Commodity market dynamic prediction method, system, medium and equipment

Abstract

The invention relates to the technical field of commercial financial information processing, and provides a commodity market dynamic prediction method and system, a medium and electronic equipment. Acquiring real-time market information data of the target commodity and submitting the real-time market information data to a market information staring system; verifying the real-time market data, generating a data set hash value based on the target data passing the verification, aggregating the target data in a distributed hash table, and storing the aggregated data in a block chain based on the data set hash value; formulating a transaction strategy based on the target data, encoding the transaction strategy into a smart contract, and deploying the smart contract on the block chain; and when the market dynamic condition of the target data is predicted to meet the triggering condition of the smart contract, automatically executing the transaction. On the basis of ensuring the data accuracy and security, the transaction is automatically executed when the market information dynamically accords with the intelligent contract, so that the intelligence, automation and high efficiency of transaction decision making are realized, and the response speed and execution precision of commodity transaction are greatly improved.

Description

Technical Field

[0001] This application relates to the technical field of commercial financial information processing. Specifically, it relates to a method, system, computer-readable medium, and electronic device for dynamically predicting commodity market conditions. Background Art

[0002] With the rapid development of global trade and the intensification of market competition, the fluctuations in commodity market conditions have a significant impact on the operating strategies and economic benefits of enterprises. Traditional methods of monitoring commodity market conditions often rely on manual analysis and empirical judgment, which are not only inefficient but also difficult to accurately capture the dynamic changes in the market. Therefore, methods for dynamically predicting commodity market conditions have emerged, which can monitor multi-dimensional data such as commodity prices, supply and demand, and transportation status in real time, providing timely and accurate commodity market information for enterprises and helping them make more scientific decisions.

[0003] In practical applications, market condition data is often scattered across multiple channels, with uneven data quality and a risk of being tampered with, affecting the accuracy of analysis and the reliability of decision-making. Summary of the Invention

[0004] This application provides a method, system, computer-readable medium, and electronic device for dynamically predicting commodity market conditions, which can at least to some extent solve the problem of low reliability of market condition data.

[0005] Other features and advantages of this application will become apparent through the following detailed description, or be learned in part through the practice of this application.

[0006] According to one aspect of this application, a method for dynamically predicting commodity market conditions is provided, including: obtaining real-time market condition data of a target commodity, and submitting the real-time market condition data to a market marking system through a submission node; in the market marking system, verifying the real-time market condition data based on the entangled pairs between verification nodes and the characteristics of each data subset in the real-time market condition data to obtain target data that passes the verification; generating a dataset hash value based on the target data, aggregating the target data into aggregated data through an aggregation node in the market marking system, writing the aggregated data into a distributed hash table, and storing the aggregated data on a blockchain based on the dataset hash value; formulating a trading strategy based on the target data, encoding the trading strategy as a smart contract, and deploying the smart contract on the blockchain; performing dynamic market condition prediction based on the aggregated data on the blockchain, and when it is predicted that the dynamic market condition meets the trigger condition of the smart contract, automatically executing a transaction in the market marking system.

[0007] In this application, based on the foregoing solution, verifying the real-time market data based on the entanglement pairs between the verification nodes and the characteristics of each data subset in the real-time market data to obtain target data that passes the verification includes: initializing the characteristics of each verification node and each data subset, performing iterative verification based on the characteristics, identifying abnormal data and malicious nodes as the first verification result; generating entanglement pairs between the verification nodes and quantum states corresponding to the data subsets, and verifying the entanglement pairs and the quantum states based on a second verification model; reaching a distributed consensus based on the first verification result and the second verification result to obtain target data that passes the verification.

[0008] In this application, based on the foregoing solution, the initializing the characteristics of each verification node and each data subset, performing iterative verification based on the characteristics, and identifying abnormal data and malicious nodes as the first verification result includes: sharding the real-time market data through the verification nodes to obtain a preset number of data subsets; initializing a first feature vector corresponding to each verification node and a second feature vector of a hyperedge corresponding to each data subset; for each hyperedge, aggregating the first feature vectors of all verification nodes connected thereto based on a preset activation function as the hyperedge feature; for each verification node, aggregating the second feature vectors of all hyperedges connected thereto based on the activation function as the node feature; repeating the above message passing process until the characteristics of the nodes and hyperedges converge; identifying abnormal data and malicious nodes based on the hyperedge feature and the node feature as the first verification result.

[0009] In this application, based on the foregoing solution, the identifying abnormal data and malicious nodes based on the hyperedge feature and the node feature includes: determining a first abnormal score based on the node feature and the first feature mean corresponding to the node feature, and if the first abnormal score is greater than or equal to a first threshold, determining that the verification node corresponding to the node feature is a malicious node; determining a second abnormal score based on the hyperedge feature and the second feature mean of the data subset, and if the second abnormal score is greater than or equal to a second threshold, determining that the data subset is abnormal data.

[0010] In this application, based on the foregoing solution, the generating entanglement pairs between the verification nodes and quantum states corresponding to the data subsets, and verifying the entanglement pairs and the quantum states based on a second verification model includes: generating entanglement pairs between the verification nodes; encoding the hash value corresponding to the data subset into a quantum state, and transmitting the quantum state to a target node based on the quantum teleportation protocol; and verifying by the target node whether the quantum state of the data subset is consistent with the original quantum state of the source node based on the entanglement pair and the quantum state, and outputting a second verification result.

[0011] In this application, based on the foregoing solution, achieving distributed consensus based on the first verification result and the second verification result to obtain target data that passes verification includes: if both the first verification result and the second verification result are true, then achieving distributed consensus to obtain target data that passes verification.

[0012] In this application, based on the foregoing solution, formulating a trading strategy based on the target data and encoding the trading strategy as a smart contract includes: training a trading strategy model based on a deep learning algorithm and the target data to generate a trading strategy; abstracting the trading strategy into executable operation instructions, and encoding the operation instructions as a smart contract using a smart contract programming language.

[0013] According to one aspect of the present application, there is provided a commodity market dynamic prediction system, including: An acquisition unit, configured to acquire real-time market data of a target commodity, and submit the real-time market data to a market marking system through a submission node; A verification unit, configured to verify the real-time market data in the market marking system based on entangled pairs between verification nodes and characteristics of each data subset in the real-time market data to obtain target data that passes verification; An aggregation unit, configured to generate a dataset hash value based on the target data, aggregate the target data through an aggregation node in the market marking system to generate aggregated data, write the aggregated data into a distributed hash table, and store the aggregated data on a blockchain based on the dataset hash value; A contract unit, configured to formulate a trading strategy based on the target data, encode the trading strategy as a smart contract, and deploy the smart contract on the blockchain; An execution unit, configured to perform dynamic market prediction based on the aggregated data on the blockchain, and automatically execute a transaction in the market marking system when it is predicted that the market dynamics meet the trigger condition of the smart contract.

[0014] According to one aspect of the present application, there is provided a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements a commodity market dynamic prediction method as described in the above embodiments.

[0015] According to one aspect of the present application, there is provided an electronic device, including: one or more processors; a storage device, configured to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement a commodity market dynamic prediction method as described in the above embodiments.

[0016] According to one aspect of the present application, there is provided a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a commodity market dynamic prediction method provided in the above various optional implementation manners.

[0017] In the technical solution of the present application, real-time market data of a target commodity is obtained, and the real-time market data is submitted to a market marking system through a submission node; a verification node verifies the real-time market data to obtain target data that passes the verification; a dataset hash value is generated based on the target data, an aggregation node aggregates the target data in a distributed hash table, and stores the aggregated data on a blockchain based on the dataset hash value; a trading strategy is formulated based on the target data, the trading strategy is encoded as a smart contract and deployed on the blockchain; a market dynamic prediction is performed based on the aggregated data on the blockchain, and when it is predicted that the market dynamic meets the trigger condition of the smart contract, a transaction is automatically executed in the market marking system. By using the entangled pairs between verification nodes and blockchain technology to efficiently verify and store these data, ensuring their accuracy, reliability and security, and formulating an intelligent trading strategy based on these data, encoding it as a smart contract and deploying it on the blockchain. Once the predicted market dynamic meets the preset conditions of the smart contract, the transaction will be automatically executed, thus realizing the intelligence, automation and high efficiency of trading decisions, and greatly improving the response speed and execution accuracy of commodity trading.

[0018] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0020] Figure 1 Schematically shows a flowchart of a commodity market dynamic prediction method in an embodiment of the present application.

[0021] Figure 2 Schematically shows a flowchart of verifying real-time market data in an embodiment of the present application.

[0022] Figure 3Schematically shows a schematic diagram of a commodity market dynamic prediction system in an embodiment of the present application.

[0023] Figure 4 Shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application. Detailed implementation manners

[0024] Now, example embodiments will be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more complete and comprehensive, and will fully convey the concept of the example embodiments to those skilled in the art.

[0025] In addition, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present application. However, those skilled in the art will realize that the technical solutions of the present application can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, well-known methods, systems, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the present application.

[0026] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0027] The flowcharts shown in the drawings are only illustrative and do not necessarily include all the content and operations / steps, nor do they necessarily have to be executed in the described order. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0028] The implementation details of the technical solutions of the present application are elaborated in detail below: Figure 1 Shows a flowchart of a method for dynamically predicting the commodity market according to an embodiment of the present application. Referring to Figure 1 As shown, the method for dynamically predicting the commodity market at least includes steps S110 to S150, which are introduced in detail as follows: In step S110, real-time market data of the target commodity is obtained, and the real-time market data is submitted to the market monitoring system through a submission node.

[0029] In one embodiment of the present application, not only traditional structured data such as financial market data is collected, but also unstructured data such as social media sentiment analysis and news event impact assessment is integrated to form a multi-modal market data source. Real-time fusion and analysis of multi-modal data are realized to provide a more comprehensive data basis for subsequent predictions.

[0030] Specifically, the structured data sources of the target commodity include, but are not limited to, traditional financial market data such as stock prices, trading volumes, and price-earnings ratios provided by stock exchanges, financial data providers, etc. The unstructured data sources of the target commodity include, but are not limited to, unstructured data such as social media sentiment related to social media platforms, news websites, and financial blogs. Specifically, social media sentiment analysis refers to using social media analysis tools to capture consumers' interactive behaviors such as comments, likes, and shares on the target commodity, understand consumers' interests and emotions, and then determine the consumption tendency of the commodity.

[0031] Exemplarily, for internal data, in this embodiment, transaction records are obtained through an Enterprise Resource Planning (ERP) interface, and the name of the goods, transaction price, quantity, and timestamp are extracted. Then, the inventory management system is parsed to monitor the changes in the status of the goods in stock. For external data, by accessing the data of each vertical industry price index platform, the benchmark price of the commodity is obtained in real time, and at the same time, the prices on e-commerce platforms are crawled to supplement the market conditions at the retail end.

[0032] Exemplarily, for network information, a web crawler framework is used to crawl the text of industry blogs and news websites, and unstructured text data such as news, social media, and industry forums is crawled; through a Bidirectional Encoder Representations from Transformers (BERT), advertisements and irrelevant content are filtered, and highly relevant information is retained. A large language model is used for sentiment analysis, event extraction, and topic clustering to generate indicators such as network popularity, sentiment polarity, and event influence; based on Granger causality test and regression analysis, the contribution degree of network factors to the price fluctuation of the target category is quantified.

[0033] After that, the obtained text is parsed. Specifically, when the text of the goods description (such as "304 stainless steel cold-rolled coil plate") is input, a text parsing model is called for entity recognition to extract features such as material (stainless steel), specification (cold-rolled), and form (coil plate); the non-standard description is mapped to the standard category tree. For example: Metal materials → Steel → Stainless steel → Cold-rolled coil plate.

[0034] Convert the collected multi-modal market data sources into a unified format for subsequent processing and analysis. Stream processing technology can also be used to quickly collect, clean, and preprocess real-time market data to ensure the timeliness and accuracy of the data.

[0035] Construct a distributed submission network based on blockchain technology. Each submission node of the distributed submission network has the preliminary ability to verify data, so as to improve the efficiency and security of data submission. Through the distributed submission network, reduce the data submission pressure of a single submission node and improve the overall performance and reliability of the system.

[0036] Quickly submit real-time market data to the market marking system through distributed submission nodes, ensuring the timeliness and accuracy of the data, and providing a reliable basis for subsequent prediction and trading strategy formulation.

[0037] In step S120, in the market marking system, based on the entangled pairs between verification nodes and the characteristics of each data subset in the real-time market data, verify the real-time market data to obtain target data that passes the verification.

[0038] In this embodiment, the verification node verifies the real-time market data, not only verifying the integrity, consistency, and timeliness of the data, but also ensuring the authenticity and reliability of the data through cross-verification with other verification nodes.

[0039] As Figure 2 shown, in an embodiment of the present application, based on the entangled pairs between verification nodes and the characteristics of each data subset in the real-time market data, verify the real-time market data to obtain target data that passes the verification, including: S210, initialize the characteristics of each verification node and each data subset, and perform iterative verification based on the characteristics to identify abnormal data and malicious nodes as the first verification result; S220, generate entangled pairs between verification nodes and quantum states corresponding to data subsets, and verify the entangled pairs and the quantum states based on a second verification model; S230, based on the first verification result and the second verification result, reach a distributed consensus to obtain target data that passes the verification.

[0040] In an embodiment of the present application, in S210, initialize the characteristics of each verification node and each data subset, and perform iterative verification based on the characteristics to identify abnormal data and malicious nodes as the first verification result, including: Slice the real-time market data through verification nodes to obtain a preset number of data subsets; Initialize the first feature vectors corresponding to each verification node, and initialize the second feature vectors of the hyperedges corresponding to each data subset. For each hyperedge, aggregate the first feature vectors of all the verification nodes it connects based on a preset activation function as the hyperedge feature. For each verification node, aggregate the second feature vectors of all the hyperedges it connects based on the activation function as the node feature. Based on the hyperedge features and the node features, identify abnormal data and malicious nodes as the first verification result.

[0041] In an embodiment of the present application, the verification nodes and the sharding rule shard the real-time market data to obtain a preset number of data subsets. Each data subset contains partially overlapping data to enhance fault tolerance. The sharding rule may be to extract data according to a preset data interval based on the data identifier of the data subset to form the data subset corresponding to the data identifier.

[0042] In this embodiment, the hypergraph neural network is defined as , where V is a node set composed of verification nodes, including verification nodes ; E is a hyperedge set, and each hyperedge and corresponds to a data subset , and connects all the verification nodes that need to verify this shard. The verification node is responsible for verifying the authenticity of the data subset .

[0043] In the hypergraph neural network, by connecting multiple verification nodes through hyperedges, the high-order relationships between multiple verification nodes can be directly modeled. For example, a data subset (data subset) is jointly verified by multiple nodes . The hyperedge connects these verification nodes to form a high-order relationship. High-order features can reflect the collaboration mode between verification nodes and the global attributes of data subsets. For example, if the verification results of multiple verification nodes for the same data subset are highly consistent, the credibility of this data subset is relatively high; otherwise, there may be abnormalities. Through multi-layer message passing, the hypergraph neural network can gradually extract the high-order features of verification nodes and hyperedges, thereby capturing abnormal patterns and malicious behaviors.

[0044] The data subset improves fault tolerance through overlapping design. Even if some verification nodes fail, the data can still be restored through other verification nodes. The hypergraph structure can capture the high-order relationships between multiple verification nodes and is more suitable for distributed verification scenarios than ordinary graph structures.

[0045] Initialize the verification nodes The corresponding first eigenvector , where the first eigenvector includes the node reputation value, computing power, and historical verification accuracy; initialize the hyperedge corresponding to the data subset The second eigenvector , where the second eigenvector includes the hash value, timestamp, and data source. By encoding the attribute information of the verification nodes and hyperedges as eigenvectors, it provides input for subsequent message passing and aggregation. The eigenvectors of the verification nodes and hyperedges can capture their attributes and relationships, providing a basis for the subsequent verification process.

[0046] For each hyperedge, aggregate the first eigenvectors of all the verification nodes connected to it based on a preset activation function. In this process, for each hyperedge, aggregate the first eigenvectors of all the verification nodes connected to it based on a preset activation function. Specifically, initialize the weight matrix and bias vector of the verification nodes corresponding to the hyperedge, obtain all the verification nodes connected to the hyperedge, and determine the first eigenvectors corresponding to all the verification nodes. Based on the first eigenvectors and the weight matrix, determine the sum of the eigenvectors, and perform activation processing on the sum of the eigenvectors and the bias vector to achieve feature aggregation, obtaining the updated eigenvector for each hyperedge The updated eigenvector is:[[]] where represents the eigenvector of hyperedge at the l -th layer, represents the first eigenvector of verification node at the l -1-th layer, represents the activation function, represents the weight matrix corresponding to the verification nodes associated with hyperedge , represents the bias vector corresponding to the verification nodes associated with hyperedge .

[0047] For each verification node, aggregate the second eigenvectors of all the hyperedges connected to it based on the activation function. In this process, for each verification node , aggregate the features of all the hyperedges connected to it, obtaining the updated eigenvector for each verification node The updated eigenvector is:[[]] where represents the first eigenvectors of all the hyperedges aggregated by verification node at the l -th layer, represents verification node The weight matrix corresponding to the associated hyperedge Indicates the verification node The bias vector corresponding to the associated hyperedge.

[0048] Repeat the above message passing process until the features of the verification nodes and hyperedges converge. Through multi-layer message passing, the features of the verification nodes and hyperedges can fully interact, capture the complex relationships between data subsets and verification nodes, and realize the interaction and update of the features of verification nodes and hyperedges. At the same time, through the message passing mechanism, the verification nodes can cooperate to complete the verification of data subsets, improving the overall efficiency of the system. The hypergraph structure can capture the complex relationships between multiple verification nodes, gradually extract high-order features through multi-layer message passing, identify abnormal data and malicious nodes, and use them as the first verification result.

[0049] Among them, based on the hyperedge features and the node features, identifying abnormal data and malicious nodes includes: Based on the node features and the first feature mean corresponding to the node features, determine the first anomaly score. If the first anomaly score is greater than or equal to the first threshold, then determine that the verification node corresponding to the node features is a malicious node; Based on the hyperedge features and the second feature mean of the data subset, determine the second anomaly score. If the second anomaly score is greater than or equal to the second threshold, then determine that the data subset is abnormal data.

[0050] In this embodiment, malicious nodes usually exhibit behavior patterns inconsistent with other nodes. During the feature aggregation process, the features of malicious nodes will have significant differences from the features of normal nodes. Based on the node features and the first feature mean corresponding to the node features, determine the first anomaly score. If the first anomaly score is greater than or equal to the first threshold, then determine that the verification node corresponding to the node features is a malicious node.

[0051] Directly use the identified malicious nodes and abnormal data as the first verification result.

[0052] In this embodiment, based on the output features corresponding to each data subset in the hypergraph neural network, determine the second feature mean of the normal data subset. Then, based on the hyperedge features corresponding to the data subset , and the second feature mean of the data subset, determine the anomaly score corresponding to each data subset as: Among them, is the second feature mean of the normal data subset.

[0053] After calculating the anomaly score, if the second verification result is true and the anomaly score is less than the set threshold, distributed consensus is reached to obtain the target data that passes the verification.

[0054] In the above anomaly detection process, malicious nodes are determined through the first anomaly score, and at the same time, abnormal data is identified through the second anomaly score. Anomaly detection is performed both at the node dimension and the data dimension, improving the comprehensiveness and reliability of anomaly detection.

[0055] In S220, entangled pairs between verification nodes and quantum states corresponding to data subsets are generated, and the entangled pairs and the quantum states are verified based on the second verification model, including: Generate entangled pairs between verification nodes; Encode the hash value corresponding to the data subset into a quantum state, and transmit the quantum state to the target node based on the quantum teleportation protocol; The target node verifies whether the quantum state of the data subset is consistent with the original quantum state of the source node based on the entangled pair and the quantum state, and outputs the second verification result.

[0056] In an embodiment of the present application, entangled pairs are generated between verification nodes through a quantum source (such as a quantum dot or a nonlinear optical crystal). Each entangled pair consists of two entangled qubits, which are respectively assigned to two verification nodes. When two verification nodes share an entangled pair, their quantum states are entangled, that is, the measurement of one verification node will immediately affect the state of the other verification node, regardless of the distance between them. The entangled pair enables the verification nodes to perform a consistency check on the hash value of the data subset through the quantum teleportation protocol, ensuring that the data has not been tampered with during transmission.

[0057] The source node encodes the hash value of the data subset (data subset) into a quantum state, performs a Bell state measurement on the quantum state and a part of the entangled pair to obtain a measurement result. The measurement result is sent to the target node through a classical channel. According to the measurement result, corresponding quantum gate operations are performed on the other part of the entangled pair to recover the quantum state.

[0058] The target node compares the recovered quantum state with the original quantum state of the source node. Specifically, the comparison result can be to calculate the inner product of the two quantum states. If the inner product is equal to 1, it means the data is consistent; otherwise, the data has been tampered with.

[0059] In the above process, the entangled pair provides the basic resource for quantum teleportation to realize the instantaneous transmission of the quantum state. Ensure the security and consistency of data transmission, prevent eavesdropping and tampering. Support high-precision data consistency verification, providing a reliable technical guarantee for the distributed verification system.

[0060] After obtaining the first verification result and the second verification result, if both the first verification result and the second verification result are true, distributed consensus is achieved, and the target data that passes the verification is obtained. In this embodiment, the verification node strictly verifies the real-time market data, including a dual verification mechanism based on the first verification result and the second verification result, effectively identifying and excluding abnormal data and malicious nodes, ensuring the authenticity and integrity of the data, and preventing data tampering and fraud.

[0061] Furthermore, the achievement of distributed consensus ensures the reliability and consistency of the target data that passes the verification. This mechanism improves the robustness and anti-attack ability of the system.

[0062] In step S130, a dataset hash value is generated based on the target data. The target data is aggregated by the aggregation node in the market marking system to generate aggregated data, the aggregated data is written into the distributed hash table, and the aggregated data is stored on the blockchain based on the dataset hash value.

[0063] In the commodity market dynamic prediction method, the target data is securely and efficiently stored on the blockchain through a series of execution processes, which not only involves the generation of the dataset hash value, but also includes the aggregation of the target data in the distributed hash table and the blockchain storage based on the dataset hash value.

[0064] In an embodiment of the present application, first, the target data is received and preprocessed, and the preprocessed target data is used as input to calculate the dataset hash value through a hash algorithm. A distributed hash table is constructed, which consists of multiple blockchain nodes, and each blockchain node is responsible for storing a part of the hash key-value pairs. The target data is grouped according to the timestamp or data type, and the hash value of each group is calculated. These hash values are used as keys, and the target data or data pointer is used as the value, and stored in the distributed hash table to generate the dataset hash table.

[0065] One or more blockchain nodes are selected from the blockchain network as storage targets. These blockchain nodes have sufficient storage capacity and computing power to ensure the security and stability of the blockchain. A transaction containing the dataset hash value is constructed, and the transaction is signed using the private key. The signed transaction is broadcast to the blockchain network. The verification nodes in the network will verify the transaction and reach a consensus through the consensus algorithm. Once a consensus is reached, the transaction will be recorded on the blockchain to form an immutable historical record.

[0066] When retrieving the data stored on the blockchain, the corresponding data or data pointer can be found in the distributed hash table through the dataset hash value. At the same time, the integrity and authenticity of the data can be verified using the transaction records on the blockchain.

[0067] By generating a dataset hash value, aggregating the target data to generate aggregated data, and writing the aggregated data into a distributed hash table, efficient storage and fast retrieval of data are achieved, improving the availability and fault tolerance of the data. By storing the aggregated data on the blockchain based on the dataset hash value and leveraging the immutability of the blockchain, the permanent preservation and authenticity of the data are ensured, providing a trusted data source for the execution of trading strategies.

[0068] In step S140, a trading strategy is formulated based on the target data, the trading strategy is encoded as a smart contract, and the smart contract is deployed on the blockchain.

[0069] In this embodiment, a prediction model capable of processing multimodal data is constructed based on deep learning or multimodal learning algorithms, and a trading strategy is formulated according to the target data. Using a smart contract template and an automated generation tool, the smart contract code is automatically generated according to the trading strategy and deployed on the blockchain.

[0070] Specifically, in the process of constructing the prediction model, price time series data, network information metrics, and category feature vectors are received at the input layer; multi-source features are dynamically weighted through an attention mechanism at the feature fusion layer; a deep learning hybrid network combining a long short-term memory network and a self-attention architecture is used at the prediction layer to output price prediction values and confidence intervals; and a visual prediction report and risk level labels are generated at the output layer.

[0071] Optionally, the trigger conditions and trading instructions of the prediction model are embedded in the smart contract.

[0072] In an embodiment of the present application, formulating a trading strategy based on the target data and encoding the trading strategy as a smart contract includes: Training a trading strategy model based on a deep learning model and the target data to generate a trading strategy; Abstracting the trading strategy into executable operation instructions and encoding the operation instructions as a smart contract using a smart contract programming language.

[0073] Specifically, structured data and unstructured data are integrated to form a multimodal dataset, providing comprehensive data support for the subsequent training of the trading strategy model and improving the prediction accuracy of the model and the profitability of the trading strategy.

[0074] According to the characteristics of the data and the requirements of the task, select a suitable deep learning model, such as a convolutional neural network, a recurrent neural network, a long short-term memory network, etc., to process and analyze multi-modal data. Extract features from the integrated multi-modal dataset as the input of the deep learning model. Use the extracted features to train the deep learning model to generate a trading strategy model that can predict market trends and formulate trading strategies. Evaluate the trained trading strategy model and verify its performance through methods such as backtesting. According to the evaluation results, optimize the model to improve its prediction accuracy and the profitability of trading strategies. Using deep learning models to process and analyze multi-modal data can capture more complex market trends and trading opportunities, providing a scientific basis for formulating trading strategies.

[0075] Abstract the trading strategies generated by the trained trading strategy model into executable operation instructions, such as buy, sell, hold, etc. These operation instructions have clear execution conditions and logic for subsequent smart contract coding. Select a smart contract programming language suitable for the blockchain platform and use the selected smart contract programming language to encode the abstracted operation instructions into a smart contract.

[0076] Optionally, in the smart contract, define the execution logic, trigger conditions, and trading parameters of the trading strategy, etc.

[0077] Optionally, test the encoded smart contract to verify its logical correctness and execution efficiency. Deploy the smart contract that passes the test to the blockchain platform for use in actual transactions.

[0078] In the above process, by abstracting trading strategies into smart contracts, the automation and intelligence of transactions are realized, the risk of human intervention is reduced, and the efficiency and accuracy of transactions are improved. Utilizing the immutability and decentralization characteristics of blockchain technology ensures the security and reliability of trading strategies and avoids potential data tampering and fraud.

[0079] In the above process, the accuracy and adaptability of trading strategies are improved through a multi-modal data-driven prediction model, which can capture complex market dynamics and trends, better respond to the complex and changing market environment, and generate intelligent trading strategies. The dynamic generation and deployment of smart contracts enable trading strategies to be automatically executed, reducing the cost and risk of human intervention and improving the efficiency and reliability of transactions.

[0080] At the same time, the formulation of trading strategies combines structured and unstructured target data, which can more comprehensively reflect market conditions and improve the flexibility and adaptability of strategies. At the same time, the trigger conditions of smart contracts can be adjusted according to market changes to ensure the effectiveness and profitability of trading strategies.

[0081] In step S150, market dynamics prediction is performed based on the aggregated data on the blockchain, and when it is predicted that the market dynamics meet the triggering conditions of the smart contract, the transaction is automatically executed in the market marking system.

[0082] In one embodiment of the present application, a real-time prediction algorithm and monitoring mechanism are used to continuously predict and monitor the market dynamics corresponding to the aggregated data on the blockchain to ensure that transactions can be executed immediately when the trigger conditions are met. When the market dynamics are predicted to meet the trigger conditions of the smart contract, the smart contract automatically executes the transaction instructions and records the transaction results on the blockchain, achieving transparency and traceability of the transaction.

[0083] Specifically, a time series module is constructed, and time series forecasting tools are used to capture price periodicity and fit seasonal fluctuations. Then, through the network information analysis module, the correlation between sentiment indicators and prices is modeled using long short-term memory networks. Finally, in the fusion prediction layer, the gating mechanism is used to weight the time series and network information features to output the price forecast for the next 7 days.

[0084] In this embodiment, the warning rules are pre-set. When the predicted price deviates from the collateral valuation by 10%, the first-level warning (email notification) is activated; if the deviation continues to expand to 15%, it is upgraded to the second-level warning (SMS and system pop-up window); combined with the liquidity index, when the category market transaction volume drops sharply by 50%, the emergency disposal process is directly triggered. Optionally, if the predicted price drop exceeds 15% of the collateral valuation, a red warning is triggered and a forced liquidation assessment is initiated; if the proportion of negative online emotions is higher than the threshold for 3 consecutive days, a yellow warning is triggered and margin calls are recommended; if the category market liquidity index is lower than the safety line, an orange warning is triggered and risk exposure is indicated.

[0085] During the execution of transactions, early warning signals are sent to the bank's core system, triggering margin calls or loan restructuring processes; at the same time, the system is linked to the trading platform to automatically issue liquidation instructions for high-risk collateral. By linking the prediction results with financial risk control rules, early warning responses can be achieved within seconds.

[0086] Furthermore, in this embodiment, the category risk heat map, network event timeline and prediction confidence interval can be displayed through a visual dashboard. At the same time, drill-down query is supported to trace the cause of the warning trigger and the historical disposal record.

[0087] The above process ensures the timeliness and accuracy of transactions through real-time market forecasting and monitoring, and improves the profitability and risk control capabilities of transactions. The triggering and execution mechanism of smart contracts makes the transaction process more automated and intelligent, reduces manual verification costs, transaction costs and risks, and improves the accuracy of market forecasting, efficiency and reliability of transactions.

[0088] In the technical solution of this application, real-time market data of the target commodity is obtained, and the real-time market data is submitted to the market monitoring system through the submission node; the verification node verifies the real-time market data to obtain the target data that passes the verification; based on the target data, a dataset hash value is generated, and the aggregation node aggregates the target data in the distributed hash table and stores the aggregated data on the blockchain based on the dataset hash value; a trading strategy is formulated based on the target data, encoded as a smart contract, and deployed on the blockchain; the market dynamics are predicted based on the aggregated data on the blockchain, and when it is predicted that the market dynamics meet the trigger conditions of the smart contract, the transaction is automatically executed in the market monitoring system. By obtaining and verifying market data in real time, its accuracy and security are ensured. Subsequently, these data are efficiently stored using a distributed hash table and blockchain technology, and an intelligent trading strategy is formulated based on these data, encoded as a smart contract and deployed on the blockchain. Once the predicted market dynamics meet the preset conditions of the smart contract, the transaction will be automatically executed, thus realizing the intelligence, automation and high efficiency of trading decisions, and greatly improving the response speed and execution accuracy of commodity trading.

[0089] The following introduces the device embodiments of this application, which can be used to execute a commodity market dynamics prediction method in the above embodiments of this application. It can be understood that the device can be a computer program (including program code) running in a computer device, for example, the device is an application software; the device can be used to execute the corresponding steps in the method provided in the embodiments of this application. For the details not disclosed in the device embodiments of this application, please refer to the embodiments of a commodity market dynamics prediction method in the above of this application.

[0090] Figure 3 The block diagram of a commodity market dynamics prediction system according to an embodiment of this application is shown.

[0091] Refer to Figure 3 As shown, a commodity market dynamics prediction system according to an embodiment of this application includes: An acquisition unit 310, configured to acquire real-time market data of the target commodity and submit the real-time market data to the market monitoring system through the submission node; A verification unit 320, configured to verify the real-time market data in the market monitoring system based on the entangled pairs between the verification nodes and the characteristics of each data subset in the real-time market data to obtain the target data that passes the verification; An aggregation unit 330, configured to generate a dataset hash value based on the target data, aggregate the target data through the aggregation node in the market monitoring system to generate aggregated data, write the aggregated data into the distributed hash table, and store the aggregated data on the blockchain based on the dataset hash value; A contract unit 340, configured to formulate a trading strategy based on the target data, encode the trading strategy into a smart contract, and deploy the smart contract on the blockchain; An execution unit 350, configured to perform a market trend dynamic prediction based on the aggregated data on the blockchain, and automatically execute a transaction in the market marking system when it is predicted that the market trend dynamics meet the trigger conditions of the smart contract.

[0092] In this application, based on the foregoing solution, validating the real-time market data based on the entanglement pairs between the verification nodes and the characteristics of each data subset in the real-time market data to obtain target data that passes the verification includes: initializing the characteristics of each verification node and each data subset, performing iterative verification based on the characteristics, identifying abnormal data and malicious nodes as the first verification result; generating entanglement pairs between the verification nodes and quantum states corresponding to the data subsets, and validating the entanglement pairs and the quantum states based on a second verification model; based on the first verification result and the second verification result, reaching a distributed consensus to obtain target data that passes the verification.

[0093] In this application, based on the foregoing solution, the initializing the characteristics of each verification node and each data subset, performing iterative verification based on the characteristics, and identifying abnormal data and malicious nodes as the first verification result includes: sharding the real-time market data through verification nodes to obtain a preset number of data subsets; initializing a first feature vector corresponding to each verification node and a second feature vector of a hyperedge corresponding to each data subset; for each hyperedge, aggregating the first feature vectors of all verification nodes connected thereto based on a preset activation function as the hyperedge feature; for each verification node, aggregating the second feature vectors of all hyperedges connected thereto based on the activation function as the node feature; repeating the above message passing process until the features of the nodes and hyperedges converge; identifying abnormal data and malicious nodes based on the hyperedge feature and the node feature as the first verification result.

[0094] In this application, based on the foregoing solution, the identifying abnormal data and malicious nodes based on the hyperedge feature and the node feature includes: determining a first anomaly score based on the node feature and a first feature mean corresponding to the node feature, and if the first anomaly score is greater than or equal to a first threshold, determining that the verification node corresponding to the node feature is a malicious node; determining a second anomaly score based on the hyperedge feature and a second feature mean of the data subset, and if the second anomaly score is greater than or equal to a second threshold, determining that the data subset is abnormal data.

[0095] In this application, based on the foregoing solution, generating entangled pairs between verification nodes and quantum states corresponding to data subsets, and verifying the entangled pairs and the quantum states based on a second verification model includes: generating entangled pairs between verification nodes; encoding the hash value corresponding to the data subset into a quantum state, and transmitting the quantum state to a target node based on a quantum teleportation protocol; and verifying, by the target node based on the entangled pairs and the quantum state, whether the quantum state of the data subset is consistent with the original quantum state of the source node, and outputting a second verification result.

[0096] In this application, based on the foregoing solution, achieving distributed consensus based on the first verification result and the second verification result to obtain target data that passes verification includes: if both the first verification result and the second verification result are true, achieving distributed consensus to obtain target data that passes verification.

[0097] In this application, based on the foregoing solution, formulating a trading strategy based on the target data and encoding the trading strategy into a smart contract includes: training a trading strategy model based on a deep learning algorithm and the target data to generate a trading strategy; abstracting the trading strategy into executable operation instructions, and encoding the operation instructions into a smart contract using a smart contract programming language.

[0098] In the technical solution of this application, real-time market data of a target commodity is obtained, and the real-time market data is submitted to a market marking system by a submitting node; a verification node verifies the real-time market data to obtain target data that passes verification; a dataset hash value is generated based on the target data, an aggregation node aggregates the target data in a distributed hash table, and stores the aggregated data on a blockchain based on the dataset hash value; a trading strategy is formulated based on the target data, the trading strategy is encoded into a smart contract, and deployed on the blockchain; a dynamic market prediction is performed based on the aggregated data on the blockchain, and when it is predicted that the market dynamics meet the trigger condition of the smart contract, a transaction is automatically executed in the market marking system. By obtaining and verifying market data in real time to ensure its accuracy and security, then using a distributed hash table and blockchain technology to efficiently store this data, and formulating an intelligent trading strategy based on this data, encoding it into a smart contract and deploying it on the blockchain. Once the predicted market dynamics meet the preset conditions of the smart contract, the transaction will be automatically executed, thus realizing the intelligence, automation and high efficiency of trading decisions, and greatly improving the response speed and execution accuracy of commodity trading.

[0099] Figure 4 The figure shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of this application.

[0100] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0101] The computer system in this embodiment includes a central processing unit 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory 402 or the program loaded from the storage section 408 into the random access memory 403, such as executing a commodity market dynamic prediction method described in the above embodiment. In the random access memory 403, various programs and data required for system operation are also stored. The central processing unit 401, the read-only memory 402, and the random access memory 403 are connected to each other via a bus 404. The input / output interface 405 is also connected to the bus 404.

[0102] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read from it can be installed into the storage section 408 as needed.

[0103] Specifically, according to the embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments of the present application include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 409 and / or installed from the removable medium 411. When the computer program is executed by the central processing unit 401, various functions defined in the system of the present application are executed.

[0104] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The computer program contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0106] The units involved in the embodiments of the present application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not, in some cases, constitute a limitation on the unit itself.

[0107] According to one aspect of the present application, there is provided a computer program product or a computer program, the computer program product or the computer program including computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above various alternative implementation manners.

[0108] As another aspect, the present application further provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or may exist alone without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements a method for dynamically predicting commodity market conditions described in the above embodiments.

[0109] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0110] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (such as a personal computer, a server, a touch terminal, or a network device, etc.) to execute the methods according to the embodiments of the present application.

[0111] After considering the specification and practicing the disclosed embodiments herein, those skilled in the art will readily conceive of other embodiments of the present application. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include known common knowledge or conventional technical means in the technical field not disclosed in the present application.

[0112] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A method for dynamic forecasting of commodity market conditions, characterized in that: include: Obtaining real-time market data of the target commodity, and submitting the real-time market data to the market marking system through the submission node; In the market marking system, based on the entangled pairs between the verification nodes and the characteristics of each data subset in the real-time market data, the real-time market data is verified to obtain the verified target data; Generate a data set hash value based on the target data, aggregate the target data through an aggregation node in the market marking system to generate aggregate data, write the aggregate data into a distributed hash table, and store the aggregate data on a blockchain based on the data set hash value; Formulate a transaction strategy based on the target data, encode the transaction strategy into a smart contract, and deploy the smart contract on the blockchain; Market dynamics prediction is performed based on the aggregated data on the blockchain, and when the market dynamics are predicted to meet the triggering conditions of the smart contract, the transaction is automatically executed in the market marking system.

2. A method for dynamic forecasting of commodity market conditions according to claim 1, characterized in that: The real-time market data is verified based on the entangled pairs between the verification nodes and the characteristics of each data subset in the real-time market data to obtain the verified target data, including: Initialize the features of each verification node and each data subset, perform iterative verification based on the features, and identify abnormal data and malicious nodes as a first verification result; Generate an entangled pair between verification nodes and a quantum state corresponding to a data subset, verify the entangled pair and the quantum state based on a second verification model, and output a second verification result; Based on the first verification result and the second verification result, a distributed consensus is reached to obtain the verified target data.

3. A method for dynamic forecasting of commodity market conditions according to claim 2, characterized in that: Initializing the features of each verification node and each data subset, performing iterative verification based on the features, and identifying abnormal data and malicious nodes as the first verification result, includes: Slice the real-time market data through the verification node to obtain a preset number of data subsets; Initialize the first eigenvector corresponding to each verification node, and initialize the second eigenvector of the hyperedge corresponding to each data subset; For each hyperedge, the first feature vectors of all verification nodes connected to it are aggregated based on the preset activation function as the hyperedge feature; For each verification node, aggregating the second feature vectors of all hyperedges connected to it based on the activation function as the node feature; Based on the hyperedge features and the node features, abnormal data and malicious nodes are identified as the first verification result.

4. A commodity market dynamic forecasting method according to claim 3, characterized in that: The identifying abnormal data and malicious nodes based on the hyperedge feature and the node feature as the first verification result includes: Determine a first anomaly score based on the node feature and a first feature mean corresponding to the node feature, and if the first anomaly score is greater than or equal to a first threshold, determine that the verification node corresponding to the node feature is a malicious node; Based on the hyperedge feature and the second feature mean of the data subset, a second anomaly score is determined; if the second anomaly score is greater than or equal to a second threshold, the data subset is determined to be abnormal data, and the identified malicious nodes and abnormal data are used as the first verification result.

5. A commodity market dynamic forecasting method according to claim 2, characterized in that: The generating of the entangled pair between the verification nodes and the quantum state corresponding to the data subset, verifying the entangled pair and the quantum state based on the second verification model, and outputting a second verification result includes: Generate entangled pairs between verification nodes; Encoding the hash value corresponding to the data subset into a quantum state, and transmitting the quantum state to a target node based on a quantum hidden state transmission protocol; The target node verifies whether the quantum state of the data subset is consistent with the original quantum state of the source node based on the entangled pair and the quantum state, and outputs a second verification result.

6. A commodity market dynamic forecasting method according to claim 2, characterized in that: The step of reaching a distributed consensus based on the first verification result and the second verification result to obtain the verified target data includes: If both the first verification result and the second verification result are true, a distributed consensus is reached and the verified target data is obtained.

7. A method for dynamic forecasting of commodity market conditions according to any one of claims 1 to 6, characterized in that: The step of formulating a trading strategy based on the target data and encoding the trading strategy into a smart contract includes: Training a trading strategy model based on a deep learning algorithm and the target data to generate a trading strategy; The trading strategy is abstracted into executable operation instructions, and the operation instructions are encoded into a smart contract using a smart contract programming language.

8. A commodity market dynamic forecasting system, characterized in that: include: An acquisition unit, used to acquire real-time market data of a target commodity, and submit the real-time market data to a market marking system through a submission node; A verification unit, in the market marking system, is used to verify the real-time market data based on the entangled pairs between the verification nodes and the characteristics of each data subset in the real-time market data to obtain the verified target data; an aggregation unit, configured to generate a data set hash value based on the target data, aggregate the target data through an aggregation node in the market marking system to generate aggregated data, write the aggregated data into a distributed hash table, and store the aggregated data on a blockchain based on the data set hash value; A contract unit, configured to formulate a transaction strategy based on the target data, encode the transaction strategy into a smart contract, and deploy the smart contract on the blockchain; An execution unit is used to predict market dynamics based on the aggregated data on the blockchain, and automatically execute transactions in the market marking system when it is predicted that the market dynamics meet the triggering conditions of the smart contract.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a commodity market dynamic prediction method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement a method for dynamically predicting commodity market conditions as described in any one of claims 1 to 7.

Images