Path planning method and device, vehicle and storage medium

Abstract

The embodiment of the invention relates to the technical field of vehicles, and discloses a path planning method and device, a vehicle and a storage medium, and the method comprises the steps: obtaining first path intention information of a user; according to the first path intention information, at least one first path planning element and a weight coefficient corresponding to the at least one first path planning element are determined, and the size of each weight coefficient is used for indicating the strength of the demand of the user for the corresponding first path planning element; and determining a target path according to the at least one first path planning element and the weight coefficient of the at least one first path planning element. By applying the technical scheme of the invention, the route planning of a complex and dynamic travel scene meeting the user requirements can be realized.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of vehicle technology, and specifically to a path planning method, device, vehicle, and storage medium. Background Art

[0002] With the rapid development of intelligent transportation and mobile internet technologies, route planning has become a core requirement for vehicle users. Currently, route planning primarily focuses on optimizing a single objective, such as calculating the shortest or fastest path, and relies on static map data and pre-set rules to generate routes.

[0003] The current path planning is unable to flexibly adapt to complex and dynamic travel scenarios. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide a path planning method, device, vehicle and storage medium to solve the technical problem in the prior art of path planning that cannot flexibly adapt to complex and dynamic travel scenarios.

[0005] According to one aspect of an embodiment of the present invention, a path planning method is provided, the method comprising:

[0006] Obtain the user's first path intention information;

[0007] Determining, based on the first route intention information, at least one first route planning element and a weight coefficient corresponding to each of the at least one first route planning element, wherein the magnitude of each weight coefficient indicates the strength of the user's demand for the corresponding first route planning element;

[0008] A target path is determined according to the at least one first path planning element and a weight coefficient of the at least one first path planning element.

[0009] According to another aspect of an embodiment of the present invention, a path planning device is provided, the device comprising:

[0010] An acquisition module is used to obtain the user's first path intention information;

[0011] a first determining module, configured to determine, based on the first route intention information, at least one first route planning element and a weight coefficient corresponding to each of the at least one first route planning element, wherein the magnitude of each weight coefficient indicates the strength of a user's demand for the corresponding first route planning element;

[0012] The second determining module is configured to determine a target path according to the at least one first path planning element and a weight coefficient of the at least one first path planning element.

[0013] According to another aspect of an embodiment of the present invention, a vehicle is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0014] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the path planning method as described above.

[0015] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores at least one executable instruction. When the executable instruction is executed on a path planning device / vehicle, the path planning device / vehicle performs the operation of the path planning method as described above.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is provided, comprising a computer program, which, when executed by a processor, enables a path planning device / vehicle to perform the operations of the above method.

[0017] The embodiment of the present invention analyzes the user's first path intention information to determine the corresponding first path planning elements and their weight coefficients, thereby accurately capturing the user's core travel demands, quantifying the strength of the demands for different elements through the weight coefficients, avoiding simplistic processing of complex intentions, and making reasonable trade-offs based on weights when there are multiple target demands to plan a path that is more in line with the user's true intentions. At the same time, the flexibility and intelligence level of path planning are improved to better adapt to dynamic and complex travel scenarios.

[0018] The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to more clearly understand the technical means of the embodiments of the present invention, they can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiments of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the drawings. In the drawings:

[0020] Figure 1 A schematic diagram of the path planning principle provided by the present invention is shown;

[0021] Figure 2 A flow chart showing a first embodiment of a path planning method provided by the present invention is shown;

[0022] Figure 3 A flow chart showing a second embodiment of the path planning method provided by the present invention is shown;

[0023] Figure 4 A flow chart showing a third embodiment of the path planning method provided by the present invention is shown;

[0024] Figure 5 A schematic structural diagram of an embodiment of a path planning device provided by the present invention is shown;

[0025] Figure 6 A schematic structural diagram of an embodiment of a vehicle provided by the present invention is shown. DETAILED DESCRIPTION

[0026] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0027] With the rapid development of intelligent transportation and mobile Internet technologies, route planning has become the core reliance of users' travel. Its technical architecture relies on geographic information systems, real-time traffic data collection and analysis technologies, and current route search algorithms to realize basic functions.

[0028] Current route planning primarily focuses on single-objective optimization, such as calculating the shortest or fastest path, and relies on static map data and preset rules to generate routes. However, as user travel scenarios become increasingly complex, current technologies face the following technical issues:

[0029] 1) The static preference setting mode is rigid, requiring users to manually select limited options such as "shortest distance" and "avoid congestion" in advance. This mode cannot flexibly adapt to complex and dynamic travel scenarios and is difficult to meet personalized needs;

[0030] 2) There are defects in handling multi-objective conflicts. When users put forward multiple conflicting requirements at the same time, there is a lack of effective dynamic trade-off mechanism. The route can only be generated by simply weighting or directly ignoring some requirements, resulting in a large deviation between the planning results and the user's actual intentions.

[0031] 3) The natural language interaction capability is weak. Users cannot describe complex intentions in everyday language, and the route cannot be adjusted dynamically in consultation with users based on real-time traffic conditions, which further limits the practicality and intelligence level of path planning.

[0032] Based on the above technical problems, the technical concept of the present invention is as follows: when faced with problems such as the inability of static preference settings in existing technologies to cope with complex needs, the lack of multi-target conflict processing, and weak natural language interaction capabilities, users realize that the core problem lies in the failure to accurately capture and quantify the user's true intentions: Therefore, by first obtaining the first path intention information, the vague needs can be converted into specific first path planning elements, and each element can be assigned a weight coefficient to quantify the strength of the demand, and then the target path can be determined based on these elements and weights. By capturing the intention information, the limitations of static options can be broken through, and the weight coefficient can be used to clarify the demand priority to deal with multi-target conflicts, and ultimately make the planned path more in line with the user's complex and dynamic demands.

[0033] The following is about the above technical conception: Figure 1 The schematic diagram of the path planning principle provided by the present invention is shown in FIG. Figure 1 As shown, the schematic diagram includes: a natural language input module, a large language model (LLM) intent parsing engine, a multi-objective path optimization engine, a route description generator, and a dynamic negotiation feedback module.

[0034] In one possible implementation, the natural language input module is used to obtain user voice, such as "I'll be at the airport at 5 o'clock, I'll refuel on the way and avoid traffic jams." The LLM intent parsing engine is used to extract route planning elements from the voice, such as 5 o'clock, airport, congestion, and refueling, and assign weight coefficients to each element. The multi-objective path optimization engine constructs an objective function based on the elements and weight coefficients. The route description generator generates comparative descriptions of each planned path based on the multiple planned paths generated by the objective function. The dynamic negotiation feedback module is used to parse user feedback information, adjust the weight coefficients of each element, and replan the path.

[0035] In combination with the above embodiments, the technical solution of the present invention is described in detail through specific embodiments. The execution subject of the present invention is a vehicle.

[0036] It should be noted that the following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0037] Figure 2 FIG1 shows a flow chart of a first embodiment of a path planning method provided by the present invention, which is executed by a vehicle. Figure 2 As shown, the method includes the following steps:

[0038] Step 21: Obtain the user's first path intention information;

[0039] In the path planning scenario, the first path intention information may refer to all path-related descriptions expressed by the user through language or behavior when planning the path, including the elements for constructing the path planning and the demand preference (or strength of demand) for each element.

[0040] For example, the first path intention information may be: arrive at the airport at 5 o'clock, refuel on the way, and avoid traffic jams.

[0041] Optionally, step 21 may include the following implementation:

[0042] The first method is to obtain the route intention voice issued by the user through the audio collection unit in the vehicle;

[0043] In this implementation, the vehicle is equipped with built-in audio acquisition units such as microphones and pickups to capture the voice commands related to route planning expressed by users in the car in natural language in real time, and convert these voice signals containing route planning elements such as destination, waypoints, time requirements, road condition preferences, etc. into electrical signals that can be recognized by the vehicle, providing the original route intention voice for subsequent voice recognition, intent analysis and route generation.

[0044] For example, the user voice is: "Go to the shopping mall in the city center", "Help me plan a route to the airport without traffic jams", "Go to the gas station first and fill up the gas, then go home", etc.

[0045] The second method is to obtain the route intention command input by the user through the central control screen in the vehicle;

[0046] In this implementation, users use the vehicle's central control screen to directly transmit route planning-related requirements (such as destination name, passing points, departure time, road condition preferences, etc.) to the vehicle through input methods such as clicking, entering text, and selecting menus.

[0047] For example, users can manually select the airport location as the destination on the map interface of the central control screen, or enter "XX gas station" in the search box and set it as a waypoint, or select path preferences such as "Avoid congestion" and "Prioritize highway" through the drop-down menu. The information corresponding to these operations will be captured and converted into path intention instructions for path planning, which will serve as the basis for subsequent generation of specific routes.

[0048] It should be understood that the first path intention information includes: path intention voice or path intention instruction.

[0049] Step 22: Determine, based on the first path intention information, at least one first path planning element and a weight coefficient corresponding to each of the at least one first path planning elements;

[0050] The size of each weight coefficient is used to indicate the strength of the user's demand for the corresponding first path planning element;

[0051] In this step, during the path planning process, the user's first path intention information is analyzed, at least one key path planning element is identified, and a corresponding weight coefficient is assigned to each path planning element. The size of these weight coefficients reflects the strength of the user's demand for different elements.

[0052] For example, a higher weight coefficient indicates that the path planning element is more important to the user, and the needs of high-weight elements will be given priority when planning the path.

[0053] Optionally, the route planning elements include any of the following intentions: time, destination, additional tasks, congestion aversion, cost, etc.

[0054] Taking the first path intention information as "arrive at the airport at 5 o'clock, refuel on the way, and avoid too much traffic" as an example, the time is before 5 o'clock, the destination is the airport, and the additional tasks are refueling and congestion.

[0055] Optionally, a possible implementation of step 22 may be: inputting the first path intention information into the first model to obtain at least one first path planning element and a weight coefficient corresponding to each of the at least one first path planning element;

[0056] Among them, the first model is obtained by training the LLM based on multiple historical first path intention information, the path planning elements corresponding to the multiple historical first path intention information, and the weight coefficients corresponding to each path planning element.

[0057] In this step, the first path intention information provided by the user is input into a pre-trained first model, and the first model automatically analyzes and outputs at least one key path planning element and a weight coefficient corresponding to each element.

[0058] For example, at least one first path planning element includes: time T, congestion index C, distance D (e.g., determined based on the current location and destination location), and additional task P. Accordingly, the weight coefficient of T is α, the weight coefficient of C is β, the weight coefficient of D is γ, and the weight coefficient of P is δ.

[0059] Accordingly, in one possible implementation, the training implementation of the first model may be:

[0060] Step 1: Obtain multiple historical path intention information;

[0061] In this implementation, a large amount of historical route intention information can be collected, which may come from the user's past route query records, travel preference data, or navigation logs. Each piece of historical route intention information usually contains a description of the user's travel needs.

[0062] Step 2: For each piece of historical route intention information, the historical route intention information is labeled using a preset method to obtain the route planning elements corresponding to the historical route intention information and the weight coefficients corresponding to the route planning elements;

[0063] In this implementation, for each historical path intention information, a preset annotation method (such as manual annotation or rule matching) is used to identify the implicit path planning elements (such as time, cost, additional tasks, etc.) therein, and a corresponding weight coefficient is assigned to each path planning element.

[0064] For example, if the user emphasizes "shortest time", the weight coefficient of the "time" factor is higher; if the user emphasizes "refueling if possible", the weight coefficient of the additional task of refueling is lower.

[0065] Step 3: Based on multiple historical path intention information, the path planning elements corresponding to the multiple historical path intention information, and the weight coefficients corresponding to each path planning element, the LLM is trained to obtain a first model.

[0066] In this implementation, LLM is used for supervised training based on the labeled dataset (including historical path intention information, corresponding path planning elements and weight coefficients).

[0067] The LLM model forms the first model by learning the mapping relationship between input (historical path intention information) and output (path planning elements and weight coefficients).

[0068] It should be understood that the above-mentioned historical path intention information, combined with the user portrait and the weather information corresponding to the historical path intention information, can also be used to initially adjust the parameters of the first model. When the first model is subsequently applied, the output results will be more accurate.

[0069] Step 23: Determine a target path based on at least one first path planning element and a weight coefficient of at least one first path planning element.

[0070] In this step, based on at least one first path planning element and its corresponding weight coefficient, the vehicle evaluates the priority of each path planning element, and combines real-time road conditions, traffic restrictions and other constraints to use a path planning algorithm (such as an improved A algorithm, Dijkstra, or a machine learning optimization model, etc.) to determine the target path required by the user.

[0071] Furthermore, based on the target path, vehicle navigation is performed so that the vehicle operates on a path that meets the user's needs.

[0072] Optionally, a possible implementation of step 23 is:

[0073] Step 1: determining at least one first path according to at least one first path planning element and a weight coefficient of at least one first path planning element;

[0074] In this implementation, a path planning algorithm is used to calculate several feasible paths, namely, at least one first path, based on the path planning elements and their weight coefficients in the user's needs.

[0075] For example, taking the improved A algorithm as an example, based on at least one first path planning element and at least one weight coefficient of the first path planning element, the objective function can be constructed as: T*α+C*β+D*γ+P*δ.

[0076] Furthermore, the real-time traffic data is integrated to generate multiple Pareto optimal paths, that is, at least one first path.

[0077] Step 2: In response to a selection operation triggered by the user based on the description information of at least one first path, the first path corresponding to the selection operation is determined as the target path.

[0078] In this implementation, descriptive information of candidate routes (such as estimated time, cost, waypoints, etc.) is displayed to the user, and the user selects one of them based on preference. The vehicle then responds to the selection operation, determines the path finally selected by the user as the target path, and applies it to navigation or subsequent planning.

[0079] In addition, the description information of at least one first path may also be a comparative description between various first paths, such as, "Route A is the fastest but passes through a congested section; Route B allows refueling but takes 12 minutes longer."

[0080] The path planning method provided by the embodiment of the present invention obtains the user's first path intention information; based on the first path intention information, determines at least one first path planning element and at least one weight coefficient corresponding to each first path planning element, and the size of each weight coefficient is used to indicate the strength of the user's demand for the corresponding first path planning element; and determines the target path based on at least one first path planning element and at least one weight coefficient of the first path planning element. This technical solution uses the user's first path intention information to determine the corresponding first path planning element and its weight coefficient, which can accurately capture the user's core travel demands, quantify the strength of the demand for different elements through the weight coefficient, avoid simplistic processing of complex intentions, and make reasonable trade-offs based on weights when there are multiple target demands to plan a path that is more in line with the user's true intention, while improving the flexibility and intelligence level of path planning and better adapting to dynamic and complex travel scenarios.

[0081] Based on the above embodiments, Figure 3 FIG2 shows a flow chart of a second embodiment of the path planning method provided by the present invention, which is executed by a vehicle. Figure 3 As shown, before step 2 in the above step 23, the following steps may also be included:

[0082] Step 31: Obtain second route intention information fed back by the user based on at least one description information;

[0083] In this step, after receiving the description information of at least one first path, the user does not select from the at least one first path, but further issues path intention information to readjust or improve the path, which is recorded as second path intention information.

[0084] For example, in the above description, at least one of the description information is: "Route A is the fastest but passes through a congested section; Route B can be refueled but takes 12 minutes longer." At this time, based on this description information, the user issues the instruction "Refueling is important, but don't exceed 6 points."

[0085] Step 32: Adjust the weight coefficient of at least one first path planning element according to the second path intention information;

[0086] In this step, the second path intention information is analyzed and the weight coefficient of at least one first path planning element is readjusted.

[0087] For example, if the second path intention information is “refueling is important, but not more than 6 points”, the weight coefficient δ corresponding to refueling and the weight coefficient α corresponding to time are increased.

[0088] Step 33: Re-determine at least one first path based on the adjusted weight coefficient of at least one first path planning element and at least one first path planning element.

[0089] In this step, after adjusting the weight coefficient of a path planning element, the vehicle will re-run the path planning algorithm based on the new weight combination to dynamically generate an optimized candidate path, that is, at least one adjusted or re-determined first path.

[0090] The implementation principle of step 33 is similar to that of step 23 above, and the adjusted weight coefficient of at least one first path planning element and at least one first path planning element are used to redetermine at least one first path and push the adjusted weight coefficient.

[0091] The path planning method provided by an embodiment of the present invention obtains second path intention information fed back by the user based on at least one descriptive information; adjusts the weight coefficient of at least one first path planning element according to the second path intention information; and redetermines at least one first path based on the adjusted weight coefficient of at least one first path planning element and at least one first path planning element. This technical solution constructs a dynamic interactive feedback channel between the user and the vehicle by obtaining the second path intention information fed back by the user based on the descriptive information, and then adjusts the weight coefficient of the first path planning element and redetermines the planned path. This allows the user to modify the core parameters of the path planning in real time according to actual changes in demand, breaking through the limitations of static preference settings and enabling the vehicle to respond more flexibly to complex and dynamic travel demands. In addition, through targeted adjustment of the weight coefficient, it is possible to accurately balance the priorities between multiple target demands, effectively solving the problem of simply weighting or ignoring some demands when multiple targets conflict, and ensuring that the regenerated path is more in line with the user's current true intention.

[0092] Based on the above embodiments, Figure 4 FIG. 1 shows a flow chart of a third embodiment of a path planning method provided by the present invention, which is executed by a vehicle. Figure 4 As shown, the method may further include the following steps:

[0093] Step 41: When a preset event is detected in front of the vehicle, play or display a first inquiry message;

[0094] The first inquiry information is used to prompt the user whether to take a detour to re-plan the route;

[0095] In this step, the preset event may be an event that affects the vehicle's continued operation along the target path, such as a traffic accident ahead, congestion ahead, temporary closure of the road ahead, etc.

[0096] Furthermore, after detecting the occurrence of the above event, the vehicle's audio unit or the vehicle's large screen plays or displays a first inquiry message prompting the user whether to take a detour to replan the route.

[0097] Step 42: In response to the user's determination operation regarding the first query information, determining an uncompleted path planning element based on the at least one first path planning element and completed path planning elements of the vehicle during driving;

[0098] After the above step 41, there may be two situations: the user agrees to re-plan the route or disagrees to re-plan the route. If the user agrees, step 42 is executed; if the user disagrees, the above-mentioned first route is continued to be applied.

[0099] In this step 42 , based on the at least one first path planning element determined above, it is determined whether the vehicle has completed the path planning element during the formal process.

[0100] For example, taking the additional task of refueling as an example, if it is detected that the vehicle has refueled or entered a gas station or other place during the previous operation, refueling is considered to be a completed path planning element.

[0101] Furthermore, the completed path planning elements in the at least one first path planning element are removed to obtain an uncompleted path planning element.

[0102] Step 43: Determine a second path based on the unfinished path planning elements and the weight coefficients corresponding to the unfinished path planning elements.

[0103] In this step, the path is replanned based on the unfinished path planning elements and the weight coefficients corresponding to the unfinished path planning elements. The implementation principle is similar to the above.

[0104] In addition, there are multiple second paths, and the user can select one at this time, or the user can provide voice feedback again to re-plan the path.

[0105] The path planning method provided by an embodiment of the present invention plays or displays a first inquiry message when a preset event is detected in front of a vehicle, and the first inquiry message is used to prompt the user whether to detour to replan the path; in response to the user's determination operation on the first inquiry message, an unfinished path planning element is determined based on at least one first path planning element and the completed path planning element of the vehicle during driving; and a second path is determined based on the unfinished path planning element and the weight coefficient corresponding to the unfinished path planning element. This technical solution plays or displays a first inquiry message when a preset event is detected in front of the vehicle, prompting the user whether to take a detour, and then determines the second path based on the user's confirmation operation and the completed and unfinished path planning elements and corresponding weight coefficients. This builds a real-time response mechanism for dealing with emergencies, allowing the vehicle to promptly capture preset events in front of the vehicle and actively ask the user, breaking through the current passivity of path planning in emergencies and making path adjustments more timely. In addition, by focusing on the unfinished path planning elements and the corresponding weight coefficients to plan a new path, it fully combines the priority of the user's initial needs, and specifically solves the impact of emergencies on the remaining journey, avoiding the fragmentation of overall needs during re-planning, so that the second path is both adapted to emergencies and meets the core demands of users, greatly improving the dynamic adaptability and user satisfaction of path planning.

[0106] Figure 5 FIG. 1 shows a schematic diagram of the structure of an embodiment of the path planning device provided by the present invention. Figure 5 As shown, the device includes:

[0107] An acquisition module 51 is used to acquire the user's first path intention information;

[0108] A first determination module 52 is configured to determine, based on the first route intention information, at least one first route planning element and a weight coefficient corresponding to each of the first route planning elements, wherein the magnitude of each weight coefficient indicates the user's demand for the corresponding first route planning element;

[0109] The second determining module 53 is configured to determine a target path according to at least one first path planning element and a weight coefficient of at least one first path planning element.

[0110] In one or more embodiments, the second determining module 53 is specifically configured to:

[0111] determining at least one first path based on at least one first path planning element and a weight coefficient of at least one first path planning element;

[0112] In response to a selection operation triggered by a user based on description information of at least one first path, the first path corresponding to the selection operation is determined as a target path.

[0113] In one or more embodiments, in response to a selection operation triggered by a user based on the description information of at least one first path, before determining the first path corresponding to the selection operation as the target path, the second determination module 53 is further configured to:

[0114] Acquire second path intention information fed back by the user based on at least one description information;

[0115] adjusting a weight coefficient of at least one first path planning element according to the second path intention information;

[0116] The at least one first path is re-determined based on the adjusted weight coefficient of the at least one first path planning element and the at least one first path planning element.

[0117] In one or more embodiments, the second determining module 53 is further configured to:

[0118] When a preset event is detected in front of the vehicle, a first inquiry message is played or displayed, where the first inquiry message is used to prompt the user whether to take a detour to re-plan the route;

[0119] In response to a user's determination operation with respect to the first query information, determining an uncompleted path planning element based on the at least one first path planning element and completed path planning elements of the vehicle during driving;

[0120] A second path is determined based on the unfinished path planning elements and the weight coefficients corresponding to the unfinished path planning elements.

[0121] In one or more embodiments, the first determining module 52 is specifically configured to:

[0122] Inputting the first path intention information into the first model to obtain at least one first path planning element and a weight coefficient corresponding to each of the at least one first path planning element;

[0123] Among them, the first model is obtained by training the large language model LLM based on multiple historical first path intention information, the path planning elements corresponding to the multiple historical first path intention information, and the weight coefficients corresponding to each path planning element.

[0124] In one or more embodiments, before inputting the first path intention information into the first model to obtain at least one first path planning element and the weight coefficient corresponding to the at least one first path planning element, the first determination module 52 is further configured to:

[0125] Obtain multiple historical route intention information;

[0126] For each historical path intention information, the historical path intention information is labeled and processed in a preset manner to obtain the path planning elements corresponding to the historical path intention information and the weight coefficients corresponding to the path planning elements;

[0127] The LLM is trained based on multiple historical path intention information, the path planning elements corresponding to the multiple historical path intention information, and the weight coefficients corresponding to the various path planning elements to obtain a first model.

[0128] In one or more embodiments, the acquisition module 51 is specifically configured to:

[0129] Acquire the route intention voice issued by the user through the audio collection unit in the vehicle;

[0130] Alternatively, the user's route intention instructions may be obtained through the vehicle's central control screen;

[0131] The first path intention information includes: path intention voice or path intention instruction.

[0132] It should be noted that it should be understood that the division of the various modules of the above device is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical element, or physically separated. Moreover, these modules can all be implemented in the form of software called by a processing element. They can also all be implemented in the form of hardware. Some modules can also be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. In addition, these modules can all or partly be integrated together or implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0133] From the above, it can be seen that the path planning device provided by the embodiment of the present invention can accurately capture the user's core travel demands by analyzing the user's first path intention information to determine the corresponding first path planning elements and their weight coefficients, quantify the strength of the demands of different elements through weight coefficients, avoid simplistic processing of complex intentions, and make reasonable trade-offs based on weights when there are multiple target demands to plan a path that is more in line with the user's true intentions, while improving the flexibility and intelligence level of path planning to better adapt to dynamic and complex travel scenarios.

[0134] Figure 6 A schematic structural diagram of an embodiment of a vehicle provided by the present invention is shown. Figure 6 As shown, the vehicle may include a processor 62 , a communications interface 64 , a memory 66 , and a communications bus 68 .

[0135] Processor 62, communication interface 64, and memory 66 communicate with each other via communication bus 68. Communication interface 64 is used to communicate with other devices, such as clients or other server network elements. Processor 62 is used to execute program 60, specifically, the steps described in the above method embodiments.

[0136] Specifically, the program 60 may include program code including computer-executable instructions.

[0137] Processor 62 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the vehicle may be of the same type, such as one or more CPUs, or may be of different types, such as one or more CPUs and one or more ASICs.

[0138] The memory 66 is used to store the program 60. The memory 66 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0139] The program 60 can be specifically called by the processor 62 to cause the vehicle to perform the following operations:

[0140] Obtain the user's first path intention information;

[0141] Determining, based on the first path intention information, at least one first path planning element and a weight coefficient corresponding to at least one first path planning element, wherein the magnitude of each weight coefficient indicates the strength of the user's demand for the corresponding first path planning element;

[0142] A target path is determined according to at least one first path planning element and a weight coefficient of at least one first path planning element.

[0143] In one or more embodiments, determining a target path based on at least one first path planning element and a weight coefficient of at least one first path planning element includes:

[0144] determining at least one first path based on at least one first path planning element and a weight coefficient of at least one first path planning element;

[0145] In response to a selection operation triggered by a user based on description information of at least one first path, the first path corresponding to the selection operation is determined as a target path.

[0146] In one or more embodiments, in response to a selection operation triggered by a user based on the description information of at least one first path, before determining the first path corresponding to the selection operation as the target path, the following steps are further performed:

[0147] Acquire second path intention information fed back by the user based on at least one description information;

[0148] adjusting a weight coefficient of at least one first path planning element according to the second path intention information;

[0149] The at least one first path is re-determined based on the adjusted weight coefficient of the at least one first path planning element and the at least one first path planning element.

[0150] In one or more embodiments, further performing:

[0151] When a preset event is detected in front of the vehicle, a first inquiry message is played or displayed, where the first inquiry message is used to prompt the user whether to take a detour to re-plan the route;

[0152] In response to a user's determination operation with respect to the first query information, determining an uncompleted path planning element based on the at least one first path planning element and completed path planning elements of the vehicle during driving;

[0153] A second path is determined based on the unfinished path planning elements and the weight coefficients corresponding to the unfinished path planning elements.

[0154] In one or more embodiments, determining, based on the first path intention information, at least one first path planning element and a weight coefficient corresponding to each of the at least one first path planning elements includes:

[0155] Inputting the first path intention information into the first model to obtain at least one first path planning element and a weight coefficient corresponding to each of the at least one first path planning element;

[0156] Among them, the first model is obtained by training the large language model LLM based on multiple historical first path intention information, the path planning elements corresponding to the multiple historical first path intention information, and the weight coefficients corresponding to each path planning element.

[0157] In one or more embodiments, before inputting the first path intention information into the first model to obtain at least one first path planning element and a weight coefficient corresponding to each of the at least one first path planning element, the method further includes:

[0158] Obtain multiple historical route intention information;

[0159] For each historical path intention information, the historical path intention information is labeled and processed in a preset manner to obtain the path planning elements corresponding to the historical path intention information and the weight coefficients corresponding to the path planning elements;

[0160] The LLM is trained based on multiple historical path intention information, the path planning elements corresponding to the multiple historical path intention information, and the weight coefficients corresponding to the various path planning elements to obtain a first model.

[0161] In one or more embodiments, obtaining the user's first path intention information includes:

[0162] Acquire the route intention voice issued by the user through the audio collection unit in the vehicle;

[0163] Alternatively, the user's route intention instructions may be obtained through the vehicle's central control screen;

[0164] The first path intention information includes: path intention voice or path intention instruction.

[0165] From the above, it can be seen that the vehicle provided by the embodiment of the present invention can accurately capture the user's core travel demands by analyzing the user's first path intention information to determine the corresponding first path planning elements and their weight coefficients, quantify the strength of the demands of different elements through the weight coefficients, avoid simplistic processing of complex intentions, and make reasonable trade-offs based on weights when there are multiple target demands to plan a path that is more in line with the user's true intentions, while improving the flexibility and intelligence level of path planning to better adapt to dynamic and complex travel scenarios.

[0166] An embodiment of the present invention provides a computer-readable storage medium storing at least one executable instruction. When the executable instruction is executed on a path planning device / vehicle, the path planning device / vehicle executes the path planning method in any of the above method embodiments.

[0167] The executable instructions may be used to cause the path planning device / vehicle to perform the following operations:

[0168] Obtain the user's first path intention information;

[0169] Determining, based on the first path intention information, at least one first path planning element and a weight coefficient corresponding to at least one first path planning element, wherein the magnitude of each weight coefficient indicates the strength of the user's demand for the corresponding first path planning element;

[0170] A target path is determined according to at least one first path planning element and a weight coefficient of at least one first path planning element.

[0171] In one or more embodiments, determining a target path based on at least one first path planning element and a weight coefficient of at least one first path planning element includes:

[0172] determining at least one first path based on at least one first path planning element and a weight coefficient of at least one first path planning element;

[0173] In response to a selection operation triggered by a user based on description information of at least one first path, the first path corresponding to the selection operation is determined as a target path.

[0174] In one or more embodiments, in response to a selection operation triggered by a user based on the description information of at least one first path, before determining the first path corresponding to the selection operation as the target path, the following steps are further performed:

[0175] Acquire second path intention information fed back by the user based on at least one description information;

[0176] adjusting a weight coefficient of at least one first path planning element according to the second path intention information;

[0177] The at least one first path is re-determined based on the adjusted weight coefficient of the at least one first path planning element and the at least one first path planning element.

[0178] In one or more embodiments, further performing:

[0179] When a preset event is detected in front of the vehicle, a first inquiry message is played or displayed, where the first inquiry message is used to prompt the user whether to take a detour to re-plan the route;

[0180] In response to a user's determination operation with respect to the first query information, determining an uncompleted path planning element based on the at least one first path planning element and completed path planning elements of the vehicle during driving;

[0181] A second path is determined based on the unfinished path planning elements and the weight coefficients corresponding to the unfinished path planning elements.

[0182] In one or more embodiments, determining, based on the first path intention information, at least one first path planning element and a weight coefficient corresponding to each of the at least one first path planning elements includes:

[0183] Inputting the first path intention information into the first model to obtain at least one first path planning element and a weight coefficient corresponding to each of the at least one first path planning element;

[0184] Among them, the first model is obtained by training the large language model LLM based on multiple historical first path intention information, the path planning elements corresponding to the multiple historical first path intention information, and the weight coefficients corresponding to each path planning element.

[0185] In one or more embodiments, before inputting the first path intention information into the first model to obtain at least one first path planning element and a weight coefficient corresponding to each of the at least one first path planning element, the method further includes:

[0186] Obtain multiple historical route intention information;

[0187] For each historical path intention information, the historical path intention information is labeled and processed in a preset manner to obtain the path planning elements corresponding to the historical path intention information and the weight coefficients corresponding to the path planning elements;

[0188] The LLM is trained based on multiple historical path intention information, the path planning elements corresponding to the multiple historical path intention information, and the weight coefficients corresponding to the various path planning elements to obtain a first model.

[0189] In one or more embodiments, obtaining the user's first path intention information includes:

[0190] Acquire the route intention voice issued by the user through the audio collection unit in the vehicle;

[0191] Alternatively, the user's route intention instructions may be obtained through the vehicle's central control screen;

[0192] The first path intention information includes: path intention voice or path intention instruction.

[0193] From the above, it can be seen that the vehicle / route planning device provided by the embodiment of the present invention can accurately capture the user's core travel demands by analyzing the user's first path intention information to determine the corresponding first path planning elements and their weight coefficients, quantify the strength of the demands of different elements through weight coefficients, avoid simplistic processing of complex intentions, and make reasonable trade-offs based on weights when there are multiple target demands to plan a path that is more in line with the user's true intentions, while improving the flexibility and intelligence level of path planning to better adapt to dynamic and complex travel scenarios.

[0194] An embodiment of the present invention provides a computer program product, including a computer program, which implements the operations of the above-mentioned path planning method when executed by a processor.

[0195] Its implementation principle and technical effects are shown in the above disclosure.

[0196] The above description of the various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced with each other and will not be repeated herein for the sake of brevity.

[0197] The methods disclosed in the various method embodiments provided by the present invention can be arbitrarily combined without conflict to obtain new method embodiments.

[0198] The features disclosed in the various product embodiments provided by the present invention can be arbitrarily combined without conflict to obtain new product embodiments.

[0199] The features disclosed in the various method or device embodiments provided by the present invention can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0200] It should be noted that the computer-readable storage medium may be a ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface mount storage device, an optical disk, or a compact disc read-only memory (CD-ROM). Various vehicles may also include any one or any combination of the above-mentioned memories.

[0201] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0202] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0203] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus necessary general hardware nodes, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, vehicle terminal or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0204] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices, apparatuses, and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0205] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0206] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The algorithm or display provided herein for the steps of the functions specified in the blocks or blocks is not inherently related to any specific computer, virtual system or other device. In addition, the embodiments of the present invention are not directed to any specific programming language.

[0207] It should be noted that the above embodiments illustrate rather than limit the invention, and that alternative embodiments may be devised by a person skilled in the art without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments should not be understood as limiting the order of execution unless otherwise specified.

Claims

1. A path planning method, characterized in that: The method comprises: Obtain the user's first path intention information; Determining, based on the first route intention information, at least one first route planning element and a weight coefficient corresponding to each of the at least one first route planning element, wherein the magnitude of each weight coefficient indicates the strength of the user's demand for the corresponding first route planning element; A target path is determined according to the at least one first path planning element and a weight coefficient of the at least one first path planning element.

2. The method according to claim 1, characterized in that The determining the target path according to the at least one first path planning element and the weight coefficient of the at least one first path planning element includes: determining at least one first path according to the at least one first path planning element and a weight coefficient of the at least one first path planning element; In response to a selection operation triggered by a user based on the description information of the at least one first path, the first path corresponding to the selection operation is determined as the target path.

3. The method according to claim 2, characterized in that Before determining, in response to a selection operation triggered by a user based on the description information of the at least one first path, the first path corresponding to the selection operation as the target path, the method further includes: Acquire second route intention information fed back by the user based on the at least one description information; adjusting a weight coefficient of the at least one first path planning element according to the second path intention information; At least one first path is re-determined based on the adjusted weight coefficient of the at least one first path planning element and the at least one first path planning element.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: When a preset event is detected in front of the vehicle, playing or displaying a first inquiry message, the first inquiry message is used to prompt the user whether to take a detour to replan the route; In response to a user's determination operation with respect to the first query information, determining an uncompleted path planning element based on the at least one first path planning element and completed path planning elements of the vehicle during driving; A second path is determined according to the unfinished path planning elements and the weight coefficients corresponding to the unfinished path planning elements.

5. The method according to any one of claims 1 to 3, characterized in that The determining, based on the first path intention information, at least one first path planning element and a weight coefficient corresponding to each of the at least one first path planning element includes: Inputting the first path intention information into a first model to obtain the at least one first path planning element and a weight coefficient corresponding to each of the at least one first path planning element; Among them, the first model is obtained by training the large language model LLM based on multiple historical first path intention information, the path planning elements corresponding to the multiple historical first path intention information, and the weight coefficients corresponding to each path planning element.

6. The method according to claim 5, characterized in that Before inputting the first path intention information into the first model to obtain the at least one first path planning element and the weight coefficient corresponding to the at least one first path planning element, the method further includes: Acquire the plurality of historical route intention information; For each piece of historical path intention information, the historical path intention information is labeled in a preset manner to obtain the path planning elements corresponding to the historical path intention information and the weight coefficients corresponding to the path planning elements; The LLM is trained based on the multiple historical path intention information, the path planning elements corresponding to the multiple historical path intention information, and the weight coefficients corresponding to each path planning element to obtain the first model.

7. The method according to any one of claims 1 to 3, characterized in that The obtaining of the user's first path intention information includes: Acquire the route intention voice issued by the user through the audio collection unit in the vehicle; Alternatively, the user's route intention instruction is obtained through the central control screen in the vehicle; The first path intention information includes: the path intention voice or the path intention instruction.

8. A path planning device, characterized in that: The device comprises: An acquisition module is used to obtain the user's first path intention information; a first determining module, configured to determine, based on the first route intention information, at least one first route planning element and a weight coefficient corresponding to each of the at least one first route planning element, wherein the magnitude of each weight coefficient indicates the strength of a user's demand for the corresponding first route planning element; The second determining module is configured to determine a target path according to the at least one first path planning element and a weight coefficient of the at least one first path planning element.

9. A vehicle, characterized in that: include: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the path planning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The storage medium stores at least one executable instruction, and when the executable instruction is executed on the path planning device / vehicle, the path planning device / vehicle performs the operation of the path planning method according to any one of claims 1 to 7.

Images