Route planning method and vehicle-mounted system

Abstract

The invention relates to an itinerary planning method and a vehicle-mounted system. The method comprises the following steps: when a multi-day journey planning request of a vehicle user is received, performing journey planning according to the multi-day journey planning request, generating a multi-day journey framework, acquiring target detailed journey content associated with a task of a daily journey, and filling the journey framework of the daily journey according to the target detailed journey content to obtain a multi-day journey framework; and generating an itinerary planning result of the multi-day itinerary planning request. Wherein the multi-day travel framework comprises a task of a daily travel and a travel framework. According to the route planning method, complex tasks are decomposed, and the planning capability and the success rate for complex schedule planning are improved. And moreover, the decomposed daily schedule planning tasks can be executed in parallel, so that the processing efficiency for complex schedule planning is greatly improved.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicle technology, and in particular to a trip planning method and an in-vehicle system. Background Technology

[0002] With the rapid development of intelligent vehicle technology, intelligent vehicles can provide users with trip planning services in in-vehicle travel scenarios. Current trip planning methods can leverage large models combined with user preferences and information collected online to plan trips.

[0003] However, traditional travel planning methods suffer from low efficiency when faced with complex travel planning with long cycles and multiple constraints. Summary of the Invention

[0004] Therefore, it is necessary to provide a trip planning method and vehicle system that can improve planning efficiency to address the aforementioned technical problems.

[0005] Firstly, this application provides a trip planning method, including:

[0006] Upon receiving a multi-day trip planning request from a vehicle user, trip planning is performed based on the request to generate a multi-day trip framework; the multi-day trip framework includes the tasks for each day's trip and the trip framework for each day's trip.

[0007] Obtain the target detailed itinerary content associated with the tasks of the daily itinerary, and populate the itinerary framework of the daily itinerary according to the target detailed itinerary content to generate the itinerary planning result of the multi-day itinerary planning request.

[0008] In one embodiment, obtaining the target detailed itinerary content associated with the task of the daily schedule includes:

[0009] Select the toolset for the daily schedule based on the tasks in the daily schedule, and determine the order in which the tools in the daily schedule are called.

[0010] The daily schedule's toolset is invoked in the specified invocation order to collect detailed schedule content associated with the tasks of the daily schedule, thereby generating the target detailed schedule content for the daily schedule.

[0011] In one embodiment, the method further includes:

[0012] Determine the starting point for planning your daily itinerary;

[0013] The toolset for the daily schedule is selected based on the tasks of the daily schedule, including:

[0014] The toolset for the daily itinerary is selected based on the planning starting point and the tasks of the daily itinerary.

[0015] In one embodiment, the method further includes:

[0016] If the daily itinerary is the first day's itinerary, then the vehicle's travel planning constraints are obtained, and the vehicle's current position in the travel planning constraints is used as the planning starting point of the first day's itinerary; or, the itinerary starting position carried in the multi-day itinerary planning request is used as the planning starting point of the first day's itinerary.

[0017] If the daily itinerary is a day other than the first day's itinerary, then the starting point for planning the other day's itinerary is determined based on the itinerary planning results or itinerary framework of the previous day's itinerary.

[0018] In one embodiment, the method further includes:

[0019] Match multiple candidate tools according to the multi-day itinerary planning request, and register the multiple candidate tools into the tool library;

[0020] The toolset for selecting daily schedules based on the tasks of the daily schedule includes:

[0021] The toolset is formed by selecting candidate tools from the tool library that match the task information of the daily schedule.

[0022] In one embodiment, the method further includes:

[0023] Based on the tool requirements corresponding to the tasks in the daily schedule, special tools are built and added to the tool library.

[0024] In one embodiment, the step of invoking the toolset to collect detailed itinerary content associated with the tasks of the daily schedule according to the invocation order, and generating the target detailed itinerary content of the daily schedule, includes:

[0025] The toolset is invoked in the order described to collect detailed itinerary content associated with the tasks of the daily schedule, thereby obtaining the original detailed itinerary content of the daily schedule.

[0026] The original detailed itinerary content of the daily itinerary is cleaned to obtain the target detailed itinerary content of the daily itinerary.

[0027] In one embodiment, the step of filling the daily itinerary framework according to the target detailed itinerary content to generate the itinerary planning result of the multi-day itinerary planning request includes:

[0028] The detailed itinerary content of each day's itinerary is integrated to generate a multi-day itinerary plan.

[0029] The multi-day itinerary planning content is filled into the daily itinerary framework according to the cockpit output specifications to generate the itinerary planning result of the multi-day itinerary planning request; the cockpit output specifications include voice specifications and / or card specifications.

[0030] In one embodiment, the step of performing itinerary planning based on the multi-day itinerary planning request and generating a multi-day itinerary framework includes:

[0031] Based on the multi-day itinerary planning request, the task is decomposed in the time dimension to determine the daily stops and recommended points of interest, so as to generate a multi-day itinerary framework that includes daily itinerary tasks and itinerary framework.

[0032] In one embodiment, the method further includes:

[0033] Obtain the travel planning constraints of the vehicle; the travel planning constraints include at least one of the vehicle information, current location, driving range, and user preferences of the vehicle user;

[0034] The step of decomposing the task along the time dimension based on the multi-day itinerary planning request includes:

[0035] Based on the multi-day itinerary planning request and the travel planning constraints, the task is decomposed in the time dimension.

[0036] Secondly, this application also provides an in-vehicle system, which includes an interface module and a multi-agent cooperation engine; the multi-agent cooperation engine includes a supervisor agent and at least one executive agent; the executive agent includes a tool selection agent and an output agent;

[0037] Specifically, the output interface of the interface module is connected to the input interface of the supervisor agent; the output interface of the supervisor agent is connected to the input interface of the tool selection agent; the output interface of the tool selection agent is connected to the input interface of the output agent; and the output interface of the output agent is connected to the input interface of the interface module.

[0038] The interface module is configured to receive a multi-day trip planning request triggered by a vehicle user and send the multi-day trip planning request to the supervisory agent; it is also configured to output the trip planning result corresponding to the multi-day trip planning request.

[0039] The supervisory agent is used to perform itinerary planning based on the multi-day itinerary planning request when it receives the multi-day itinerary planning request, and generate a multi-day itinerary framework; the multi-day itinerary framework includes the tasks of each day's itinerary and the itinerary framework of each day's itinerary;

[0040] The tool selects an intelligent agent to obtain detailed target itinerary content associated with the tasks in the daily itinerary.

[0041] The output agent is used to fill in the daily itinerary framework according to the target detailed itinerary content, generate the itinerary planning result of the multi-day itinerary planning request, and transmit the itinerary planning result to the interface module.

[0042] The aforementioned trip planning method and in-vehicle system, upon receiving a multi-day trip planning request from a vehicle user, perform trip planning based on the request, generate a multi-day trip framework, obtain the target detailed trip content associated with the tasks of each day's trip, and populate the daily trip framework based on the target detailed trip content, generating the trip planning result for the multi-day trip planning request. The multi-day trip framework includes the tasks and trip framework of each day's trip. This trip planning method decomposes the multi-day trip into daily trips based on the multi-day trip planning request, first performing framework planning, and then performing detailed trip planning based on the daily trip framework planning. This achieves a method of decomposing complex tasks, improving the planning capability and success rate for complex schedules. Furthermore, the planning tasks of the decomposed daily trips can be executed in parallel, greatly improving the processing efficiency for complex schedules. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a diagram illustrating the application environment of the route planning method in one embodiment;

[0045] Figure 2 This is one of the flowcharts illustrating a route planning method in one embodiment;

[0046] Figure 3 This is a second flowchart illustrating a trip planning method in one embodiment;

[0047] Figure 4 This is the third flowchart of a route planning method in one embodiment;

[0048] Figure 5 This is the fourth flowchart of a trip planning method in one embodiment;

[0049] Figure 6 This is the fifth flowchart of a trip planning method in one embodiment;

[0050] Figure 7 This is one of the schematic diagrams of the architecture of the vehicle system in one embodiment;

[0051] Figure 8 This is the second schematic diagram of the architecture of the vehicle system in one embodiment;

[0052] Figure 9 This is the third schematic diagram of the architecture of the vehicle system in one embodiment;

[0053] Figure 10 This is the fourth schematic diagram of the architecture of the vehicle system in one embodiment;

[0054] Figure 11 This is a structural block diagram of a route planning device in one embodiment;

[0055] Figure 12 This is a schematic diagram of the internal structure of an in-vehicle terminal or cloud server in one embodiment. Detailed Implementation

[0056] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings. Preferred embodiments of this application are shown in the drawings. However, this application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a thorough and complete understanding of the disclosure of this application.

[0057] It should be understood that although the terms “first,” “second,” etc., may be used herein to describe various elements, this does not indicate any order, quantity, or importance, but is merely used to distinguish different components. These terms are used only to distinguish one element from another. For example, without departing from the scope of this application, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. Words such as “comprising” or “including” mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, without excluding other elements or objects.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0059] Currently, in-vehicle terminals can be equipped with in-vehicle systems. These systems can provide users with trip planning services. For example, if a user has travel needs, they can seek help from the in-vehicle system to plan their trip, greatly facilitating their driving. However, current in-vehicle systems typically rely on large language models combined with user preferences and online search information to complete trip planning. This method is prone to logical confusion or unstable output leading to planning task failure when dealing with long-term and complex trip planning, or it requires a significant amount of time for analysis, resulting in extremely low planning efficiency.

[0060] In view of this, embodiments of this application propose a trip planning method, apparatus, in-vehicle equipment, vehicle, storage medium, and program product, which can improve the success rate and efficiency of trip planning.

[0061] It should be noted that the beneficial effects or technical problems solved by the embodiments of this application are not limited to this one, but may also be other implicit or related problems. For details, please refer to the description of the embodiments below.

[0062] The itinerary planning method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, the vehicle-mounted terminal 102 communicates with the cloud server 104 via a network. A data storage system can store the data that the cloud server 104 needs to process. The data storage system can be integrated into the cloud server 104 or located in the cloud or on other network servers. The vehicle-mounted terminal 102 can provide trip planning services to vehicle users. Optionally, the vehicle-mounted terminal 102 can receive multi-day trip planning requests triggered by vehicle users in the target vehicle, and obtain relevant information required for trip planning from the cloud server 104. Then, based on the multi-day trip planning request and relevant information, it performs trip planning to obtain the final trip planning result, which can be presented to the vehicle user on the vehicle-mounted terminal 102. Optionally, when the vehicle terminal 102 receives a multi-day trip planning request triggered by a user in the target vehicle, it can send the request to the cloud server 104. The computing server 104 obtains the relevant information required for trip planning based on the request, performs trip planning based on the request and relevant information, obtains the final trip planning result, and finally sends the result back to the vehicle terminal 102, allowing it to present the result to the user. The vehicle terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. The cloud server 104 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0063] In one exemplary embodiment, such as Figure 2 As shown, a route planning method is provided, which can be applied to... Figure 1 Taking the vehicle-mounted terminal as an example, this trip planning method includes:

[0064] S201: Upon receiving a multi-day trip planning request from a vehicle user, perform trip planning based on the request and generate a multi-day trip framework.

[0065] The multi-day itinerary planning request includes the request content, such as "Please plan a 5-day self-driving, tram-based itinerary for me, with children, who enjoy natural scenery." The multi-day itinerary framework includes daily itinerary tasks and itinerary frameworks. The daily itinerary tasks can be understood as the overall multi-day itinerary planning task, which is then broken down into multiple tasks in chronological order. Each task matches a daily itinerary plan, for example, the task for day 1, day 2, ..., day N. The daily itinerary framework can include the corresponding time information, stops (i.e., accommodations), and recommended points of interest (POIs). Multiple POIs are allowed, but generally no more than two. The time information includes the date and time of the daily itinerary, such as XX year XX month XX day, or it can include a time indication, such as directly indicating which day of the overall itinerary the daily itinerary belongs to, for example, the daily itinerary is the first day's itinerary, or the daily itinerary is the second day's itinerary. For example, suppose when planning a 3-day trip, the multi-day itinerary framework includes the tasks and itinerary framework for day 1, day 2, and day 3. The itinerary framework for day 1 includes the time information, accommodation, and corresponding recommended points of interest for day 1; the itinerary framework for day 2 includes the time information, accommodation, and corresponding recommended points of interest for day 2; and the itinerary framework for day 3 includes the time information, accommodation, and corresponding recommended points of interest for day 3.

[0066] In this embodiment, when a vehicle user has a trip planning need, they can input a trip planning command on the in-vehicle terminal. The in-vehicle terminal can then trigger the generation of a multi-day trip planning request based on the planning needs indicated by the command, including the requested content. The in-vehicle terminal can then break down the requested content into multiple daily trip tasks and perform a framework-style daily trip planning for each task, essentially providing a rough single-day trip plan. This framework-style daily trip planning focuses on recommending corresponding stops and points of interest for each day's trip, resulting in a daily trip framework. Finally, a multi-day trip framework is formed based on the trip frameworks and tasks for all days. Optionally, the in-vehicle terminal can output the multi-day trip framework in a predetermined structured JSON format. Optionally, the in-vehicle terminal can also display the multi-day trip framework on an in-vehicle display screen. For example, the multi-day trip framework can be expressed in the following form:

[0067] “plan”:[

[0068] { “day”:1, Dujiangyan Day Trip

[0069] "docking_place": "Near Dujiangyan City"

[0070] “recommended_pois”: [“Qingcheng Mountain”, “Dujiangyan Scenic Area”]

[0071] },

[0072] { “day”:2, A day trip to Mount Siguniang

[0073] "docking_place": "Four Sisters Mountain Town"

[0074] “recommended_pois”:[“Shuangqiaogou, Mount Siguniang”]

[0075] },

[0076] / / ...other days ]

[0078] S202, obtain the detailed itinerary content of the target associated with the daily itinerary, and populate the itinerary framework of the daily itinerary based on the detailed itinerary content of the target, generating the itinerary planning result of the multi-day itinerary planning request.

[0079] The detailed itinerary content includes itinerary information from multiple dimensions, such as detailed information related to waypoints, points of interest (POIs), restaurants, accommodations, and transportation.

[0080] In this embodiment, when a multi-day itinerary framework is obtained based on the aforementioned steps, the daily itinerary can be further planned separately on a daily basis. Specifically, during planning, optionally, the daily itinerary can be planned in chronological order, for example, planning the daily itinerary sequentially from day 1, day 2, ..., day N until all days are planned; optionally, the multi-day itinerary can also be planned in parallel, for example, simultaneously planning the daily itinerary for day 1, day 2, ..., day N until all days are planned. When specifically planning the daily itinerary, after obtaining the daily itinerary tasks and itinerary framework, tools from a third-party platform can be used to collect detailed itinerary content associated with the daily itinerary tasks, obtaining the target detailed itinerary content for each day. Optionally, after collecting the detailed itinerary content associated with the daily itinerary tasks, since this content may contain redundant or interfering information, this content can be filtered to obtain the target detailed itinerary content for each day.

[0081] Once the detailed daily itinerary information is obtained, it can be populated into the daily itinerary framework to supplement the daily itinerary details and create the complete daily itinerary. Finally, the complete daily itinerary information is summarized and organized to form the itinerary planning result for the multi-day itinerary planning request. Optionally, since the detailed daily itinerary information includes multiple dimensions and is quite extensive, with some matching vehicle users and others not, the itinerary information matching vehicle users can be further parsed from the detailed daily itinerary information according to the multi-day itinerary planning request. Then, based on the parsed matching itinerary information, the multi-day itinerary content can be organized to generate the itinerary planning result for the multi-day itinerary planning request.

[0082] The trip planning method described in the above embodiments, upon receiving a multi-day trip planning request from a vehicle user, performs trip planning based on the request, generates a multi-day trip framework, obtains the target detailed trip content associated with the tasks of each day's trip, and fills in the daily trip framework based on the target detailed trip content to generate the trip planning result for the multi-day trip planning request. The multi-day trip framework includes the tasks and the trip framework for each day's trip. This trip planning method decomposes the multi-day trip into daily trips based on the multi-day trip planning request, first performing framework planning, and then performing detailed trip planning based on the framework planning of each daily trip. This achieves a method of decomposing complex tasks, improving the planning ability and success rate for complex schedules. Furthermore, the planning tasks of the decomposed daily trips can be executed in parallel, greatly improving the processing efficiency for complex schedules.

[0083] In one exemplary embodiment, a method is provided for obtaining detailed itinerary content for a daily schedule, such as... Figure 3 As shown, the method includes:

[0084] S301, Select the toolset for the daily schedule based on the tasks of the daily schedule, and determine the order in which the tools in the daily schedule are called.

[0085] The toolset may include tools such as waypoint planning, POI search, restaurant selection, hotel search, time management, weather forecast, and charging station search.

[0086] In this embodiment, after obtaining the daily itinerary tasks based on the aforementioned steps, the daily itinerary can be further decomposed to determine multiple sub-tasks corresponding to the daily itinerary. For example, if the itinerary for the first day is "starting from Lijiang Old Town, heading to Jade Dragon Snow Mountain, finding a restaurant with a rating of 4.0 or higher for lunch along the way, and finally returning to the accommodation in Lijiang, taking weather factors into account," the daily itinerary can be decomposed into five sub-tasks: 1. Querying the geographical coordinates of the starting point and the destination; 2. Planning the route from the starting point to the destination; 3. Searching for restaurants that meet the criteria along the route; 4. Querying the weather for the day; 5. Planning the route from the destination back to the accommodation. Then, one or more available tools are selected from the system's registered tool library for each sub-task. For example, for the sub-task of "querying the geographical coordinates of the starting point and the destination," a POI positioning tool can be selected; for the sub-task of "planning the route from the starting point to the destination," a route planning tool can be selected; and for the sub-task of "querying the weather for the day," a weather query tool can be selected. The tools for all the sub-tasks corresponding to the daily itinerary are collected to form the daily itinerary toolset.

[0087] Since the toolset for a daily schedule contains multiple tools, and these tools may or may not have dependencies, they can be used in different orders, such as linear, parallel, or conditional branching. Once the toolset corresponding to the daily schedule is determined, the calling order of the tools in the toolset can be determined based on the dependencies between the tools in the toolset, forming a tool call chain. This facilitates the subsequent rapid invocation of tools to collect schedule content based on this call chain. For example, if there is a parameter passing dependency between tool A and tool B, and the output parameter of tool A needs to be used as the input of tool B, the calling order between tool A and tool B can be determined as a linear calling order. If there is no dependency between tool A and tool B, the calling order between tool A and tool B can be determined as a simultaneous parallel calling order. If the output result of tool A is the calling condition of tool B and tool C, the calling order between tool A, tool B, and tool C can be determined as the order of conditional branches. For this type of order, for example, if the output result of tool A meets the preset condition, tool B needs to be selected to execute the subsequent subtask; if the output result of tool A does not meet the preset condition, tool C needs to be selected to execute the subsequent subtask. It should be noted that if some tools in the toolset have dependencies, while other tools do not, when calling the toolset, some tools can be called in a linear order, while other tools can be called in a parallel order.

[0088] Exemplary illustration of the above steps: Example 1, assuming the task for the first day's itinerary is "Starting from Lijiang Old Town, heading to Jade Dragon Snow Mountain, finding a restaurant with a rating of 4.0 or higher for lunch along the way, and finally returning to the accommodation in Lijiang, considering weather factors." This day's itinerary corresponds to five sub-tasks: 1. Query the coordinates of the starting point and the destination; 2. Plan the path from the starting point to the destination; 3. Search for restaurants that meet the criteria along the path; 4. Query the weather for the day; 5. Plan the path from the destination back to the accommodation. The tool call chain for this day's itinerary can be:

[0089] Step 1: Use the "POI Collection Tool" as the tool; parameters are "Lijiang Old Town" and "Attractions"; subtask is "Get Starting Point Coordinates and ID"; call order is "linear order".

[0090] Step 2, using the "POI Collection Tool"; parameters are "Jade Dragon Snow Mountain" and "Natural Landscape"; subtask "Get Endpoint Coordinates and ID"; call order is "parallel order (can be executed in parallel with Step 1)".

[0091] Step 3, use the "Weather Query Tool" as the tool; parameters are "Lijiang" and "Time"; subtask is "Get Weather Information"; call order is "parallel order (can be executed in parallel with Step 1 and Step 2)".

[0092] Step 4, use the "Route Planning Tool" as the tool; the parameters are "Starting point coordinates", "Ending point coordinates", and "Driving"; the subtask is "Plan the main route"; the calling order is "Linear sequence (executed after Step 1 and Step 2 above, or after Step 3 above)".

[0093] Step 5, use the "POI Search Tool" tool; parameters are "path", "restaurant", "rating 4.0"; subtask "find restaurants on the path"; call order is "linear order (execute after step 4 above)".

[0094] Step 6: Use the "POI Details Search Tool" as the tool; parameters are "found restaurants" and "recommended restaurants"; subtask is "get restaurant details"; call order is "linear order (executed after step 5 above)".

[0095] Step 7, use the "Route Planning Tool" as the tool; the parameters are "Coordinates on Yulong", "Accommodation (stop)" and "Self-driving"; the subtask is "Plan the return route"; the calling order is "Linear sequence (executed after Step 2 above)".

[0096] Steps 1, 2, and 3 can be executed in parallel first, step 4 can be executed alone, steps 5 and 7 can be executed in parallel, and step 6 can be executed last.

[0097] S302, in the order of invocation, call the toolset of the daily schedule to collect detailed schedule content associated with the tasks of the daily schedule, and generate the target detailed schedule content of the daily schedule.

[0098] In this embodiment, once the calling order of the tools in the daily schedule's toolset is determined, the tools in the toolset can be called in that order to execute their respective subtasks, thus collecting the detailed schedule content associated with each subtask. For example, when the calling order is linear, all subtasks of the daily schedule can be executed sequentially using the tools in the toolset; when the calling order is parallel, all subtasks of the daily schedule can be executed in parallel using the tools in the toolset. Once the detailed schedule content associated with all subtasks of the daily schedule is collected, the target detailed schedule content for the daily schedule can be obtained. It should be noted that the target detailed schedule content for the daily schedule is essentially a tool call record, meaning that the target detailed schedule content for the daily schedule includes a series of information such as tool name, tool parameters, and tool return results during the calling process of the corresponding toolset.

[0099] In one exemplary embodiment, a method for selecting a toolset is also provided, such as Figure 4 As shown, the method includes:

[0100] S401, determine the starting point for planning your daily itinerary.

[0101] In this embodiment of the application, since a multi-day trip is a continuous trip and the planning of a multi-day trip may also be a continuous plan, the planning starting point of each day's trip is related to the planning ending point of the previous day's trip. Therefore, the planning starting point of each day's trip can be determined based on the planning ending point of the previous day's trip. Since there is no previous day, the planning starting point of the first day's trip can be determined based on the planning needs of the vehicle user or based on the current location of the vehicle.

[0102] Next, let's explain in detail. When the daily itinerary is the first day's itinerary, there are two optional methods for determining the planning starting point of the daily itinerary. The first method involves obtaining the vehicle's travel planning constraints and using the vehicle's current location from these constraints as the planning starting point for the first day's itinerary. These travel planning constraints include the vehicle's current location, vehicle information, and user preferences. Specifically, when determining the planning starting point for the first day's itinerary, you can first obtain the preset travel planning constraints, extract the vehicle's current location from these constraints, and then directly use the vehicle's current location as the planning starting point for the first day's itinerary. This means that when the first day's itinerary begins, the vehicle will depart from its current location to start the journey.

[0103] The second method involves using the trip start location carried in the multi-day trip planning request as the planning start point for the first day's trip. Specifically, since the multi-day trip planning request represents the vehicle user's planning needs and carries the planned trip start location, when it is necessary to determine the planning start point for the first day's trip, the trip start location can be extracted from the multi-day trip planning request and then used as the planning start point for the first day's trip. This means that when the first day's trip begins, the vehicle will depart from this trip start location to start the journey.

[0104] When a daily itinerary is for a day other than the first day's itinerary, the method for determining the planning starting point of the daily itinerary includes determining the planning starting point of the other day's itinerary based on the itinerary planning results or itinerary framework of the previous day's itinerary. This application's embodiments involve two methods for determining the planning starting point of other day's itinerary: The first method is that when the vehicle terminal plans the daily itinerary sequentially according to time, the planning starting point of the other day's itinerary can be determined based on the itinerary planning results of the previous day's itinerary. Specifically, since the planning starting point of other day's itinerary is related to the planning endpoint of the previous day's itinerary, after planning the itinerary of the previous day and obtaining the itinerary planning results, the itinerary planning results will include the planned endpoint of the previous day's itinerary. When it is necessary to determine the planning starting point of other day's itinerary, the itinerary planning results of the previous day's itinerary can be obtained first, then the planned endpoint of the previous day's itinerary can be determined from it, and then the planned endpoint of the previous day's itinerary can be directly determined as the planning starting point of the other day's itinerary.

[0105] The second method involves the onboard terminal planning trips for multiple days in parallel. When determining the starting point for other days' trips, the terminal can obtain the trip framework of the previous day's trip and extract the stops from it. Then, based on these stops, the starting point for other days' trips can be determined. It should be noted that the method for determining which day's trip a day belongs to can be specifically based on the daily trip framework. For example, the time information corresponding to each day's trip can be extracted from the daily trip framework, and then the day's trip can be directly determined based on that time information.

[0106] S402: Select the toolset for the daily itinerary based on the planning starting point and tasks of the daily itinerary.

[0107] In this embodiment, after obtaining the daily itinerary tasks based on the aforementioned steps, the daily itinerary can be further decomposed to determine multiple sub-tasks corresponding to the daily itinerary. Then, based on the planning starting point of the daily itinerary, one or more available tools are selected from the system-registered tool library for each sub-task. Specifically, the planning starting point of the daily itinerary can be used as a tool parameter for tool selection. The method for selecting the toolset can be found in the aforementioned step S301, and will not be repeated here. The above method considers the spatial logical coherence between daily itineraries and selects corresponding tools for itinerary planning, which can provide vehicle users with comprehensive itinerary planning results, making the planned itinerary results more in line with the needs of vehicle users.

[0108] In one exemplary embodiment, a method for pre-screening tools is also provided, namely... Figure 3 The method described in the embodiment further includes the steps of: matching multiple candidate tools according to the multi-day itinerary planning request, and registering the multiple candidate tools in the tool library; correspondingly, when executing the above S301 "selecting the toolset for the daily itinerary according to the tasks of the daily itinerary", the specific steps are: filtering out candidate tools that match the task information of the daily itinerary from the tool library to form a toolset.

[0109] In this embodiment, before executing step S301 "selecting the toolset for the daily itinerary based on the tasks of the daily itinerary," all available tools can be dynamically filtered as candidate tools based on the vehicle user's planning needs. Specifically, since a multi-day itinerary planning request represents the vehicle user's planning needs, upon receiving a multi-day itinerary planning request, all available tools can be retrieved from the system-registered tool library as candidate tools based on the total task corresponding to the multi-day itinerary planning request, and then a tool library is formed based on all candidate tools. After obtaining the tasks of the daily itinerary, the daily itinerary can be further decomposed to determine multiple sub-tasks corresponding to the daily itinerary. Then, corresponding candidate tools can be selected from the tool library for each sub-task to form a toolset, which can be directly called when planning the daily itinerary. The above method achieves filtering before tool invocation, reduces interference between tools, and thus improves tool processing efficiency, thereby improving itinerary planning efficiency.

[0110] In one exemplary embodiment, a method for optimizing a tool library may also be provided, comprising: building specialized tools based on the tool requirements corresponding to the tasks of a daily schedule, and adding the specialized tools to the tool library.

[0111] Tool requirements are used to describe the characteristics that a tool must possess when used to process a task. For example, some time calculation tasks require tools to have accurate calculation capabilities; some reasoning tasks require tools to have high reasoning capabilities.

[0112] Specialized tools can include any type of tool, such as waypoint planning tools, POI search tools, restaurant selection tools, hotel search tools, time management tools, weather query tools, and charging station query tools. Optionally, specialized tools can be improvements on existing tools tailored to the needs of daily itinerary tasks. Alternatively, specialized tools can be self-developed tools matched to the needs of daily itinerary tasks, such as training large models capable of complex logical reasoning. For example, large model-based tools are generally not good at complex calculations, and using such tools can easily lead to logical confusion in itinerary planning, resulting in planning failure. To avoid this problem, the computational modules of large model-based tools can be encapsulated into specialized tools. This allows large model-based tools to focus their reasoning and planning on core tasks, while entrusting precise, deterministic calculations to the encapsulated specialized tools, fundamentally ensuring the accuracy and reliability of the results.

[0113] In this embodiment, after the vehicle terminal builds a dedicated tool based on the tool requirements corresponding to the daily trip tasks, the dedicated tool can be added to the tool library to optimize the tool library. This makes it easier to select a toolset based on the optimized tool library when performing similar trip planning tasks in the future, thereby completing the next trip planning. This allows the vehicle terminal to continuously optimize the toolset library during each trip planning process, which can improve the intelligence of the vehicle terminal in trip planning.

[0114] In one exemplary embodiment, after collecting detailed itinerary content associated with the tasks of the daily schedule, this detailed itinerary content can be cleaned to reduce redundant and interfering information. Therefore... Figure 3 In the embodiment, step S302, "calling the toolset in the order of invocation to collect detailed itinerary content associated with the tasks of the daily schedule, and generating the target detailed itinerary content for the daily schedule," is as follows: Figure 5 As shown, it includes:

[0115] S501, in the order of invocation, calls the toolset to collect detailed schedule content associated with the tasks of the daily schedule, and obtains the original detailed schedule content of the daily schedule.

[0116] In this embodiment, once the calling order of the tools in the daily schedule's toolset is determined, the tools in the toolset can be called in that order to execute their respective subtasks, thus collecting the detailed schedule content associated with each subtask. For example, when the calling order is linear, all subtasks of the daily schedule can be executed sequentially using the tools in the toolset; when the calling order is parallel, all subtasks of the daily schedule can be executed in parallel using the tools in the toolset. Once the detailed schedule content associated with all subtasks of the daily schedule has been collected, the original detailed schedule content of the daily schedule can be obtained.

[0117] S502 cleans the original detailed itinerary content of each day's itinerary to obtain the target detailed itinerary content for each day's itinerary.

[0118] In this embodiment, since data collected using third-party tools may have issues such as inconsistent structure, excessive length, and inclusion of irrelevant fields, the original detailed itinerary content of each day can be cleaned after obtaining it to output information with a unified structure, concise details, and no redundancy, thus obtaining the target detailed itinerary content for each day. This method can reduce the data processing burden and thereby improve data processing speed.

[0119] In one exemplary embodiment, a method is provided for integrating and outputting detailed daily itinerary content, namely... Figure 2 In the embodiment, S202, "filling in the daily itinerary framework according to the target detailed itinerary content, and generating the itinerary planning result of the multi-day itinerary planning request," is as follows: Figure 6 As shown, it includes:

[0120] S601 integrates the detailed itinerary content of each day's itinerary to generate multi-day itinerary planning content.

[0121] In this embodiment, the detailed itinerary content of the daily schedule is essentially the tool call record when the aforementioned toolset is invoked, and this tool call record contains a lot of scattered information, as detailed above. Figure 3 Example 1 in the embodiments contains scattered information such as various tool names, parameters, and tool return results. Therefore, it is necessary to integrate the detailed itinerary content of each day's itinerary to edit the scattered information into a coherent or sequential narrative text, generating multi-day itinerary planning content. During this integration, contextual understanding can be used to edit the scattered information into a coherent or sequential narrative text. Therefore, contextual information can be obtained from the multi-day itinerary planning request beforehand, and the detailed itinerary content can be integrated later based on this contextual information.

[0122] S602, according to the cockpit output specifications, fills the multi-day itinerary planning content into the daily itinerary framework, and generates the itinerary planning result of the multi-day itinerary planning request.

[0123] The cockpit output specification is a predefined format that may include voice specifications and / or card specifications.

[0124] In this embodiment, the daily itinerary framework can be used as a template, and then the planning content of multi-day itineraries can be filled into the daily itinerary template to generate a complete itinerary planning content for the daily itinerary. Then, the complete itinerary planning content of the daily itinerary can be edited according to the editing method or predefined format corresponding to the cabin output specification to generate an itinerary planning result that can be output and conforms to the multi-day itinerary planning request of the cabin output specification.

[0125] Optionally, when the cockpit output specifications include voice specifications, when editing the complete daily trip planning content, the complete trip planning content can be converted into daily trip voice data according to the voice specifications. Finally, the voice data of multiple daily trips are summarized into the trip planning result for a multi-day trip planning request. Later, when the vehicle initiates each daily trip, the daily trip voice data can be played back through the voice output device.

[0126] Optionally, when the cockpit output specifications include card specifications, the editing of the complete daily itinerary planning content can be specifically converted into a daily itinerary planning information list according to the card specifications. This planning information list includes information about the itinerary points, such as the name, latitude and longitude, address, rating, and business hours of the POI. Then, corresponding card content is created based on the content of each itinerary point in the daily itinerary planning information list. Finally, the card content of multiple daily itineraries is summarized into the itinerary planning result of a multi-day itinerary planning request. Later, when the vehicle initiates each daily itinerary, the card content corresponding to the daily itinerary can be displayed as cards on the in-vehicle terminal's screen.

[0127] In one exemplary embodiment, a method for constructing a multi-day itinerary framework is provided, namely... Figure 2 S201 in the embodiment, "Perform itinerary planning based on multi-day itinerary planning request and generate multi-day itinerary framework", includes: decomposing tasks in the time dimension based on multi-day itinerary planning request, determining daily stops and recommended points of interest, so as to generate a multi-day itinerary framework including daily itinerary tasks and itinerary framework.

[0128] In this embodiment, a large model can be used to decompose tasks along the time dimension based on the multi-day itinerary planning request. For example, the planning task requested by the multi-day itinerary planning request can be taken as the total task, and the planning tasks of each day's itinerary in the multi-day itinerary can be taken as individual tasks in the total task. For the tasks of each day's itinerary, the stops and recommended points of interest in the daily itinerary can be roughly determined first to build a daily itinerary framework.

[0129] Optionally, the in-vehicle terminal can also decompose tasks based on the vehicle's travel planning constraints. Specifically, when executing the step "perform travel planning based on multi-day travel planning requests and generate a multi-day travel framework," the specific steps are: obtaining the vehicle's travel planning constraints; and decomposing the task along the time dimension based on the multi-day travel planning requests and travel planning constraints. The travel planning constraints include at least one of the following: vehicle information, current location, remaining driving range, and user preferences of the vehicle user. User preferences can be predefined based on the vehicle user's profile or historical conversations.

[0130] In this embodiment, a large model can be used to decompose tasks along the time dimension based on multi-day trip planning requests and travel planning constraints. For example, daily stops and recommended points of interest can be selected based on vehicle users' preferences. This method enables the large model to better understand vehicle users' needs and reason accordingly, accurately determining daily stops and recommended points of interest, thereby generating a multi-day trip framework that meets vehicle users' needs.

[0131] In one exemplary embodiment, an in-vehicle system is also provided, such as Figure 7 As shown, the in-vehicle system includes an interface module 11 and a multi-agent collaboration engine 12. The multi-agent collaboration engine 12 includes a supervisor agent 121 and at least one executive agent 122; each executive agent 122 includes a tool selection agent 122_a and an output agent 122_b; the output interface of the interface module 11 is connected to the input interface of the supervisor agent 121; the output interface of the supervisor agent 121 is connected to the input interface of the tool selection agent 122_a; the output interface of the tool selection agent 122_a is connected to the input interface of the output agent 122_b; and the output interface of the output agent 122_b is connected to the input interface of the interface module 11.

[0132] The interface module 101 is used to receive multi-day trip planning requests triggered by vehicle users and send the multi-day trip planning requests to the supervisory intelligent agent 121; it is also used to output the trip planning results corresponding to the multi-day trip planning requests.

[0133] When a multi-day itinerary planning request is received, the supervisor agent 121 performs itinerary planning based on the request and generates a multi-day itinerary framework. The multi-day itinerary framework includes the tasks for each day's itinerary and the itinerary framework for each day's itinerary. The itinerary framework includes stops and recommended points of interest.

[0134] The tool selects agent 122_a to obtain detailed schedule content of the target associated with the tasks in the daily schedule.

[0135] Output agent 122_b, which is used to fill the daily itinerary framework according to the target detailed itinerary content, generate the itinerary planning result of the multi-day itinerary planning request, and transmit the itinerary planning result to interface module 11.

[0136] The aforementioned vehicle-mounted system can run on the vehicle-mounted terminal or on a computing server that communicates with the vehicle-mounted terminal. The vehicle-mounted system can perform the aforementioned... Figures 2-6 The trip planning method described in any embodiment. Specifically, when a vehicle user has a trip planning need, they can input a trip planning command on the in-vehicle terminal. At this time, the in-vehicle terminal can trigger the generation of a multi-day trip planning request based on the planning needs indicated by the trip planning command, so that the multi-day trip planning request includes the requested content. When the in-vehicle system is running on the in-vehicle terminal, the in-vehicle terminal can send the above-mentioned multi-day trip planning request to the interface module 101 of the in-vehicle system. The interface module 11 can receive the above-mentioned multi-day trip planning request, and then send the multi-day trip planning request to the supervisor agent 121 in the multi-agent collaboration engine 12. The supervisor agent 121 determines the requested content based on the multi-day trip planning request, and breaks down the requested content into multiple daily trip tasks. Then, a framework-style daily trip planning is performed for the daily trip tasks, focusing on recommending corresponding stops and points of interest for the daily trip, thus obtaining the daily trip framework. Optionally, the supervisor agent 121 can edit the multi-day itinerary framework according to a predetermined structured JSON format, and distribute the edited multi-day itinerary framework to at least one executive agent 122, which will then complete the subsequent itinerary planning.

[0137] When each execution agent 122 performs subsequent schedule planning, it plans its own daily itinerary. Specifically, during daily itinerary planning, the tool selection agent 122_a first connects to a third-party platform to collect itinerary content associated with the daily itinerary, obtaining the target detailed itinerary content for the daily itinerary. Then, the tool selection agent 122_a can send the target detailed itinerary content of the daily itinerary to the corresponding output agent 122_b. The output agent 122_b, based on the multi-day itinerary planning request, parses the itinerary content matching the vehicle user from the target detailed itinerary content of the daily itinerary, and then organizes the itinerary content of the multi-day itinerary based on the parsed itinerary content matching the vehicle user to generate and output the itinerary planning result of the daily itinerary planning request. It should be noted that the aforementioned multiple execution agents 122 can plan daily schedules in chronological order. For example, each execution agent 122 can plan daily schedules sequentially from day 1, day 2, ..., day N until all days are planned. Alternatively, the aforementioned multiple execution agents 122 can also plan schedules for multiple days in parallel. For example, multiple execution agents 122 can simultaneously plan daily schedules for day 1, day 2, ..., day N until all days are planned.

[0138] The in-vehicle system described in the above embodiments enables multi-agent collaborative multi-day itinerary planning. The supervisor agent decomposes the multi-day itinerary planning task into daily steps and generates a top-level multi-day itinerary framework. Then, the executor agents fill in the daily details based on the framework provided by the supervisor agent, collaborating with the supervisor agent to complete the multi-day itinerary planning. This method of decomposing complex tasks improves the planning capability and success rate for complex schedules. Furthermore, multiple executor agents can execute daily itinerary planning tasks in parallel, significantly improving the processing efficiency for complex schedules.

[0139] In an exemplary embodiment, the above-mentioned tool selects agent 122_a, which is specifically used to select the toolset of the daily schedule according to the tasks of the daily schedule, and determine the calling order of each tool in the toolset: calling the toolset in the calling order to collect detailed schedule content associated with the tasks of the daily schedule, and generating the target detailed schedule content of the daily schedule.

[0140] In this embodiment, when each tool selection agent 122_a receives the corresponding daily schedule task and schedule framework issued by the supervisor agent 121, it can further decompose the daily schedule task to determine multiple sub-tasks corresponding to the daily schedule. For specific decomposition methods, please refer to [link to relevant documentation]. Figure 3The method described in the embodiments will not be elaborated here. Finally, the tool is used to select agent 122_a to gather all the tools for the sub-tasks corresponding to the daily schedule to form the toolset for the daily schedule.

[0141] Once the tool selection agent 122_a determines the calling order of the tools in the daily schedule's toolset, it can execute the corresponding subtasks according to the calling order, thus collecting detailed schedule information associated with each subtask. For specific methods on how to collect this information, please refer to [link to relevant documentation]. Figure 3 The methods described in the embodiments will not be elaborated here. It should be noted that when the vehicle system includes multiple tool selection agents 122_a, these multiple tool selection agents 122_a can be executed serially or in parallel.

[0142] Regarding the aforementioned method of using tools to select the daily schedule for agent 122_a, and the method described above... Figure 4 The method described in the following embodiments is basically the same as that described in the foregoing. For details, please refer to the foregoing. Figure 4 The methods described in the following embodiments are not repeated here.

[0143] In an exemplary embodiment, the aforementioned output agent 122_b is specifically used to integrate the target detailed itinerary content of the daily itinerary to generate the planning content of a multi-day itinerary; and to fill the planning content of the multi-day itinerary into the itinerary framework of the daily itinerary according to the cockpit output specifications to generate the itinerary planning result of the multi-day itinerary planning request; the cockpit output specifications include voice specifications and / or card specifications.

[0144] In this embodiment, after the tool selector 122_a collects the target detailed itinerary content of the daily itinerary by calling the tool, it obtains the tool call record and can output the tool call record to the output agent 122_b. The output agent 122_b can integrate the target detailed itinerary content of the daily itinerary to edit the scattered information into a coherent or sequential narrative text, generating multi-day itinerary planning content. During integration, the context management module can be used to obtain context information based on the multi-day itinerary planning request, and based on the context information, the scattered information can be edited into a coherent or sequential narrative text, integrating it into the target detailed itinerary content. The output agent 122_b can also fill the multi-day itinerary planning content into the daily itinerary framework according to the cockpit output specifications, generating the itinerary planning result of the multi-day itinerary planning request.

[0145] Optionally, when the cockpit output specifications include voice specifications, the output agent 122_b can specifically convert the complete daily trip planning content into daily trip voice data according to the voice specifications, and finally summarize the voice data of multiple daily trips into a multi-day trip planning request trip planning result. Afterwards, the output agent 122_b can transmit the trip planning result to the interface module 11, so that the daily trip planning result can be played back via the voice output device when the vehicle starts each daily trip.

[0146] Optionally, when the cockpit output specification includes a card specification, the output agent 122_b can specifically convert the complete trip planning content into a daily trip planning information list according to the card specification. This planning information list includes the content of the trip points, such as the name, latitude and longitude, address, rating, and business hours of the POI. Then, corresponding card content is created based on the content of each trip point in the daily trip planning information list. Finally, the card content of multiple daily trips is summarized into the trip planning result of the multi-day trip planning request. Afterward, the output agent 122_b can transmit the trip planning result to the interface module 11, so that when the vehicle starts each daily trip, the card content corresponding to the daily trip can be displayed on the display screen of the vehicle terminal in the form of cards.

[0147] In one exemplary embodiment, such as Figure 8 As shown, the above-mentioned vehicle system also includes a tool selection module 13, the input interface of which is connected to the output interface of the supervisor intelligent module 121; the output interface of the tool selection module 13 is connected to the input interface of multiple tool selection intelligent agents 122_a.

[0148] Specifically, the tool filtering module 13 is used to match multiple candidate tools based on the multi-day itinerary planning request and register these candidate tools in the tool library. Then, the tool selection agent 122_a can filter candidate tools from the tool library that match the task information of the daily itinerary to form a toolset. The data cleaning method for this part is the same as described above. Figure 5 The methods described in the embodiments are basically the same; for details, please refer to the foregoing. Figure 5 The methods described in the embodiments are not repeated here.

[0149] In one exemplary embodiment, such as Figure 9As shown, the aforementioned vehicle-mounted system also includes an encapsulation module 14. The input interface of the encapsulation module 14 is connected to the output interface of the tool filtering module 13, and the output interface of the encapsulation module 14 is connected to the input interface of each tool selection agent 122_a. Specifically, the encapsulation module 14 is used to construct dedicated tools based on the tool requirements corresponding to the tasks of the daily itinerary, and add these dedicated tools to the tool library. The method for optimizing this part of the tool library is basically the same as the method for optimizing the tool library described in the previous embodiments. For details, please refer to the method described in the previous embodiments; it will not be repeated here.

[0150] In one exemplary embodiment, such as Figure 10 As shown, the aforementioned execution agent 12 also includes a data cleaning module 122_c. The input interface of this data cleaning module 15 is connected to the output interface of the tool selection agent 122_a. Specifically, the data cleaning module 15 cleans the original detailed itinerary content of the daily itinerary output by the tool selection agent 122_a to obtain the target detailed itinerary content. Then, the data cleaning module 15 transmits the cleaned target detailed itinerary content to the output agent 122_b, allowing the output agent 122_b to edit and output the cleaned target detailed itinerary content in a predefined format. For the method of using the data cleaning module 15 to clean the original detailed itinerary content, please refer to the aforementioned... Figure 5 The methods described in the embodiments are not repeated here.

[0151] In an exemplary embodiment, when performing multi-day trip planning, the supervisory agent 121 can specifically decompose tasks along the time dimension based on the multi-day trip planning request, determine daily stops and recommended points of interest, and generate a multi-day trip framework including daily trip tasks and a trip framework. Optionally, the supervisory agent 121 can also obtain vehicle travel planning constraints and decompose tasks along the time dimension based on the multi-day trip planning request and travel planning constraints. The travel planning constraints include at least one of the vehicle's vehicle information, current location, remaining range, and the user preferences of the vehicle's user. For details on the method of using the supervisory agent 121 for multi-day trip planning, please refer to the embodiments of the corresponding methods described above; further details are provided in the foregoing description and will not be repeated here.

[0152] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0153] Based on the same inventive concept, this application also provides a travel planning apparatus for implementing the travel planning method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more travel planning apparatus embodiments provided below can be found in the limitations of the travel planning method described above, and will not be repeated here.

[0154] In one exemplary embodiment, such as Figure 11 As shown, a trip planning device is provided, comprising:

[0155] The first planning module 21 is used to perform trip planning based on the multi-day trip planning request received from a vehicle user, and generate a multi-day trip framework; the multi-day trip framework includes the tasks of each day's trip and the trip framework of each day's trip.

[0156] The second planning module 22 is used to obtain the target detailed itinerary content associated with the tasks of the daily itinerary, and to fill in the itinerary framework of the daily itinerary according to the target detailed itinerary content to generate the itinerary planning result of the multi-day itinerary planning request.

[0157] Each module in the aforementioned travel planning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0158] In one exemplary embodiment, an in-vehicle terminal or cloud server is provided, the internal structure of which can be shown in the following diagram. Figure 12As shown. The vehicle-mounted terminal or cloud server includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of this computer device provides computing and control capabilities. The memory of this computer device includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface of this computer device is used for exchanging information between the processor and external devices. The communication interface of this computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a trip planning method. The display unit of this computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0159] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the solution of this application and does not constitute a limitation on the vehicle terminal or cloud server to which the solution of this application is applied. The specific vehicle terminal or cloud server may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0160] In an exemplary embodiment, the aforementioned vehicle-mounted terminal or cloud server includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0161] Upon receiving a multi-day trip planning request from a vehicle user, trip planning is performed based on the request to generate a multi-day trip framework; the multi-day trip framework includes the tasks for each day's trip and the trip framework for each day's trip.

[0162] Obtain the target detailed itinerary content associated with the tasks of the daily itinerary, and populate the itinerary framework of the daily itinerary according to the target detailed itinerary content to generate the itinerary planning result of the multi-day itinerary planning request.

[0163] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0164] Select the toolset for the daily schedule based on the tasks in the daily schedule, and determine the order in which the tools in the daily schedule are called.

[0165] The daily schedule's toolset is invoked in the specified invocation order to collect detailed schedule content associated with the tasks of the daily schedule, thereby generating the target detailed schedule content for the daily schedule.

[0166] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0167] Determine the starting point for planning your daily itinerary;

[0168] The toolset for the daily schedule is selected based on the tasks of the daily schedule, including:

[0169] The toolset for the daily itinerary is selected based on the planning starting point and the tasks of the daily itinerary.

[0170] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0171] If the daily itinerary is the first day's itinerary, then the vehicle's travel planning constraints are obtained, and the vehicle's current position in the travel planning constraints is used as the planning starting point of the first day's itinerary; or, the itinerary starting position carried in the multi-day itinerary planning request is used as the planning starting point of the first day's itinerary.

[0172] If the daily itinerary is a day other than the first day's itinerary, then the starting point for planning the other day's itinerary is determined based on the itinerary planning results or itinerary framework of the previous day's itinerary.

[0173] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0174] Match multiple candidate tools according to the multi-day itinerary planning request, and register the multiple candidate tools into the tool library;

[0175] The toolkit for selecting the daily schedule based on the tasks of the daily schedule includes:

[0176] The toolset is formed by selecting candidate tools from the tool library that match the task information of the daily schedule.

[0177] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0178] Based on the tool requirements corresponding to the tasks in the daily schedule, special tools are built and added to the tool library.

[0179] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0180] The toolset is invoked in the order described to collect detailed itinerary content associated with the tasks of the daily schedule, thereby obtaining the original detailed itinerary content of the daily schedule.

[0181] The original detailed itinerary content of the daily itinerary is cleaned to obtain the target detailed itinerary content of the daily itinerary.

[0182] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0183] The detailed itinerary content of each day's itinerary is integrated to generate a multi-day itinerary plan.

[0184] The multi-day itinerary planning content is filled into the daily itinerary framework according to the cockpit output specifications to generate the itinerary planning result of the multi-day itinerary planning request; the cockpit output specifications include voice specifications and / or card specifications.

[0185] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0186] Based on the multi-day itinerary planning request, the task is decomposed in the time dimension to determine the daily stops and recommended points of interest, so as to generate a multi-day itinerary framework that includes daily itinerary tasks and itinerary framework.

[0187] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0188] Obtain the travel planning constraints of the vehicle; the travel planning constraints include at least one of the vehicle information, current location, driving range, and user preferences of the vehicle user;

[0189] The step of decomposing the task along the time dimension based on the multi-day itinerary planning request includes:

[0190] Based on the multi-day itinerary planning request and the travel planning constraints, the task is decomposed in the time dimension.

[0191] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0192] Upon receiving a multi-day trip planning request from a vehicle user, trip planning is performed based on the request to generate a multi-day trip framework; the multi-day trip framework includes the tasks for each day's trip and the trip framework for each day's trip.

[0193] Obtain the target detailed itinerary content associated with the tasks of the daily itinerary, and populate the itinerary framework of the daily itinerary according to the target detailed itinerary content to generate the itinerary planning result of the multi-day itinerary planning request.

[0194] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0195] Select the toolset for the daily schedule based on the tasks in the daily schedule, and determine the order in which the tools in the daily schedule are called.

[0196] The daily schedule's toolset is invoked in the specified invocation order to collect detailed schedule content associated with the tasks of the daily schedule, thereby generating the target detailed schedule content for the daily schedule.

[0197] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0198] Determine the starting point for planning your daily itinerary;

[0199] The toolset for the daily schedule is selected based on the tasks of the daily schedule, including:

[0200] The toolset for the daily itinerary is selected based on the planning starting point and the tasks of the daily itinerary.

[0201] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0202] If the daily itinerary is the first day's itinerary, then the vehicle's travel planning constraints are obtained, and the vehicle's current position in the travel planning constraints is used as the planning starting point of the first day's itinerary; or, the itinerary starting position carried in the multi-day itinerary planning request is used as the planning starting point of the first day's itinerary.

[0203] If the daily itinerary is a day other than the first day's itinerary, then the starting point for planning the other day's itinerary is determined based on the itinerary planning results or itinerary framework of the previous day's itinerary.

[0204] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0205] Match multiple candidate tools according to the multi-day itinerary planning request, and register the multiple candidate tools into the tool library;

[0206] The toolkit for selecting the daily schedule based on the tasks of the daily schedule includes:

[0207] The toolset is formed by selecting candidate tools from the tool library that match the task information of the daily schedule.

[0208] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0209] Based on the tool requirements corresponding to the tasks in the daily schedule, special tools are built and added to the tool library.

[0210] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0211] The toolset is invoked in the order described to collect detailed itinerary content associated with the tasks of the daily schedule, thereby obtaining the original detailed itinerary content of the daily schedule.

[0212] The original detailed itinerary content of the daily itinerary is cleaned to obtain the target detailed itinerary content of the daily itinerary.

[0213] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0214] The detailed itinerary content of each day's itinerary is integrated to generate a multi-day itinerary plan.

[0215] The multi-day itinerary planning content is filled into the daily itinerary framework according to the cockpit output specifications to generate the itinerary planning result of the multi-day itinerary planning request; the cockpit output specifications include voice specifications and / or card specifications.

[0216] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0217] Based on the multi-day itinerary planning request, the task is decomposed in the time dimension to determine the daily stops and recommended points of interest, so as to generate a multi-day itinerary framework that includes daily itinerary tasks and itinerary framework.

[0218] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0219] Obtain the travel planning constraints of the vehicle; the travel planning constraints include at least one of the vehicle information, current location, driving range, and user preferences of the vehicle user;

[0220] The step of decomposing the task along the time dimension based on the multi-day itinerary planning request includes:

[0221] Based on the multi-day itinerary planning request and the travel planning constraints, the task is decomposed in the time dimension.

[0222] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0223] Upon receiving a multi-day trip planning request from a vehicle user, trip planning is performed based on the request to generate a multi-day trip framework; the multi-day trip framework includes the tasks for each day's trip and the trip framework for each day's trip.

[0224] Obtain the target detailed itinerary content associated with the tasks of the daily itinerary, and populate the itinerary framework of the daily itinerary according to the target detailed itinerary content to generate the itinerary planning result of the multi-day itinerary planning request.

[0225] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0226] Select the toolset for the daily schedule based on the tasks in the daily schedule, and determine the order in which the tools in the toolset are called.

[0227] The toolset is invoked in the order described to collect detailed itinerary content associated with the tasks of the daily schedule, and the target detailed itinerary content of the daily schedule is generated.

[0228] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0229] Determine the starting point for planning your daily itinerary;

[0230] The toolset for the daily schedule is selected based on the tasks of the daily schedule, including:

[0231] The toolset for the daily itinerary is selected based on the planning starting point and the tasks of the daily itinerary.

[0232] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0233] If the daily itinerary is the first day's itinerary, then the vehicle's travel planning constraints are obtained, and the vehicle's current position in the travel planning constraints is used as the planning starting point of the first day's itinerary; or, the itinerary starting position carried in the multi-day itinerary planning request is used as the planning starting point of the first day's itinerary.

[0234] If the daily itinerary is a day other than the first day's itinerary, then the starting point for planning the other day's itinerary is determined based on the itinerary planning results or itinerary framework of the previous day's itinerary.

[0235] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0236] Match multiple candidate tools according to the multi-day itinerary planning request, and register the multiple candidate tools into the tool library;

[0237] The toolset for selecting daily schedules based on the tasks of the daily schedule includes:

[0238] The toolset is formed by selecting candidate tools from the tool library that match the task information of the daily schedule.

[0239] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0240] Based on the tool requirements corresponding to the tasks in the daily schedule, special tools are built and added to the tool library.

[0241] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0242] The toolset is invoked in the order described to collect detailed itinerary content associated with the tasks of the daily schedule, thereby obtaining the original detailed itinerary content of the daily schedule.

[0243] The original detailed itinerary content of the daily itinerary is cleaned to obtain the target detailed itinerary content of the daily itinerary.

[0244] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0245] The detailed itinerary content of each day's itinerary is integrated to generate a multi-day itinerary plan.

[0246] The multi-day itinerary planning content is filled into the daily itinerary framework according to the cockpit output specifications to generate the itinerary planning result of the multi-day itinerary planning request; the cockpit output specifications include voice specifications and / or card specifications.

[0247] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0248] Based on the multi-day itinerary planning request, the task is decomposed in the time dimension to determine the daily stops and recommended points of interest, so as to generate a multi-day itinerary framework that includes daily itinerary tasks and itinerary framework.

[0249] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0250] Obtain the travel planning constraints of the vehicle; the travel planning constraints include at least one of the vehicle information, current location, driving range, and user preferences of the vehicle user;

[0251] The step of decomposing the task along the time dimension based on the multi-day itinerary planning request includes:

[0252] Based on the multi-day itinerary planning request and the travel planning constraints, the task is decomposed in the time dimension.

[0253] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0254] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0255] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0256] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A trip planning method, characterized in that, The method includes: Upon receiving a multi-day trip planning request from a vehicle user, trip planning is performed based on the request to generate a multi-day trip framework; the multi-day trip framework includes the tasks for each day's trip and the trip framework for each day's trip. Obtain the target detailed itinerary content associated with the tasks of the daily itinerary, and populate the itinerary framework of the daily itinerary according to the target detailed itinerary content to generate the itinerary planning result of the multi-day itinerary planning request.

2. The method according to claim 1, characterized in that, The process of obtaining the target detailed itinerary content associated with the tasks in the daily itinerary includes: Select the toolset for the daily schedule based on the tasks in the daily schedule, and determine the order in which the tools in the daily schedule are called. The daily schedule's toolset is invoked in the specified invocation order to collect detailed schedule content associated with the tasks of the daily schedule, thereby generating the target detailed schedule content for the daily schedule.

3. The method according to claim 2, characterized in that, The method further includes: Determine the starting point for planning your daily itinerary; The toolset for each daily schedule is selected based on the tasks described in the daily schedule, including: The toolset for the daily itinerary is selected based on the planning starting point and the tasks of the daily itinerary.

4. The method according to claim 3, characterized in that, The method further includes: If the daily itinerary is the first day's itinerary, then the vehicle's travel planning constraints are obtained, and the vehicle's current position in the travel planning constraints is used as the planning starting point of the first day's itinerary; or, the itinerary starting position carried in the multi-day itinerary planning request is used as the planning starting point of the first day's itinerary. If the daily itinerary is a day other than the first day's itinerary, then the starting point for planning the other day's itinerary is determined based on the itinerary planning results or itinerary framework of the previous day's itinerary.

5. The method according to claim 2, characterized in that, The method further includes: Match multiple candidate tools according to the multi-day itinerary planning request, and register the multiple candidate tools into the tool library; The toolkit for selecting the daily schedule based on the tasks of the daily schedule includes: The toolset is formed by selecting candidate tools from the tool library that match the task information of the daily schedule.

6. The method according to claim 5, characterized in that, The method further includes: Based on the tool requirements corresponding to the tasks in the daily schedule, special tools are built and added to the tool library.

7. The method according to claim 2, characterized in that, The step of calling the toolset in the order of invocation to collect detailed itinerary content associated with the tasks of the daily itinerary and generating the target detailed itinerary content of the daily itinerary includes: The toolset is invoked in the order described to collect detailed itinerary content associated with the tasks of the daily schedule, thereby obtaining the original detailed itinerary content of the daily schedule. The original detailed itinerary content of the daily itinerary is cleaned to obtain the target detailed itinerary content of the daily itinerary.

8. The method according to any one of claims 1-7, characterized in that, The step of filling in the daily itinerary framework based on the target detailed itinerary content to generate the itinerary planning result of the multi-day itinerary planning request includes: The detailed itinerary content of each day's itinerary is integrated to generate a multi-day itinerary plan. The multi-day itinerary planning content is filled into the daily itinerary framework according to the cockpit output specifications to generate the itinerary planning result of the multi-day itinerary planning request; the cockpit output specifications include voice specifications and / or card specifications.

9. The method according to claim 1, characterized in that, The step of planning the itinerary based on the multi-day itinerary planning request and generating a multi-day itinerary framework includes: Based on the multi-day itinerary planning request, the task is decomposed in the time dimension to determine the daily stops and recommended points of interest, so as to generate a multi-day itinerary framework that includes daily itinerary tasks and itinerary framework.

10. The method according to claim 9, characterized in that, The method further includes: Obtain the travel planning constraints of the vehicle; the travel planning constraints include at least one of the vehicle information, current location, driving range, and user preferences of the vehicle user; The step of decomposing the task along the time dimension based on the multi-day itinerary planning request includes: Based on the multi-day itinerary planning request and the travel planning constraints, the task is decomposed in the time dimension.

11. A vehicle-mounted system, characterized in that, The in-vehicle system includes an interface module and a multi-agent cooperation engine; the multi-agent cooperation engine includes a supervisor agent and at least one executive agent; the executive agent includes a tool selection agent and an output agent. Specifically, the output interface of the interface module is connected to the input interface of the supervisor agent; the output interface of the supervisor agent is connected to the input interface of the tool selection agent; the output interface of the tool selection agent is connected to the input interface of the output agent; and the output interface of the output agent is connected to the input interface of the interface module. The interface module is configured to receive a multi-day trip planning request triggered by a vehicle user and send the multi-day trip planning request to the supervisory agent; it is also configured to output the trip planning result corresponding to the multi-day trip planning request. The supervisory agent is used to perform itinerary planning based on the multi-day itinerary planning request when it receives the multi-day itinerary planning request, and generate a multi-day itinerary framework; the multi-day itinerary framework includes the tasks of each day's itinerary and the itinerary framework of each day's itinerary; The tool selects an intelligent agent to obtain detailed target itinerary content associated with the tasks in the daily itinerary. The output agent is used to fill in the daily itinerary framework according to the target detailed itinerary content, generate the itinerary planning result of the multi-day itinerary planning request, and transmit the itinerary planning result to the interface module.

Images