A cloud computing-based aviation material procurement inquiry and quotation method and system

Abstract

The application belongs to the technical field of aviation material procurement, and discloses a cloud computing-based aviation material procurement inquiry and quotation method and system.The method comprises the following steps: a cloud data center is used to build a blockchain network and a supplier portrait database, and an artificial intelligence model is constructed; real-time aviation material procurement demand information is subjected to semantic enhancement, and aviation material demand matching is performed; according to the real-time aviation material demand matching result, inquiry sheets are generated, and a plurality of real-time inquiry sheets are sent to a plurality of target suppliers; according to the real-time quotation information of the target suppliers, supplier quotation analysis is performed, and a quotation report is generated; a cooperative supplier is confirmed, a procurement process is generated, and a real-time procurement process is obtained; and the blockchain network is used to perform distributed storage on aviation material procurement inquiry and quotation data.The application solves the problems of high cost, low efficiency, non-transparent information and poor traceability in the prior art.

Description

Technical Field

[0001] This invention belongs to the field of aviation material procurement technology, specifically relating to a cloud computing-based aviation material procurement inquiry and quotation method and system. Background Technology

[0002] To ensure the safe and reliable operation of aircraft, airlines need to regularly maintain and repair them, which requires a large amount of aviation materials. Aviation materials include aircraft parts, consumables, and standard components. These materials are typically characterized by high technology content, high precision, and high reliability, and their production and certification processes strictly adhere to aviation industry norms and standards. Therefore, aviation materials are often expensive, and the supply chain is relatively closed. Due to the special nature and cost factors of aviation materials, airlines usually conduct a quotation inquiry process when purchasing them. This involves inquiring with suppliers about prices, delivery times, payment terms, etc., and receiving corresponding quotations from suppliers. This allows airlines to compare the products and services of different suppliers and make the optimal purchasing decision.

[0003] Existing aircraft material procurement inquiry and quotation technologies have the following shortcomings:

[0004] 1) In the existing technology, the procurement of aircraft materials often relies on manual methods, which requires a lot of manpower and resources, is costly, and is inefficient when dealing with a large amount of aircraft material data, resulting in a slow procurement process and affecting the maintenance and repair progress of airlines.

[0005] 2) In the existing aircraft material procurement process, information is often opaque, the fairness and reasonableness of supplier quotations are difficult to verify, trust issues are easily generated, and the traceability of the resulting aircraft material procurement quotation data is poor. Summary of the Invention

[0006] To address the problems of high cost, low efficiency, lack of information transparency, and poor traceability in existing technologies, the present invention aims to provide a cloud computing-based method and system for procuring and quoting aircraft materials.

[0007] The technical solution adopted in this invention is as follows:

[0008] A cloud-based method for procuring and quoting aircraft materials includes the following steps:

[0009] The cloud data center will build a blockchain network and a supplier profile database, and use artificial intelligence algorithms to construct an aviation material knowledge graph, an aviation material demand matching model, a quotation generation model, a supplier quotation analysis model, a quotation report generation model, and a procurement process generation model.

[0010] In the cloud data center, the aviation material knowledge graph is used to semantically enhance the real-time aviation material procurement demand information. Based on the semantically enhanced real-time aviation material procurement demand information, the aviation material demand matching model is used to match aviation material demand in the supplier profile database to obtain the real-time aviation material demand matching results.

[0011] The cloud data center uses a quotation generation model to generate quotation orders based on the semantically enhanced real-time aviation material procurement demand information and the target supplier profiles of several target suppliers in the real-time aviation material demand matching results. This generates several real-time quotation orders, which are then sent to several target suppliers.

[0012] The cloud data center uses a supplier quotation analysis model to analyze supplier quotations based on the real-time quotation information of the target supplier. Based on the target supplier profile and the obtained real-time quotation analysis results, a quotation report generation model is used to generate a real-time quotation report.

[0013] In the cloud data center, cooperative suppliers are identified, real-time quotation information and supplier profiles are extracted, and a procurement process generation model is used to generate a real-time procurement process based on semantically enhanced real-time aviation material procurement demand information, supplier profiles, and real-time quotation information.

[0014] The cloud data center uses a blockchain network to distribute and store real-time aviation material procurement demand information, cooperative suppliers, real-time cooperative quotation information, cooperative supplier profiles, and corresponding real-time cooperative supplier quotation analysis results.

[0015] Furthermore, the cloud data center establishes a blockchain network and supplier profile database, and uses artificial intelligence algorithms to construct an aviation material knowledge graph, an aviation material demand matching model, a quotation generation model, a supplier quotation analysis model, a quotation report generation model, and a procurement process generation model, including the following steps:

[0016] A cloud data center is used to deploy an initial blockchain network with a distributed ledger, and to set up smart contracts and the IPFS system to obtain the final blockchain network.

[0017] Collect information on a number of aviation materials, historical aviation material procurement needs, historical pricing information, and supplier information from several suppliers.

[0018] Based on supplier information, a pre-trained supplier profile generation model is used to generate corresponding supplier profiles, and a supplier profile library is built based on several supplier profiles.

[0019] Using a pre-trained named entity and entity relationship extraction model, several named entities and corresponding knowledge entity relationships for each piece of aviation material knowledge are extracted, and an aviation material knowledge graph is constructed based on the named entities and knowledge entity relationships of all aviation material knowledge.

[0020] Based on the supplier profile database and aviation material knowledge graph, and using artificial intelligence algorithms, we construct aviation material demand matching models, inquiry form generation models, supplier quotation analysis models, quotation report generation models, and procurement process generation models, based on some historical aviation material procurement demand information and some historical quotation information.

[0021] Furthermore, the supplier profile generation model is built based on the RF-MLP algorithm;

[0022] The named entity and entity relationship extraction model is built based on the BERT-Double CRF algorithm;

[0023] The aircraft material demand matching model is constructed based on the Double GCN-MLP algorithm;

[0024] The Request for Quotation (RFQ) generation model is built based on the cGAN-MLP algorithm;

[0025] The supplier quotation analysis model is built based on the LSTM-Atention-MLP algorithm;

[0026] The quotation report generation model is built based on the cGAN-MLP algorithm;

[0027] The procurement process generation model is built based on the DQN algorithm.

[0028] Furthermore, in the cloud data center, an aviation materials knowledge graph is used to semantically enhance real-time aviation materials procurement demand information. Based on the semantically enhanced real-time aviation materials procurement demand information, an aviation materials demand matching model is used to match aviation materials demand in a supplier profile database to obtain real-time aviation materials demand matching results. This includes the following steps:

[0029] In the cloud data center, a named entity and entity relationship extraction model is used to extract several demand named entities from real-time aircraft material procurement demand information and the demand entity relationships between each demand named entity and other demand named entities.

[0030] Obtain the similarity between several knowledge named entities in the aviation material knowledge graph and each demand named entity. Take the knowledge named entity with the highest similarity as the associated knowledge named entity of the corresponding demand named entity, and take the knowledge named entity of the associated knowledge named entity as the associated knowledge entity relationship of the corresponding demand named entity.

[0031] Map the associated knowledge named entities to the corresponding requirement named entities, and add all the associated knowledge entity relationships of the associated knowledge named entities to the corresponding requirement named entities;

[0032] Traverse all named entities of real-time aircraft material procurement demand information, and build a graph structure based on all named entities of demand, all related knowledge named entities, all demand entity relationships and all related knowledge entity relationships to obtain semantically enhanced real-time aircraft material procurement demand information.

[0033] Using the aircraft material demand matching model, we extract the real-time demand information graph structure features of the semantically enhanced real-time aircraft material procurement demand information and the real-time supplier profile graph structure features of each supplier profile in the supplier profile database.

[0034] Based on the structural features of the real-time demand information graph and the structural features of several real-time supplier profile graphs, a matching score for the aircraft material demand is generated for each supplier. Several suppliers whose matching scores exceed the scoring threshold are selected as target suppliers to obtain the real-time aircraft material demand matching results.

[0035] Furthermore, the cloud data center, based on the semantically enhanced real-time aircraft material procurement demand information and the target supplier profiles of several target suppliers in the real-time aircraft material demand matching results, uses an inquiry form generation model to generate several real-time inquiry forms, and sends these real-time inquiry forms to several target suppliers, including the following steps:

[0036] In the cloud data center, the target supplier profile graph structure features of each target supplier in the real-time aviation material demand matching results are extracted, and the real-time demand information graph structure features and the target real-time supplier profile graph structure features of the semantically enhanced real-time aviation material procurement demand information are input into the inquiry form generation model.

[0037] Based on the structural features of the real-time demand information graph and the structural features of the target real-time supplier profile graph, the Request for Quotation generation model is used to embed conditional information to obtain the first real-time conditional information embedding feature.

[0038] Based on the embedded features of the first real-time condition information, a quotation order is generated to obtain the corresponding real-time quotation order. All target suppliers in the real-time aviation material demand matching results are traversed to obtain several real-time quotation orders, and these several real-time quotation orders are sent to several target suppliers.

[0039] Furthermore, the cloud data center, based on the target supplier's real-time quotation information, uses a supplier quotation analysis model to perform supplier quotation analysis, and based on the target supplier profile and the obtained real-time quotation analysis results, uses a quotation report generation model to generate a real-time quotation report, including the following steps:

[0040] The cloud data center receives real-time quotation information from each target supplier and inputs the semantically enhanced real-time demand information graph structure features of the real-time aviation material procurement demand information, the target supplier's real-time supplier profile graph structure features, and the real-time quotation information into the supplier quotation analysis model.

[0041] Using a supplier quotation analysis model, the real-time quotation information sequence features are extracted. Based on preset attention weights, the real-time demand information graph structure features, the target real-time supplier profile graph structure features, and the real-time quotation information sequence features are weighted and fused to obtain real-time weighted fused features.

[0042] Based on the real-time weighted fusion characteristics, supplier quotation analysis is performed to obtain the corresponding real-time quotation analysis results. The real-time demand information graph structure characteristics, the target real-time supplier profile graph structure characteristics, the real-time quotation information sequence characteristics, and the real-time quotation analysis results are then input into the quotation report generation model.

[0043] Based on the structural features of the real-time demand information graph, the structural features of the target real-time supplier profile graph, the features of the real-time quotation information sequence, and the real-time quotation analysis results, the quotation report generation model is used to embed conditional information to obtain the second real-time conditional information embedding feature.

[0044] Based on the embedded features of the second real-time condition information, a quotation report is generated to obtain the real-time quotation report of the corresponding target supplier. By traversing the real-time quotation information of all target suppliers, a real-time quotation report of each target supplier is obtained.

[0045] Furthermore, the cloud data center identifies partner suppliers, extracts real-time quote information and supplier profiles, and, based on the semantically enhanced real-time aircraft material procurement demand information, partner supplier profiles, and real-time quote information, uses a procurement process generation model to generate a real-time procurement process, including the following steps:

[0046] The cloud data center selects a cooperative supplier from all target suppliers in the real-time aviation material demand matching results based on the real-time confirmation information input by the user, and extracts the corresponding real-time quotation information and cooperative supplier profile.

[0047] Extract the structural features of the real-time supplier profile and the sequence features of the real-time quotation information from the real-time supplier profile. Then, input the structural features of the real-time supplier profile, the sequence features of the real-time quotation information, and the structural features of the real-time demand information graph of the semantically enhanced real-time aviation material procurement demand into the procurement process generation model.

[0048] Based on the structural features of the real-time supplier profile graph, the sequence features of the real-time quotation information, and the structural features of the real-time demand information graph of the semantically enhanced real-time aviation material procurement demand information, a procurement process generation model is used to generate the procurement process and obtain the real-time procurement process.

[0049] Furthermore, based on the structural features of the real-time supplier profile graph, the sequence features of the real-time quotation information, and the structural features of the real-time demand information graph of the semantically enhanced real-time aircraft material procurement demand information, a procurement process generation model is used to generate the real-time procurement process, which includes the following steps:

[0050] Based on the structural characteristics of the real-time demand information graph, a search and matching process is performed in the experience replay pool of the procurement process generation model to obtain the successfully matched real-time procurement process generation experience.

[0051] Based on the experience of generating real-time procurement processes, the structural features of real-time cooperative supplier profiles, the sequence features of real-time cooperative quotation information, and the structural features of real-time demand information graphs of semantically enhanced real-time aviation material procurement demand information, the procurement process generation model is updated to obtain an updated procurement process generation model.

[0052] The updated procurement process generation model is used to generate the procurement process, resulting in a real-time procurement process.

[0053] Furthermore, the cloud data center uses a blockchain network to distribute and store real-time aircraft material procurement demand information, cooperating suppliers, real-time quotations, supplier profiles, and corresponding real-time supplier quotation analysis results, including the following steps:

[0054] By linking real-time aircraft material procurement demand information, cooperative suppliers, cooperative real-time quotation information, cooperative supplier profiles, and corresponding cooperative real-time supplier quotation analysis results, real-time aircraft material procurement inquiry and quotation data can be obtained.

[0055] The real-time aircraft material procurement inquiry and quotation data is stored in the IPFS system to obtain the real-time data hash value. The smart contract is called to generate the corresponding real-time transaction data and real-time transaction records based on the real-time data hash value. The transaction data is distributed and stored using the blockchain network to obtain the corresponding real-time storage address.

[0056] Real-time search tags are generated for real-time aircraft material procurement inquiry and quotation data. The real-time storage address, real-time search tags, and real-time transaction records are written into the distributed ledger to obtain an updated distributed ledger. The updated distributed ledger is then synchronized to the blockchain network.

[0057] A cloud computing-based aircraft material procurement inquiry and quotation system is used to implement aircraft material procurement inquiry and quotation methods. The system is deployed in a cloud data center and includes a blockchain network construction and model building unit, a semantic enhancement and aircraft material demand matching unit, an inquiry form generation and sending unit, a quotation analysis and quotation report generation unit, a procurement process generation unit, and a distributed storage unit connected in sequence.

[0058] The beneficial effects of this invention are as follows:

[0059] This invention provides a cloud-based method and system for aircraft material procurement and quotation. It employs highly intelligent artificial intelligence algorithms to automate aircraft material demand matching, quotation generation, supplier quotation analysis, quotation report generation, and procurement process generation. This avoids reliance on manual review and analysis, reducing human and material costs. Furthermore, the AI ​​model's strong data processing capabilities enable it to uncover deeper information about procurement needs and quotation schemes, improving the efficiency and speed of the aircraft material procurement and quotation process. It also enhances the accuracy of quotation comparison and procurement processes, making it suitable for large-scale aircraft material data procurement scenarios. The use of a cloud data center for unified management of aircraft material procurement and quotation improves computing power, strengthens information exchange, and provides a transparent platform. A blockchain network ensures that all quotations and transaction records are traceable and verifiable, increasing fair competition among suppliers.

[0060] Other beneficial effects of the present invention will be further explained in the specific embodiments. Attached Figure Description

[0061] Figure 1 This is a flowchart of the cloud computing-based aircraft material procurement inquiry and quotation method in this invention.

[0062] Figure 2 This is a structural block diagram of the cloud computing-based aircraft material procurement inquiry and quotation system of this invention. Detailed Implementation

[0063] The present invention will be further explained below with reference to the accompanying drawings and specific embodiments.

[0064] Example 1:

[0065] like Figure 1 As shown in the figure, this embodiment provides a cloud computing-based method for requesting and quoting quotations for aircraft materials, including the following steps:

[0066] S1: Cloud data center, building a blockchain network and supplier profile database, and using artificial intelligence algorithms to construct an aviation material knowledge graph, aviation material demand matching model, inquiry form generation model, supplier quotation analysis model, quotation report generation model, and procurement process generation model, including the following steps:

[0067] S1-1: Cloud data center, deploying an initial blockchain network with a distributed ledger, and setting up smart contracts and the InterPlanetary File System (IPFS) to obtain the final blockchain network;

[0068] S1-2: Collect information on a number of aviation materials, historical aviation material procurement needs, historical price quotes, and supplier information for several suppliers.

[0069] The aircraft material procurement requirements include the aircraft material model, quantity, quality requirements, delivery time, and budget. The supplier information includes the supplier's basic information, qualifications, historical quotations, and reputation rating.

[0070] S1-3: Based on the supplier information, use a pre-trained supplier profile generation model to generate corresponding supplier profiles, and build a supplier profile library based on several supplier profiles.

[0071] The supplier profile generation model is built on the Random Forest (RF)-Multilayer Perceptron (MLP) algorithm, and the supplier profile generation model includes a key feature screening module built on the RF algorithm and a supplier profile generation module built on the MLP algorithm, which are connected in sequence.

[0072] The key feature filtering module filters the input supplier information through its internal Classification and Regression Tree (CART). It can process a large number of feature components and generate a key feature importance score for each feature component. Based on the key feature importance score, it selects the most stable and discriminative feature component. The trained key feature filtering module can directly filter the newly input supplier information based on the selected key features to obtain key features for evaluating suppliers, including qualifications, historical pricing records, cooperation records, etc. The supplier profile generation module, as a fully connected network, can predict supplier profile labels based on the filtered key features.

[0073] S1-4: Using a pre-trained named entity and entity relationship extraction model, extract several named entities and corresponding several knowledge entity relationships for each piece of aviation material knowledge, and construct an aviation material knowledge graph based on the several named entities and several knowledge entity relationships of all aviation material knowledge.

[0074] The named entity and entity relationship extraction model is built on the Bidirectional Encoder Representations from Transformers (BERT)-Double Conditional Random Fields (CRF) algorithm. The model includes a text feature extraction module based on the BERT algorithm, a named entity extraction module based on the CRF algorithm, and an entity relationship extraction module based on the CRF algorithm. The text feature extraction module is connected to the named entity extraction module and the entity relationship extraction module, respectively.

[0075] The BERT module can capture deep semantic information in the preprocessed appendix user manual text data, which is very useful for identifying different types of entities and extracting relationships between entities. The CRF module can consider the dependencies between adjacent labels, which can help the model learn the sequence dependencies of entity labels, thereby improving the accuracy of named entity labeling. In the entity relationship labeling task, the CRF module handles the classification of relationships between entity pairs, especially when dealing with multiple entities and relationships, to achieve entity relationship labeling.

[0076] S1-5: Based on the supplier profile database and aviation material knowledge graph, and using historical aviation material procurement demand information and historical quotation information, artificial intelligence algorithms are used to construct an aviation material demand matching model, a quotation generation model, a supplier quotation analysis model, a quotation report generation model, and a procurement process generation model, including the following steps:

[0077] S1-5-1: Using a knowledge graph, knowledge mapping is performed on several historical aircraft material procurement demand information to obtain several semantically enhanced historical aircraft material procurement demand information.

[0078] Through mapping, the original information in the aircraft material procurement demand information is endowed with additional semantic information. This information comes from the structured knowledge in the aircraft material knowledge graph. The originally simple aircraft material procurement demand information is transformed into semantic entities and relationships rich in contextual information. Furthermore, the aircraft material procurement demand information is transformed from the original low-dimensional data into high-dimensional data with graph structure information, which improves the ability of the aircraft material procurement demand information to represent procurement demand and provides high-dimensional information expression for subsequent model analysis.

[0079] S1-5-2: Based on several semantically enhanced historical aircraft material procurement demand information and several supplier profiles, a deep learning algorithm is used to construct an aircraft material demand matching model, and generate historical demand information graph structure features of several semantically enhanced historical aircraft material procurement demand information and historical supplier profile graph structure features of several supplier profiles.

[0080] The aircraft material demand matching model is constructed based on the Double Graph Convolutional Network (GCN)-MLP algorithm. The model includes a first graph structure feature extraction module based on the GCN algorithm, a second graph structure feature extraction module based on the GCN algorithm, and an aircraft material demand matching module based on the MLP algorithm. Both the first and second graph structure feature extraction modules are connected to the aircraft material demand matching module. The MLP network, as a fully connected network, performs aircraft material demand matching evaluation based on the demand information graph structure features and the supplier profile graph structure features, obtaining a corresponding aircraft material demand matching score. This score reflects the degree of matching between the supplier information contained in the supplier profile and the aircraft material procurement demand information.

[0081] The GCN network performs feature propagation on graph-structured data through convolution-like operations, extracting node features (positional features, image features, etc.) and edge features of positional relationships between nodes from several segmented images in the graph-structured data, and constructing complex, high-dimensional global graph structure features.

[0082] S1-5-3: Based on the structural features of several historical demand information graphs, as well as several supplier profiles and corresponding real inquiry forms, a deep learning algorithm is used to build an inquiry form generation model;

[0083] The inquiry form generation model is constructed based on the Conditional Generative Adversarial Network (cGAN)-MLP algorithm. The inquiry form generation model includes an inquiry form generation module constructed based on the cGAN algorithm and a first conditional information embedding module and a first conditional information processing module, both constructed based on the MLP algorithm. The inquiry form generation module includes a first generator and a first discriminator, both constructed based on the Recurrent Neural Network (RNN) algorithm. The first generator is connected to the first conditional information embedding module and the first discriminator, respectively. The first discriminator is connected to the first conditional information processing module.

[0084] The conditional information embedding module processes the feature forms of all input modalities, including graph structure features and sequence features, to obtain conditional information embedding features in sequence format, thus integrating conditional information into the generation process. The generator processes the sequence data and random noise output by the conditional information embedding module to generate the preliminary content of the inquiry form or quotation report. The conditional information processing module processes the additional conditional information included in the features of all modalities to help the discriminator more accurately judge the authenticity of the inquiry form or quotation report. The discriminator analyzes the generated inquiry form or quotation report to determine whether it is authentic and meets the given conditional information. The generator and discriminator compete with each other through an adversarial training process. The generator attempts to generate inquiry forms or quotation reports that can deceive the discriminator, while the discriminator attempts to better identify real and fake inquiry forms or quotation reports.

[0085] S1-5-4: Based on the structural features of several historical demand information graphs, the structural features of several historical supplier profile graphs, and several historical quotation information, a supplier quotation analysis model is constructed using a deep learning algorithm, and the historical quotation information sequence features and corresponding historical quotation analysis results are generated.

[0086] The supplier pricing analysis model is built on the Long Short-Term Memory (LSTM)-Atention-MLP algorithm, and the supplier pricing analysis model includes a sequence feature extraction module built on the LSTM algorithm, an attention weight module built on the Attention mechanism, and a supplier pricing analysis module built on the MLP algorithm, which are connected in sequence.

[0087] The LSTM network extracts the sequential features of the quotation information. The attention weight module uses preset attention weight values ​​to weight and fuse the input demand information graph structure features, supplier profile graph structure features, and quotation information sequence features, thereby enhancing the model's attention to important features and improving the accuracy and efficiency of the model's predictions.

[0088] S1-5-5: Based on the structural features of several historical demand information graphs, the sequence features of several historical quotation information graphs, and the structural features of several historical supplier profile graphs, as well as the corresponding historical quotation analysis results and real quotation reports, a quotation report generation model is constructed using a deep learning algorithm.

[0089] The quotation report generation model is built based on the cGAN-MLP algorithm. The quotation report generation model includes a quotation report generation module built based on the cGAN algorithm and a second conditional information embedding module and a second conditional information processing module both built based on the MLP algorithm. The quotation report generation module includes a second generator and a second discriminator both built based on the RNN algorithm. The second generator is connected to the second conditional information embedding module and the second discriminator respectively. The second discriminator is connected to the second conditional information processing module.

[0090] S1-5-6: Based on the structural features of several historical demand information graphs, the structural features of several historical supplier profile graphs, and the sequence features of several historical quotation information, a procurement process generation model is constructed using reinforcement learning algorithms.

[0091] The procurement process generation model is built based on the Deep Q Network (DQN) algorithm, and includes an intelligent agent, a Deep Q Network, and an experience replay pool.

[0092] The deep Q-network is used to output the Q-value for each state in the state space and each possible action in the action space, based on the state space, action space, and reward function. The agent is used to obtain the reward value and control the deep Q-network to update the Q-value based on the reward value. The experience replay pool is used to store the historical procurement process generation experience generated during the training process.

[0093] Based on the structural features of several historical demand information graphs, the structural features of several historical supplier profile graphs, and the sequence features of several historical quotation information, a procurement process generation model is constructed using reinforcement learning algorithms, including the following steps:

[0094] S1-5-6-1: Use the procurement process generation problem as a simulation environment for the DQN algorithm, and use the DQN algorithm to build an initial procurement process generation model;

[0095] S1-5-6-2: Generate several corresponding procurement process states based on the structural features of the historical demand information graph, the structural features of the historical supplier profile graph, and the sequence features of the historical quotation information.

[0096] S1-5-6-3: Define the state space of the DQN algorithm, and define the action space of the DQN algorithm based on several preset procurement process actions;

[0097] S1-5-6-4: Define the reward function of the DQN algorithm based on the impact of preset procurement process actions on the status of historical procurement processes;

[0098] S1-5-6-5: Based on the state space, action space, and reward function, input several historical demand information graph structure features, several historical supplier profile graph structure features, and several historical quotation information sequence features to train the agent of the initial procurement process generation model, obtain the final procurement process generation model, and generate several historical procurement process generation experiences.

[0099] S1-5-6-6: Store the historical procurement process generation experience into the experience replay pool of the final procurement process generation model;

[0100] S2: The cloud data center uses an aviation materials knowledge graph to semantically enhance real-time aviation materials procurement demand information. Based on the semantically enhanced real-time aviation materials procurement demand information, an aviation materials demand matching model is used to match aviation materials demand in a supplier profile database to obtain real-time aviation materials demand matching results. This includes the following steps:

[0101] S2-1: Cloud Data Center, using the Named Entity and Entity Relationship Extraction Model, extracts several demand named entities from real-time aviation material procurement demand information and the demand entity relationships between each demand named entity and other demand named entities.

[0102] S2-2: Obtain the similarity between several knowledge named entities in the aviation material knowledge graph and each demand named entity, take the knowledge named entity with the highest similarity as the associated knowledge named entity of the corresponding demand named entity, and take the knowledge named entity of the associated knowledge named entity as the associated knowledge entity relationship of the corresponding demand named entity.

[0103] S2-3: Map the associated knowledge named entities to the corresponding requirement named entities, and add all associated knowledge entity relationships of the associated knowledge named entities to the corresponding requirement named entities;

[0104] S2-4: Traverse all named entities of real-time aircraft material procurement demand information, and build a graph structure based on all named entities of demand, all related knowledge named entities, all demand entity relationships and all related knowledge entity relationships to obtain semantically enhanced real-time aircraft material procurement demand information.

[0105] S2-5: Using the first graph structure feature extraction module of the aviation material demand matching model, extract the real-time demand information graph structure features of the semantically enhanced real-time aviation material procurement demand information; using the second graph structure feature extraction module, extract the real-time supplier profile graph structure features of each supplier profile in the supplier profile library.

[0106] S2-6: Based on the structural features of the real-time demand information graph and the structural features of several real-time supplier profile graphs, the aircraft material demand matching module is used to generate an aircraft material demand matching score for each supplier, and several suppliers whose aircraft material demand matching scores exceed the score threshold are selected as target suppliers to obtain the real-time aircraft material demand matching results.

[0107] S3: The cloud data center, based on the semantically enhanced real-time aircraft material procurement demand information and the target supplier profiles of several target suppliers in the real-time aircraft material demand matching results, uses the inquiry form generation model to generate several real-time inquiry forms, and sends these real-time inquiry forms to several target suppliers, including the following steps:

[0108] S3-1: Cloud Data Center, extracts the target supplier profile graph structure features of each target supplier in the real-time aviation material demand matching results, and inputs the real-time demand information graph structure features and the target real-time supplier profile graph structure features of the semantically enhanced real-time aviation material procurement demand information into the Request for Quotation generation model;

[0109] S3-2: Based on the structural features of the real-time demand information graph and the structural features of the target real-time supplier profile graph, the first conditional information embedding module of the inquiry form generation model is used to embed conditional information to obtain the first real-time conditional information embedding feature.

[0110] S3-3: Based on the embedded features of the first real-time condition information, use the first generator to generate the inquiry form, obtain the corresponding real-time inquiry form, traverse all target suppliers in the real-time aviation material demand matching result, obtain several real-time inquiry forms, and send several real-time inquiry forms to several target suppliers.

[0111] S4: Cloud Data Center. Based on the real-time quotation information of the target supplier, a supplier quotation analysis model is used to analyze the supplier quotation. Based on the target supplier profile and the obtained real-time quotation analysis results, a quotation report is generated using a quotation report generation model to obtain a real-time quotation report. This includes the following steps:

[0112] S4-1: Cloud Data Center, which receives real-time quotation information returned by each target supplier, and inputs the semantically enhanced real-time demand information graph structure features of the real-time aviation material procurement demand information, the target supplier's real-time supplier profile graph structure features, and the real-time quotation information into the supplier quotation analysis model.

[0113] S4-2: Using the sequence feature extraction module of the supplier quotation analysis model, extract the real-time quotation information sequence features, and according to the preset attention weight, use the attention weight module to perform weighted fusion of the real-time demand information graph structure features, the target real-time supplier profile graph structure features, and the real-time quotation information sequence features to obtain real-time weighted fusion features.

[0114] S4-3: Based on the real-time weighted fusion characteristics, use the supplier quotation analysis module to perform supplier quotation analysis, obtain the corresponding real-time quotation analysis results, and input the real-time demand information graph structure characteristics, the target real-time supplier profile graph structure characteristics, the real-time quotation information sequence characteristics, and the real-time quotation analysis results into the quotation report generation model;

[0115] The quotation analysis results include price evaluation results, supplier qualification evaluation results, and delivery cycle evaluation results. The price evaluation results are used to predict whether the supplier's quotation meets the budget of the aviation material procurement needs. The supplier qualification evaluation results are used to predict whether the supplier's qualifications meet the quality requirements. The delivery cycle evaluation results are used to predict whether the supplier's supply can meet the delivery time.

[0116] S4-4: Based on the structural features of the real-time demand information graph, the structural features of the target real-time supplier profile graph, the features of the real-time quotation information sequence, and the real-time quotation analysis results, the second conditional information embedding module of the quotation report generation model is used to embed conditional information to obtain the second real-time conditional information embedding features.

[0117] S4-5: Based on the embedded features of the second real-time condition information, use the second generator to generate a quotation report, obtain the real-time quotation report of the corresponding target supplier, traverse the real-time quotation information of all target suppliers, and obtain the real-time quotation report of each target supplier.

[0118] S5: Cloud Data Center confirms partner suppliers, extracts real-time quote information and supplier profiles, and uses a procurement process generation model based on semantically enhanced real-time aircraft material procurement demand information, partner supplier profiles, and real-time quote information to generate a real-time procurement process, including the following steps:

[0119] S5-1: Cloud Data Center. Based on the real-time confirmation information input by the user, it selects a cooperative supplier from all target suppliers in the real-time aviation material demand matching results and extracts the corresponding real-time quotation information and cooperative supplier profile.

[0120] S5-2: Extract the structural features of the real-time supplier profile and the sequence features of the real-time quotation information from the real-time supplier profile, and input the structural features of the real-time supplier profile, the sequence features of the real-time quotation information, and the real-time demand information graph structural features of the semantically enhanced real-time aviation material procurement demand information into the procurement process generation model.

[0121] S5-3: Based on the structural features of the real-time supplier profile graph, the sequence features of the real-time quotation information, and the structural features of the real-time demand information graph of the semantically enhanced real-time aircraft material procurement demand, a procurement process generation model is used to generate the real-time procurement process, including the following steps:

[0122] S5-3-1: Based on the structural characteristics of the real-time demand information graph, search and match in the experience replay pool of the procurement process generation model to obtain the successfully matched real-time procurement process generation experience.

[0123] S5-3-2: Based on the experience of generating real-time procurement processes, the structural features of the real-time supplier profile graph, the sequence features of real-time quotation information, and the structural features of the real-time demand information graph of semantically enhanced real-time aircraft material procurement demand information, the procurement process generation model is updated to obtain the updated procurement process generation model, including the following steps:

[0124] S5-3-2-1: Based on the experience generated from the real-time procurement process, update the action space of the procurement process generation model to obtain the updated action space;

[0125] S5-3-2-2: Based on the experience of generating real-time procurement processes, the structural features of real-time cooperative supplier profiles, the sequence features of real-time cooperative quotation information, and the structural features of real-time demand information graphs of semantically enhanced real-time aviation material procurement demand information, the state space of the procurement process generation model is updated to obtain the updated state space.

[0126] S5-3-2-3: Connect the updated state space to the input layer of the deep Q-network of the procurement process generation model, and connect the updated action space to the output layer of the deep Q-network of the procurement process generation model to obtain the updated deep Q-network, i.e., the updated procurement process generation model.

[0127] S5-3-3: Using the updated procurement process generation model, generate the procurement process to obtain a real-time procurement process, including the following steps:

[0128] S5-3-3-1: Based on the reward function, obtain the reward value of each possible action of the real-time procurement process in the updated action space for each state of the real-time procurement process in the updated state space, and use an agent to control the updated deep Q network to generate the Q value of each possible action of the real-time procurement process in the updated action space.

[0129] S5-3-3-2: Based on the reward value, use an intelligent agent to iteratively update the Q value of possible actions in the real-time procurement process, obtain the updated Q value, until the number of iterations reaches the iteration threshold, and use a greedy strategy to select the possible action of the real-time procurement process with the highest updated Q value as the action to be executed in the real-time procurement process, and integrate all the actions to be executed in the real-time procurement process to obtain the real-time procurement process strategy.

[0130] The procurement process strategy is used to formulate procurement process plans. If the price analysis results are all normal, the procurement process will proceed according to the preset standard process, including public announcement, purchase request, order placement, and payment. If the price evaluation results are not satisfactory, the procurement process will also include negotiation with the supplier. If the delivery cycle evaluation results are not satisfactory, the procurement process will also include negotiation with the supplier on the delivery cycle.

[0131] S6: Cloud Data Center, using a blockchain network, distributes and stores real-time aircraft material procurement demand information, cooperating suppliers, real-time quotations from cooperating suppliers, supplier profiles, and corresponding real-time supplier quotation analysis results. This includes the following steps:

[0132] S6-1: Link real-time aircraft material procurement demand information, cooperative suppliers, cooperative real-time quotation information, cooperative supplier profiles, and corresponding cooperative real-time supplier quotation analysis results to obtain real-time aircraft material procurement inquiry and quotation data;

[0133] S6-2: Store real-time aircraft material procurement inquiry and quotation data in the IPFS system, obtain real-time data hash value, call smart contract, generate corresponding real-time transaction data and real-time transaction records based on real-time data hash value, use blockchain network to distribute the transaction data and obtain the corresponding real-time storage address;

[0134] S6-3: Generate real-time search tags for real-time aircraft material procurement inquiry and quotation data, and write the real-time storage address, real-time search tags, and real-time transaction records into the distributed ledger to obtain an updated distributed ledger, and synchronize the updated distributed ledger to the blockchain network.

[0135] Example 2:

[0136] like Figure 2 As shown, this embodiment provides a cloud computing-based aircraft material procurement inquiry and quotation system to implement an aircraft material procurement inquiry and quotation method. The system is deployed in a cloud data center and includes a blockchain network construction and model building unit, a semantic enhancement and aircraft material demand matching unit, an inquiry form generation and sending unit, a quotation analysis and quotation report generation unit, a procurement process generation unit, and a distributed storage unit connected in sequence.

[0137] The blockchain network construction and model building unit is used to build a blockchain network and supplier profile database, and uses artificial intelligence algorithms to build an aviation material knowledge graph, an aviation material demand matching model, a quotation generation model, a supplier quotation analysis model, a quotation report generation model, and a procurement process generation model.

[0138] The semantic enhancement and aircraft material demand matching unit is used to enhance the semantics of real-time aircraft material procurement demand information using an aircraft material knowledge graph, and then use an aircraft material demand matching model to match aircraft material demand in a supplier profile database based on the semantically enhanced real-time aircraft material procurement demand information to obtain real-time aircraft material demand matching results.

[0139] The Request for Quotation (RFQ) generation and sending unit is used to generate RFQs based on the semantically enhanced real-time aviation material procurement demand information and the target supplier profiles of several target suppliers in the real-time aviation material demand matching results, using the RFQ generation model to obtain several real-time RFQs, and then send the several real-time RFQs to several target suppliers.

[0140] The quotation analysis and quotation report generation unit is used to analyze supplier quotations based on the real-time quotation information of the target supplier using a supplier quotation analysis model, and generate a quotation report based on the target supplier profile and the obtained real-time quotation analysis results using a quotation report generation model to obtain a real-time quotation report.

[0141] The procurement process generation unit is used to confirm cooperative suppliers, extract real-time quotation information and cooperative supplier profiles, and generate a real-time procurement process using the procurement process generation model based on the semantically enhanced real-time aviation material procurement demand information, cooperative supplier profiles and real-time quotation information.

[0142] The distributed storage unit is used to distribute and store real-time aviation material procurement demand information, cooperative suppliers, real-time cooperative quotation information, cooperative supplier profiles, and corresponding real-time cooperative supplier quotation analysis results using a blockchain network.

[0143] This invention provides a cloud-based method and system for aircraft material procurement and quotation. It employs highly intelligent artificial intelligence algorithms to automate aircraft material demand matching, quotation generation, supplier quotation analysis, quotation report generation, and procurement process generation. This avoids reliance on manual review and analysis, reducing human and material costs. Furthermore, the AI ​​model's strong data processing capabilities enable it to uncover deeper information about procurement needs and quotation schemes, improving the efficiency and speed of the aircraft material procurement and quotation process. It also enhances the accuracy of quotation comparison and procurement processes, making it suitable for large-scale aircraft material data procurement scenarios. The use of a cloud data center for unified management of aircraft material procurement and quotation improves computing power, strengthens information exchange, and provides a transparent platform. A blockchain network ensures that all quotations and transaction records are traceable and verifiable, increasing fair competition among suppliers.

[0144] This invention is not limited to the optional embodiments described above, and anyone can derive other various forms of products based on the inspiration of this invention. The specific embodiments described above should not be construed as limiting the scope of protection of this invention; the scope of protection of this invention should be determined by the claims, and the specification can be used to interpret the claims.

Claims

1. A cloud computing-based method for requesting and quoting quotations for aircraft materials, characterized in that: Includes the following steps: The cloud data center will build a blockchain network and a supplier profile database, and use artificial intelligence algorithms to construct an aviation material knowledge graph, an aviation material demand matching model, a quotation generation model, a supplier quotation analysis model, a quotation report generation model, and a procurement process generation model. In the cloud data center, the aviation material knowledge graph is used to semantically enhance the real-time aviation material procurement demand information. Based on the semantically enhanced real-time aviation material procurement demand information, the aviation material demand matching model is used to match aviation material demand in the supplier profile database to obtain the real-time aviation material demand matching results. The cloud data center uses a quotation generation model to generate quotation orders based on the semantically enhanced real-time aviation material procurement demand information and the target supplier profiles of several target suppliers in the real-time aviation material demand matching results. This generates several real-time quotation orders, which are then sent to several target suppliers. The cloud data center uses a supplier quotation analysis model to analyze supplier quotations based on the real-time quotation information of the target supplier. Based on the target supplier profile and the obtained real-time quotation analysis results, a quotation report generation model is used to generate a real-time quotation report. In the cloud data center, cooperative suppliers are identified, real-time quotation information and supplier profiles are extracted, and a procurement process generation model is used to generate a real-time procurement process based on semantically enhanced real-time aviation material procurement demand information, supplier profiles, and real-time quotation information. The method for constructing the procurement process generation model includes the following steps: The procurement process generation problem is used as a simulation environment for the DQN algorithm. The DQN algorithm is then used to construct an initial procurement process generation model. Based on the structural features of historical demand information graphs, the structural features of historical supplier profile graphs, and the sequence features of historical quotation information, several corresponding procurement process states are generated. Define the state space of the DQN algorithm, and define the action space of the DQN algorithm based on several preset procurement process actions; Based on the impact of preset procurement process actions on the status of historical procurement processes, the reward function of the DQN algorithm is defined. Based on the state space, action space, and reward function, the agent of the initial procurement process generation model is trained by inputting several historical demand information graph structure features, several historical supplier profile graph structure features, and several historical quotation information sequence features to obtain the final procurement process generation model and generate several historical procurement process generation experiences. The experience generated from historical procurement processes is stored in the experience replay pool of the final procurement process generation model; The cloud data center uses a blockchain network to distribute and store real-time aviation material procurement demand information, cooperative suppliers, real-time cooperative quotation information, cooperative supplier profiles, and corresponding real-time cooperative supplier quotation analysis results.

2. The cloud computing-based aircraft material procurement quotation method according to claim 1, characterized in that: The cloud data center establishes a blockchain network and supplier profile database, and uses artificial intelligence algorithms to construct an aviation material knowledge graph, an aviation material demand matching model, a quotation generation model, a supplier quotation analysis model, a quotation report generation model, and a procurement process generation model, including the following steps: A cloud data center is used to deploy an initial blockchain network with a distributed ledger, and to set up smart contracts and the IPFS system to obtain the final blockchain network. Collect information on a number of aviation materials, historical aviation material procurement needs, historical pricing information, and supplier information from several suppliers. Based on supplier information, a pre-trained supplier profile generation model is used to generate corresponding supplier profiles, and a supplier profile library is built based on several supplier profiles. Using a pre-trained named entity and entity relationship extraction model, several named entities and corresponding knowledge entity relationships for each piece of aviation material knowledge are extracted, and an aviation material knowledge graph is constructed based on the named entities and knowledge entity relationships of all aviation material knowledge. Based on the supplier profile database and aviation material knowledge graph, and using artificial intelligence algorithms, we construct aviation material demand matching models, inquiry form generation models, supplier quotation analysis models, quotation report generation models, and procurement process generation models, based on some historical aviation material procurement demand information and some historical quotation information.

3. The cloud computing-based aircraft material procurement quotation method according to claim 2, characterized in that: The supplier profile generation model is built based on the RF-MLP algorithm; The named entity and entity relationship extraction model described above is constructed based on the BERT-Double CRF algorithm; The aforementioned aircraft material demand matching model is constructed based on the Double GCN-MLP algorithm; The aforementioned inquiry form generation model is constructed based on the cGAN-MLP algorithm; The supplier quotation analysis model described above is constructed based on the LSTM-Atention-MLP algorithm; The aforementioned quotation report generation model is built based on the cGAN-MLP algorithm; The procurement process generation model is built based on the DQN algorithm.

4. The cloud computing-based aircraft material procurement quotation method according to claim 3, characterized in that: The cloud data center uses an aviation materials knowledge graph to semantically enhance real-time aviation materials procurement demand information. Based on the semantically enhanced real-time aviation materials procurement demand information, an aviation materials demand matching model is used to match aviation materials demand with a supplier profile database to obtain real-time aviation materials demand matching results. The process includes the following steps: In the cloud data center, a named entity and entity relationship extraction model is used to extract several demand named entities from real-time aircraft material procurement demand information and the demand entity relationships between each demand named entity and other demand named entities. Obtain the similarity between several knowledge named entities in the aviation material knowledge graph and each demand named entity. Take the knowledge named entity with the highest similarity as the associated knowledge named entity of the corresponding demand named entity, and take the knowledge named entity of the associated knowledge named entity as the associated knowledge entity relationship of the corresponding demand named entity. Map the associated knowledge named entities to the corresponding requirement named entities, and add all the associated knowledge entity relationships of the associated knowledge named entities to the corresponding requirement named entities; Traverse all named entities of real-time aircraft material procurement demand information, and build a graph structure based on all named entities of demand, all related knowledge named entities, all demand entity relationships and all related knowledge entity relationships to obtain semantically enhanced real-time aircraft material procurement demand information. Using the aircraft material demand matching model, we extract the real-time demand information graph structure features of the semantically enhanced real-time aircraft material procurement demand information and the real-time supplier profile graph structure features of each supplier profile in the supplier profile database. Based on the structural features of the real-time demand information graph and the structural features of several real-time supplier profile graphs, a matching score for the aircraft material demand is generated for each supplier. Several suppliers whose matching scores exceed the scoring threshold are selected as target suppliers to obtain the real-time aircraft material demand matching results.

5. The cloud computing-based aircraft material procurement quotation method according to claim 4, characterized in that: The cloud data center, based on the semantically enhanced real-time aircraft material procurement demand information and the target supplier profiles of several target suppliers from the real-time aircraft material demand matching results, uses a quotation request generation model to generate several real-time quotation requests, and then sends these real-time quotation requests to several target suppliers, including the following steps: In the cloud data center, the target supplier profile graph structure features of each target supplier in the real-time aviation material demand matching results are extracted, and the real-time demand information graph structure features and the target real-time supplier profile graph structure features of the semantically enhanced real-time aviation material procurement demand information are input into the inquiry form generation model. Based on the structural features of the real-time demand information graph and the structural features of the target real-time supplier profile graph, the Request for Quotation generation model is used to embed conditional information to obtain the first real-time conditional information embedding feature. Based on the embedded features of the first real-time condition information, a quotation order is generated to obtain the corresponding real-time quotation order. All target suppliers in the real-time aviation material demand matching results are traversed to obtain several real-time quotation orders, and these several real-time quotation orders are sent to several target suppliers.

6. The cloud computing-based aircraft material procurement quotation method according to claim 5, characterized in that: The cloud data center analyzes supplier quotes using a supplier quote analysis model based on real-time quote information from target suppliers. Then, based on the target supplier profile and the obtained real-time quote analysis results, a quote report generation model is used to generate a real-time quote report. This process includes the following steps: The cloud data center receives real-time quotation information from each target supplier and inputs the semantically enhanced real-time demand information graph structure features of the real-time aviation material procurement demand information, the target supplier's real-time supplier profile graph structure features, and the real-time quotation information into the supplier quotation analysis model. Using a supplier quotation analysis model, the real-time quotation information sequence features are extracted. Based on preset attention weights, the real-time demand information graph structure features, the target real-time supplier profile graph structure features, and the real-time quotation information sequence features are weighted and fused to obtain real-time weighted fused features. Based on the real-time weighted fusion characteristics, supplier quotation analysis is performed to obtain the corresponding real-time quotation analysis results. The real-time demand information graph structure characteristics, the target real-time supplier profile graph structure characteristics, the real-time quotation information sequence characteristics, and the real-time quotation analysis results are then input into the quotation report generation model. Based on the structural features of the real-time demand information graph, the structural features of the target real-time supplier profile graph, the features of the real-time quotation information sequence, and the real-time quotation analysis results, the quotation report generation model is used to embed conditional information to obtain the second real-time conditional information embedding feature. Based on the embedded features of the second real-time condition information, a quotation report is generated to obtain the real-time quotation report of the corresponding target supplier. By traversing the real-time quotation information of all target suppliers, a real-time quotation report of each target supplier is obtained.

7. The cloud computing-based aircraft material procurement quotation method according to claim 6, characterized in that: In the cloud data center, cooperative suppliers are identified, real-time quotation information and supplier profiles are extracted, and based on the semantically enhanced real-time aircraft material procurement demand information, supplier profiles, and real-time quotation information, a procurement process generation model is used to generate a real-time procurement process, including the following steps: The cloud data center selects a cooperative supplier from all target suppliers in the real-time aviation material demand matching results based on the real-time confirmation information input by the user, and extracts the corresponding real-time quotation information and cooperative supplier profile. Extract the structural features of the real-time supplier profile and the sequence features of the real-time quotation information from the real-time supplier profile. Then, input the structural features of the real-time supplier profile, the sequence features of the real-time quotation information, and the structural features of the real-time demand information graph of the semantically enhanced real-time aviation material procurement demand into the procurement process generation model. Based on the structural features of the real-time supplier profile graph, the sequence features of the real-time quotation information, and the structural features of the real-time demand information graph of the semantically enhanced real-time aviation material procurement demand information, a procurement process generation model is used to generate the procurement process and obtain the real-time procurement process.

8. The cloud computing-based aircraft material procurement quotation method according to claim 7, characterized in that: Based on the structural features of the real-time supplier profile graph, the sequence features of the real-time quotation information, and the structural features of the real-time demand information graph of the semantically enhanced real-time aircraft material procurement demand, a procurement process generation model is used to generate the real-time procurement process, which includes the following steps: Based on the structural characteristics of the real-time demand information graph, a search and matching process is performed in the experience replay pool of the procurement process generation model to obtain the successfully matched real-time procurement process generation experience. Based on the experience of generating real-time procurement processes, the structural features of real-time cooperative supplier profiles, the sequence features of real-time cooperative quotation information, and the structural features of real-time demand information graphs of semantically enhanced real-time aviation material procurement demand information, the procurement process generation model is updated to obtain an updated procurement process generation model. The updated procurement process generation model is used to generate the procurement process, resulting in a real-time procurement process.

9. A cloud computing-based aircraft material procurement quotation method according to claim 8, characterized in that: The cloud data center uses a blockchain network to distribute and store real-time aircraft material procurement demand information, cooperating suppliers, real-time quotations, supplier profiles, and corresponding real-time supplier quotation analysis results. This includes the following steps: By linking real-time aircraft material procurement demand information, cooperative suppliers, real-time cooperative quotation information, cooperative supplier profiles, and corresponding real-time cooperative supplier quotation analysis results, real-time aircraft material procurement inquiry and quotation data can be obtained. The real-time aircraft material procurement inquiry and quotation data is stored in the IPFS system to obtain the real-time data hash value. The smart contract is called to generate the corresponding real-time transaction data and real-time transaction records based on the real-time data hash value. The transaction data is distributed and stored using the blockchain network to obtain the corresponding real-time storage address. Real-time search tags are generated for real-time aircraft material procurement inquiry and quotation data. The real-time storage address, real-time search tags, and real-time transaction records are written into the distributed ledger to obtain an updated distributed ledger. The updated distributed ledger is then synchronized to the blockchain network.

10. A cloud computing-based aircraft material procurement inquiry and quotation system, used to implement the aircraft material procurement inquiry and quotation method as described in any one of claims 1-9, characterized in that: The system is deployed in a cloud data center and includes a blockchain network building and model building unit, a semantic enhancement and aviation material demand matching unit, an inquiry form generation and sending unit, a quotation analysis and quotation report generation unit, a procurement process generation unit, and a distributed storage unit, which are connected in sequence.

Images