Unmanned aerial vehicle logistics distribution method, system and equipment based on large model, and medium

Abstract

The invention provides an unmanned aerial vehicle logistics distribution method, system and device based on a large model, and a medium, and relates to the technical field of air transportation, and the method comprises the steps: collecting the logistics distribution demand information of a user; analyzing the logistics distribution demand information of the user through a large model, refining the demand category, judging the demand degree and sorting, and generating a logistics distribution scheme in combination with the current unmanned aerial vehicle deployment state and the current traffic state; sending the logistics distribution scheme to a user for confirmation, and issuing a task execution instruction after the confirmation is passed; and responding to the task execution instruction through the unmanned aerial vehicle, and executing a distribution task according to the confirmed logistics distribution scheme. According to the method, the large model is combined with the unmanned aerial vehicle logistics scheduling decision, and compared with a traditional unmanned aerial vehicle logistics distribution method, user demands can be effectively known, the demands are sorted, a reasonable solution is provided, and the intelligent degree of unmanned aerial vehicle logistics distribution and the unmanned aerial vehicle logistics distribution efficiency can be further improved.

Description

Technical Field

[0001] The present invention relates to the field of aviation transportation technology, and in particular to a large-scale model-based unmanned aerial vehicle logistics distribution method, system, equipment and medium. Background Art

[0002] Drone logistics is a new mode of freight transportation that can effectively alleviate the congestion problem of land freight and achieve efficient and fast logistics material delivery. In addition, drone logistics can replace human logistics to engage in repetitive and monotonous freight work, which will improve freight efficiency and save labor costs.

[0003] With the continuous development of the low-altitude economy, the number of drone logistics users has gradually increased, and user needs vary. The traditional logistics scheduling and distribution methods do not have enough time to analyze user needs one by one, and the urgency of user needs is difficult to distinguish. It is impossible to sort the importance of logistics distribution, resulting in the difficulty in exerting the speed of drone logistics distribution. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a drone logistics distribution method, system, equipment and medium based on a big model. The method combines the big model with drone logistics scheduling decisions. Compared with traditional drone logistics distribution methods, it can effectively understand user needs, sort the needs, and propose reasonable solutions, which can further improve the intelligence of drone logistics distribution.

[0005] The embodiment of the present application provides the following technical solution: a drone logistics distribution method based on large model control, comprising:

[0006] Collect users' logistics and distribution demand information;

[0007] The large model is used to analyze the user's logistics and distribution demand information, refine the demand categories, determine the urgency of the demand and sort it, and generate a logistics and distribution plan based on the current drone deployment status and current traffic conditions;

[0008] Send the logistics distribution plan to the user for confirmation, and issue the task execution instruction after confirmation;

[0009] The drone responds to the mission execution instruction and executes the delivery mission according to the confirmed logistics delivery plan.

[0010] According to an embodiment of the present application, the logistics distribution plan is sent to the user for confirmation, and after the confirmation, a task execution instruction is issued, including:

[0011] The logistics distribution plan is sent to the user end for the user to make a judgment and decision, and the user decision result is obtained. If the user decision result is agreement, a task execution instruction is issued. If not, the logistics distribution plan is regenerated through the large model.

[0012] According to an embodiment of the present application, sending the logistics distribution plan to the user for confirmation includes:

[0013] The logistics distribution plan is broken down into a number of subtasks, and the subtasks are displayed on the user side for the user to make judgments and decisions.

[0014] According to an embodiment of the present application, after issuing the task execution instruction, the method further includes:

[0015] The flight environment of drones performing delivery tasks is monitored in real time, and the estimated delivery time is fed back to the user.

[0016] According to an embodiment of the present application, the user's logistics and delivery demand information is collected, and the user's logistics and delivery demand information includes the materials required by the user, the material delivery location, the material delivery time and the urgency of the demand.

[0017] According to an embodiment of the present application, collecting the user's logistics and delivery demand information also includes: uniformly encoding the user's logistics and delivery demand information according to set rules and storing it.

[0018] According to one embodiment of the present application, the large model is a generative pre-trained artificial intelligence model.

[0019] The present application also provides a UAV logistics distribution system based on large model control, including:

[0020] Demand collection module, used to collect users' logistics and distribution demand information;

[0021] The demand analysis and decision-making module is used to analyze the user's logistics and distribution demand information through a large model, refine the demand categories, determine the urgency of the demand and sort it, and generate a logistics and distribution plan based on the current drone deployment status and current traffic status;

[0022] The task confirmation module is used to send the logistics distribution plan to the user for confirmation, and issue the task execution instruction after confirmation;

[0023] The task execution module is used to respond to the task execution instruction through the drone and execute the delivery task according to the confirmed logistics delivery plan.

[0024] The present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned large-model-based control-based drone logistics distribution method when executing the computer program.

[0025] The present application also provides a computer-readable storage medium, which stores a computer program for executing the above-mentioned drone logistics distribution method based on large model control.

[0026] Compared with the prior art, the beneficial effects that can be achieved by at least one of the above technical solutions adopted in the embodiments of this specification include at least: the embodiments of the present invention change the information analysis and processing mode of traditional logistics distribution, combine the big model with the UAV logistics scheduling decision, expand the form of user demand description to the human language form, and introduce the big model. The big model is used to analyze and process user needs, which can realize the rapid processing of massive demands and sort them according to the urgency of the needs, solve the problem of rapid decision-making in UAV logistics distribution, and make the distribution plan more humane. And on the basis of the big model decision, the decision confirmation mode of human in the loop is introduced for users to make decisions and judgments, which improves the safety and reliability of the decision-making plan and improves the efficiency of UAV logistics distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 This is a schematic diagram of the flow of the drone logistics distribution method according to an embodiment of the present invention;

[0029] Figure 2 It is a schematic diagram of the structure of the UAV logistics distribution system according to an embodiment of the present invention;

[0030] Figure 3 It is an implementation architecture diagram of the drone logistics distribution system according to an embodiment of the present invention;

[0031] Figure 4 is a schematic diagram of the structure of the computer device of the present invention;

[0032] Among them, 1-demand collection module, 2-demand analysis and decision module, 3-task confirmation module, 4-task execution module, 101-demand input end, 102-demand storage end, 103-demand feedback end, 201-information processing unit, 202-large model decision unit, 301-task display unit, 302-confirmation unit, 303-flight monitoring unit, 401-UAV, 402-material loading area. DETAILED DESCRIPTION

[0033] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0034] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the following embodiments and the features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0035] like Figure 1 As shown, an embodiment of the present invention provides a UAV logistics distribution method based on large model control, comprising:

[0036] S101. Collecting user's logistics and distribution demand information;

[0037] S102. Analyze the user's logistics and distribution demand information through a large model, refine the demand categories, determine the urgency of the demand and sort it, and generate a logistics and distribution plan based on the current drone deployment status and current traffic status;

[0038] S103. Send the logistics distribution plan to the user for confirmation, and issue a task execution instruction after confirmation;

[0039] S104. Respond to the task execution instruction through the drone and execute the delivery task according to the confirmed logistics delivery plan.

[0040] The large model in this embodiment is a generative pre-trained artificial intelligence model. As a generative pre-trained artificial intelligence model, the large model can understand user needs through human natural language communication and generate corresponding decision-making plans. Combining the large model with drone logistics scheduling can further promote the intelligence of drone logistics and solve the problem of unclear needs and urgency of drone logistics distribution systems. The embodiment of the present invention combines the large model with drone logistics scheduling decisions. Compared with traditional drone logistics distribution methods, it can effectively understand user needs, analyze the importance of user needs, and propose reasonable solutions, which can further improve the intelligence of drone logistics distribution.

[0041] In a specific implementation of this embodiment, the logistics distribution plan is sent to the user for confirmation, and after the confirmation is passed, a task execution instruction is issued, including: sending the logistics distribution plan to the user end for the user to make a judgment and decision, obtaining the user's decision result, and if the user's decision result is agreement, then issuing a task execution instruction, if not, regenerating the logistics distribution plan through the large model. Based on the large model decision, this embodiment introduces a human-in-the-loop decision confirmation mode, improves the efficiency of drone logistics distribution, and improves the safety and reliability of the decision plan.

[0042] In specific implementation, the logistics distribution plan is sent to the user for confirmation, including: breaking down the logistics distribution plan into a number of subtasks, and displaying the subtasks on the user side for the user to make judgments and decisions. This embodiment divides the entire logistics distribution plan into a number of subtasks for the user to make judgments and decisions, which not only improves the efficiency of the user's judgment and decision-making, but also ensures the accuracy and reliability of the user's judgment and decision-making.

[0043] In a specific implementation of this embodiment, after issuing the task execution instruction, it also includes: real-time monitoring of the flight environment of the drone performing the delivery task, and feeding back the estimated delivery time to the user end. When the drone performs the delivery task, this embodiment monitors the current flight environment in real time to understand the delivery situation, including the progress of the delivery task execution, the estimated delivery time and other information, and feeds back the acquired delivery information to the user end, so that the user can grasp the delivery situation in real time.

[0044] In specific implementation, the user's logistics and distribution demand information is collected through the user terminal, and the user's logistics and distribution demand information includes the materials required by the user, the material distribution location, the material distribution time and the urgency of the demand. After collecting the user's logistics and distribution demand information, the user's logistics and distribution demand information is uniformly encoded according to the set rules and stored for reference, or the large model is fed back and optimized through the stored historical logistics and distribution demand information.

[0045] like Figure 2 As shown, an unmanned aerial vehicle logistics distribution system based on large model control according to an embodiment of the present invention includes:

[0046] Demand collection module 1, used to collect users' logistics and distribution demand information;

[0047] Demand analysis and decision module 2 is used to analyze the user's logistics and distribution demand information through a large model, refine the demand categories, determine the urgency of the demand and sort it, and generate a logistics and distribution plan based on the current drone deployment status and current traffic status;

[0048] Task confirmation module 3, used to send the logistics distribution plan to the user for confirmation, and issue the task execution instruction after confirmation;

[0049] The task execution module 4 is used to respond to the task execution instruction through the drone and execute the delivery task according to the confirmed logistics delivery plan.

[0050] The embodiment of the present invention combines drone logistics distribution with a large model module, and utilizes the language analysis and decision-making capabilities of the large model to further refine and rank user needs, and generate a drone logistics distribution plan that integrates information such as the urgency of distribution and the types of materials. The system is divided into a demand collection module 1, a demand analysis and decision module 2, a task confirmation module 3, and a task execution module 4 according to internal modules. Among them, the demand collection module 1 is used to collect human language logistics distribution needs proposed by users; the demand analysis and decision module 2 has a built-in large model unit and a human-in-the-loop analysis unit, which is used to analyze the needs proposed by users, refine the demand categories, judge the urgency of the needs, and generate a decision plan; the task confirmation module 3 is used to confirm the decision plan generated by the previous module, and then transmit it to the task execution module 4; the task execution module 4 contains multiple drones, which is the execution unit of the entire system and is used to execute specific distribution tasks.

[0051] In specific implementation, the demand collection module 1 is used to collect the user's material distribution needs in various forms. The demand collection module 1 is divided into a demand input terminal 101 and a demand storage terminal 102. The demand input terminal 101 is used to receive demand information in the form of text, voice, etc. from the user client, and uniformly encode the demand information and transmit it to the demand storage terminal 102 for storage; the demand feedback terminal 103 is used to display key information such as drone delivery time in real time.

[0052] In specific implementation, the demand analysis and decision module 2 is mainly composed of an information processing unit 201 and a large model decision unit 202, which is used to receive the demand information of the demand collection module 1. The information processing unit 201 parses the demand information into text information that can be recognized by the large model decision unit 202, and transmits the information to the large model decision unit 202, identifies, analyzes and processes the demand information, focuses on analyzing the urgency of the demand, sorts the demand according to the urgency, and then forms a logistics distribution plan.

[0053] In specific implementation, the task confirmation module 3 includes a task display unit 301, a confirmation unit 302, and a flight monitoring unit 303, which is used to decompose the decision plan generated by the demand analysis decision module 2 into a number of subtasks, and then display the subtasks on the task display unit 301 for the user to make judgments and decisions, and transmit the user's decision information to the confirmation unit 302, and the confirmation unit 302 determines whether to transmit the task information to the task execution module 4; the flight monitoring unit 303 is used to monitor the flight environment in real time to ensure flight safety.

[0054] In specific implementation, the task execution module 4 is used to execute specific logistics distribution tasks, including several drones 401 and a material loading area 402. After receiving the task information, the drone 401 flies to the material loading area 402 to load the required goods, and then flies to the user's designated location with the goods for material distribution.

[0055] The specific process of a UAV logistics distribution system based on large model control in performing tasks in an embodiment of the present invention is as follows:

[0056] like Figure 3As shown, the user inputs the demand information including the materials, location, time, urgency and other information required by the user at the user demand input terminal 101 through the client, and then the demand storage terminal 102 stores the user demand and transmits the information such as the deployment status of the drone, the current traffic status, and the user demand to the information processing unit 201. The information processing unit 201 decomposes the user demand information into text language information, and then uploads it to the large model decision unit 202 in the form of a chat dialogue. The large model decision unit 202 generates a task plan and a decision plan; then transmits it to the task confirmation module 3, and the task confirmation module 3 decomposes the task information into several task information. The task display unit 301 receives the task instruction and displays it in the task display unit 301. Then the person in the loop confirms the task through the confirmation unit 302. If the person feels that the task planning is unreasonable, it is submitted to the large model decision unit 202 for re-planning until the planned solution meets the human needs. Then the confirmation unit 302 issues the task execution instruction to the task execution module 4. The UAV 401 in the task execution module 4 loads the goods in the material loading area 402 and delivers them to the user's designated location. During the transportation of the goods, the flight monitoring unit 303 performs real-time flight monitoring to ensure flight safety throughout the entire process, and feeds back the estimated delivery time to the demand feedback terminal 103.

[0057] The embodiment of the present invention is based on a drone logistics distribution system controlled by a large model, which changes the information analysis and processing mode of traditional logistics distribution, expands the form of user demand description to human language form, and introduces a large model decision unit 202. By using the large model to analyze and process user needs, it can realize rapid processing of massive demands and sort them according to the urgency of the demands, thus solving the problem of rapid decision-making in drone logistics distribution and making the distribution plan more humane.

[0058] The drone logistics distribution system controlled by the large model introduces a task confirmation module 3 on the basis of the large model decision, decomposes the decision plan generated by the demand analysis decision module 2 into several subtasks, and then displays the subtasks on the task display unit 301 for the user to make judgments and decisions, and transmits the user's decision information to the confirmation unit 302, which determines whether to transmit the task information to the task execution module 4, thereby improving the safety and reliability of the decision plan.

[0059] The embodiment of the present invention decomposes the task execution module 4 into a plurality of drones 401 and a material loading area 402. After receiving the task information, the drone 401 flies to the material loading area 402 to load the required goods, and then flies to the user's designated location with the goods, thereby meeting the user's personalized material transportation needs.

[0060] In one embodiment, a computer device is provided, such as Figure 4As shown, it includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned drone logistics distribution method based on large model control is implemented.

[0061] Specifically, the computer device may be a computer terminal, a server or a similar computing device.

[0062] In this embodiment, a computer-readable storage medium is provided, which stores a computer program for executing the above-mentioned drone logistics distribution method based on large model control.

[0063] Specifically, computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable storage media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0064] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present invention are not limited to any specific combination of hardware and software.

[0065] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A UAV logistics distribution method based on large model control, characterized in that: include: Collect users' logistics and distribution demand information; The large model is used to analyze the user's logistics and distribution demand information, refine the demand categories, determine the urgency of the demand and sort it, and generate a logistics and distribution plan based on the current drone deployment status and current traffic conditions; Send the logistics distribution plan to the user for confirmation, and issue the task execution instruction after confirmation; The drone responds to the mission execution instruction and executes the delivery mission according to the confirmed logistics delivery plan.

2. The UAV logistics distribution method based on large model control according to claim 1 is characterized in that: The logistics distribution plan is sent to the user for confirmation. After confirmation, the task execution instruction is issued, including: The logistics distribution plan is sent to the user end for the user to make a judgment and decision, and the user decision result is obtained. If the user decision result is agreement, a task execution instruction is issued. If not, the logistics distribution plan is regenerated through the large model.

3. The UAV logistics distribution method based on large model control according to claim 2 is characterized in that: Send the logistics distribution plan to the user for confirmation, including: The logistics distribution plan is broken down into a number of subtasks, and the subtasks are displayed on the user side for the user to make judgments and decisions.

4. The UAV logistics distribution method based on large model control according to claim 1 is characterized in that: After issuing the task execution instruction, it also includes: The flight environment of drones performing delivery tasks is monitored in real time, and the estimated delivery time is fed back to the user.

5. The UAV logistics distribution method based on large model control according to claim 1 is characterized in that: Collect the user's logistics and distribution demand information, which includes the materials required by the user, the material distribution location, the material distribution time and the urgency of the demand.

6. The UAV logistics distribution method based on large model control according to claim 1 is characterized in that: Collecting the user's logistics and distribution demand information also includes: uniformly encoding the user's logistics and distribution demand information according to set rules and storing it.

7. The UAV logistics distribution method based on large model control according to claim 1 is characterized in that: The large model is a generative pre-trained artificial intelligence model.

8. A UAV logistics distribution system based on large model control, characterized in that: include: Demand collection module, used to collect users' logistics and distribution demand information; The demand analysis and decision-making module is used to analyze the user's logistics and distribution demand information through a large model, refine the demand categories, determine the urgency of the demand and sort it, and generate a logistics and distribution plan based on the current drone deployment status and current traffic status; The task confirmation module is used to send the logistics distribution plan to the user for confirmation, and issue the task execution instruction after confirmation; The task execution module is used to respond to the task execution instruction through the drone and execute the delivery task according to the confirmed logistics delivery plan.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the drone logistics distribution method based on large model control described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for executing the drone logistics distribution method based on large model control as described in any one of claims 1 to 7.

Images