Air traffic control equipment auxiliary troubleshooting method based on large model and terminal

Abstract

The embodiment of the invention discloses an air traffic control equipment auxiliary troubleshooting method based on a large model and a terminal. The method comprises the following steps: inputting fault information of air traffic control equipment; retrieving a knowledge base to obtain document information most related to the fault information; constructing an enhanced prompt according to the fault information and the document information; and transmitting the enhanced prompt to the large model, so that the large model generates an auxiliary decision-making suggestion for equipment troubleshooting. According to the method, domain knowledge in the air traffic control equipment fault operation and maintenance knowledge base is fused with semantic understanding and generation capability of a large model, so that accurate pushing of operation and maintenance suggestions and emergency disposal processes of the to-be-handled faults can be realized, operation and maintenance personnel are assisted to quickly position and dispose the faults, and the method has great significance in guaranteeing flight safety and improving efficiency. And the improvement of the control service quality has important practical significance. In addition, the blank that the large model is not applied to auxiliary troubleshooting of the air traffic control equipment is filled.

Description

Technical Field

[0001] The present invention relates to the technical fields of natural language processing and auxiliary troubleshooting, and particularly relates to a method and a terminal for auxiliary troubleshooting of air traffic control equipment based on a large model. Background Art

[0002] With the rapid development of the national economy, the civil aviation traffic volume continues to show an upward trend. To ensure the safe operation and efficient management of flights, stricter requirements are put forward for the stability of air traffic control equipment and the timeliness of equipment fault handling.

[0003] Currently, the mainstream methods for auxiliary troubleshooting of equipment mainly rely on technical routes such as knowledge graphs, and both the efficiency and accuracy need to be improved. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and a terminal for auxiliary troubleshooting of air traffic control equipment based on a large model in view of the deficiencies of the prior art.

[0005] To achieve the above purpose, in a first aspect, an embodiment of the present invention provides a method for auxiliary troubleshooting of air traffic control equipment based on a large model, including:

[0006] Input the fault information of the air traffic control equipment into the operation and maintenance terminal;

[0007] Retrieve the pre-constructed knowledge base for fault operation and maintenance of air traffic control equipment according to the fault information, and obtain the document information most relevant to the fault information;

[0008] Construct an enhanced prompt according to the fault information and the document information;

[0009] Transmit the enhanced prompt to the large model so that the large model generates auxiliary decision-making suggestions for equipment troubleshooting.

[0010] As a preferred implementation manner of the present application, before inputting the fault information of the air traffic control equipment into the operation and maintenance terminal, the method further includes constructing a knowledge base for fault operation and maintenance of air traffic control equipment, specifically:

[0011] Collect document materials; the document materials include an expert library, a typical case library, and an experience library;

[0012] Construct a knowledge base for fault operation and maintenance of air traffic control equipment according to the document materials.

[0013] As a specific implementation manner of the present application, constructing a knowledge base for fault operation and maintenance of air traffic control equipment according to the document materials specifically includes:

[0014] Use a document loader to load the documents in the knowledge base for fault operation and maintenance of air traffic control equipment, and use a document splitter to split the long documents into fixed-length and overlapping text blocks;

[0015] Use an embedding model to convert the text block into a text vector, and store the text vector and its corresponding index in a vector database.

[0016] As a specific implementation manner of this application, obtaining the document information most relevant to the fault information specifically includes:

[0017] Use an embedding model to convert the fault information into a target text vector;

[0018] Use a retriever to retrieve, in the air traffic control equipment fault operation and maintenance knowledge base, the document information with the most similar semantics to the target text vector; among them, the methods used during retrieval include similarity retrieval and full-text retrieval.

[0019] As a specific implementation manner of this application, constructing an enhanced prompt according to the fault information and the document information specifically includes:

[0020] Construct an initial prompt, including background setting and task description;

[0021] Input the fault information and the most similar document information into the initial prompt to construct an enhanced prompt.

[0022] As a preferred implementation manner of this application, the method further includes:

[0023] Display the auxiliary decision-making suggestions for equipment troubleshooting generated by the large model on the operation and maintenance terminal.

[0024] In a second aspect, an embodiment of this application further provides an air traffic control equipment auxiliary troubleshooting terminal based on a large model, including:

[0025] A query input module, configured to input the fault information of the air traffic control equipment;

[0026] A similarity retrieval module, configured to retrieve, according to the fault information, a pre-constructed air traffic control equipment fault operation and maintenance knowledge base to obtain the document information most relevant to the fault information;

[0027] A prompt enhancement module, configured to construct an enhanced prompt according to the fault information and the document information;

[0028] A suggestion generation module, configured to transmit the enhanced prompt to the large model so that the large model generates auxiliary decision-making suggestions for equipment troubleshooting.

[0029] Further, as a preferred implementation manner of this application, the terminal further includes:

[0030] A data input module, configured to input document materials; the document materials include an expert library, a typical case library, and an experience library;

[0031] A knowledge base construction module, configured to construct an air traffic control equipment fault operation and maintenance knowledge base according to the said document materials;

[0032] A display module, configured to display the auxiliary decision-making suggestions for equipment troubleshooting generated by the large model.

[0033] Thirdly, an embodiment of the present invention further provides an air traffic control equipment auxiliary troubleshooting terminal based on a large model, including a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are interconnected. Among them, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method of the first aspect above.

[0034] Implementing the embodiments of the present invention provides an air traffic control equipment auxiliary troubleshooting method and terminal based on a large model. By integrating the domain knowledge in the air traffic control equipment fault operation and maintenance knowledge base with the semantic understanding and generation capabilities of the large model, the method and terminal can achieve accurate push of operation and maintenance suggestions and emergency disposal processes for the faults to be processed, assist the operation and maintenance personnel to quickly locate and dispose of the faults, and have important practical significance for ensuring flight safety and improving the quality of air traffic control services. In addition, the embodiments of the present invention also fill the blank that the large model has not been applied to air traffic control equipment auxiliary troubleshooting. Description of the Drawings

[0035] In order to more clearly illustrate the specific implementation manners of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required to be used in the description of the specific implementation manners or the prior art.

[0036] Figure 1 It is a flowchart of the air traffic control equipment auxiliary troubleshooting method provided by the embodiment of the present invention.

[0037] Figure 2 It is a schematic diagram of the air traffic control equipment fault operation and maintenance knowledge base of the present invention.

[0038] Figure 3 It is a structural diagram of the air traffic control equipment auxiliary troubleshooting terminal provided by the embodiment of the present invention.

[0039] Figure 4 It is a schematic diagram of the data input module of the present invention.

[0040] Figure 5 It is a schematic diagram of the query input module and the display module of the present invention.

[0041] Figure 6 It is a schematic diagram of the similarity retrieval module of the present invention.

[0042] Figure 7 is Figure 3Another structural diagram of the terminal shown Detailed implementation manners

[0043] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention

[0044] It should be understood that when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations

[0045] As Figure 1 shown, an air traffic control equipment assisted troubleshooting method based on a large model provided by an embodiment of the present invention includes:

[0046] S1. Construct an air traffic control equipment fault operation and maintenance knowledge base

[0047] Among them, the air traffic control equipment fault operation and maintenance knowledge base is as Figure 2 shown. Step S1 specifically includes:

[0048] S11. Collect relevant document materials and construct an air traffic control equipment fault operation and maintenance knowledge base. This knowledge base includes an expert database, a typical case database, and an experience database

[0049] Among them, the expert database is a device fault solution provided by device manufacturers and senior operation and maintenance experts, providing authoritative handling suggestions and technical support for various device faults; the typical case database is knowledge points and coping strategies with universal guiding significance refined by senior operation and maintenance experts through historical typical case analysis; the experience database is knowledge formed by front-line operation and maintenance personnel based on actual operation and maintenance experience, providing practical references for quickly locating and solving device faults

[0050] S12. Use a document loader to load the documents in the knowledge base. The supported document formats include DOCX, EXCEL, PDF, TXT, MD, etc. The long document is segmented into fixed-length overlapping text blocks by a document splitter. In this embodiment, the document block length is set to 1000 TOKEN, and the overlapping ratio is 0.2

[0051] S13. Use an embedding model to convert the text blocks in step S13 into text vectors, and store the text vectors and their corresponding indexes in a vector database. The embedding model used in this embodiment is mxbai-embed-large

[0052] S2. Input device fault information at the operation and maintenance terminal.

[0053] Specifically, inputting device fault information at the operation and maintenance terminal according to the fault phenomenon can include device name, fault phenomenon, or fault code, etc. There is no display regulation for the input format, and a natural language description that is semantically clear and smooth is sufficient.

[0054] S3. Retrieve the most relevant document information from the knowledge base for the device fault information.

[0055] Specifically in implementation, step S3 includes:

[0056] S31. Use the embedding model mxbai-embed-large to convert the device fault information input in step S2 into a text vector.

[0057] S32. Use the retriever to retrieve the document information in the vector database in step S14 that is semantically most similar to the text vector in step S31. The retrieval method used in this embodiment is hybrid similarity, which is calculated by weighted combination of keyword similarity and vector similarity.

[0058] S4. Construct an enhanced prompt based on the device fault information and the relevant document information.

[0059] Specifically in implementation, step S5 includes:

[0060] S41. Construct an initial prompt, including background setting, task description, etc. The initial prompt constructed in this embodiment is:

[0061] You are an intelligent assistant. Please summarize the content of the knowledge base to answer the question. Please list the data in the knowledge base in detail. When all the content in the knowledge base is irrelevant to the question, your answer must include the sentence "The answer you want is not found in the knowledge base!" The answer needs to consider the chat history.

[0062] S42. Inject the device fault information input in step S21 and the most similar document information retrieved in step S32 into the initial prompt to construct an enhanced prompt. The enhanced prompt constructed in this embodiment is:

[0063] You are an intelligent assistant. Please answer the question based on the user's question and summarize the content of the knowledge base. Please list the data in the knowledge base in detail. When all the content in the knowledge base is irrelevant to the question, your answer must include the sentence "The answer you want is not found in the knowledge base!" The answer needs to consider the chat history.

[0064] The following is the question:

[0065] {question}

[0066] The above is the question

[0067] The following is the knowledge base:

[0068] {knowledge}

[0069] The above is the knowledge base.

[0070] S5. Pass the prompt to the large model to generate auxiliary decision-making suggestions for equipment troubleshooting.

[0071] Specifically, use the enhanced prompt constructed in step S42 as the input of the large model. The large model generates fault operation and maintenance suggestions and displays them on the operation and maintenance terminal.

[0072] As can be seen from the above description, the method for assisting in troubleshooting air traffic control equipment based on a large model provided by the embodiments of the present invention can realize the precise push of operation and maintenance suggestions and emergency disposal processes for faults to be processed by integrating the domain knowledge in the air traffic control equipment fault operation and maintenance knowledge base with the semantic understanding and generation capabilities of the large model. It can assist operation and maintenance personnel in quickly locating and disposing of faults, which has important practical significance for ensuring flight safety and improving the quality of air traffic control services. In addition, the embodiments of the present invention also fill the gap that large models have not been applied to assist in troubleshooting air traffic control equipment.

[0073] Based on the same inventive concept, the embodiments of the present invention provide an air traffic control equipment auxiliary troubleshooting terminal based on a large model. It should be noted that this terminal can be understood as an operation and maintenance terminal. As Figure 3 shown, this terminal may include:

[0074] A data input module for inputting the document materials required for building the knowledge base; a schematic diagram of this module is as Figure 4 shown;

[0075] A knowledge base construction module for constructing an air traffic control equipment fault operation and maintenance knowledge base according to the document materials;

[0076] A data storage module for storing the air traffic control equipment fault operation and maintenance knowledge base, including its vectors and index information;

[0077] A query input module for inputting the fault information of the air traffic control equipment; a schematic diagram of this module is as Figure 5 shown;

[0078] A similarity retrieval module for retrieving the pre-constructed air traffic control equipment fault operation and maintenance knowledge base according to the fault information to obtain the most relevant document information to the fault information; a schematic diagram of this module is as Figure 6 shown;

[0079] A hint enhancement module for constructing an enhanced prompt based on the fault information and document information;

[0080] A suggestion generation module for passing the enhanced prompt to a large model so that the large model generates auxiliary decision-making suggestions for equipment fault troubleshooting;

[0081] A display module for displaying the auxiliary decision-making suggestions for equipment fault troubleshooting generated by the large model; The schematic diagram of this module is as Figure 5 shown.

[0082] It should be noted that for the specific working process of this embodiment, please refer to the method embodiment part mentioned above, which will not be elaborated here.

[0083] Furthermore, another embodiment of the present invention also provides an air traffic control equipment auxiliary fault troubleshooting terminal based on a large model. As Figure 7 shown, this terminal may include: one or more processors 101, one or more input devices 102, one or more output devices 103, and a memory 104. The above-mentioned processors 101, input devices 102, output devices 103, and memory 104 are interconnected through a bus 105. The memory 104 is used to store computer programs, and the computer programs include program instructions. The processor 101 is configured to call the program instructions to execute the methods in the method embodiment part mentioned above.

[0084] It should be understood that in the embodiments of the present invention, the so-called processor 101 may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0085] The input device 102 may include a keyboard, etc., and the output device 103 may include a display (such as an LCD), a speaker, etc.

[0086] This memory 104 may include a read-only memory and a random access memory, and provide instructions and data to the processor 101. A part of the memory 104 may also include a non-volatile random access memory. For example, the memory 104 may also store information about the device type.

[0087] In a specific implementation, the processor 101, input device 102, and output device 103 described in the embodiments of the present invention may implement the implementation manners described in the embodiments of the method for assisting in troubleshooting air traffic control equipment based on a large model provided by the embodiments of the present invention, which will not be elaborated herein.

[0088] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0089] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling, direct coupling, or communication connection may be an indirect coupling or communication connection through some interfaces, devices, or units, and can also be in the form of electrical, mechanical, or other connections.

[0090] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present invention.

[0091] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0092] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for assisting troubleshooting of air traffic control equipment based on a large model, characterized in that: include: Enter the fault information of the air traffic control equipment in the operation and maintenance terminal; According to the fault information, a pre-built air traffic control equipment fault operation and maintenance knowledge base is retrieved to obtain document information most relevant to the fault information; Construct an enhanced prompt according to the fault information and document information; The enhanced prompt is delivered to the big model so that the big model generates auxiliary decision suggestions for equipment troubleshooting.

2. The method according to claim 1, characterized in that Before the operation and maintenance terminal inputs the fault information of the air traffic control equipment, the method further includes constructing an air traffic control equipment fault operation and maintenance knowledge base, specifically: Collecting document materials; the document materials include an expert database, a typical case database and an experience database; Construct an air traffic control equipment fault operation and maintenance knowledge base based on the document information.

3. The method according to claim 2, characterized in that The specific construction of the air traffic control equipment fault operation and maintenance knowledge base based on the above document materials is as follows: Using a document loader to load documents in the air traffic control equipment fault operation and maintenance knowledge base, and using a document splitter to split the long documents into fixed-length, overlapping text blocks; The text block is converted into a text vector using an embedding model, and the text vector and its corresponding index are stored in a vector database.

4. The method according to claim 3, characterized in that The document information most relevant to the fault information is specifically: Using an embedding model to convert the fault information into a target text vector; A retriever is used to retrieve document information that is most similar to the target text vector semantics in the air traffic control equipment fault operation and maintenance knowledge base; wherein the retrieval method includes similarity retrieval and full-text retrieval.

5. The method according to claim 1, characterized in that The enhanced prompt is constructed according to the fault information and document information as follows: Construct the initial prompt, including background settings and task description; The fault information and the most similar document information are input into the initial prompt to construct an enhanced prompt.

6. The method according to claim 1, characterized in that The method further comprises: The auxiliary decision-making suggestions for equipment troubleshooting generated by the large model are displayed on the operation and maintenance terminal.

7. An air traffic control equipment auxiliary troubleshooting terminal based on a large model, characterized in that: include: Query input module, used to input fault information of air traffic control equipment; A similarity search module is used to search a pre-built air traffic control equipment fault operation and maintenance knowledge base according to the fault information to obtain document information most relevant to the fault information; A prompt enhancement module, used to construct an enhanced prompt according to the fault information and document information; The suggestion generation module is used to transmit the enhanced prompt to the large model so that the large model generates auxiliary decision-making suggestions for equipment troubleshooting.

8. The terminal according to claim 7, characterized in that The terminal further includes: A data input module is used to input document data; the document data includes an expert database, a typical case database and an experience database; The knowledge base construction module is used to construct an air traffic control equipment fault operation and maintenance knowledge base based on the document data, specifically: Using a document loader to load documents in the air traffic control equipment fault operation and maintenance knowledge base, and using a document splitter to split the long documents into fixed-length, overlapping text blocks; The text block is converted into a text vector using an embedding model, and the text vector and its corresponding index are stored in a vector database.

9. The terminal according to claim 7 or 8, characterized in that: The terminal also includes a display module for displaying auxiliary decision-making suggestions for equipment troubleshooting generated by the large model.

10. An air traffic control equipment auxiliary troubleshooting terminal based on a large model, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 6.

Images