Task processing method, device, system, electronic device, storage medium and product

Abstract

The present disclosure relates to a task processing method, device, system, electronic device, storage medium and product. The method comprises: generating a plurality of travel planning sub-tasks corresponding to a target travel intention; any travel planning sub-task corresponds to at least one sub-travel in the target travel intention; distributing the plurality of travel planning sub-tasks to a plurality of sub-agents; different sub-agents receive different travel planning sub-tasks; receiving sub-travel planning information sent by the plurality of sub-agents; the sub-travel planning information is obtained based on the plurality of sub-agents processing the travel planning sub-tasks received by each sub-agent; and performing information fusion on the sub-travel planning information sent by the plurality of sub-agents to obtain travel planning information corresponding to the target travel intention. The present disclosure improves the task processing efficiency of complex travel planning tasks.

Description

Technical Field

[0001] This disclosure relates to the field of smart mobility technology, and in particular to a task processing method, apparatus, system, electronic device, storage medium, and product. Background Technology

[0002] Trip planning refers to the process of systematically designing aspects such as transportation, routes, time, accommodation, and dining based on the travel needs of travelers. It aims to provide travelers with efficient, reasonable, and feasible travel arrangements, thereby improving their travel experience and efficiency.

[0003] The route planning methods in related technologies often suffer from long processing times and abnormalities when dealing with complex tasks, making it difficult to adapt to complex scenarios and resulting in low overall processing efficiency. Summary of the Invention

[0004] This disclosure provides a task processing method, apparatus, system, electronic device, storage medium, and product to at least solve the problem of low processing efficiency for complex tasks in related technologies. The technical solution of this disclosure is as follows: According to a first aspect of the present disclosure, a task processing method is provided, comprising: Generate multiple trip planning subtasks corresponding to the target trip intent; each trip planning subtask corresponds to at least one segment of the target trip intent, and the multiple trip planning subtasks are independent of each other; Multiple trip planning subtasks are distributed to multiple sub-agents; different sub-agents receive different trip planning subtasks. Receives sub-trip planning information from multiple sub-agents; the sub-trip planning information is obtained by the multiple sub-agents processing the trip planning sub-tasks they received. Information fusion is performed on the sub-trip planning information sent by multiple sub-agents to obtain the trip planning information corresponding to the target trip intention.

[0005] According to a second aspect of the present disclosure, a task processing method is provided, comprising: Receive trip planning sub-tasks distributed by the main intelligent agent; trip planning sub-tasks are tasks generated by the main intelligent agent based on the target trip intent; each trip planning sub-task corresponds to at least one sub-trip in the target trip intent; Process the itinerary planning sub-tasks to obtain the sub-itinerary planning information corresponding to the itinerary planning sub-tasks; Send the sub-trip planning information corresponding to the trip planning sub-task to the main intelligent agent; so that the main intelligent agent can perform information fusion based on the sub-trip planning information corresponding to the trip planning sub-task to obtain the trip planning information corresponding to the target trip intention.

[0006] According to a third aspect of the present disclosure, a task processing method is provided, comprising: The main agent generates multiple trip planning subtasks corresponding to the target trip intent and distributes the multiple trip planning subtasks to multiple sub-agents; each trip planning subtask corresponds to at least one segment of the target trip intent, and the trip planning subtasks received by different sub-agents are different, and the multiple trip planning subtasks are independent of each other; Multiple sub-agents process their respective received trip planning sub-tasks to obtain sub-trip planning information; and then send the sub-trip planning information to the main agent. The main intelligent agent fuses the sub-trip planning information sent by multiple sub-intelligent agents to obtain the trip planning information corresponding to the target trip intention.

[0007] According to a fourth aspect of the present disclosure, a task processing apparatus is provided, comprising: The subtask generation module is used to generate multiple trip planning subtasks corresponding to the target trip intent; each trip planning subtask corresponds to at least one sub-trip in the target trip intent, and the multiple trip planning subtasks are independent of each other. The subtask distribution module is used to distribute multiple trip planning subtasks to multiple sub-agents; different sub-agents receive different trip planning subtasks. The sub-trip planning information receiving module is used to receive sub-trip planning information sent by multiple sub-agents; the sub-trip planning information is obtained by multiple sub-agents processing the trip planning sub-tasks they receive. The sub-trip planning information fusion module is used to fuse sub-trip planning information sent by multiple sub-agents to obtain the trip planning information corresponding to the target trip intention.

[0008] According to a fifth aspect of the present disclosure, a task processing apparatus is provided, comprising: The subtask receiving module is used to receive trip planning subtasks distributed by the main agent; the trip planning subtask is a task generated by the main agent based on the target trip intent; any trip planning subtask corresponds to at least one sub-trip in the target trip intent; The subtask processing module is used to process the itinerary planning subtasks and obtain the sub-itinerary planning information corresponding to the itinerary planning subtasks. The sub-trip planning information sending module is used to send the sub-trip planning information corresponding to the trip planning sub-task to the main intelligent agent; so that the main intelligent agent can perform information fusion based on the sub-trip planning information corresponding to the trip planning sub-task to obtain the trip planning information corresponding to the target trip intention.

[0009] According to a sixth aspect of the present disclosure, a task processing system is provided, comprising: The main agent generates multiple trip planning subtasks corresponding to the target trip intent and distributes the multiple trip planning subtasks to multiple sub-agents; each trip planning subtask corresponds to at least one segment of the target trip intent, and different sub-agents receive different trip planning subtasks, and the multiple trip planning subtasks are independent of each other; Multiple sub-agents process the received trip planning sub-tasks to obtain sub-trip planning information and send the sub-trip planning information to the main agent. The main intelligent agent is also used to fuse the sub-trip planning information sent by multiple sub-intelligent agents to obtain the trip planning information corresponding to the target trip intention.

[0010] According to a seventh aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the task processing method described above.

[0011] According to an eighth aspect of the present disclosure, a computer-readable storage medium is provided that, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the task processing method described above.

[0012] According to a ninth aspect of the present disclosure, a computer program product is provided, comprising a computer program stored in a readable storage medium, wherein at least one processor of a computer device reads from the readable storage medium and executes the computer program, causing the device to perform the task processing method described above.

[0013] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects: In this disclosure, the main intelligent agent generates trip planning subtasks corresponding to multiple sub-trips in the target trip intent, and distributes the multiple trip planning subtasks to multiple sub-intelligent agents. The sub-intelligent agents can process the received trip planning subtasks to obtain sub-trip planning information. The main intelligent agent can fuse the sub-trip planning information sent by multiple sub-intelligent agents to obtain the trip planning information corresponding to the target trip intent.

[0014] Specifically, the main agent breaks down the target travel intention into multiple independent travel planning subtasks and distributes them to multiple sub-agents for parallel processing. Each sub-agent, based on its comprehensive planning capabilities, independently generates a sub-travel planning scheme containing complete local information. Subsequently, the main agent fuses these schemes and outputs the final travel planning result.

[0015] This scheme, through the distributed collaborative deployment of the main intelligent agent and multiple sub-intelligent agents, fully leverages the independence between the trip planning sub-tasks, provides a foundation for parallel processing, and significantly improves the carrying capacity and processing efficiency for complex trip planning tasks.

[0016] Meanwhile, since each sub-agent only plans for its own clearly defined independent trip planning sub-tasks, the sub-trip planning information it generates is a relatively complete sub-trip solution. Therefore, during the fusion phase, the main agent only needs to splice and structurally integrate the various independent sub-trip solutions based on the trip sequence, avoiding the complex cross-fusion problems caused by the lack of an effective splitting mechanism in existing technologies, and further improving the convenience and overall efficiency of trip planning information fusion.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0019] Figure 1 This is a schematic diagram of an implementation environment according to an exemplary embodiment.

[0020] Figure 2 This is a flowchart illustrating a system-side task processing method according to an exemplary embodiment.

[0021] Figure 3 This is a flowchart illustrating a task processing method on the main intelligent agent side according to an exemplary embodiment.

[0022] Figure 4 This is a flowchart illustrating a task processing method on the sub-agent side according to an exemplary embodiment.

[0023] Figure 5 This is a system architecture diagram of a task processing system according to an exemplary embodiment.

[0024] Figure 6 This is a schematic diagram illustrating the implementation flow of a task processing method according to an exemplary embodiment.

[0025] Figure 7 This is a schematic diagram illustrating a trip planning information display according to an exemplary embodiment.

[0026] Figure 8 This is a block diagram of a task processing apparatus according to an exemplary embodiment.

[0027] Figure 9 This is a block diagram of another task processing apparatus according to an exemplary embodiment.

[0028] Figure 10 This is a schematic diagram of an electronic device structure according to an exemplary embodiment.

[0029] Figure 11 This is a schematic diagram of another electronic device structure according to an exemplary embodiment. Detailed Implementation

[0030] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0031] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0032] 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 display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0033] Before detailing the embodiments of this application, the technical terms related to the embodiments of this application will be explained first: Large Language Model (LLM) and Multi-Agent System: This embodiment uses a large language model as the underlying model for the main agent and sub-agents. The main agent and multiple sub-agents work together through role division and collaboration (the main agent is responsible for trip breakdown and overall planning, while the sub-agents are responsible for the independent execution of trip planning sub-tasks) to complete the trip planning task based on the target trip intent.

[0034] Tool invocation: refers to the process by which an intelligent agent accesses an external system through a predefined interface. In this embodiment, the main intelligent agent can obtain traffic information through tool invocation to facilitate traffic planning for any two adjacent sub-trips; sub-intelligent agents can obtain traffic information, points of interest information, weather services, etc., through tool invocation to generate sub-trip planning information.

[0035] Verification and judgment models: These models are responsible for evaluating the global synergy of multi-agent schemes and the rationality of sub-agent schemes.

[0036] In travel planning scenarios, travelers provide their intended travel itinerary, and the system generates corresponding travel planning information accordingly. With the development of electronic maps and tourism, users' travel needs are becoming increasingly diverse, including long-distance intercity travel, local city sightseeing, short road trips, and scenic area tours. These scenarios often involve complex travel intentions, such as those involving multiple locations, multiple days, multiple modes of transportation, and multiple constraints. Currently, related technologies suffer from long processing times and low overall efficiency when handling complex travel planning tasks.

[0037] In view of this, this disclosure provides a new approach. To facilitate understanding of this application, the implementation environment on which this application is based is first described. Please refer to... Figure 1 The illustration shows an implementation environment provided by an embodiment of the present disclosure. The implementation environment may include at least one terminal 110 and a server 120, which can communicate with each other via a network.

[0038] Optionally, terminal 110 may include: smartphones, tablets, laptops, digital assistants, smart wearable devices, in-vehicle terminals, servers, etc. Terminal 110 has an interactive application installed and running. In this embodiment, the interactive application may be an application providing trip planning functionality, such as a map application, social application, instant messaging application, live streaming application, game application, e-commerce application, virtual reality (VR) application, augmented reality (AR) application, etc. This application embodiment does not limit the specific type of application.

[0039] Optionally, server 120 provides background services for the interactive application installed on terminal 110. Terminal 110 can communicate with server 120 based on browser / server (B / S) mode or client / server (C / S) mode. The operating system running on terminal 110 in this embodiment may include, but is not limited to, Android, iOS, Linux, Windows, etc.

[0040] Server 120 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0041] In travel scenarios, travelers can input their intended travel route through a visual interactive interface provided by the terminal. After receiving the intention, the server performs trip planning processing, generates corresponding trip planning information, and sends the trip planning information to the terminal. The terminal can display the trip planning information in a visual form on the interactive interface. The trip planning information may include at least one of the following: planned route, waypoints, trip sequence, and mode of transportation information, so that travelers can intuitively view and confirm the trip planning results.

[0042] Figure 2 This is a flowchart of a task processing method provided in an embodiment of this application. The method can be... Figure 1 The server shown executes the action, and a main agent and multiple sub-agents can be deployed on the server. For example... Figure 2 As shown, the method may include the following steps: S210. The main agent generates multiple trip planning subtasks corresponding to the target trip intention, and distributes the multiple trip planning subtasks to multiple sub-agents; each trip planning subtask corresponds to at least one segment of the target trip intention, and the trip planning subtasks received by different sub-agents are different, and the multiple trip planning subtasks are independent of each other.

[0043] S220. Multiple sub-agents process the received trip planning sub-tasks to obtain sub-trip planning information; and send the sub-trip planning information to the main agent.

[0044] S230. The main intelligent agent fuses the sub-trip planning information sent by multiple sub-intelligent agents to obtain the trip planning information corresponding to the target trip intention.

[0045] The steps of the task processing method and the corresponding technical effects are described in detail below from the perspectives of the main intelligent agent and the sub-intelligent agents, respectively, with reference to the embodiments.

[0046] In an optional embodiment, the implementation flow of the task processing method can be described from the perspective of the main intelligent agent; see the relevant documentation for details. Figure 3 It illustrates a task processing method on the main intelligent agent side, which may include: S310. Generate multiple trip planning subtasks corresponding to the target trip intent; each trip planning subtask corresponds to at least one segment of the target trip intent, and the multiple trip planning subtasks are independent of each other.

[0047] In this embodiment, the main intelligent agent, as the global control entity for the overall trip planning task, is responsible for determining multiple sub-trips based on the target trip intention and generating corresponding trip planning sub-tasks for each sub-trip. Any trip planning sub-task can be a sub-task that plans a single sub-trip, or a sub-task that plans two or more sub-trips.

[0048] A target trip intent can be an expression of a traveler's travel goals, needs, and constraints, and can include intent information in the form of text, voice, images, and video. Trip elements included in a target trip intent may include: travel locations, such as departure point, destination, and points of interest along the way; travel time, such as departure time, arrival time, tour duration, and total trip duration; and travel constraint information, such as transportation preferences, budget, and comfort requirements.

[0049] In one example, if the user's intended itinerary is "I want to spend three days in city A, visiting attractions a, b, and c, then three days in city B, and finally returning home (city C)," the main agent extracts the itinerary elements: the locations (city A, city B, city C, attractions a, b, and c) and the duration (three days for each). Based on these elements, it breaks down the itinerary into "Sub-itinerary 1: Three days in city A" and "Sub-itinerary 2: Three days in city B," generating corresponding itinerary planning subtasks: "Itinerary Planning Subtask 1: Planning an itinerary for three days in city A" and "Itinerary Planning Subtask 2: Planning an itinerary for three days in city B."

[0050] In this embodiment, a sub-trip can be a relatively independent and separately planned trip unit that is split from the target trip corresponding to the target trip intent. The main intelligent agent can extract the trip elements from the target trip intent and automatically split the target trip intent to ensure that multiple sub-trips can be combined to form a complete target trip according to a preset time sequence or logical relationship.

[0051] S320. Distribute multiple trip planning subtasks to multiple sub-agents; different sub-agents receive different trip planning subtasks.

[0052] In this embodiment, the main intelligent agent can determine the number of sub-intelligent agents to be scheduled based on the number of tasks in the trip planning sub-tasks, thereby determining multiple sub-intelligent agents to be scheduled. It should be noted that the number of trip planning sub-tasks can be greater than or equal to the number of sub-intelligent agents to be scheduled. Different sub-intelligent agents may receive the same or different number of trip planning sub-tasks. A sub-intelligent agent can be a local execution entity oriented towards a trip planning sub-task.

[0053] In one optional embodiment, each sub-agent can correspond to a specific travel location and specifically handle sub-trips containing that location. The same travel location can correspond to at least one sub-agent. Optionally, each sub-agent can be trained using training samples associated with the target travel location. For example, for the travel planning sub-tasks "spend three days in city A" and "spend three days in city B," the sub-agents can be sent to sub-agents trained using travel planning training samples from cities A and B, respectively. By distributing travel planning sub-tasks to suitable sub-agents for task processing, the processing efficiency of travel planning sub-tasks can be improved.

[0054] In another alternative embodiment, the master agent may also determine multiple sub-agents to be scheduled based on the load status of each sub-agent, and distribute multiple schedule planning sub-tasks to the multiple sub-agents; the corresponding determined sub-agents to be scheduled may be multiple sub-agents with low load rates.

[0055] S330. Receive sub-trip planning information sent by multiple sub-agents; the sub-trip planning information is obtained by the multiple sub-agents processing the trip planning sub-tasks they received.

[0056] Each sub-agent, upon receiving a trip planning sub-task distributed by the master agent, can process the received trip planning sub-task, obtain the corresponding sub-trip planning information, and send it to the master agent.

[0057] For example, in the example above, the main agent can receive the sub-trip planning information corresponding to sub-trip 1 and the sub-trip planning information corresponding to sub-trip 2, respectively.

[0058] S340. Information fusion is performed on the sub-trip planning information sent by multiple sub-agents to obtain the trip planning information corresponding to the target trip intention.

[0059] Since each sub-agent possesses comprehensive trip planning capabilities, the sub-trip planning information it outputs is a relatively complete local solution (sub-trip planning scheme). Therefore, the main agent only needs to splice and structure the individual sub-trip schemes to obtain the trip planning information corresponding to the target trip intention.

[0060] Furthermore, during the process of splicing sub-trip planning information, if the target trip intention indicates the trip order of each sub-trip segment, the sub-trip planning information can be spliced ​​based on the trip order; if the target trip intention does not indicate the trip order of each sub-trip segment, the sub-trip planning information can be spliced ​​randomly, or the sub-trip planning information corresponding to each sub-trip segment can be spliced ​​according to the reasonableness of the sorting of different sub-trip segments.

[0061] The master agent breaks down the target travel intention into multiple independent travel planning subtasks and distributes them to multiple sub-agents for parallel processing. Each sub-agent, based on its comprehensive planning capabilities, independently generates a sub-travel planning scheme containing complete local information. Subsequently, the master agent fuses these schemes and outputs the final travel planning result.

[0062] This scheme, through the distributed collaborative deployment of a master agent and multiple sub-agents, fully leverages the independence between subtasks, providing a foundation for parallel processing and significantly improving the capacity and efficiency for handling complex trip planning tasks. Simultaneously, since each sub-agent only plans for its own clearly defined and independent sub-trips, the generated sub-trip planning information consists of relatively complete sub-trip schemes. Therefore, during the fusion phase, the master agent only needs to splice and structurally integrate the various independent sub-trip schemes based on the trip sequence, avoiding the complex cross-fusion problems caused by the lack of an effective decomposition mechanism in existing technologies, further improving the convenience and overall efficiency of trip planning information fusion.

[0063] Optionally, in this embodiment, trip elements can be extracted from the target trip intent, and then the target trip can be split based on the extraction results to obtain multiple sub-trips. Correspondingly, multiple trip planning sub-tasks corresponding to the target trip intent are generated, including: Extract travel elements from the target travel intention to obtain travel locations and travel times; The itinerary is broken down based on the travel location and travel time to obtain multiple segments of the itinerary; Generate multiple segments of the itinerary, each corresponding to a itinerary planning subtask.

[0064] In this embodiment, the itinerary elements are key elements that characterize the target itinerary intention. Different itinerary intentions may include different itinerary elements. By extracting the itinerary elements from the target itinerary intention, the corresponding itinerary location and itinerary time can be obtained. The itinerary location may include at least one of the following: the departure point, destination, and points of interest along the way. The itinerary time includes at least one of the following: departure time, arrival time, tour duration, and overall itinerary duration.

[0065] In one optional embodiment, a correspondence between travel locations and travel times can be established. A set of travel locations and travel times with a corresponding relationship can form a sub-trip. Then, multiple sets of travel locations and travel times with a corresponding relationship can be determined based on the extracted travel locations and travel times, thereby obtaining multiple sub-trips.

[0066] Optionally, when the destinations extracted from the target travel intention include multiple transit points, a sub-trip can be determined based on the multiple transit points and their corresponding travel times. For example, the target travel intention could be "I want to go to city A for three days, and I must visit attractions a, b, and c, then go to city B for three days, and then go home (city C). Please help me plan this." The extracted transit points could include city A and city B, and the extracted travel times could be three days in city A and three days in city B. Accordingly, the overall trip can be divided into sub-trip 1: three days in city A, and sub-trip 2: three days in city B. Furthermore, the above sub-trips can be further subdivided. For example, sub-trip 1 can be further subdivided into sub-trip 11: day 1 in city A, sub-trip 12: day 2 in city A, and sub-trip 13: day 3 in city A; similarly, sub-trip 2 can be subdivided into sub-trip 21, sub-trip 22, and sub-trip 23. The specific granularity of the sub-trip division can be determined according to the actual situation, and this embodiment does not limit it.

[0067] Optionally, the travel destinations extracted from the target travel intention include a transit point. Sub-trips can be split based on multiple associated regions corresponding to this transit point, with each associated region corresponding to one sub-trip. The associated region corresponding to the transit point can be a geographical area or a neighboring area of ​​the transit point, or an area accessible by transportation, functionally related, or covered by services from the transit point. Furthermore, a sub-trip can be determined based on each associated region and the travel time. For example, if the target travel intention is "I want to go to city A for three days," the transit point is extracted as city A, and multiple associated regions of city A are determined (such as associated region D, associated region E, and associated region F). Based on this, the overall trip is split into: Sub-trip 1: Spend one day in associated region D, Sub-trip 2: Spend one day in associated region E, and Sub-trip 3: Spend one day in associated region F.

[0068] In this embodiment, key elements representing the target trip intention (such as trip location and trip time) are extracted to facilitate trip segmentation based on key elements, thereby improving the convenience and efficiency of trip segmentation.

[0069] When a trip is broken down into multiple sub-trips based on the target trip intent, the main agent can generate trip planning sub-tasks corresponding to each of the sub-trips; optionally, generating trip planning sub-tasks corresponding to each of the multiple sub-trips includes: Obtain traffic information between adjacent sub-trips; Based on traffic information between adjacent sub-trips and the travel sequence of multiple sub-trips, traffic planning information between adjacent sub-trips is generated; the travel sequence represents the order in which multiple sub-trips are completed, and is determined based on the target travel intention. Based on the traffic planning information between adjacent sub-trips, the arrival time and departure time of each sub-trip are determined; the arrival time of each sub-trip is the time when it arrives at the associated location of each sub-trip, and the departure time of each sub-trip is the time when it leaves the associated location, and the associated location is the location passed through by each sub-trip. Based on the arrival and departure times of each segment of the trip, generate trip planning subtasks for each segment of the trip.

[0070] Traffic information between any two adjacent sub-trips includes the mode of transportation connecting the adjacent sub-trips (such as trains, long-distance buses, airplanes, etc.), travel time cost, toll cost, and transfer convenience. The main intelligent agent can perform global-level traffic planning by calling relevant train / bus / flight tools and estimated arrival time tools, thus enabling traffic planning between multiple sub-trips.

[0071] When the target itinerary intention clearly indicates the order of the multiple sub-trips, the order of the corresponding multiple sub-trips shall be consistent with the order indicated in the target itinerary intention; when the target itinerary intention does not clearly indicate the order of the multiple sub-trips, a reasonable itinerary order may be determined randomly or based on the geographical relationship between the multiple sub-trips.

[0072] Traffic planning information between any two adjacent sub-trips refers to the information related to the planned modes of transportation from the end point of the previous sub-trip to the start point of the next sub-trip, in order to achieve a smooth connection. Based on the trip sequence and associated locations of multiple sub-trips, the starting and ending points of traffic planning can be determined, and then, combined with traffic information, the traffic planning information between adjacent sub-trips can be determined.

[0073] Based on the generated traffic planning information, the arrival and departure times of each sub-trip can be determined. For the current sub-trip, its arrival time can be the time when it departs from the associated location of the previous sub-trip and arrives at the associated location of the current sub-trip, and the departure time of the current sub-trip can be the time when it departs from the associated location of the current sub-trip and goes to the associated location of the next sub-trip.

[0074] In this embodiment, the main intelligent agent can also plan the transportation from the current location of the traveler to the first destination to determine the arrival time of the first sub-trip; and plan the transportation from the last destination back to the current location of the traveler to determine the departure time of the last sub-trip.

[0075] For example, if the target travel intention is "I want to spend three days in city A, visiting attractions a, b, and c, then three days in city B, and finally returning home (city C), please plan it for me," the main agent generates sub-itinerary 1: three days in city A, and sub-itinerary 2: three days in city B. If sub-itinerary 1 precedes sub-itinerary 2 in the travel sequence, the traffic planning information can include: traffic planning information from city C (the traveler's current location) to city A, traffic planning information from city A to city B, and traffic planning information from city B to city C. This determines the arrival times in city A, departure times in city A, arrival times in city B, and departure times in city B. The arrival / departure times in city A constitute the time constraint for sub-itinerary 1; the arrival / departure times in city B constitute the time constraint for sub-itinerary 2.

[0076] After obtaining the arrival and departure times of each sub-trip, the corresponding trip planning sub-tasks for each sub-trip can be generated. The arrival and departure times of each sub-trip constitute time planning constraints for the trip planning of the sub-trips, instructing the sub-agent to perform local trip planning while satisfying global traffic connectivity, thereby avoiding conflicts between local sub-trip planning and global trip planning, and improving the rationality and global consistency of trip planning.

[0077] In one optional embodiment, the target trip intent is the traveler's expression of at least one piece of information, such as travel goal, travel needs, and travel constraints, representing the overall intent of the target trip. When multiple sub-trips are derived based on the target trip intent, each sub-trip can correspond to a specific sub-trip intent. Optionally, based on the arrival times and departure times of each of the multiple sub-trips, a trip planning sub-task corresponding to each of the multiple sub-trips is generated, including: The intent of the target trip is reconstructed to generate the sub-trip intents corresponding to each of the multiple sub-trip segments. Based on the arrival time, departure time, and sub-trip intention of each segment of the trip, a trip planning sub-task is generated for each segment of the trip.

[0078] In this embodiment, intention reconstruction of the target trip intention can be achieved by extracting the intention information associated with multiple sub-trips from the target trip intention and combining them to generate clear, independent and executable sub-trip intentions.

[0079] For example, if the intended itinerary is "I want to spend three days in city A, and I must visit attractions a, b, and c, then I will spend three days in city B, and then go home (city C), please help me plan it out", the resulting sub-itineraries after breaking down the itinerary include sub-itinerary 1 (spending three days in city A) and sub-itinerary 2 (spending three days in city B); the intended itinerary for sub-itinerary 1 is "I want to spend three days in city A, and I must visit attractions a, b, and c", and the intended itinerary for sub-itinerary 2 is "a three-day travel guide for city B".

[0080] The main agent can generate corresponding trip planning sub-tasks based on the arrival time, departure time, and sub-trip intention of each of the multiple sub-trips, so that the sub-agents can better understand the trip planning requirements and improve the accuracy of the sub-trip planning. Furthermore, since the sub-trip intention is obtained by reconstructing the global target trip intention, the corresponding sub-trip intention conforms to the global planning requirements, ensuring that the sub-trip planning is consistent with the overall trip goal and works in synergy with it.

[0081] After receiving sub-trip planning information from multiple sub-agents, the main agent can also perform a global consistency check on the sub-trip planning information sent by the multiple sub-agents; correspondingly, after receiving sub-trip planning information from multiple sub-agents, the method further includes: Detect whether the sub-trip planning information sent by multiple sub-agents meets the global trip planning conditions; the global trip planning conditions include: The arrival time of the first sub-trip is earlier than the trip start time in the sub-trip planning information corresponding to the first sub-trip; the arrival time of the first sub-trip is the time when it arrives at the associated location of the first sub-trip, and the associated location is the location that the first sub-trip passes through; The departure time of the last sub-trip is later than the trip end time in the sub-trip planning information corresponding to the last sub-trip; the departure time of the last sub-trip is the time of departure from the associated location of the last sub-trip; The sub-trip planning information sent by multiple sub-agents satisfies the preset object constraints, which are associated with the object configuration information of the travel object.

[0082] The main intelligent agent can have its own detection capabilities, or it can call other verification models to detect sub-trip planning information. Any model with sub-trip planning information detection capabilities can be applied to this embodiment, and this embodiment does not make any specific limitations.

[0083] In this embodiment, the first sub-trip and the last sub-trip are the first and last sub-trips in the trip sequence, respectively. The fact that the arrival time of the first sub-trip is earlier than the trip start time in the sub-trip planning information corresponding to the first sub-trip indicates that the arrival time and the trip start time of the first sub-trip are reasonably connected. Similarly, the fact that the departure time of the last sub-trip is later than the trip end time in the sub-trip planning information corresponding to the last sub-trip indicates that the departure time and the trip end time of the last sub-trip are reasonably connected.

[0084] Object configuration information can include object attribute information and object constraint information reflected in the target itinerary intent. Object constraint information can include required points of interest, fixed number of days, no early mornings, preferred cuisine, and a relaxed itinerary pace. Preset object constraints are based on these dimensions to constrain the itinerary planning information.

[0085] In this embodiment, after receiving sub-trip planning information sent by multiple sub-agents, the main agent improves the rationality and global consistency of the trip planning by detecting the rationality of time connection and the object constraint conditions.

[0086] If the main agent detects that there is sub-trip planning information that does not meet the preset trip planning conditions, it can issue a local correction instruction for the relevant sub-trip planning information to obtain sub-trip planning information that meets the preset trip planning conditions; optionally, the method for correcting the sub-trip planning information in this embodiment may include: In the case of sub-trip planning information that does not meet the preset trip planning conditions, determine the target sub-agent corresponding to the sub-trip planning information that does not meet the preset trip planning conditions; Send planning information correction instructions to the target sub-agent; Receive the corrected sub-trip planning information sent by the target sub-agent based on the planning information correction instruction.

[0087] Optionally, if the arrival time of the first sub-trip is not earlier than its trip start time, the sub-agent corresponding to the first sub-trip is identified as the target sub-agent, and a correction instruction containing the indication information of "inappropriate connection between arrival time and start time" is sent to it; if the departure time of the last sub-trip is later than its trip end time, the sub-agent corresponding to the last sub-trip is identified as the target sub-agent, and a correction instruction containing the indication information of "inappropriate connection between departure time and end time" is sent to it.

[0088] Furthermore, sub-agents whose sub-trip planning information does not meet preset object constraints can be designated as target sub-agents. Correspondingly, a planning information correction instruction can be sent to the target sub-agent, enabling it to correct its planning based on the instruction and obtain the corrected sub-trip planning information. The planning information correction instruction may include indications that the trip planning information does not meet preset object constraints.

[0089] In this embodiment, when the main agent detects that there is sub-trip planning information that does not meet the global trip planning conditions, the corresponding sub-agent can be scheduled to correct the sub-trip planning information to obtain sub-trip planning information that meets the global trip planning conditions, thus ensuring the accuracy of sub-trip planning and global consistency.

[0090] In one optional embodiment, information fusion is performed on the sub-trip planning information sent by multiple sub-agents to obtain trip planning information corresponding to the target trip intention, including: The sub-trip planning information sent by multiple sub-agents is spliced ​​together to obtain spliced ​​planning information; The splicing planning information is processed in a structured manner to generate structured travel planning information corresponding to the target travel intention.

[0091] Since each component possesses comprehensive trip planning capabilities, its output sub-trip planning information constitutes a relatively complete sub-trip planning scheme. The main agent can fuse the sub-trip planning information received from multiple sub-agents by directly concatenating the sub-trip planning information corresponding to different segments of the trip to obtain the trip planning information corresponding to the target trip intent. If the target trip intent indicates the trip order of each segment, the corresponding sub-trip planning information can be concatenated based on the trip order to obtain the concatenated planning information. If the target trip intent does not indicate the trip order of each segment, the corresponding sub-trip planning information can be randomly concatenated, or concatenated based on the reasonableness of the sorting of different segments to obtain the concatenated planning information.

[0092] Given the stitching planning information, it can be structured to obtain structured travel planning information corresponding to the target travel intention. Structured travel planning information may include at least: Itinerary titles and summaries are divided by city and day; Major transportation information between any two adjacent sub-trips (such as train / bus / plane schedules, times, departure / arrival cities); Transportation information (such as driving, walking, cycling, etc.) and estimated arrival time within each segment of the trip; POI card information (attractions, hotels, restaurants, etc. and their attributes) for each time period.

[0093] In this embodiment, structured data is used to represent the trip during the trip planning stage. City segments, dates, times, transportation, POI nodes, etc. are organized with standard fields. On the one hand, routes can be drawn directly and clickable POI detail cards can be rendered. On the other hand, it is also convenient for subsequent storage, retrieval and editing, avoiding the instability caused by secondary parsing of long text.

[0094] In an optional embodiment, the implementation process of the task processing method can be described from the perspective of the sub-agent; see the relevant documentation for details. Figure 4 It illustrates a task processing method on the sub-agent side, which may include: S410. Receive a trip planning subtask distributed by the main agent; the trip planning subtask is a task generated by the main agent based on the target trip intention; any trip planning subtask corresponds to at least one sub-trip in the target trip intention.

[0095] In this embodiment, the sub-agent is the main body that performs local execution of the trip planning sub-task. Any trip planning sub-task can be trip planning for a segment of a trip or multiple segments of a trip.

[0096] The intended purpose of a trip can be the expression of at least one of the following information by the traveler: travel goal, travel needs, travel constraints, etc. (in the form of text, voice, pictures, videos, etc.) to convey the purpose of the trip and the constraints of the traveler.

[0097] The travel elements included in the target travel intention may include: travel locations, such as departure point, destination, and points of interest along the way; travel time, such as departure time, arrival time, sightseeing duration, and total travel duration; and travel constraints, such as preferred mode of transportation, budget, and comfort requirements.

[0098] In this embodiment, a sub-trip can be a relatively independent and separately planned trip unit that is split from the target trip corresponding to the target trip intent. The main intelligent agent can extract the trip elements from the target trip intent and automatically split the target trip intent to ensure that multiple sub-trips can be combined to form a complete target trip according to a preset time sequence or logical relationship.

[0099] Accordingly, any trip planning subtask can be a task that instructs the planning of at least one segment of a trip. Trip planning subtasks are components of the overall trip planning task. An overall trip planning task can be broken down into multiple independent or collaborative trip planning subtasks.

[0100] In one example, if the user's intended itinerary is "I want to spend three days in city A, visiting attractions a, b, and c, then three days in city B, and finally returning home (city C)," the main agent extracts the itinerary elements: the locations (city A, city B, city C, attractions a, b, and c) and the duration (three days for each). Based on these elements, it breaks down the itinerary into "Sub-itinerary 1: Three days in city A" and "Sub-itinerary 2: Three days in city B," generating corresponding itinerary planning subtasks: "Itinerary Planning Subtask 1: Planning an itinerary for three days in city A" and "Itinerary Planning Subtask 2: Planning an itinerary for three days in city B."

[0101] S420. Perform task processing on the itinerary planning subtask to obtain the sub-itinerary planning information corresponding to the itinerary planning subtask.

[0102] Each sub-agent, upon receiving a trip planning sub-task distributed by the master agent, can process the received trip planning sub-task, obtain the corresponding sub-trip planning information, and send it to the master agent.

[0103] For example, for the itinerary planning sub-tasks of "planning a three-day trip in city A" and "planning a three-day trip in city B", the sub-agents process the information respectively, generate the corresponding sub-itinerary planning information, and send it to the main agent.

[0104] S430. Send the sub-trip planning information corresponding to the trip planning sub-task to the main intelligent agent; so that the main intelligent agent can perform information fusion based on the sub-trip planning information corresponding to the trip planning sub-task to obtain the trip planning information corresponding to the target trip intention.

[0105] Since each sub-agent possesses comprehensive trip planning capabilities, its output sub-trip planning information consists of relatively complete local solutions (sub-trip planning schemes). Therefore, the main agent only needs to splice and structurally integrate the various independent sub-trip schemes to obtain the trip planning information corresponding to the target trip intention.

[0106] Furthermore, in the process of splicing the sub-trip planning information corresponding to different segments of the trip, if the target trip intention indicates the trip order of each segment of the trip, the sub-trip planning information corresponding to each segment of the trip can be spliced ​​based on the trip order; if the target trip intention does not indicate the trip order of each segment of the trip, the sub-trip planning information corresponding to each segment of the trip can be spliced ​​randomly, or the sub-trip planning information corresponding to each segment of the trip can be spliced ​​based on the reasonableness of the sorting of different segments of the trip.

[0107] The master agent breaks down the target travel intention into multiple independent travel planning subtasks and distributes them to multiple sub-agents for parallel processing. Each sub-agent, based on its comprehensive planning capabilities, independently generates a sub-travel planning scheme containing complete local information. Subsequently, the master agent fuses these schemes and outputs the final travel planning result.

[0108] This scheme, through the distributed collaborative deployment of a master agent and multiple sub-agents, fully leverages the independence between subtasks, providing a foundation for parallel processing and significantly improving the capacity and efficiency for handling complex trip planning tasks. Simultaneously, since each sub-agent only plans for its own clearly defined and independent sub-trips, the generated sub-trip planning information consists of relatively complete sub-trip schemes. Therefore, during the fusion phase, the master agent only needs to splice and structurally integrate the various independent sub-trip schemes based on the trip sequence, avoiding the complex cross-fusion problems caused by the lack of an effective decomposition mechanism in existing technologies, further improving the convenience and overall efficiency of trip planning information fusion.

[0109] In one optional embodiment, the trip planning subtask includes the arrival time of at least one sub-trip and the departure time of at least one sub-trip; the arrival time of each sub-trip is the time when it arrives at the associated location of each sub-trip, and the departure time of each sub-trip is the time when it leaves the associated location, where the associated location is the location passed through by each sub-trip. The itinerary planning subtask is processed to obtain the sub-itinerary planning information corresponding to the itinerary planning subtask, including: Based on the arrival time of at least one sub-trip and the departure time of at least one sub-trip, perform trip planning on at least one sub-trip to obtain the sub-trip planning information corresponding to the trip planning sub-task.

[0110] The arrival and departure times of the multiple sub-trips included in the trip planning sub-task constitute time planning constraints for the trip planning of the multiple sub-trips. The trip planning sub-task generated based on the arrival and departure times can instruct the sub-agent to perform local trip planning for the multiple sub-trips under the premise of satisfying the time planning constraints, thereby avoiding conflicts between local sub-trip planning and global trip planning, and improving the rationality and global consistency of trip planning.

[0111] In another optional embodiment, when multiple sub-trips are obtained based on the target trip intent, each sub-trip may correspond to a corresponding sub-trip intent; accordingly, the trip planning sub-task also includes at least one sub-trip intent corresponding to a sub-trip; the sub-trip intent is obtained based on intent reconstruction of the target trip intent; Based on the arrival time of at least one sub-trip and the departure time of at least one sub-trip, perform trip planning on at least one sub-trip to obtain the sub-trip planning information corresponding to the trip planning sub-task, including: Based on the sub-trip intention corresponding to at least one sub-trip, the arrival time of at least one sub-trip, and the departure time of at least one sub-trip, trip planning is performed on at least one sub-trip to obtain the sub-trip planning information corresponding to the trip planning sub-task.

[0112] In this embodiment, intention reconstruction of the target trip intention can be achieved by extracting the intention information associated with multiple sub-trips from the target trip intention and combining the extracted intention information to obtain multiple clear, independent and executable sub-trip intentions.

[0113] For example, if the intended itinerary is "I want to spend three days in city A, and I must visit attractions a, b, and c, then I will spend three days in city B, and then go home (city C), please help me plan it out", the resulting sub-itineraries after breaking down the itinerary include sub-itinerary 1: spending three days in city A, and sub-itinerary 2: spending three days in city B. The intended itinerary for sub-itinerary 1 is "I want to spend three days in city A, and I must visit attractions a, b, and c", while the intended itinerary for sub-itinerary 2 is "a three-day travel guide for city B".

[0114] The main agent can generate corresponding trip planning subtasks based on the arrival time, departure time, and sub-trip intent of each of the multiple sub-trips. This allows the sub-agents that receive the trip planning subtasks to better understand the trip planning requirements based on the sub-trip intents, thereby improving the accuracy of the sub-trip planning. Furthermore, the sub-trip intents are obtained by reconstructing the global target trip intents. The corresponding sub-trip intents conform to the global planning requirements, ensuring that the sub-trip planning is consistent with and coordinated with the overall trip objective.

[0115] Furthermore, the sub-trip intent includes the point of interest intent; based on the arrival time of at least one sub-trip and the departure time of at least one sub-trip, trip planning is performed on at least one sub-trip to obtain the sub-trip planning information corresponding to the trip planning sub-task, including: Obtain at least one point of interest from the associated locations of at least one sub-trip; Information fusion is performed on at least one point of interest and the intent of the point of interest to determine the target point of interest corresponding to at least one sub-trip; Based on the target point of interest, the arrival time of at least one sub-trip, and the departure time of at least one sub-trip, perform trip planning for at least one sub-trip to obtain the sub-trip planning information corresponding to the trip planning sub-task.

[0116] Points of interest intent can include the points of interest that the traveler wants to visit. By combining the points of interest information and points of interest intent obtained from POI tools, point of interest planning information that meets the traveler's travel intent can be planned.

[0117] In another optional embodiment, based on the sub-trip intention corresponding to at least one sub-trip, the arrival time of at least one sub-trip, and the departure time of at least one sub-trip, trip planning is performed on at least one sub-trip to obtain sub-trip planning information corresponding to the trip planning sub-task, including: When there are multiple target points of interest determined based on the sub-trip intent corresponding to at least one sub-trip, determine the route order of the multiple target points of interest. Based on the route sequence of multiple target points of interest, the arrival time of at least one sub-trip, and the departure time of at least one sub-trip, a trip planning is performed on at least one sub-trip to obtain the sub-trip planning information corresponding to the trip planning sub-task. The path order represents the sequential order in which multiple target points of interest are reached. The path order is determined based on at least one of the following: Spatial location of multiple target points of interest, such as: distance between target points of interest, orientation relationship, etc.; Traffic information between multiple points of interest, such as travel time, mode of transportation, transfer convenience, and travel cost between the points of interest; Time constraints for multiple target points of interest, such as opening hours, closing times, and recommended visit time periods; Information on the constraints of a traveler on multiple target points of interest, such as preferences in the travel intention; Weather conditions for at least one segment of the trip, such as: sunny days allow for planning visits to outdoor points of interest, rainy days allow for planning visits to indoor points of interest, etc.

[0118] In this embodiment, the route sequence of multiple target points of interest can be determined from multiple dimensions such as spatial location, traffic information, time constraint information, object constraint information, and weather conditions during at least one segment of the journey, thereby improving the overall rationality and feasibility of the journey planning.

[0119] In one optional embodiment, based on the sub-trip intention corresponding to at least one sub-trip, the arrival time of at least one sub-trip, and the departure time of at least one sub-trip, trip planning is performed on at least one sub-trip to obtain sub-trip planning information corresponding to the trip planning sub-task, including: When there are multiple target points of interest determined based on the sub-trip intent corresponding to at least one sub-trip, traffic information between multiple target points of interest is obtained. Based on traffic information between multiple target points of interest, generate traffic planning information between multiple target points of interest; Based on traffic planning information between multiple target points of interest, arrival time of at least one sub-trip, and departure time of at least one sub-trip, trip planning is performed on at least one sub-trip to obtain sub-trip planning information corresponding to the trip planning sub-task.

[0120] The target interest points determined based on the sub-trip intent can be the interest points that the traveler wants to go to, as identified by the sub-agent from the sub-trip intent, or interest points recommended by the sub-agent.

[0121] The sub-agent can access traffic information between target points of interest within a sub-trip, such as estimated arrival time tools, including routes, modes of transportation, travel time and costs, road congestion, and transfer convenience. By performing traffic analysis on the traffic information between any two target points of interest, traffic analysis results can be obtained; subsequently, comprehensive traffic planning can be performed to obtain traffic planning information between multiple target points of interest.

[0122] Correspondingly, route planning can be performed based on traffic planning information between multiple target points of interest, arrival times of at least one sub-trip, and departure times of at least one sub-trip, to obtain corresponding sub-trip planning information. Based on the time planning constraints corresponding to the sub-trip, the sub-agent further plans the traffic between multiple target points of interest within the sub-trip, enabling refined planning of traffic information within the sub-trip and achieving smooth connection and efficient passage between each target point of interest.

[0123] In another optional embodiment, after processing the itinerary planning subtask to obtain the sub-itinerary planning information corresponding to the itinerary planning subtask, the method further includes: Detect information from at least one of the following detection dimensions corresponding to the sub-trip planning information: Traffic rationality detection in sub-trip planning information, such as whether the planned traffic modes for each road segment involve detours; Check the time rationality of the itinerary time in the sub-itinerary planning information, such as whether the itinerary time matches the opening time of the point of interest and the available reservation time; Check the rationality of the connection between sub-trip planning information, such as whether there is a smooth connection between sub-trips (before / after) and between points of interest within a sub-trip; Matching and detection of sub-trip planning information with the object configuration information of the travel object. For example, the object configuration information may include object attribute information and object constraint information reflected by the travel object in the target trip intention (such as required points of interest, fixed number of days, multiple food options, etc.).

[0124] In this embodiment, the sub-agent itself may have detection capabilities, or it may call other verification models to detect the sub-trip planning information. Any model with sub-trip planning information detection capabilities can be applied to this embodiment, and this embodiment does not impose any specific limitations.

[0125] In this embodiment, the sub-agent can detect the generated sub-trip planning information from multiple detection dimensions to identify planning defects (such as unreasonable traffic planning, unreasonable time planning, unreasonable connections, and mismatch with object configuration information) at the sub-trip level in advance, thereby improving the comprehensiveness and timeliness of sub-trip planning information detection. Furthermore, by having the sub-agent detect the sub-trip planning information in advance, local abnormal planning information can be eliminated in advance, reducing the cost for the main agent to initiate planning detection at the global level later, and improving the efficiency of multi-agent collaborative trip planning.

[0126] In an optional embodiment, if the sub-agent detects a planning defect in the sub-trip planning information, it can automatically correct the planning defect; correspondingly, the task processing method of this embodiment further includes: If there is an anomaly in the trip planning information of at least one detection dimension corresponding to the sub-trip planning information, the sub-trip planning information is automatically corrected based on at least one detection dimension to obtain the corrected sub-trip planning information.

[0127] Optionally, if the sub-agent automatically corrects the sub-trip planning information based on at least one detection dimension, it can re-obtain the information required for trip planning by calling the external tool corresponding to the corresponding detection dimension, and correct the planning defects based on the obtained information. That is, by making targeted corrections to the planning information with defects, the corrected sub-trip planning information can be obtained.

[0128] For example, if a detour is detected between point of interest 1 and point of interest 2 in the sub-trip planning information, the sub-agent can re-invoke the estimated arrival time tool to obtain traffic information between point of interest 1 and point of interest 2, and re-plan the traffic route between point of interest 1 and point of interest 2.

[0129] For example, if a time connection problem is detected between point of interest 3 and point of interest 4 in the sub-trip planning information, the shortest time from point of interest 3 to point of interest 4 is t1, while the planned time interval between point of interest 3 and point of interest 4 in the sub-trip planning information is t2, t1>t2, so the trip from point of interest 3 to point of interest 4 can be replanned; for example, the planned time to arrive at point of interest 4 can be postponed.

[0130] In this embodiment, when a sub-agent detects planning defects in the sub-trip planning information, it can automatically correct these defects to ensure that the output meets the detection criteria and planning conditions. By eliminating locally abnormal planning information in advance, the sub-agent reduces the cost for the main agent to initiate planning checks at all levels, thereby improving the efficiency of multi-agent collaborative trip planning while ensuring the reasonableness of the sub-trip planning information.

[0131] In one optional embodiment, this embodiment provides a task processing system based on a master agent and multiple sub-agents, which can be deployed in... Figure 1 Please refer to the server. Figure 5 It shows a system architecture diagram of a task processing system, wherein the task processing system may include a main intelligent agent 510 and multiple sub-intelligent agents 520. The main intelligent agent 510 is used to generate multiple trip planning subtasks corresponding to the target trip intention, and distribute the multiple trip planning subtasks to multiple sub-intelligent agents; any trip planning subtask corresponds to at least one sub-trip in the target trip intention, and different sub-intelligent agents receive different trip planning subtasks; Multiple sub-agents 520 are used to process the received trip planning sub-tasks to obtain sub-trip planning information; and send the sub-trip planning information to the main agent. The main intelligent agent 510 is also used to fuse the sub-trip planning information sent by multiple sub-intelligent agents to obtain the trip planning information corresponding to the target trip intention.

[0132] Furthermore, the task processing system may also include: Memory unit 530 stores relevant information about the travel object (such as frequently used departure points and saved route guides), conversation context (planned information of the main agent and sub-agents), and cached results related to tool calls. This ensures contextual consistency and personalization for the main agent 510 during global planning and sub-trip splitting. Sub-agents 520 ensure compliance with the travel object's object constraints when executing trip planning sub-tasks.

[0133] Verification model 540: Each sub-agent 520 can correspond to at least one verification model 540. The verification model 540 can work with the judgment model to reflect on the sub-trip planning information output by the sub-agent 520 and provide natural language feedback, so that the sub-agent 520 can improve the planning results based on the feedback.

[0134] The main agent 510 operates based on a large language model and possesses complex reasoning and planning capabilities, utilizing the memory unit 530 and various toolkits. It is responsible for semantic understanding and reasoning planning of the traveler's intended journey, breaking down complex journeys into multiple journey planning sub-tasks, connecting these sub-tasks with the main transportation system, and distributing these sub-tasks to different sub-agents 520 for processing. In one embodiment, the main agent 510 is also responsible for summarizing the sub-journey planning information output by the sub-agents 520, performing global consistency checks, and overall reflection and optimization, ultimately outputting a fixed paradigm for front-end display. For example, the main agent 510 can check whether the arrival time of the main transportation system is consistent with the first day's itinerary, whether the end time of the last segment of the journey conflicts with the departure time of subsequent main transportation, and whether the restaurant and hotel arrangements conform to the traveler's object constraint information.

[0135] Sub-agent 520 completes the itinerary planning sub-tasks issued by the main agent 510 by calling different sets of tools and the memory unit 530, performing itinerary planning for sub-itineraries and conducting local reasoning and reflection. Sub-agent 520 can detect the daily itinerary compactness, whether the itinerary meets the object constraints of required points of interest and travel companions, check for unreasonable transportation within sub-itineraries, and detect unreasonable travel time within sub-itineraries. When a problem is detected, sub-agent 520 generates feedback descriptions in natural language and internally triggers replanning based on the feedback results: re-calling tools based on the feedback; adjusting the combination of attractions, the order of visits, points of interest, transportation methods, restaurant and hotel selections, etc.; iterating until the preset rationality standard is met or the maximum number of iterations is reached. Finally, each sub-agent outputs a stable itinerary plan result after reflection and optimization.

[0136] The following uses a travel scenario as an example to explain the implementation process of this embodiment in detail. Please refer to [link / reference]. Figure 6 The corresponding implementation process may include: S610. The main intelligent agent extracts the travel elements from the target travel intention to obtain the travel location and travel time.

[0137] S612. The main intelligent agent splits the trip based on the trip location and trip time to obtain multiple sub-trips.

[0138] S614. The main intelligent agent generates traffic planning information between adjacent sub-trips based on traffic information between adjacent sub-trips and the trip sequence of multiple sub-trips.

[0139] S616. The main intelligent agent determines the arrival time and departure time of each segment of the multi-segment ...

[0140] S618. The main agent reconstructs the intent of the target trip and generates the sub-trip intents corresponding to each of the multiple sub-trips.

[0141] S620. The main agent generates trip planning subtasks for each of the multiple trip segments based on their respective arrival times, departure times, and intentions. These trip planning subtasks are then distributed to multiple sub-agents.

[0142] S622. When the number of target interest points determined based on the sub-trip intent corresponding to at least one sub-trip is multiple, the sub-agent determines the route order of multiple target interest points.

[0143] S624. The sub-agent generates traffic planning information between multiple target points of interest based on traffic information between multiple target points of interest.

[0144] S626. The sub-agent performs trip planning for at least one sub-trip based on the route sequence of multiple target points of interest, the traffic planning information between multiple target points of interest, the arrival time of at least one sub-trip, and the departure time of at least one sub-trip, and obtains the sub-trip planning information corresponding to the trip planning sub-task.

[0145] S628. The sub-agent performs at least one dimension of detection on the sub-trip planning information.

[0146] S630. If the sub-agent detects anomalies in at least one detection dimension of the sub-trip planning information, it automatically corrects the sub-trip planning information based on at least one detection dimension to obtain corrected sub-trip planning information. The corrected sub-trip planning information is then sent to the main agent.

[0147] S632. The main agent detects whether the sub-trip planning information sent by multiple sub-agents meets the global trip planning conditions.

[0148] S634. The main agent determines the target sub-agent corresponding to the sub-trip planning information that does not meet the preset trip planning conditions, and sends a planning information correction instruction to the target sub-agent corresponding to the sub-trip planning information that does not meet the preset trip planning conditions.

[0149] S636. The target sub-agent corrects the sub-trip planning information based on the planning information correction instruction, and sends the corrected sub-trip planning information to the main agent.

[0150] S638. The main agent performs information splicing and structuring processing on the sub-trip planning information sent by multiple sub-agents to obtain structured trip planning information.

[0151] Furthermore, structured itinerary planning information can be sent to Figure 1 The terminal shown can parse structured travel planning information and draw it on the terminal interface; please refer to [link / reference]. Figure 7 The document illustrates a schematic diagram of itinerary planning information. Taking the target itinerary intention as "I want to go to city A for three days, and I must visit attractions a, b, and c, then go to city B for three days, and then go home (city C). Please help me plan it," the itinerary planning information can be displayed by showing at least one of the following: planned route, points along the way, itinerary sequence, and mode of transportation. Itinerary cards 720 can be displayed in the itinerary planning information display interface 710. Itinerary cards 720 may include an overview card and multiple sub-itinerary cards. By triggering different itinerary cards, different itinerary planning information can be viewed.

[0152] Figure 7 (a) shows that when the trip overview card is triggered, the corresponding trip overview information corresponding to the target trip intention can be displayed. The trip overview information may include the trip route, mode of transportation, etc. for each sub-trip, and may also display the trip title and summary by city and by day.

[0153] Taking multiple sub-itineraries as an example: Sub-itinerary 11: Day 1 in City A, Sub-itinerary 12: Day 2 in City A, Sub-itinerary 13: Day 3 in City A; Sub-itinerary 21: Day 1 in City B, Sub-itinerary 22: Day 2 in City B, Sub-itinerary 23: Day 3 in City B, the corresponding sub-itinerary cards can include cards corresponding to Sub-itinerary 11, Sub-itinerary 12, Sub-itinerary 13, Sub-itinerary 21, Sub-itinerary 22, and Sub-itinerary 23 respectively. Figure 7 (b) shows that when the card corresponding to sub-trip 11 is triggered, the sub-trip planning information of sub-trip 11 can be viewed. The sub-trip planning information may include the route, mode of transportation, etc. of sub-trip 11, and may also display POI card information within sub-trip 11, such as attraction, restaurant, hotel, etc. By triggering the POI card information, the detailed information of the corresponding POI can be displayed.

[0154] It should be noted that any of the methods described above in this embodiment can be combined based on the actual implementation situation and have corresponding beneficial effects, which will not be elaborated here.

[0155] Figure 8 This is a block diagram of a task processing apparatus according to an exemplary embodiment. (Refer to...) Figure 8 The device includes: The subtask generation module 810 is used to generate multiple trip planning subtasks corresponding to the target trip intent; each trip planning subtask corresponds to at least one sub-trip in the target trip intent, and the multiple trip planning subtasks are independent of each other. The subtask distribution module 820 is used to distribute multiple trip planning subtasks to multiple sub-agents; different sub-agents receive different trip planning subtasks. The sub-trip planning information receiving module 830 is used to receive sub-trip planning information sent by multiple sub-agents; the sub-trip planning information is obtained by multiple sub-agents processing the trip planning sub-tasks they receive. The sub-trip planning information fusion module 840 is used to fuse the sub-trip planning information sent by multiple sub-intelligent agents to obtain the trip planning information corresponding to the target trip intention.

[0156] Furthermore, the subtask generation module 810 is used for: Extract travel elements from the target travel intention to obtain travel locations and travel times; The itinerary is broken down based on the travel location and travel time to obtain multiple segments of the itinerary; Generate multiple segments of the itinerary, each corresponding to a itinerary planning subtask.

[0157] Furthermore, the subtask generation module 810 is used for: Obtain traffic information between adjacent sub-trips; Based on traffic information between adjacent sub-trips and the trip sequence of multiple sub-trips, traffic planning information between adjacent sub-trips is generated; the trip sequence represents the temporal order of completing multiple sub-trips, and the trip sequence is determined based on the target trip intention; Based on the traffic planning information between adjacent sub-trips, the arrival time and departure time of each sub-trip are determined; the arrival time of each sub-trip is the time of arrival at the associated location of each sub-trip, and the departure time of each sub-trip is the time of departure from the associated location, which is the location passed through by each sub-trip. Based on the arrival time and departure time of each segment of the trip, generate trip planning subtasks for each segment of the trip.

[0158] Furthermore, the subtask generation module 810 is used for: The intent of the target trip is reconstructed to generate the sub-trip intents corresponding to each of the multiple sub-trip segments. Based on the arrival time, departure time, and sub-trip intention of each segment of the trip, generate the trip planning sub-tasks corresponding to each segment of the trip.

[0159] Furthermore, the device also includes a first detection module for: Detect whether the sub-trip planning information sent by multiple sub-agents satisfies the global trip planning conditions; the global trip planning conditions include: The arrival time of the first sub-trip is earlier than the trip start time in the sub-trip planning information corresponding to the first sub-trip; the arrival time of the first sub-trip is the time when it arrives at the associated location of the first sub-trip, and the associated location is the location that the first sub-trip passes through; The departure time of the last sub-trip is later than the trip end time in the sub-trip planning information corresponding to the last sub-trip; the departure time of the last sub-trip is the time of departure from the associated location of the last sub-trip; The sub-trip planning information sent by multiple sub-agents satisfies the preset object constraints, which are associated with the object configuration information of the travel object.

[0160] Furthermore, the device also includes a first correction module for: In the case of sub-trip planning information that does not meet the preset trip planning conditions, determine the target sub-agent corresponding to the sub-trip planning information that does not meet the preset trip planning conditions; Send planning information correction instructions to the target sub-agent; Receive the corrected sub-trip planning information sent by the target sub-agent based on the planning information correction instruction.

[0161] Furthermore, the sub-trip planning information fusion module 840 is used for: The sub-trip planning information sent by multiple sub-agents is spliced ​​together to obtain spliced ​​planning information; The splicing planning information is processed in a structured manner to generate structured travel planning information corresponding to the target travel intention.

[0162] Figure 9 This is a block diagram of another task processing apparatus according to an exemplary embodiment. (Refer to...) Figure 9 The device includes: The subtask receiving module 910 is used to receive the trip planning subtask distributed by the main intelligent agent; the trip planning subtask is a task generated by the main intelligent agent based on the target trip intention; any trip planning subtask corresponds to at least one sub-trip in the target trip intention; The subtask processing module 920 is used to process the itinerary planning subtasks and obtain the sub-itinerary planning information corresponding to the itinerary planning subtasks. The sub-trip planning information sending module 930 is used to send the sub-trip planning information corresponding to the trip planning sub-task to the main intelligent agent; so that the main intelligent agent can perform information fusion based on the sub-trip planning information corresponding to the trip planning sub-task to obtain the trip planning information corresponding to the target trip intention.

[0163] Furthermore, the trip planning subtask includes the arrival time of at least one sub-trip and the departure time of at least one sub-trip; the arrival time of each sub-trip is the time when it arrives at the associated location of each sub-trip, and the departure time of each sub-trip is the time when it leaves the associated location, and the associated location is the location passed through by each sub-trip. Subtask processing module 920 is used for: Based on the arrival time of at least one sub-trip and the departure time of at least one sub-trip, perform trip planning on at least one sub-trip to obtain the sub-trip planning information corresponding to the trip planning sub-task.

[0164] Furthermore, the trip planning subtask also includes at least one sub-trip intent corresponding to a sub-trip; the sub-trip intent is obtained by reconstructing the intent of the target trip. Subtask processing module 920 is used for: Based on the sub-trip intention corresponding to at least one sub-trip, the arrival time of at least one sub-trip, and the departure time of at least one sub-trip, trip planning is performed on at least one sub-trip to obtain the sub-trip planning information corresponding to the trip planning sub-task.

[0165] Furthermore, the subtask processing module 920 is used for: When there are multiple target points of interest determined based on the sub-trip intent corresponding to at least one sub-trip, determine the route order of the multiple target points of interest. Based on the route sequence of multiple target points of interest, the arrival time of at least one sub-trip, and the departure time of at least one sub-trip, a trip planning is performed on at least one sub-trip to obtain the sub-trip planning information corresponding to the trip planning sub-task. The path order represents the sequential order in which multiple target points of interest are reached. The path order is determined based on at least one of the following: Spatial location of multiple target points of interest; Traffic information between multiple points of interest; Temporal constraint information for multiple target points of interest; The object constraint information of the traveler on multiple target points of interest; Weather conditions for at least one segment of the trip.

[0166] Furthermore, the subtask processing module 920 is used for: When there are multiple target points of interest determined based on the sub-trip intent corresponding to at least one sub-trip, traffic information between multiple target points of interest is obtained. Based on traffic information between multiple target points of interest, generate traffic planning information between multiple target points of interest; Based on traffic planning information between multiple target points of interest, arrival time of at least one sub-trip, and departure time of at least one sub-trip, trip planning is performed on at least one sub-trip to obtain sub-trip planning information corresponding to the trip planning sub-task.

[0167] Furthermore, the device also includes a second detection module for: Detect information from at least one of the following detection dimensions corresponding to the sub-trip planning information: Traffic rationality detection of traffic planning information in sub-trip planning information; Detecting the time reasonableness of travel times in sub-travel planning information; Testing the rationality of the connection between sub-trip planning information; Matching and detection of sub-trip planning information with the object configuration information of the travel object.

[0168] Furthermore, the device also includes a second correction module for: If there is an anomaly in the trip planning information of at least one detection dimension corresponding to the sub-trip planning information, the sub-trip planning information is automatically corrected based on at least one detection dimension to obtain the corrected sub-trip planning information.

[0169] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0170] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc. When the instructions in the computer-readable storage medium are executed by the processor of an electronic device, the electronic device is able to perform any of the methods described above.

[0171] In an exemplary embodiment, a computer program product is also provided, comprising a computer program stored in a readable storage medium, wherein at least one processor of a computer device reads from the readable storage medium and executes the computer program, causing the device to perform any of the methods described above.

[0172] Figure 10 This is a block diagram illustrating an electronic device for task processing according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 10As shown, this electronic device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a task processing method.

[0173] Figure 11 This is a block diagram illustrating an electronic device for task processing according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as follows: Figure 11 As shown, the electronic device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a task processing method. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0174] Those skilled in the art will understand that Figure 10 and Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the electronic device to which the present disclosure is applied. A specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0175] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0176] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A task processing method, characterized in that, The method includes: Generate multiple trip planning subtasks corresponding to the target trip intention; each trip planning subtask corresponds to at least one segment of the target trip intention, and the multiple trip planning subtasks are independent of each other; The multiple trip planning subtasks are distributed to multiple sub-agents; different sub-agents receive different trip planning subtasks. The system receives sub-trip planning information sent by the plurality of sub-agents; the sub-trip planning information is obtained by the plurality of sub-agents processing the trip planning sub-tasks they each receive. The sub-trip planning information sent by the multiple sub-intelligent agents is fused to obtain the trip planning information corresponding to the target trip intention.

2. The method according to claim 1, characterized in that, The multiple trip planning subtasks corresponding to the generated target trip intent include: The travel elements are extracted from the target travel intention to obtain the travel location and travel time; The itinerary is divided into multiple segments based on the travel locations and travel times; Generate the corresponding itinerary planning subtasks for each of the multiple sub-segments.

3. The method according to claim 2, characterized in that, The generation of the trip planning sub-tasks corresponding to each of the multiple sub-trips includes: Obtain traffic information between adjacent sub-trips; Based on the traffic information between adjacent sub-trips and the trip sequence of the multiple sub-trips, traffic planning information between adjacent sub-trips is generated; wherein, the trip sequence represents the temporal order of completing the multiple sub-trips, and the trip sequence is determined based on the target trip intention; Based on the traffic planning information between adjacent sub-trips, the arrival time and departure time of each of the multiple sub-trips are determined; the arrival time of each sub-trip is the time of arrival at the associated location of each sub-trip, and the departure time of each sub-trip is the time of departure from the associated location, wherein the associated location is the location passed through by each sub-trip. Based on the arrival time and departure time of each of the multiple sub-trips, a trip planning sub-task is generated for each of the multiple sub-trips.

4. The method according to claim 1, characterized in that, After receiving the sub-trip planning information sent by the plurality of sub-agents, the method further includes: The system detects whether the sub-trip planning information sent by the multiple sub-agents meets the global trip planning conditions; the global trip planning conditions include: The arrival time of the first sub-trip is earlier than the trip start time in the sub-trip planning information corresponding to the first sub-trip; the arrival time of the first sub-trip is the time when it arrives at the associated location of the first sub-trip, and the associated location is the location passed through by the first sub-trip; The departure time of the last sub-trip is later than the trip end time in the sub-trip planning information corresponding to the last sub-trip; the departure time of the last sub-trip is the time of departure from the associated location of the last sub-trip; The sub-trip planning information sent by the multiple sub-intelligent agents satisfies preset object constraints, which are associated with the object configuration information of the travel object.

5. The method according to claim 1, characterized in that, The process of fusing the sub-trip planning information sent by the multiple sub-agents to obtain the trip planning information corresponding to the target trip intention includes: The sub-trip planning information sent by the multiple sub-intelligent agents is spliced ​​together to obtain spliced ​​planning information; The splicing planning information is processed in a structured manner to generate structured travel planning information corresponding to the target travel intention.

6. A task processing method, characterized in that, The method includes: Receive a trip planning subtask distributed by the main intelligent agent; the trip planning subtask is a task generated by the main intelligent agent based on the target trip intention; each trip planning subtask corresponds to at least one sub-trip in the target trip intention; The itinerary planning sub-task is processed to obtain the sub-itinerary planning information corresponding to the itinerary planning sub-task; The sub-trip planning information corresponding to the trip planning sub-task is sent to the main intelligent agent, so that the main intelligent agent can perform information fusion based on the sub-trip planning information corresponding to the trip planning sub-task to obtain the trip planning information corresponding to the target trip intention.

7. The method according to claim 6, characterized in that, The trip planning subtask includes the arrival time of at least one sub-trip and the departure time of the at least one sub-trip; the arrival time of each sub-trip is the time of arrival at the associated location of each sub-trip, and the departure time of each sub-trip is the time of departure from the associated location, wherein the associated location is the location passed through by each sub-trip; The step of processing the itinerary planning sub-task to obtain the sub-itinerary planning information corresponding to the itinerary planning sub-task includes: Based on the arrival time and departure time of the at least one sub-trip, trip planning is performed on the at least one sub-trip to obtain the sub-trip planning information corresponding to the trip planning sub-task.

8. A task processing method, characterized in that, The method includes: The main agent generates multiple trip planning subtasks corresponding to the target trip intention, and distributes the multiple trip planning subtasks to multiple sub-agents; each trip planning subtask corresponds to at least one segment of the target trip intention, and different sub-agents receive different trip planning subtasks, and the multiple trip planning subtasks are independent of each other; The multiple sub-agents process their respective received trip planning sub-tasks to obtain sub-trip planning information; and then send the sub-trip planning information to the main agent. The main intelligent agent fuses the sub-trip planning information sent by the multiple sub-intelligent agents to obtain the trip planning information corresponding to the target trip intention.

9. A task processing device, characterized in that, The device includes: The subtask generation module is used to generate multiple trip planning subtasks corresponding to the target trip intention; each trip planning subtask corresponds to at least one sub-trip in the target trip intention, and the multiple trip planning subtasks are independent of each other. The subtask distribution module is used to distribute the multiple itinerary planning subtasks to multiple sub-agents; different sub-agents receive different itinerary planning subtasks. The sub-trip planning information receiving module is used to receive sub-trip planning information sent by the multiple sub-agents; the sub-trip planning information is obtained by the multiple sub-agents processing the trip planning sub-tasks they receive. The sub-trip planning information fusion module is used to fuse the sub-trip planning information sent by the multiple sub-intelligent agents to obtain the trip planning information corresponding to the target trip intention.

10. A task processing device, characterized in that, The device includes: The subtask receiving module is used to receive trip planning subtasks distributed by the main intelligent agent; the trip planning subtask is a task generated by the main intelligent agent based on the target trip intention; any trip planning subtask corresponds to at least one sub-trip in the target trip intention. The subtask processing module is used to process the itinerary planning subtasks to obtain the sub-itinerary planning information corresponding to the itinerary planning subtasks. The sub-trip planning information sending module is used to send the sub-trip planning information corresponding to the trip planning sub-task to the main intelligent agent; so that the main intelligent agent can perform information fusion based on the sub-trip planning information corresponding to the trip planning sub-task to obtain the trip planning information corresponding to the target trip intention.

11. A task processing system, characterized in that, The system includes a main intelligent agent and multiple sub-intelligent agents; The main intelligent agent is used to generate multiple trip planning sub-tasks corresponding to the target trip intention, and distribute the multiple trip planning sub-tasks to multiple sub-intelligent agents; Each trip planning subtask corresponds to at least one segment of the target trip intent. Different sub-agents receive different trip planning subtasks, and the multiple trip planning subtasks are independent of each other. The multiple sub-agents are used to process the received trip planning sub-tasks to obtain sub-trip planning information; and send the sub-trip planning information to the main agent. The main intelligent agent is also used to fuse the sub-trip planning information sent by the multiple sub-intelligent agents to obtain the trip planning information corresponding to the target trip intention.

12. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the task processing method as described in any one of claims 1 to 5, or the task processing method as described in any one of claims 6 to 7, or the task processing method as described in claim 8.

13. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the task processing method as described in any one of claims 1 to 5, or the task processing method as described in any one of claims 6 to 7, or the task processing method as described in claim 8.

14. A computer program product, characterized in that, The computer program product includes a computer program stored in a readable storage medium, wherein at least one processor of a computer device reads from the readable storage medium and executes the computer program, causing the device to perform the task processing method as described in any one of claims 1 to 5, or the task processing method as described in any one of claims 6 to 7, or the task processing method as described in claim 8.

Images