Financial asset management and securitization system based on big data, ai and blockchain

Abstract

The application relates to the technical field of asset management, and particularly discloses a financial asset management and securitization system based on big data, AI and a block chain, which comprises a data extraction module, a data evaluation module and a data management module.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of asset management, and particularly relates to a financial asset management and securitization system based on big data, AI and blockchains. BACKGROUND

[0002] At present, with the continuous development of the financial market, financial institutions and investors have increasing demand for financial asset management and securitization. Traditional financial asset management methods have problems such as low data processing efficiency, difficulty in accurately assessing risks, and complicated securitization processes. The emergence of big data, AI and blockchain technologies provides new possibilities for solving these problems.

[0003] Big data can help financial institutions comprehensively and accurately analyze market trends and asset risks, and improve the timeliness and accuracy of decision-making.

[0004] AI technology, especially machine learning algorithms, can automatically analyze historical data, discover market patterns, and improve trading efficiency and profitability.

[0005] Blockchain technology, with its decentralized and tamper-proof characteristics, ensures data security and transparency, and is particularly suitable for recording and trading financial assets.

[0006] However, in the process of managing financial assets in the prior art, big data, AI and blockchain technologies cannot be well integrated, increasing management complexity and redundancy, leading to problems such as not timely and not accurate financial asset management.

[0007] Therefore, the present application proposes a financial asset management and securitization system based on big data, AI and blockchains. SUMMARY

[0008] The present application provides a financial asset management and securitization system based on big data, AI and blockchains, which can improve the efficiency and accuracy of data processing by using big data, AI and blockchain technologies to acquire and efficiently process multi-source financial asset data, and can more accurately assess asset quality, thereby optimizing asset maintenance strategies and meeting user demand for target financial asset maintenance, and improving overall financial risk management.

[0009] The present application provides a financial asset management and securitization system based on big data, AI and blockchains, which includes:

[0010] A data extraction module is used to acquire multi-source asset data of target financial assets based on big data, AI and blockchains, and to process the data to obtain first processed data.

[0011] a data evaluation module configured to perform data evaluation on the first processed data in combination with the evaluation data type, so as to determine a first asset quality of the target financial asset;

[0012] a data management module configured to perform asset maintenance on the target financial asset based on the first asset quality and an asset type of the target financial asset;

[0013] a securitization module configured to determine whether the target financial asset that has undergone asset maintenance can be securitized, and to perform asset securitization on the target financial asset that can be securitized according to an asset securitization scheme.

[0014] Preferably, the big data, AI and blockchain-based financial asset management and securitization system comprises:

[0015] an asset data acquisition unit configured to acquire first asset data of the target financial asset based on big data technology, second asset data of the target financial asset based on AI technology, and third asset data of the target financial asset based on blockchain technology;

[0016] an asset data comparison unit configured to compare the first asset data, the second asset data and the third asset data one by one, so as to determine the similarity of asset data between different data sources, thereby obtaining a similarity set of the target financial asset;

[0017] a similarity comparison unit configured to extract the maximum similarity and the minimum similarity of asset data between different data sources in the similarity set, and determine a first difference between the maximum similarity and the minimum similarity;

[0018] an asset data optimization unit configured to compare the first difference with a preset minimum difference, and determine multi-source asset data of the target financial asset based on the comparison result;

[0019] an asset data processing unit configured to perform data standardization processing on the multi-source asset data, so as to obtain first processed data.

[0020] Preferably, the big data, AI and blockchain-based financial asset management and securitization system comprises:

[0021] an asset data optimization subunit configured to compare the first difference with the preset minimum difference;

[0022] if the first difference is less than the preset minimum difference, the multi-source asset data of the target financial asset is obtained based on asset data in the overlapping part of the first asset data, the second asset data and the third asset data;

[0023] If the first difference is not less than the preset minimum difference, multi-source asset data of the target financial asset is obtained based on all asset data of the first asset data, the second asset data and the third asset data.

[0024] Preferably, the big data, AI and blockchain-based financial asset management and securitization system comprises a data evaluation module, which comprises:

[0025] A type judgment unit is configured to determine a first evaluation data type that needs to be evaluated based on asset characteristics and asset evaluation requirements of the target financial asset;

[0026] A model construction unit is configured to select a first evaluation method with the highest matching degree with the target financial asset and a first evaluation model of the target financial asset constructed based on the first evaluation method from an evaluation model database based on the first evaluation data type and the asset characteristics of the target financial asset;

[0027] A second model unit is configured to perform model training and initial optimization on the first evaluation model based on an AI algorithm to obtain a second evaluation model;

[0028] A model reference unit is configured to extract a first evaluation reference model corresponding to a financial asset with the highest degree of coincidence with the asset characteristics and the first evaluation data type of the target financial asset from a preset financial asset database, and extract a second evaluation reference model corresponding to a financial asset with the second highest degree of coincidence with the asset characteristics and the first evaluation data type of the target financial asset from the evaluation model database;

[0029] An evaluation difference unit is configured to judge a first evaluation difference between a second evaluation method corresponding to the first evaluation reference model and a third evaluation method corresponding to the second evaluation reference model;

[0030] If the first evaluation difference is not greater than a preset standard evaluation difference, a third evaluation model is obtained by performing comprehensive model optimization on the second evaluation model based on the first evaluation reference model and the second evaluation reference model;

[0031] If the first evaluation difference is greater than the preset standard evaluation difference, a third evaluation reference model corresponding to a financial asset with the third highest degree of coincidence with the asset characteristics and the first evaluation data type of the target financial asset is extracted from the preset financial asset database;

[0032] A fourth evaluation method corresponding to the third evaluation reference model is compared with the second evaluation method corresponding to the first evaluation reference model, so as to determine a second evaluation difference based on a comparison result, and rejudge the evaluation difference;

[0033] A data evaluation unit is configured to input the first processing data into the third evaluation model to obtain a first evaluation result of the target financial asset, and obtain a first asset quality of the target financial asset in combination with the asset characteristics of the target financial asset.

[0034] Preferably, the big data, AI and blockchain-based financial asset management and securitization system performs comprehensive model optimization on the second evaluation model based on the first evaluation reference model and the second evaluation reference model to obtain a third evaluation model, including:

[0035] extracting the second evaluation parameters of the second evaluation method in the first evaluation reference model to obtain a first parameter set, and simultaneously extracting the third evaluation parameters of the third evaluation method in the second evaluation reference model to obtain a second parameter set;

[0036] extracting the first evaluation parameters of the first evaluation method in the second evaluation model to obtain an initial parameter set, and obtaining a first parameter table corresponding to the first parameter set, the second parameter set and the initial parameter set;

[0037] adjusting the evaluation parameters in the initial parameter set based on the corresponding evaluation parameters in the first parameter table to obtain a first adjustment evaluation parameter T corresponding to each first evaluation parameter in the initial parameter set i , thereby obtaining a first adjustment evaluation parameter set;

[0038] wherein T i is the i-th first adjustment evaluation parameter, s i is the parameter value of the i-th first evaluation parameter in the initial parameter set, s i ′ is the parameter value of the second evaluation parameter consistent with the parameter type of the i-th first evaluation parameter in the first parameter table, s i ″ is the parameter value of the third evaluation parameter consistent with the parameter type of the i-th first evaluation parameter in the first parameter table, μ i is the parameter conversion coefficient of the parameter type corresponding to the i-th first evaluation parameter, α1 is the evaluation weight of the second evaluation parameter, α2 is the evaluation weight of the third evaluation parameter, and ε is the adjustment error factor, wherein the evaluation weight of the second evaluation parameter is greater than the evaluation weight of the third evaluation parameter;

[0039] performing model optimization on the second evaluation model based on the first adjustment evaluation parameter set to obtain a third evaluation model.

[0040] Preferably, the big data, AI and blockchain-based financial asset management and securitization system comprises a data management module, including:

[0041] a strategy determination unit configured to determine an asset maintenance strategy of a target financial asset by combining a first asset quality with an asset type and asset characteristics of the target financial asset;

[0042] a strategy judgment unit configured to judge the asset maintenance strategy based on an asset maintenance standard to determine the strategy feasibility of the asset maintenance strategy.

[0043] An asset maintenance unit is configured to perform asset maintenance on the target financial asset based on the asset maintenance strategy if the asset maintenance strategy is feasible.

[0044] Preferably, the big data, AI and blockchain-based financial asset management and securitization system comprises a securitization module, which comprises:

[0045] An asset judgment unit is configured to obtain real-time market demand of a financial market and determine whether the target financial asset can be securitized based on the real-time market demand.

[0046] If the target financial asset can be securitized, the securitization is predicted based on the market demand of the real-time financial market and the asset quality of the target financial asset to obtain a first prediction result.

[0047] A scheme determination unit is configured to obtain a standard securitization scheme for securitization and adjust the standard securitization scheme in combination with the target financial asset to obtain a first asset securitization scheme.

[0048] An asset securitization unit is configured to securitize the target financial asset based on the first asset securitization scheme.

[0049] Preferably, the big data, AI and blockchain-based financial asset management and securitization system further comprises a securitization module, which comprises:

[0050] A securitization monitoring unit is configured to monitor the securitization progress at each moment in real time during the securitization of the target financial asset.

[0051] A securitization supervision unit is configured to compare the securitization progress with the first asset securitization scheme to determine whether the real-time securitization progress matches the first asset securitization scheme.

[0052] If not, the first asset securitization scheme is adjusted based on the securitization progress.

[0053] If so, it is determined that the securitization of the target asset is qualified.

[0054] The present application has the following beneficial effects over the prior art: through multi-source acquisition and efficient processing of financial assets based on big data, AI and blockchain technologies, the efficiency and accuracy of data processing can be improved, and the asset quality can be more accurately evaluated, thereby optimizing the asset maintenance strategy and making the maintenance of the target financial asset more meet the user demand and improving the overall financial risk management level.

[0055] Other features and advantages of the present application will be set forth in the description that follows, and in part will be apparent from the description, or can be learned by practice of the application. The purposes and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims hereof.

[0056] The technical solutions of the present application are described in further detail below with the aid of the accompanying drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0057] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, illustrate embodiments of the present application and are used to explain the present application, and do not constitute a limitation of the present application. In the drawings:

[0058] Figure 1 The figure is a schematic diagram of the financial asset management and securitization system based on big data, AI and blockchain in the embodiments of the present application. DETAILED DESCRIPTION

[0059] The preferred embodiments of the present application are described below in conjunction with the accompanying drawings, and it should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and do not limit the present application.

[0060] Embodiment 1:

[0061] The present application provides a financial asset management and securitization system based on big data, AI and blockchain, which refers to Figure 1 , comprising:

[0062] The data extraction module is used to acquire multi-source asset data of the target financial asset based on big data, AI and blockchain, and perform data processing to obtain first processing data;

[0063] The data evaluation module is used to evaluate the first processing data in combination with the evaluation data type, so as to determine the first asset quality of the target financial asset;

[0064] The data management module is used to maintain the target financial asset based on the first asset quality and the asset type of the target financial asset;

[0065] The securitization module is used to determine whether the target financial asset that is maintained can be securitized, and to determine the asset securitization scheme of the target financial asset that can be securitized to perform asset securitization.

[0066] In this embodiment, big data refers to a collection of data that cannot be captured, managed and processed within a certain time range by conventional software tools, and is a massive, high-growth and diversified information asset that requires new processing modes to have stronger decision-making, insight discovery and process optimization capabilities.

[0067] In this embodiment, the blockchain is a distributed database that combines data blocks in a chain-like manner according to time sequence to form a specific data structure, and uses cryptography to ensure the security of data transmission and access. Blockchain technology has characteristics such as decentralization, non-tamperability, traceability, etc.

[0068] In this embodiment, the target financial asset refers to specific financial assets invested or held by enterprises or individuals, such as stocks, bonds, funds, futures, options, etc. These assets are the objects of investment activities and the source of investment income.

[0069] In this embodiment, multi-source asset data refers to data about target financial assets obtained from different sources, which may include financial markets, financial institutions, trading platforms, public information, etc.

[0070] In this embodiment, the first processed data refers to data obtained after preliminary processing and analysis of multi-source asset data, which provides a basis for subsequent evaluation and decision-making.

[0071] In this embodiment, the evaluation data type refers to the type of data used to evaluate the quality of the target financial asset, which includes financial data, market data, risk data, etc.

[0072] In this embodiment, the first asset quality refers to the preliminary judgment about the quality of the target financial asset obtained after evaluating the first processed data based on the evaluation data type.

[0073] In this embodiment, the asset type refers to the type of the target financial asset, which includes stocks, bonds, funds, etc. Different types of assets have different characteristics and risks.

[0074] In this embodiment, asset maintenance refers to the management and maintenance of the target financial asset to ensure its normal operation and maximize its value.

[0075] In this embodiment, asset securitization refers to the process of separating and restructuring the risk and return elements of assets that lack liquidity but can generate predictable stable cash flows, and then converting them into securities that can be sold and circulated in the financial market.

[0076] In this embodiment, the asset securitization scheme refers to the specific plan and strategy developed to achieve asset securitization, including asset selection, structure design, risk assessment and control, etc.

[0077] The above technology has the beneficial effect that: through multi-source acquisition and efficient processing of financial assets based on big data, AI and blockchain technologies, the efficiency and accuracy of data processing can be improved, and the quality of assets can be more accurately evaluated, thereby optimizing asset maintenance strategies, making the maintenance of target financial assets more meet user needs, and improving the overall financial risk management level.

[0078] Embodiment 2:

[0079] Based on the financial asset management and securitization system based on big data, AI and blockchain in embodiment 1, the data extraction module comprises:

[0080] The asset data acquisition unit is configured to acquire first asset data of the target financial asset based on big data technology, acquire second asset data of the target financial asset based on AI technology, and acquire third asset data of the target financial asset based on blockchain technology.

[0081] The asset data comparison unit is configured to compare the first asset data, the second asset data and the third asset data one by one to determine the similarity of asset data between different data sources, thereby obtaining a similarity set of the target financial asset.

[0082] The similarity comparison unit is configured to extract the maximum similarity and the minimum similarity of asset data between different data sources in the similarity set, and determine a first difference between the maximum similarity and the minimum similarity.

[0083] The asset data optimization unit is configured to compare the first difference with a preset minimum difference, and determine multi-source asset data of the target financial asset based on the comparison result.

[0084] The asset data processing unit is configured to perform data standardization processing on the multi-source asset data to obtain first processing data.

[0085] In this embodiment, big data refers to a collection of data that cannot be captured, managed and processed within a certain time range by conventional software tools, and is a massive, high-growth and diversified information asset that requires new processing modes to have stronger decision-making, insight discovery and process optimization capabilities.

[0086] In this embodiment, blockchain is a distributed database that combines data blocks in a chain manner according to time sequence to form a specific data structure, and uses cryptography to ensure the security of data transmission and access. Blockchain technology has the characteristics of decentralization, non-tamperability and traceability.

[0087] In this embodiment, the target financial asset refers to a specific financial asset invested or held by an enterprise or an individual, such as stocks, bonds, funds, futures, options, etc. These assets are the objects of investment activities and the sources of investment income.

[0088] In this embodiment, similarity refers to the degree of similarity of asset data between different data sources. The asset data obtained from different data sources may be the same or different.

[0089] In this embodiment, the similarity set refers to a set containing multiple similarity values, which reflect the degree of similarity of asset data between different data sources.

[0090] In this embodiment, the maximum similarity refers to the maximum value among all similarity values in the similarity set, which represents the most similar degree of asset data between different data sources.

[0091] In this embodiment, the minimum similarity refers to the minimum value among all similarity values in the similarity set, which represents the least similar degree of asset data between different data sources.

[0092] In this embodiment, the first difference refers to the difference between the maximum similarity and the minimum similarity, which reflects the range of differences in the degree of similarity of asset data between different data sources.

[0093] In this embodiment, the preset minimum difference refers to a preset minimum difference threshold when performing data comparison. When the first difference is less than the preset minimum difference, it can be considered that the asset data between different data sources has a high degree of similarity, and the corresponding first asset data or second asset data or third asset data can be integrated to obtain multi-source asset data of the target financial asset, which can be used for data processing and analysis.

[0094] In this embodiment, the multi-source asset data refers to a set of data of the target financial asset obtained from different data sources, which may include transaction records, market trends, financial reports, etc.

[0095] In this embodiment, data standardization processing refers to the process of converting data from different sources and different formats into a unified format and standard, in order to facilitate subsequent data analysis and processing.

[0096] In this embodiment, the first processed data refers to the financial asset data obtained after the multi-source asset data is subjected to data standardization processing.

[0097] The beneficial effects of the above technology are: by comparing the extracted data, the multi-source asset data obtained based on the comparison results is more consistent with the asset data of the target financial asset, thereby making the analysis and management of the target financial asset more accurate.

[0098] Embodiment 3

[0099] On the basis of Embodiment 2, the financial asset management and securitization system based on big data, AI and blockchain, the asset data optimization unit comprises:

[0100] The asset data optimization sub-unit is configured to compare the first difference with a preset minimum difference.

[0101] If the first difference is less than the preset minimum difference, the multi-source asset data of the target financial asset is obtained based on the asset data of the overlapping part in the first asset data, the second asset data and the third asset data.

[0102] If the first difference is not less than the preset minimum difference, the multi-source asset data of the target financial asset is obtained based on all asset data of the first asset data, the second asset data and the third asset data.

[0103] In this embodiment, the first difference refers to the difference between the maximum similarity and the minimum similarity, which reflects the difference range of the similarity of asset data between different data sources.

[0104] In this embodiment, the preset minimum difference refers to a preset minimum difference threshold when data comparison is performed. When the first difference is less than the preset minimum difference, it can be considered that the asset data between different data sources has a high similarity, and then the corresponding first asset data or second asset data or third asset data can be integrated to obtain the multi-source asset data of the target financial asset, which can be used for data processing and analysis.

[0105] In this embodiment, the multi-source asset data refers to a data set of the target financial asset obtained from different data sources, which may include transaction records, market trends, financial reports, etc.

[0106] The beneficial effects of the above technology are that by comparing the extracted data, data processing is performed based on the comparison result, so that the obtained multi-source asset data is more consistent with the asset data of the target financial asset, and the analysis and management of the target financial asset are more accurate.

[0107] Embodiment 4

[0108] On the basis of Embodiment 2, the data evaluation module of the financial asset management and securitization system based on big data, AI and blockchain comprises:

[0109] The type judgment unit is configured to determine a first evaluation data type that needs to be evaluated based on asset characteristics and asset evaluation requirements of the target financial asset.

[0110] The model construction unit is configured to select, from the evaluation model database, a first evaluation method with the highest matching degree with the target financial asset based on the first evaluation data type and asset characteristics of the target financial asset, and construct a first evaluation model of the target financial asset based on the first evaluation method.

[0111] The second model unit is configured to perform model training and initial optimization on the first evaluation model based on an AI algorithm to obtain a second evaluation model.

[0112] The model reference unit is configured to extract, from the preset financial asset database, a first evaluation reference model corresponding to a financial asset with the highest degree of coincidence with the asset characteristics and the first evaluation data type of the target financial asset, and extract, from the evaluation model database, a second evaluation reference model corresponding to a financial asset with the second highest degree of coincidence with the asset characteristics and the first evaluation data type of the target financial asset.

[0113] The evaluation difference unit is configured to determine a first evaluation difference between a second evaluation method corresponding to the first evaluation reference model and a third evaluation method corresponding to the second evaluation reference model.

[0114] If the first evaluation difference is not greater than a preset standard evaluation difference, the second evaluation model is subjected to comprehensive model optimization based on the first evaluation reference model and the second evaluation reference model to obtain a third evaluation model.

[0115] If the first evaluation difference is greater than the preset standard evaluation difference, a third evaluation reference model corresponding to a financial asset with the third highest degree of coincidence with the asset characteristics and the first evaluation data type of the target financial asset is extracted from the preset financial asset database.

[0116] The fourth evaluation method corresponding to the third evaluation reference model is compared with the second evaluation method corresponding to the first evaluation reference model, so as to determine a second evaluation difference based on a comparison result, and re-determine the evaluation difference.

[0117] The data evaluation unit is configured to input the first processing data into the third evaluation model to obtain a first evaluation result of the target financial asset, and obtain a first asset quality of the target financial asset in combination with the asset characteristics of the target financial asset.

[0118] In this embodiment, the asset characteristics refer to unique properties or characteristics possessed by the target financial asset, such as size, liquidity, risk level, and potential yield.

[0119] In this embodiment, the asset evaluation requirement refers to specific requirements or purposes for evaluating the target financial asset, such as determining the value, risk level, and investment potential of the target financial asset.

[0120] In this embodiment, the first evaluation data type is a specific data type that needs to be evaluated according to the asset characteristics and evaluation requirements of the target financial asset, such as financial data, market data, credit data, etc.

[0121] In this embodiment, the evaluation model database is a database for storing various evaluation models, and the evaluation models of the evaluation model database can be used for evaluation of different types of financial assets.

[0122] In this embodiment, the first evaluation method is an evaluation method with the highest matching degree with the target financial asset selected from the evaluation model database.

[0123] In this embodiment, the first evaluation model is an evaluation model of the target financial asset constructed based on the first evaluation method.

[0124] In this embodiment, the second evaluation model is an evaluation model trained and optimized by an AI algorithm.

[0125] In this embodiment, the first evaluation reference model refers to an evaluation model corresponding to a financial asset with the highest degree of coincidence with the characteristics of the target financial asset and the first evaluation data type extracted from the preset financial asset database, and the second evaluation reference model refers to an evaluation model corresponding to a financial asset with the second highest degree of coincidence with the characteristics of the target financial asset and the first evaluation data type extracted from the preset financial asset database.

[0126] In this embodiment, the second evaluation method refers to an evaluation method corresponding to the first evaluation reference model, and the third evaluation method refers to an evaluation method corresponding to the second evaluation reference model.

[0127] In this embodiment, the first evaluation difference refers to the evaluation difference between the second evaluation method and the third evaluation method.

[0128] In this embodiment, the preset standard evaluation difference is a preset standard for judging whether the evaluation difference is acceptable.

[0129] In this embodiment, the third evaluation model is an evaluation model obtained by comprehensively optimizing the second evaluation model based on the first evaluation reference model and the second evaluation reference model.

[0130] In this embodiment, the third evaluation reference model refers to an evaluation model corresponding to a financial asset with the third highest degree of coincidence with the characteristics of the target financial asset and the first evaluation data type extracted from the preset financial asset database when the evaluation difference is greater than the preset standard.

[0131] In this embodiment, the fourth evaluation method refers to an evaluation method corresponding to the third evaluation reference model.

[0132] In this embodiment, the second evaluation difference refers to an evaluation difference between a fourth evaluation method corresponding to the third evaluation reference model and a second evaluation method corresponding to the first evaluation reference model.

[0133] In this embodiment, the first evaluation result is a result obtained by evaluating the target financial asset through the third evaluation model.

[0134] In this embodiment, the first asset quality refers to an asset quality evaluation result obtained in combination with the asset characteristics of the target financial asset and the first evaluation result.

[0135] The above-mentioned beneficial effects of the above-mentioned technology are that, by adjusting and optimizing the evaluation model, the determined evaluation model can be more accurate and can better meet the asset evaluation demand, so that the asset management of the target financial asset is more efficient and accurate.

[0136] Embodiment 5:

[0137] On the basis of embodiment 4, the financial asset management and securitization system based on big data, AI and blockchain, the second evaluation model is comprehensively optimized based on the first evaluation reference model and the second evaluation reference model to obtain the third evaluation model, comprising:

[0138] The second evaluation parameters of the second evaluation method in the first evaluation reference model are extracted to obtain a first parameter set, and the third evaluation parameters of the third evaluation method in the second evaluation reference model are extracted to obtain a second parameter set;

[0139] The first evaluation parameters of the first evaluation method in the second evaluation model are extracted to obtain an initial parameter set, and the first parameter set, the second parameter set and the initial parameter set are correspondingly obtained to obtain a first parameter table;

[0140] Based on the corresponding evaluation parameters in the first parameter table, the evaluation parameters in the initial parameter set are adjusted to obtain a first adjustment evaluation parameter T i , corresponding to each first evaluation parameter in the initial parameter set;

[0141] wherein T i is the i th first adjustment evaluation parameter, s i is the parameter value of the i th first evaluation parameter in the initial parameter set, s i ′ is the parameter value of the second evaluation parameter in the first parameter table which is consistent with the parameter type of the i th first evaluation parameter, s i ″ is the parameter value of the third evaluation parameter in the first parameter table which is consistent with the parameter type of the i th first evaluation parameter, and μ iis a parameter conversion coefficient corresponding to the parameter type of the i-th first evaluation parameter, a1 is an evaluation weight of the second evaluation parameter, a2 is an evaluation weight of the third evaluation parameter, and ε is an adjustment error factor, wherein the evaluation weight of the second evaluation parameter is greater than the evaluation weight of the third evaluation parameter;

[0142] Based on the first adjusted evaluation parameter set, the second evaluation model is optimized to obtain a third evaluation model.

[0143] In this embodiment, the second evaluation parameter refers to a parameter contained in the second evaluation method in the first evaluation parameter model, and the third evaluation parameter refers to a parameter contained in the third evaluation method in the second evaluation parameter model.

[0144] In this embodiment, the first parameter set refers to a set composed of the second evaluation parameters, and the second parameter set refers to a set composed of the third evaluation parameters.

[0145] In this embodiment, the initial parameter set is a parameter set composed of evaluation parameters in the first evaluation method in the second evaluation model.

[0146] In this embodiment, the first parameter table is a parameter table corresponding to the evaluation parameters in the first parameter set, the second parameter set and the initial parameter set.

[0147] In this embodiment, the first adjusted evaluation parameter is an evaluation parameter obtained by adjusting the first evaluation parameter according to the first parameter table.

[0148] In this embodiment, the third evaluation model refers to an evaluation model obtained by adjusting the corresponding evaluation parameter in the second evaluation model with the first adjusted evaluation parameter in the first adjusted evaluation parameter set.

[0149] The beneficial effects of the above technology are: by adjusting and optimizing the evaluation model, the determined evaluation model can be more accurate, and can better meet the asset evaluation demand, so that the asset management of the target financial asset is more efficient and accurate.

[0150] Embodiment 6:

[0151] Based on the financial asset management and securitization system based on big data, AI and block chain in embodiment 4, the data management module comprises:

[0152] The strategy determination unit is configured to combine the first asset quality with the asset type and asset characteristics of the target financial asset to determine the asset maintenance strategy of the target financial asset.

[0153] The strategy judgment unit is configured to judge the asset maintenance strategy based on the asset maintenance standard, so as to determine the strategy feasibility of the asset maintenance strategy.

[0154] An asset maintenance unit is configured to perform asset maintenance on the target financial asset based on the asset maintenance strategy if the asset maintenance strategy is feasible.

[0155] In this embodiment, the first asset quality refers to a preliminary judgment on the quality of the target financial asset obtained by evaluating the first processing data according to the evaluation data type.

[0156] In this embodiment, the asset type refers to the type of the target financial asset, and the asset type includes stocks, bonds, funds, etc. Different types of assets have different characteristics and risks.

[0157] In this embodiment, the asset maintenance strategy refers to a series of maintenance and management measures developed to ensure that the target financial asset can continuously and stably generate value. These strategies may include regular inspection, preventive maintenance, risk management, asset allocation, and other aspects.

[0158] In this embodiment, asset maintenance refers to the management and maintenance work performed on the target financial asset to ensure its normal operation and maximize its value.

[0159] The above technology has the beneficial effect that by determining the asset maintenance strategy, the asset maintenance of the target financial asset can be more timely and effective, and the overall financial risk management level of the target financial asset is improved.

[0160] Embodiment 7:

[0161] Based on the financial asset management and securitization system based on big data, AI and blockchain in embodiment 6, the securitization module includes:

[0162] An asset judgment unit is configured to obtain real-time market demand of a financial market, and determine whether the target financial asset can be securitized based on the real-time market demand.

[0163] If the target financial asset can be securitized, the asset securitization is predicted based on the market demand of the real-time financial market and the asset quality of the target financial asset, and a first prediction result is obtained.

[0164] A scheme determination unit is configured to obtain a standard securitization scheme for securitization, and adjust the standard securitization scheme in combination with the target financial asset to obtain a first asset securitization scheme.

[0165] An asset securitization unit is configured to securitize the target financial asset based on the first asset securitization scheme.

[0166] In this embodiment, the real-time market demand refers to the immediate demand of investors or consumers in the financial market for a certain financial asset or financial product, which changes with market conditions, economic situation, investor expectations and other factors.

[0167] In this embodiment, the first prediction result refers to the prediction result of asset securitization based on the market demand of the real-time financial market and the asset quality of the target financial asset.

[0168] In this embodiment, the standard securitization scheme refers to a general and standardized asset securitization operation process and scheme. For example, the standard securitization scheme includes asset selection, structure design, credit enhancement, security issuance and other links, and is applicable to various types of financial assets.

[0169] In this embodiment, asset securitization refers to the process of separating and recombining risk and return factors in assets that lack liquidity but can generate predictable stable cash flow through certain structural arrangements, and then converting them into securities that can be sold and circulated in the financial market.

[0170] In this embodiment, the first asset securitization scheme refers to a specific plan and strategy developed to achieve asset securitization, including asset selection, structure design, risk assessment and control, etc.

[0171] The beneficial effects of the above technology are that by combining real-time market demand to judge the target financial asset, asset securitization prediction is performed, and a more accurate asset securitization scheme is obtained.

[0172] Embodiment 8:

[0173] Based on embodiment 7, the financial asset management and securitization system based on big data, AI and blockchain, the securitization module further comprises:

[0174] The securitization monitoring unit is configured to monitor the securitization progress at each moment in real time during the asset securitization process of the target financial asset.

[0175] The securitization monitoring unit is configured to compare the securitization progress with the first asset securitization scheme, so as to determine whether the real-time securitization progress matches the first asset securitization scheme.

[0176] If not, the first asset securitization scheme is adjusted based on the securitization progress.

[0177] Otherwise, it is determined that the asset securitization of the target asset is qualified.

[0178] In this embodiment, the securitization progress refers to the real-time securitization progress of the target financial asset in the asset securitization process.

[0179] In this embodiment, asset securitization refers to the process of separating and recombining the risk and return elements of assets that lack liquidity but can generate predictable stable cash flows through certain structural arrangements, and then converting them into securities that can be sold and circulated in the financial market.

[0180] In this embodiment, the first asset securitization plan refers to the specific plan and strategy developed to achieve asset securitization, including asset selection, structure design, risk assessment and control, etc.

[0181] The beneficial effects of the above technology are: by monitoring the securitization progress in real time, comparing with the first asset securitization plan, the asset securitization plan can be adjusted in time and accurately, so that the asset securitization can more accurately meet the user's demand.

[0182] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A financial asset management and securitization system based on big data, AI and blockchain, characterized in that, The method comprises the following steps: A data extraction module is used to obtain multi-source asset data of a target financial asset based on big data, AI and blockchain, and perform data processing to obtain first processed data; A data evaluation module is used to perform data evaluation on the first processed data in combination with an evaluation data type, so as to determine a first asset quality of the target financial asset; A data management module is used to perform asset maintenance on the target financial asset based on the first asset quality and an asset type of the target financial asset; A securitization module is used to determine whether the target financial asset that has undergone asset maintenance can be securitized, and determine an asset securitization scheme of the target financial asset that can be securitized to perform asset securitization; The data extraction module comprises: An asset data acquisition unit is used to acquire first asset data of the target financial asset based on big data technology, second asset data of the target financial asset based on AI technology and third asset data of the target financial asset based on blockchain technology; An asset data comparison unit is used to compare the first asset data, the second asset data and the third asset data one by one, so as to determine the similarity of asset data between different data sources, thereby obtaining a similarity set of the target financial asset; A similarity comparison unit is used to extract the maximum similarity and the minimum similarity of asset data between different data sources in the similarity set, and determine a first difference value of the maximum similarity and the minimum similarity; An asset data optimization unit is used to compare the first difference value with a preset minimum difference value, and determine multi-source asset data of the target financial asset based on the comparison result; An asset data processing unit is used to perform data standardization processing on the multi-source asset data to obtain the first processed data; The data evaluation module comprises: A type judgment unit is used to determine a first evaluation data type that needs to be evaluated based on asset characteristics and asset evaluation requirements of the target financial asset; A model construction unit is used to select a first evaluation method with the highest matching degree with the target financial asset and a first evaluation model of the target financial asset constructed based on the first evaluation method from an evaluation model database based on the first evaluation data type and the asset characteristics of the target financial asset; A second model unit is used to perform model training and initial optimization on the first evaluation model based on an AI algorithm to obtain a second evaluation model; A model reference unit is used to extract a first evaluation reference model corresponding to a financial asset with the highest degree of coincidence with the asset characteristics and the first evaluation data type of the target financial asset from a preset financial asset database, and extract a second evaluation reference model corresponding to a financial asset with the second highest degree of coincidence with the asset characteristics and the first evaluation data type of the target financial asset from the evaluation model database; An evaluation difference unit is used to determine a first evaluation difference of a second evaluation method corresponding to the first evaluation reference model and a third evaluation method corresponding to the second evaluation reference model; If the first evaluation difference is not greater than a preset standard evaluation difference, the second evaluation model is comprehensively optimized based on the first evaluation reference model and the second evaluation reference model to obtain a third evaluation model; If the first evaluation difference is greater than the preset standard evaluation difference, a third evaluation reference model corresponding to a financial asset with the third highest degree of coincidence with the asset characteristics and the first evaluation data type of the target financial asset is extracted from a preset financial asset database; The fourth evaluation method corresponding to the third evaluation reference model is compared with the second evaluation method corresponding to the first evaluation reference model, so as to determine the second evaluation difference based on the comparison result, and re-determine the evaluation difference; The data evaluation unit is configured to input the first processing data into the third evaluation model to obtain a first evaluation result of the target financial asset, and combine the asset characteristics of the target financial asset to obtain a first asset quality of the target financial asset. 2.The big data, Al and blockchain-based financial asset management and securitization system of claim 1, wherein, The asset data optimization unit comprises: The asset data optimization subunit is configured to compare the first difference with a preset minimum difference; If the first difference is less than the preset minimum difference, multi-source asset data of the target financial asset is obtained based on the asset data of the overlapping part of the first asset data, the second asset data and the third asset data; If the first difference is not less than the preset minimum difference, multi-source asset data of the target financial asset is obtained based on all asset data of the first asset data, the second asset data and the third asset data. 3.The big data, Al and blockchain-based financial asset management and securitization system of claim 1, wherein, The second evaluation model is optimized based on the first evaluation reference model and the second evaluation reference model to obtain a third evaluation model, comprising: The second evaluation parameters of the second evaluation method in the first evaluation reference model are extracted to obtain a first parameter set, and at the same time, the third evaluation parameters of the third evaluation method in the second evaluation reference model are extracted to obtain a second parameter set; The first evaluation parameters of the first evaluation method in the second evaluation model are extracted to obtain an initial parameter set, and the first parameter set, the second parameter set and the initial parameter set are correspondingly obtained to obtain a first parameter table; adjusting the evaluation parameters in the initial parameter set based on the corresponding evaluation parameters in the first parameter table, to obtain a first adjusted evaluation parameter T corresponding to each first evaluation parameter in the initial parameter set i , thereby obtaining the first adjusted evaluation parameter set; wherein T i is the ith first adjustment evaluation parameter, s i is the parameter value of the ith first evaluation parameter in the initial parameter set, s i ′ is the parameter value of the second evaluation parameter in the first parameter table consistent with the parameter type of the ith first evaluation parameter, s i ″ is the parameter value of the third evaluation parameter in the first parameter table consistent with the parameter type of the ith first evaluation parameter, μ i is the parameter conversion coefficient of the parameter type corresponding to the ith first evaluation parameter, α1 is the evaluation weight of the second evaluation parameter, α2 is the evaluation weight of the third evaluation parameter, and ε is the adjustment error factor, wherein the evaluation weight of the second evaluation parameter is greater than the evaluation weight of the third evaluation parameter. The second evaluation model is optimized based on the first adjusted evaluation parameter set to obtain a third evaluation model. 4.The big data, Al and blockchain-based financial asset management and securitization system of claim 1, wherein, The data management module comprises: The strategy determination unit is configured to combine the first asset quality with the asset type and the asset characteristics of the target financial asset to determine an asset maintenance strategy of the target financial asset; The strategy judgment unit is configured to judge the asset maintenance strategy based on the asset maintenance standard, so as to determine the strategy feasibility of the asset maintenance strategy; The asset maintenance unit is configured to perform asset maintenance on the target financial asset based on the asset maintenance strategy if the asset maintenance strategy is feasible. 5.The big data, Al and blockchain-based financial asset management and securitization system of claim 4, wherein, The securitization module comprises: The asset judgment unit is configured to obtain real-time market demand of a financial market, and judge whether the target financial asset can be securitized based on the real-time market demand; If the target financial asset can be securitized, the asset securitization is predicted based on the market demand of the real-time financial market and the asset quality of the target financial asset to obtain a first prediction result; The scheme determination unit is configured to obtain a standard securitization scheme for securitization, and adjust the standard securitization scheme in combination with the target financial asset to obtain a first asset securitization scheme; The asset securitization unit is configured to securitize the target financial asset based on the first asset securitization scheme. 6.The big data, Al and blockchain-based financial asset management and securitization system of claim 5, wherein, The securitization module further comprises: The securitization monitoring unit is configured to monitor the securitization progress in real time during the asset securitization process of the target financial asset; The securitization monitoring unit is configured to compare the securitization progress with the first asset securitization scheme, so as to determine whether the real-time securitization progress matches the first asset securitization scheme; If not, the first asset securitization scheme is adjusted based on the securitization progress; Otherwise, it is determined that the asset securitization of the target asset is qualified.

Images