Federal data service method and device based on scene generation and supply and demand matching, electronic equipment and medium

Abstract

The invention relates to the field of electric digital data processing, in particular to a federal data service method and device based on scene generation and supply and demand matching, electronic equipment and a medium, and the method comprises the following steps: constructing an artificial scene; obtaining factors and variables influencing supply and demand matching efficiency and precision, analyzing the artificial scene, the demand information and the supply information to obtain an analysis result, performing supply and demand matching according to the analysis result, and outputting a matching result; and predicting the demand information and the supply information, and carrying out supply and demand matching according to the predicted demand information and supply information. According to the invention, the reasoning and decision-making capabilities of artificial intelligence are integrated into a block chain system, the consensus process is monitored in real time and the consensus parameters are dynamically adjusted by using an intelligent algorithm, and the real-time achievement and dynamic adjustment of a consistent supply and demand matching decision are promoted, so that the adaptability of the supply and demand decision to scene polymorphism and relation coupling is ensured.

Description

Technical Field

[0001] The present invention relates to the field of electronic digital data processing, and in particular to a method, device, electronic device and medium for providing a federated data service based on scenario generation and supply-demand matching. Background Art

[0002] Data flows between different organizations and is used by people to provide various services, making data more open, personalized, and complex. This situation leads to many different usage scenarios, and the requirements in these scenarios vary greatly, and different data may be required for each scenario.

[0003] At the same time, these seemingly different scenarios actually have some common rules or characteristics, but these common rules are not easy to discover and understand, that is, the hidden nature of the relationship between data. Due to the existence of hiddenness, it is difficult to express and explain the relationship between data in a unified way. When the supply side provides data to the demand side, it is difficult for the supply and demand sides to match, and the matching efficiency is not high.

[0004] The Chinese patent with publication number CN116777551A discloses a textile machine demand matching system integrating optimization algorithm and blockchain, including: demand text receiving module, receiving demand text from demand publisher and saving it in database after natural language processing; data processing module, receiving demand text product data to generate text vector, using optimization algorithm for data feature missing value supplement to supplement data missing value and sending to demand matching module; demand matching module, classifying and matching text vector to find better matching result; result feedback module, outputting matching result and feeding back demand publisher and service provider; transaction module, calling blockchain smart contract to save transaction data in blockchain after generating transaction data, broadcasting and verifying between nodes to reach data consistency. The system can quickly and accurately match demand, improve demand publisher satisfaction and transaction efficiency, and ensure the authenticity and reliability of transactions by utilizing the tamper-proof characteristics of blockchain.

[0005] However, in the process of supply and demand matching, there are dynamic changes in the scene. The dynamic changes in the scene may cause the results of supply and demand matching to change. If the changes in the scene cause the supply and demand matching to change dynamically, and when matching the demand with the supplier, the initial state of the demander is still used as a reference, it will lead to deviations in the matching results. Summary of the invention

[0006] In order to solve the problem that dynamic changes in demand sides lead to deviations in matching results during supply and demand matching, the present invention provides a method, device, electronic device and medium for a federated data service based on scenario generation and supply and demand matching.

[0007] The present invention provides a federated data service method based on scenario generation and supply-demand matching, which adopts the following technical solutions: A method for providing a federated data service based on scenario generation and supply-demand matching includes the following steps: Demand information and supply information are written into the blockchain; Acquire multi-source data and virtual-reality fusion data, and construct an artificial scene according to the multi-source data and the virtual-reality fusion data; Analyze the artificial scenario, calculate the model to extract factors and variables that affect the efficiency and accuracy of supply and demand matching, and explore the relationship between the factors and variables; Analyze the artificial scenario, the demand information, and the supply information through the calculation model to obtain an analysis result, perform supply and demand matching according to the analysis result, and output a matching result; According to the matching result, as well as the real-time demand information and supply information, the demand information and the supply information are predicted, and supply and demand matching is performed according to the predicted demand information and the supply information.

[0008] In a specific possible implementation mode, when analyzing the artificial scene, analysis is performed from multiple perspectives.

[0009] In a specific implementation scheme, the method for constructing the artificial scene comprises the following steps: Acquire scene data from multiple collection sources, extract key elements and indicators from the scene data, Identify scenarios based on the key elements and indicators, and then calibrate and authenticate the scenario data; Through the verification of functions and performance, the scene data is further adjusted and predicted to form a multi-perspective scene representation framework.

[0010] In a specific implementation scheme, the computational model includes an LSTM neural network and a random destination allocation strategy algorithm based on computational experiments.

[0011] In a specific implementation scheme, the method of extracting the factors and variables that affect the efficiency and accuracy of supply-demand matching through the computational model and exploring the relationship between the factors and variables comprises the following steps: Determining input and output according to the requirement information; The historical transaction data in the blockchain is used for model training of the computing model; extracting the factors and variables from the historical transaction data; Based on the factors and variables, the relationships between the factors and variables are discovered.

[0012] In a specific embodiment, the method for obtaining the analysis result comprises the following steps: Set algorithm parameters according to scene data; Generating a plurality of random matching schemes according to the algorithm parameters; The matching degree of the matching scheme is calculated, the matching scheme is screened according to a matching degree threshold, the matching scheme whose matching degree is greater than or equal to the matching degree threshold is retained, and the retained matching scheme constitutes the analysis result.

[0013] In a specific implementation scheme, when matching supply and demand based on the predicted demand information and supply information, the real-time demand information and supply information are used as verification of the initial predictions of the demand information and supply information to optimize the calculation model.

[0014] The present invention also provides a federated data service device based on scenario generation and supply-demand matching, which adopts the following technical solution: A federated data service device based on scenario generation and supply-demand matching, comprising: one or more processors; memory; And one or more computer programs, wherein one or more of the computer programs are stored in the memory, and one or more of the computer programs include instructions, which, when executed by the processor, enable the scenario-based generation and supply-demand matching federal data service device to perform the above-mentioned scenario-based generation and supply-demand matching federal data service method.

[0015] The present invention also provides an electronic device, which adopts the following technical solution: An electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the above-mentioned scenario-based generation and supply-demand matching federated data service method.

[0016] The present invention also provides a non-transitory computer-readable storage medium storing computer instructions, which adopts the following technical solution: A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the above-mentioned scenario-based generation and supply-demand matching federated data service method.

[0017] Compared with the prior art, the beneficial effects of the present invention are specifically embodied in: 1. Integrate the reasoning and decision-making capabilities of artificial intelligence into the blockchain system, use artificial intelligence algorithms to build scenarios to predict changes in demand-side scenarios, and output supply and demand matching solutions based on the prediction results to achieve dynamic adjustment of supply and demand matching and improve the accuracy of supply and demand matching, thereby ensuring the adaptability of supply and demand decisions in the face of scenario polymorphism and relationship coupling.

[0018] 2. By generating artificial scenarios, artificial intelligence can reproduce and adjust supply and demand matching, analyze the relationship between factors and variables in supply and demand matching, and make the reasoning about the relationship between factors and variables more verifiable. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flowchart of the federated data service method based on scenario generation and supply and demand matching.

[0020] Figure 2 This is a flowchart of step S200.

[0021] Figure 3 It is an architectural diagram of the federated data service approach based on scenario generation and supply-demand matching. DETAILED DESCRIPTION

[0022] The following combination Figure 1-Figure 2 The present invention is described in further detail.

[0023] The method for federated data service based on scenario generation and supply-demand matching provided in the embodiment of the present invention can be applied on a server or a terminal. The server can be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. The terminal can be a user equipment (User Equipment, UE) such as a mobile phone, smart phone, laptop computer, digital broadcast receiver, personal digital assistant (PDA), tablet computer (PAD) with strong computing power, handheld device, vehicle-mounted device, wearable device, computing device or other processing device connected to a wireless modem, mobile station (Mobile Station, MS), mobile terminal (Mobile Terminal), etc., and the present invention is not limited here.

[0024] The method of scenario-based generation and supply-demand matching of federated data services includes the following steps: S100, demand information is uploaded and broadcasted on the chain, and supply information is uploaded on the chain.

[0025] The demand information of the demander is written into the blockchain, and the demand information is broadcast to the supplier through the blockchain, so that the supplier can view and respond in real time. After the supplier obtains the demand information, it generates supply information based on the demand information and its own resources and capabilities, and writes the supply information into the blockchain to respond to the demander.

[0026] S200 builds an artificial scene based on multi-source data and virtual-real fusion data, matches supply and demand based on the dynamic analysis results of the artificial scene, and outputs the matching results.

[0027] Multi-source data includes demand information, supply information, third-party information, blockchain historical data, market data, etc. Virtual-reality fusion data is based on multi-source data and is generated by further prediction and simulation of multi-source data.

[0028] The blockchain stores artificial intelligence algorithms, which build different artificial scenarios of supply and demand matching based on multi-source data and virtual-real fusion data, and analyze artificial scenarios from different perspectives, such as focusing on inventory from an inventory perspective, focusing on supply from a procurement perspective, and focusing on demand from a sales perspective. By analyzing artificial scenarios from multiple perspectives, we can understand the supply and demand matching situation as comprehensively as possible.

[0029] Through multi-perspective analysis of artificial scenes, we can identify factors and variables that affect the efficiency and accuracy of supply and demand matching in different artificial scenes, further analyze the relationship between factors and variables, and build a calculation model between factors and variables. Factors and variables include demand, supply, delivery deadline, etc. Multi-perspective artificial scene analysis can more accurately analyze the factors and variables that affect supply and demand matching, and then correct and optimize the calculation model in the dynamically changing scene, and verify it. Furthermore, the calculation model can also predict scene changes, so as to perform dynamic supply and demand matching in dynamic scenes.

[0030] In addition, in the process of analyzing artificial scenarios, we maintain the acquisition of multi-source data, and verify the predicted data in the artificial scenarios through the subsequently acquired multi-source data, so as to optimize and correct the analysis results, so that the predicted artificial scenarios are more in line with the actual scenarios, thereby improving the accuracy of subsequent supply and demand matching.

[0031] To facilitate understanding, the following example is given with reference to a specific artificial intelligence algorithm.

[0032] After both the demand side and the supply side write data into the blockchain, PtMS (Parallel Transportation Management Systems) collects the scenario data of the supply side and the demand side in real time through multiple collection sources. Based on the scenario data, the dynamically changing scenarios of the supply side and the demand side are simulated. PtMS observes, understands and captures the scenario composition from different angles, and extracts the key elements and indicators of the scenario. The scenario is identified through key elements and indicators, and then the scenario data of the scenario is adjusted through calibration and certification to improve the rationality of the scenario. Then, through the verification of functions and performance, the scenario data is further adjusted and predicted, and the simulated scenario is further optimized to form a multi-perspective scenario representation framework.

[0033] The LSTM neural network sets input and output according to demand information, uses historical transaction data in the blockchain to train the supply and demand matching model, extracts trend, periodicity, seasonality and other characteristics from the historical transaction data. These characteristics are the factors and variables that affect supply and demand matching, and analyzes the specific impact of changes in factors and variables that affect supply and demand matching on supply and demand matching.

[0034] The random destination allocation strategy algorithm based on computational experiments sets algorithm parameters such as weights according to the scene data in the artificial scene, and generates multiple random supply information matching schemes for the demand information according to the algorithm parameters. The matching degree between the demand information and each matching scheme is calculated, and according to the pre-set matching degree threshold, the matching schemes with a matching degree greater than or equal to the matching degree threshold are retained. The matching scheme output by the random destination allocation strategy algorithm based on computational experiments is the analysis result.

[0035] The LSTM neural network that has completed model training further analyzes the matching scheme according to the changes in factors and variables and selects the optimal matching scheme. The LSTM neural network can also predict the dynamic changes of demand information and supply information based on real-time scene data, realize dynamic matching of supply and demand, select the optimal matching scheme according to the real-time changes of the scene, output the matching results, and write the matching results into the blockchain.

[0036] Furthermore, since the random destination allocation strategy algorithm based on computational experiments is a randomly generated matching solution, it can avoid local optimal solutions in the process of finding the optimal matching solution. Moreover, the random destination allocation strategy algorithm based on computational experiments can also build a controlled reasoning environment to reduce the interference of uncontrollable variables, and then the LSTM neural network can reproduce and adjust complex behaviors to ensure causal link analysis in a variable environment, so that the relational reasoning in polymorphic scenarios has better verifiability.

[0037] By integrating the reasoning and decision-making capabilities of PtMS, LSTM neural networks and random destination allocation strategy algorithms based on computational experiments into the blockchain system, the supply and demand matching process is monitored in real time and the supply and demand matching parameters are adjusted dynamically, which facilitates the agile configuration and intelligent execution of intelligent components supported by knowledge in the field of subsequent supply and demand matching, so as to promote the real-time achievement and dynamic adjustment of consistent supply and demand matching decisions, thereby ensuring the adaptability of supply and demand matching decisions in the face of scenario polymorphism and relationship coupling.

[0038] It should be noted that after the artificial scene is generated, PtMS continuously collects scene data from the supply and demand sides in real time, verifies the predicted scene changes and corrects errors through the real-time collected data, and uses it as a sample for analyzing the change rules to further improve the accuracy of the artificial scene generated by PtMS. The LSTM neural network obtains the real-time supply and demand matching data, verifies and corrects the errors of the predicted supply and demand matching results, and uses the real-time supply and demand matching data as a sample for subsequent supply and demand matching predictions, improving the accuracy of the LSTM neural network for supply and demand matching.

[0039] S300 dynamically adjusts and optimizes supply and demand matching based on matching results.

[0040] Since the artificial intelligence algorithm, demand information, supply information, and matching results are all written into the blockchain and broadcasted through the blockchain, both the supply and demand parties can view the matching results at any time. Based on the matching results in the blockchain, both the supply and demand parties can adjust their own strategies and resource allocations in accordance with their actual conditions, and then adjust the demand information and supply information. The artificial intelligence algorithm repeats step S200 and matches supply and demand again, making the matching results more flexible and accurate. At the same time, the adjustment of demand information and supply information can serve as a verification of the artificial intelligence algorithm's prediction of dynamic changes in the scene, correct and optimize the prediction of the artificial intelligence algorithm, improve the accuracy and efficiency of the artificial intelligence algorithm, and provide more reliable support for supply and demand matching.

[0041] The present invention also discloses a federated data service device based on scenario generation and supply-demand matching, comprising: one or more processors; a memory; And one or more computer programs, wherein the one or more computer programs are stored in a memory, and the one or more computer programs include instructions, which, when executed by a processor, enable a scenario-based federal data service device that matches supply and demand to perform the above-mentioned scenario-based federal data service method that matches supply and demand.

[0042] The present invention also discloses an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned scenario-based generation and supply-demand matching federated data service method.

[0043] The present invention also discloses a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to enable a computer to execute the above-mentioned scenario-based generation and supply-demand matching federated data service method.

[0044] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for providing a federated data service based on scenario generation and supply-demand matching, characterized in that: The steps include: Demand information and supply information are written into the blockchain; Acquire multi-source data and virtual-reality fusion data, and construct an artificial scene according to the multi-source data and the virtual-reality fusion data; Analyze the artificial scenario, calculate the model to extract factors and variables that affect the efficiency and accuracy of supply and demand matching, and explore the relationship between the factors and variables; Analyze the artificial scenario, the demand information, and the supply information through the calculation model to obtain an analysis result, perform supply and demand matching according to the analysis result, and output a matching result; According to the matching result, as well as the real-time demand information and supply information, the demand information and the supply information are predicted, and supply and demand matching is performed according to the predicted demand information and the supply information.

2. The method for providing a federated data service based on scenario generation and supply-demand matching according to claim 1, characterized in that: When analyzing the artificial scene, the analysis is performed from multiple perspectives.

3. The method for providing a federated data service based on scenario generation and supply-demand matching according to claim 1, characterized in that: The method for constructing the artificial scene comprises the following steps: Acquire scene data from multiple collection sources, extract key elements and indicators from the scene data, Identify scenarios based on the key elements and indicators, and then calibrate and authenticate the scenario data; Through the verification of functions and performance, the scene data is further adjusted and predicted to form a multi-perspective scene representation framework.

4. The method for providing a federated data service based on scenario generation and supply-demand matching according to claim 1, characterized in that: The computational model includes an LSTM neural network and a random destination allocation strategy algorithm based on computational experiments.

5. The method for providing a federated data service based on scenario generation and supply-demand matching according to claim 1, characterized in that: The method of extracting the factors and variables that affect the efficiency and accuracy of supply-demand matching through the calculation model and exploring the relationship between the factors and variables comprises the following steps: Determining input and output according to the requirement information; The historical transaction data in the blockchain is used for model training of the computing model; extracting the factors and variables from the historical transaction data; Based on the factors and variables, the relationships between the factors and variables are discovered.

6. The method for providing a federated data service based on scenario generation and supply-demand matching according to claim 1, characterized in that: The method for obtaining the analysis result comprises the following steps: Set algorithm parameters according to scene data; Generating a plurality of random matching schemes according to the algorithm parameters; The matching degree of the matching scheme is calculated, the matching scheme is screened according to a matching degree threshold, the matching scheme whose matching degree is greater than or equal to the matching degree threshold is retained, and the retained matching scheme constitutes the analysis result.

7. The method for providing a federated data service based on scenario generation and supply-demand matching according to claim 1, characterized in that: When matching supply and demand according to the predicted demand information and supply information, the real-time demand information and supply information are used as verification of the initial prediction of the demand information and supply information to optimize the calculation model.

8. A federated data service device based on scenario generation and supply-demand matching, characterized in that: include: one or more processors; Memory; And one or more computer programs, wherein one or more of the computer programs are stored in the memory, and one or more of the computer programs include instructions, which, when executed by the processor, enable the federal data service device based on scenario generation and supply and demand matching to perform the federal data service method based on scenario generation and supply and demand matching as described in any one of claims 1-7.

9. An electronic device, characterized in that: include: at least one processor; And a memory communicatively connected to at least one processor; wherein the memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the scenario-based generation and supply-demand matching federated data service method described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the scenario-based generation and supply-demand matching federated data service method described in any one of claims 1-7.

Images