add(geocode("home"));

[0191] waypoints.addAll(geocodeList("restaurant"));

[0192] waypoints.add(geocode("company"));

[0193] DriveRouteQuery query=new

[0194] DriveRouteQuery(fromAndTo,mode,waypoints,null,null);

[0195] The technical solution provided in this disclosure, based on a preset algorithm, determines the arrangement order of at least one explicit waypoint and the first implicit waypoint, and generates a fusion planning path based on the arrangement order of at least one explicit waypoint and the first implicit waypoint, the navigation start point, and the navigation end point. Therefore, it can ensure that the generated fusion planning path meets the potential needs of users and avoid detour problems caused by random arrangement, thereby improving vehicle navigation efficiency and user experience.

[0196] In some embodiments, such as Figure 7 As shown above, in the above Figure 1 Based on the illustrated embodiment, the following steps may also be included:

[0197] Step 206: Obtain the first waiting time corresponding to the first implicit waypoint.

[0198] The first time to be used includes the travel time to reach the first implicit waypoint and / or the time spent at the first implicit waypoint.

[0199] In some examples, traffic data can be acquired in real time at preset intervals. This traffic data can include current road congestion, traffic flow, speed limits, lane control information, etc. Based on the traffic data, the travel time to the first implicit waypoint is calculated. The historical dwell time at the first implicit waypoint can be obtained from third-party software as the dwell time at the first implicit waypoint. Furthermore, the dwell time at the second implicit waypoint can be adjusted appropriately based on whether the current time is during peak hours.

[0200] Step 207: In response to the first waiting time being greater than the first actual remaining time, output the second prompt message.

[0201] The second prompt message is used to ask the user whether to choose to change the implicit waypoint.

[0202] In some examples, the first actual remaining time can be calculated based on the current time and the time constraint in the implicit waypoint constraint. For example, if the current time is 13:30 and the time constraint in the implicit waypoint constraint is before 14:30, the first actual remaining time is 60 minutes.

[0203] In some examples, the second prompt information may be a voice prompt or a text prompt. When the second prompt information is a text prompt, outputting the second prompt information includes: displaying the text prompt information on the vehicle's display screen (e.g., the central control screen); when the second prompt information is a voice prompt, outputting the second prompt information includes: playing the voice prompt information through the vehicle's microphone.

[0204] For example, consider a first waiting time of 70 minutes and a first actual remaining time of 60 minutes. Since the first waiting time is longer than the first actual remaining time, the remaining navigation time may be insufficient due to road congestion or other reasons. In this case, a second prompt message can be output: "Please confirm whether to change the implicit waypoint; Yes, No", to prompt the user whether to choose to change the implicit waypoint.

[0205] Step 208: In response to the confirmation operation of the second prompt information, the first implicit waypoint is replaced with the second implicit waypoint.

[0206] The second implicit waypoint is determined based on the implicit waypoint constraint conditions.

[0207] In some examples, the second implicit path point can be any implicit path point other than the first implicit path point in the candidate path point set obtained in the above embodiments. For determining the second implicit path point based on implicit path point constraints, please refer to the detailed explanation of determining the first implicit path point based on implicit path point constraints in the above embodiments; this disclosure will not repeat that detail.

[0208] Step 209: Generate a fused planning path based on the second implicit waypoint and the initial planned path.

[0209] In some examples, the TSP greedy algorithm can be used to insert a second implicit waypoint into the initial planned path to generate a merged planned path. The start and end nodes in the merged planned path are the same as those in the initial planned path.

[0210] In some embodiments, such as Figure 8 As shown above, in the above Figure 7 Based on the illustrated embodiment, the initial planned path includes a first explicit waypoint; step 209 may specifically include the following:

[0211] Step 2091: Obtain the second waiting time corresponding to the second implicit waypoint.

[0212] The second time to be used includes the travel time to reach the second implicit waypoint and / or the time spent at the second implicit waypoint.

[0213] In some examples, traffic data can be acquired in real time at preset intervals. This traffic data can include current road congestion, traffic flow, speed limits, lane control information, etc. Based on the traffic data, the travel time to the second implicit waypoint is calculated. Historical dwell times at the second implicit waypoint can be obtained from third-party software as the dwell time at that waypoint. Furthermore, the dwell time at the second implicit waypoint can be adjusted appropriately based on whether the current time is during peak hours.

[0214] Step 2092: In response to the second waiting time being greater than the second actual remaining time, output the third prompt message.

[0215] The third prompt message is used to ask the user whether to change the explicit waypoint.

[0216] In some examples, the second actual remaining time can be calculated based on the current time and the time constraint in the implicit waypoint constraint. For example, if the current time is 14:10 and the time constraint in the implicit waypoint constraint is before 14:30, the second actual remaining time is 20 minutes.

[0217] In some examples, the aforementioned third prompt information can be a voice prompt or a text prompt. When the third prompt information is a text prompt, outputting the third prompt information includes: displaying the text prompt information on the vehicle's display screen (e.g., the central control screen); when the third prompt information is a voice prompt, outputting the third prompt information includes: playing the voice prompt information through the vehicle's microphone.

[0218] For example, let's take a second waiting time of 30 minutes and a first actual remaining time of 20 minutes. Since the second waiting time is longer than the second actual remaining time, the remaining navigation time may be insufficient due to road congestion or other reasons. In this case, a third prompt message can be output: "Please confirm whether to change the explicit waypoint; Yes, No", to prompt the user whether to choose to change the explicit waypoint.

[0219] Step 2093: In response to the confirmation operation of the third prompt information, the first explicit waypoint is replaced with the second explicit waypoint.

[0220] In some examples, a second explicit waypoint can be determined based on a geographic knowledge graph to replace the first explicit waypoint. When the user confirms the change, the first explicit waypoint is replaced with the second explicit waypoint. At this point, the initial planned route needs to be regenerated based on the navigation key information, including the navigation start point, navigation key points, and the second explicit waypoint. For example, the first explicit waypoint "Yangtze River Avenue" can be replaced with the second explicit waypoint "Linjiang Avenue".

[0221] Step 2094: Generate a fused planning path based on the second implicit waypoint and the initial planning path including the second explicit waypoint.

[0222] In some examples, the TSP greedy algorithm can be used to insert a second implicit waypoint into the regenerated initial planned path, which includes the second explicit waypoint, to generate a merged planned path. The start and end nodes in the merged planned path are the same as those in the initial planned path.

[0223] The technical solution provided in this disclosure can obtain the waiting time of implicit waypoints in real time. When the waiting time exceeds the actual remaining time of the route planning, the implicit waypoints can be replaced after user confirmation. If the replaced implicit waypoints still cannot meet the time requirements, the explicit waypoints can be adjusted after user confirmation. Therefore, it can not only achieve dynamic adjustment of the fused route planning by monitoring the vehicle in real time, but also avoid blindly modifying the user's intentions through user confirmation. This ensures that the navigation planning of the vehicle in complex scenarios meets the user's various constraints, thus significantly improving navigation efficiency.

[0224] Exemplary device

[0225] Figure 9 This is a schematic diagram of a path planning generation apparatus provided as an exemplary embodiment of the present disclosure. The apparatus can be installed in electronic devices such as terminal devices and servers, or on objects such as vehicles, to execute the path planning generation method of any of the above embodiments of the present disclosure.

[0226] like Figure 9 As shown, the above-mentioned device 300 includes:

[0227] The first acquisition module 301 is used to acquire input commands from the user inside the vehicle;

[0228] The first parsing module 302 is used to parse the input command to obtain navigation key information and implicit waypoint constraints for path planning;

[0229] The first planning module 303 is used to generate an initial planned path based on the navigation key information;

[0230] The first determining module 304 is used to determine the first implicit path point based on the implicit path point constraint conditions;

[0231] The second planning module 305 is used to generate a fusion planning path for the vehicle based on the first implicit waypoint and the initial planning path.

[0232] In one possible implementation, the first determining module 304 is specifically used to obtain a set of candidate waypoints based on the implicit waypoint constraints.

[0233] Based on the set of candidate waypoints, the first implicit waypoint is determined.

[0234] In one possible implementation, the implicit waypoint constraint includes a first constraint; the first determining module 304 is specifically used to perform implicit waypoint search based on the distance constraint in the first constraint and the initial planned path to obtain a basic search area;

[0235] Determine the remaining time required for the vehicle route planning, and determine the vehicle's drivable range based on the remaining time required and the vehicle's speed;

[0236] Based on the drivable range and the basic search area, a feasible search range is determined;

[0237] Based on the time constraint and type constraint in the first constraint, implicit path points are searched within the feasible search range to obtain a set of candidate path points.

[0238] In one possible implementation, the first determining module 304 is specifically used to calculate the comprehensive score of the multiple candidate implicit path points in response to the candidate path point set including multiple candidate implicit path points.

[0239] The first implicit path point is determined based on the combined scores of multiple candidate implicit path points.

[0240] In one possible implementation, the implicit waypoint constraint further includes a second constraint; the second constraint includes, but is not limited to, at least one of the following: a price constraint, a user rating constraint; the first determining module 304 is specifically used to filter the candidate waypoint set based on the second constraint to obtain an updated candidate waypoint set.

[0241] In one possible implementation, the device 300 further includes:

[0242] The constraint adjustment module is used to adjust the constraint conditions of the implicit path points in response to the fact that the set of candidate path points does not include candidate implicit path points;

[0243] The first determining module 304 is further configured to determine the candidate path point set based on the adjusted implicit path point constraints.

[0244] or,

[0245] The first output module is used to output a first prompt message in response to the fact that the candidate waypoint set does not include candidate implicit waypoints; the first prompt message is used to prompt the user that no implicit waypoint that meets the user's needs has been found.

[0246] In one possible implementation, the first parsing module 302 is specifically used to obtain preset basic navigation prompt words;

[0247] Using the basic navigation prompts, the first language model is guided to parse the input command to obtain the key navigation information;

[0248] The key navigation information includes at least: navigation start point and navigation end point.

[0249] In one possible implementation, the first parsing module 302 is specifically used to obtain preset waypoint constraint prompts;

[0250] Using the path point constraint prompts, the second language model is guided to parse the input command and obtain the implicit path point constraint conditions.

[0251] In one possible implementation, the initial planned path includes a navigation start point, a navigation end point, and at least one explicit waypoint; the second planning module 305 is specifically used to determine the arrangement order of the at least one explicit waypoint and the first implicit waypoint based on a preset algorithm;

[0252] The fusion planning path is generated based on the arrangement order of the at least one explicit waypoint and the first implicit waypoint, the navigation start point, and the navigation end point.

[0253] In one possible implementation, the second planning module 305 is specifically used to determine the arrangement order of the at least one explicit waypoint and the first implicit waypoint based on the preset algorithm and the order priority of the at least one explicit waypoint in response to the user specifying the order priority of the at least one explicit waypoint.

[0254] In one possible implementation, the device 300 further includes:

[0255] The second acquisition module is used to acquire the first waiting time corresponding to the first implicit waypoint; the first waiting time includes the travel time to reach the first implicit waypoint and / or the stay time at the first implicit waypoint.

[0256] The second output module is used to output a second prompt message in response to the first waiting time being greater than the first actual remaining time; the second prompt message is used to prompt the user whether to choose to change the implicit waypoint;

[0257] A first replacement module is configured to replace the first implicit path point with a second implicit path point in response to a confirmation operation of the second prompt information; wherein the second implicit path point is determined based on the implicit path point constraint conditions;

[0258] The second planning module 305 is also used to generate the fused planning path based on the second implicit waypoint and the initial planning path.

[0259] In one possible implementation, the initial planned path includes a first explicit waypoint; the device 300 further includes:

[0260] The third acquisition module is used to acquire the second waiting time corresponding to the second implicit waypoint; the second waiting time includes the travel time to reach the second implicit waypoint and / or the stay time at the second implicit waypoint;

[0261] The third output module is used to output a third prompt message in response to the second waiting time being greater than the second actual remaining time; the third prompt message is used to prompt the user whether to choose to change the explicit waypoint.

[0262] The second replacement module is used to replace the first explicit waypoint with the second explicit waypoint in response to the confirmation operation of the third prompt information.

[0263] The second planning module 305 is specifically used to generate the fused planning path based on the second implicit waypoint and the initial planning path including the second explicit waypoint.

[0264] The beneficial technical effects corresponding to the exemplary embodiments of this device can be found in the corresponding beneficial technical effects of the exemplary method section above, and will not be repeated here.

[0265] Exemplary electronic devices

[0266] Figure 10 A structural diagram of an electronic device provided in an embodiment of this disclosure includes at least one processor 111 and a memory 112.

[0267] The processor 111 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0268] The memory 112 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 111 may execute one or more computer program instructions to implement the path planning generation method and / or other desired functions of the various embodiments of this disclosure described above.

[0269] In one example, the electronic device 11 may also include an input device 113 and an output device 114, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0270] The input device 113 may include various sensors, including but not limited to: a distance sensor for detecting the distance between a target object and the vehicle; an image sensor for acquiring information about the vehicle's surrounding environment. In some examples, the input device may also include a pressure sensor for detecting seat pressure to determine the presence and location of passengers; a temperature sensor for monitoring the temperature inside the cabin; a humidity sensor for monitoring the humidity inside the cabin to assist in regulating the in-vehicle environment; an air quality sensor for monitoring in-vehicle air quality, such as carbon dioxide and volatile organic compounds (VOCs); a light sensor for detecting the intensity of light inside and outside the vehicle; an acceleration sensor for detecting changes in the vehicle's acceleration; a distance sensor for detecting the distance between the vehicle and other objects; a touchscreen sensor for interaction with the vehicle's infotainment system; biometric sensors, such as fingerprint recognition and facial recognition; a heart rate monitor for monitoring the driver's heart rate; a sound sensor for voice recognition and interaction to enable voice control; a seat sensor for monitoring seat usage, such as whether the seat is occupied and the passenger's body size; and wireless communication sensors, such as Bluetooth and Wi-Fi, for connecting to smart devices to achieve data transmission and remote control. In addition to the examples given above, the input device may include more or fewer sensors, which will not be elaborated here.

[0271] The output device 114 can output various information or signals to other hardware or devices, which may include displays, car audio systems, seats, windows, steering wheels, communication networks, and their connected remote output devices. The displays may include multiple different displays such as a driver's side display, a passenger side display, and a rear-seat display. The car audio system may include multiple speakers located in different positions within the vehicle cabin, and each display or speaker can operate independently.

[0272] Of course, for the sake of simplicity, Figure 10 Only some of the components of the electronic device 11 relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 11 may include any other suitable components depending on the specific application.

[0273] Exemplary computer program products and computer-readable storage media

[0274] In addition to the methods and apparatus described above, embodiments of this disclosure may also provide a computer program product, including computer program instructions that, when executed by a processor, cause the processor to perform the steps of the path planning generation method described in the "Exemplary Methods" section above.

[0275] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of embodiments of this disclosure. These programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0276] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the path planning generation methods of the various embodiments of this disclosure described in the "Exemplary Methods" section above.

[0277] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, but is not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0278] The basic principles of this disclosure have been described above with reference to specific embodiments. However, the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0279] Various modifications and variations can be made to this disclosure without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, this disclosure is also intended to include such modifications and variations.< / latlonpoint>

Claims

1. A method for generating a planned path, comprising: Obtain input commands from users inside the vehicle; The input instructions are parsed to obtain key navigation information and implicit waypoint constraints for path planning; Based on the aforementioned key navigation information, an initial planned path is generated; Based on the implicit waypoint constraints, the first implicit waypoint is determined; Based on the first implicit waypoint and the initial planned path, a fusion planned path for the vehicle is generated.

2. The method according to claim 1, wherein, The determination of the first implicit pathpoint based on the implicit pathpoint constraint includes: Based on the implicit waypoint constraints, a set of candidate waypoints is obtained; Based on the set of candidate waypoints, the first implicit waypoint is determined.

3. The method according to claim 2, wherein, The implicit waypoint constraint includes a first constraint; the process of obtaining a candidate waypoint set based on the implicit waypoint constraint includes: Based on the distance constraint in the first constraint and the initial planned path, an implicit waypoint search is performed to obtain the basic search area; Determine the remaining time required for the vehicle route planning, and determine the vehicle's drivable range based on the remaining time required and the vehicle's speed; Based on the drivable range and the basic search area, a feasible search range is determined; Based on the time constraint and type constraint in the first constraint, implicit path points are searched within the feasible search range to obtain a set of candidate path points.

4. The method according to claim 2, wherein, The step of determining the first implicit pathpoint based on the candidate pathpoint set includes: In response to the candidate path point set including multiple candidate implicit path points, a comprehensive score is calculated for each of the multiple candidate implicit path points; The first implicit path point is determined based on the combined scores of multiple candidate implicit path points.

5. The method according to claim 3, wherein, The implicit waypoint constraint also includes a second constraint; the second constraint includes, but is not limited to, at least one of the following: a price constraint, a user rating constraint; Based on the time and type constraints in the first constraint, implicit path points are searched within the feasible search range to obtain a set of candidate path points, including: Based on the second constraint, the set of candidate waypoints is filtered to obtain an updated set of candidate waypoints.

6. The method according to claim 3 or 5, after searching for implicit path points in the feasible search range based on the time constraint and type constraint in the first constraint to obtain a set of candidate path points, the method further includes: In response to the fact that the candidate waypoint set does not include candidate implicit waypoints, the constraints on the implicit waypoints are adjusted. The candidate waypoint set is determined based on the adjusted implicit waypoint constraints; or, In response to the fact that the set of candidate waypoints does not include candidate implicit waypoints, a first prompt message is output; The first prompt message is used to inform the user that no implicit path point that meets the user's needs has been found.

7. The method according to claim 1, wherein, The process of parsing the input command to obtain key navigation information for path planning includes: Retrieve preset basic navigation prompts; Using the basic navigation prompts, the first language model is guided to parse the input command to obtain the key navigation information; The key navigation information includes at least: navigation start point and navigation end point.

8. The method according to claim 1, wherein, The process of parsing the input command to obtain key navigation information and implicit waypoint constraints for path planning includes: Retrieve preset waypoint constraint prompts; Using the path point constraint prompts, the second language model is guided to parse the input command and obtain the implicit path point constraint conditions.

9. The method according to claim 1, wherein, The initial planned path includes a navigation start point, a navigation end point, and at least one explicit waypoint; The step of generating the fused planned path for the vehicle based on the first implicit waypoint and the initial planned path includes: Based on a preset algorithm, the arrangement order of the at least one explicit waypoint and the first implicit waypoint is determined; The fusion planning path is generated based on the arrangement order of the at least one explicit waypoint and the first implicit waypoint, the navigation start point, and the navigation end point.

10. The method according to claim 9, wherein, The step of determining the arrangement order of the at least one explicit waypoint and the first implicit waypoint based on a preset algorithm includes: In response to the user specifying the order priority of the at least one explicit waypoint, the arrangement order of the at least one explicit waypoint and the first implicit waypoint is determined based on the preset algorithm and the order priority of the at least one explicit waypoint.

11. The method according to claim 1, further comprising: Obtain the first waiting time corresponding to the first implicit waypoint; The first time to be used includes the travel time to reach the first implicit waypoint and / or the time spent at the first implicit waypoint; In response to the first pending time being greater than the first actual remaining time, a second prompt message is output. The second prompt message is used to ask the user whether to choose to change the implicit waypoint; In response to the confirmation operation of the second prompt information, the first implicit path point is replaced with the second implicit path point; wherein the second implicit path point is determined based on the implicit path point constraint conditions; The fused planning path is generated based on the second implicit waypoint and the initial planned path.

12. The method of claim 11, wherein the initial planned path includes a first explicit waypoint; The step of generating the fused planning path based on the second implicit waypoint and the initial planned path includes: Obtain the second waiting time corresponding to the second implicit waypoint; the second waiting time includes the travel time to reach the second implicit waypoint and / or the stay time at the second implicit waypoint; In response to the second waiting time being greater than the second actual remaining time, a third prompt message is output; the third prompt message is used to prompt the user whether to choose to change the explicit waypoint. In response to the confirmation operation of the third prompt information, the first explicit waypoint is replaced with the second explicit waypoint; The fused planning path is generated based on the second implicit waypoint and the initial planned path including the second explicit waypoint.

13. A path planning generation device, comprising: The first acquisition module is used to acquire input commands from users inside the vehicle; The first parsing module is used to parse the input command to obtain key navigation information and implicit waypoint constraints for path planning; The first planning module is used to generate an initial planned path based on the navigation key information; The first determining module is used to determine the first implicit path point based on the implicit path point constraint conditions; The second planning module is used to generate a fusion planning path for the vehicle based on the first implicit waypoint and the initial planning path.

14. A computer-readable storage medium storing a computer program for performing the path generation method according to any one of claims 1-12.

15. An electronic device, the electronic device comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method for generating a planned path as described in any one of claims 1-12.

Images