Risk prevention and control method and system of block chain fused artificial intelligence big data Internet of Things

Abstract

The invention discloses a risk prevention and control method and system for a block chain fused artificial intelligence big data Internet of Things, and the embodiment of the risk prevention and control method for the block chain fused artificial intelligence big data Internet of Things comprises the steps: collecting multi-modal original data through Internet of Things equipment and the Internet, performing identity authentication on the data source by using a distributed digital identity system of the block chain; aggregating the multi-modal original data into intermediate state data according to main body, time and operator dimensions; according to a preset risk index, performing real-time calculation on the intermediate state data to generate a risk index value; matching the risk index value with a plurality of rule models generated based on artificial intelligence to generate a risk assessment result; and screening out key intermediate state data according to a risk assessment result, establishing an association relationship between the key intermediate state data and the risk index value, the risk assessment result and decision information, and performing credible evidence storage through a block chain base layer. And a high-credibility, high-real-time, high-precision and intelligent risk prevention and control mode is provided.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a risk prevention and control method and system that integrates blockchain, artificial intelligence, big data, and the Internet of Things. Background Technology

[0002] With the acceleration of globalization and the increasing interconnectedness of society, social risk management is facing unprecedented challenges. Risks such as public health crises, economic fluctuations, environmental disasters, and information warfare are increasingly occurring and expanding in scope, and their complexity is continuously escalating due to rapid social changes. Traditional risk management methods have shown significant limitations in addressing these dynamic and multi-dimensional risks.

[0003] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0004] The purpose of this invention is to provide a highly reliable, real-time, accurate, and intelligent risk prevention and control method and system.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a risk prevention and control method integrating blockchain, artificial intelligence, big data, and the Internet of Things, comprising the following steps: collecting multimodal raw data through IoT devices and the Internet, and authenticating the data source using the distributed digital identity system of blockchain; aggregating the multimodal raw data into intermediate data according to the dimensions of subject, time, and operator; performing real-time calculation on the intermediate data according to preset risk indicators to generate risk indicator values; matching the generated risk indicator values ​​with multiple rule models generated based on artificial intelligence to generate risk assessment results, wherein the risk assessment results include one or more of the following: risk level labels, probability values, and disposal suggestions; selecting key intermediate data based on the risk assessment results, establishing a correlation between the key intermediate data and the corresponding risk indicator values, risk assessment results, and decision information, and performing trusted storage through the blockchain infrastructure layer.

[0006] In one embodiment of the present invention, the method further includes: in response to the decision information involving multi-departmental cooperation, providing cross-departmental data sharing and information interaction based on a blockchain-based distributed digital identity system and privacy-preserving data sharing technology.

[0007] In one embodiment of the present invention, the device for collecting multimodal raw data includes one or more of the following: environmental sensors, surveillance cameras, mobile terminals, financial transaction terminals, and network behavior collection devices; the multimodal raw data includes one or more of the following: environmental monitoring data, public safety data, equipment operation data, economic activity data, and network behavior data.

[0008] In one embodiment of the present invention, the method further includes: storing the aggregated intermediate data into the blockchain base layer.

[0009] In one embodiment of the present invention, the preset risk indicator is matched with the rule model; and the step of performing real-time calculation on intermediate data according to the preset risk indicator to generate a risk indicator value includes: performing real-time calculation and analysis on the generated intermediate data stream to generate a risk indicator value, wherein the real-time calculation and analysis includes at least one of the following: cascading merging, incremental calculation, distributed caching, and merging of associated timestamps.

[0010] In one embodiment of the present invention, the subject dimension is defined as the data source entity, including device number, user account or organization identifier; the time dimension indicates the data window is divided into slices according to a preset time unit; and the operator dimension indicates the calculation method used for the calculation.

[0011] In one embodiment of the present invention, the method further includes: automatically deploying multiple rule models based on smart contracts and on-chain / off-chain collaboration models; wherein the number of parameters of the rule models deployed based on smart contracts is less than the number of parameters of the rule models deployed based on on-chain / off-chain collaboration models.

[0012] Secondly, this invention provides a risk prevention and control system integrating blockchain, artificial intelligence, big data, and the Internet of Things, comprising: a data perception layer, including various IoT devices for collecting multimodal raw data; a blockchain layer, including a distributed digital identity system and a blockchain foundation layer, wherein the distributed digital identity system is used for identity authentication of data sources; an analysis and calculation layer, used to aggregate raw data into intermediate data according to subject, time, and operator dimensions; to perform real-time calculations on the intermediate data according to preset risk indicators to generate risk indicator values; and a decision layer, used to: match the generated risk indicator values ​​with multiple rule models generated based on artificial intelligence to generate risk assessment results; and to screen key intermediate data according to the risk assessment results, establish a correlation between the key intermediate data and the corresponding risk indicator values, risk assessment results, and decision information, and perform trusted storage through the blockchain foundation layer.

[0013] In one embodiment of the present invention, the blockchain layer is further configured to: in response to the decision information involving multi-departmental cooperation, provide cross-departmental data sharing and information interaction based on a distributed digital identity system and privacy-preserving data sharing technology.

[0014] In one embodiment of the present invention, the blockchain layer is further used to: automatically deploy multiple rule models based on smart contracts and on-chain / off-chain collaboration models; wherein the number of parameters of the rule models deployed based on smart contracts is less than the number of parameters of the rule models deployed based on on-chain / off-chain collaboration models.

[0015] Compared with existing technologies, the risk prevention and control method and system of the present invention, which integrates blockchain with artificial intelligence, big data and the Internet of Things, uses blockchain as the foundation of trust and combines it with distributed digital identity (DID) management and trusted evidence storage to ensure that the entire process from data source, processing to final result is trustworthy, tamper-proof and traceable, effectively solving the trust deficiency problem in existing technologies. Through intermediate data expression and calculation modes, the amount of data that needs to be processed and uploaded to the chain is significantly reduced, significantly lowering computational complexity and bridging the gap between real-time big data processing and blockchain performance, enabling millisecond-level real-time calculation and analysis of massive risk data. Through the automatic construction, fusion optimization and automated deployment of multi-dimensional intelligent rules, combined with real-time and trusted data, the accuracy and intelligence level of risk identification, assessment, prediction and early warning are significantly improved. While realizing data value mining and sharing, various technical means such as encryption, distributed storage, and privacy computing are used to effectively prevent data leakage and abuse, protecting data privacy and security. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of one embodiment of a risk prevention and control method integrating blockchain, artificial intelligence, big data, and the Internet of Things according to the present invention;

[0017] Figure 2 This is a schematic diagram of one embodiment of a risk prevention and control system that integrates blockchain, artificial intelligence, big data, and the Internet of Things according to the present invention. Detailed Implementation

[0018] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but it should be understood that the scope of protection of the present invention is not limited to the specific embodiments.

[0019] Unless otherwise expressly stated, throughout the specification and claims, the term "comprising" or its variations such as "including" or "comprises" shall be understood to include the stated elements or components without excluding other elements or other components.

[0020] like Figure 1The diagram illustrates a process of an embodiment of a risk control method based on blockchain integration with artificial intelligence, big data, and the Internet of Things, according to the present invention. Figure 1 The risk prevention and control method shown here, which integrates blockchain with artificial intelligence, big data, and the Internet of Things, includes the following steps:

[0021] Step 101: Collect multimodal raw data through IoT devices and the Internet, and use the distributed digital identity system of blockchain to authenticate the source of the data.

[0022] Step 102: Aggregate the multimodal raw data into intermediate data according to the dimensions of subject, time, and operator.

[0023] Step 103: Based on the preset risk indicators, perform real-time calculations on the intermediate data to generate risk indicator values.

[0024] Step 104: Match the generated risk indicator values ​​with multiple rule models generated based on artificial intelligence to generate risk assessment results.

[0025] In this embodiment, the risk assessment results include one or more of the following: risk level label, probability value, and treatment recommendations.

[0026] Step 105: Select key intermediate data based on the risk assessment results, establish a correlation between the key intermediate data and the corresponding risk indicator values, risk assessment results, and decision information, and perform trusted storage through the blockchain infrastructure layer.

[0027] It should be noted that the method provided by this invention, based on blockchain as a foundation of trust, combined with distributed digital identity (DID) management and trusted evidence storage, ensures that the entire process from data source, processing to final result is trustworthy, tamper-proof, and traceable, effectively solving the trust deficiency problem in existing technologies. Through intermediate data expression and computation modes, it significantly reduces the amount of data that needs to be processed and uploaded to the blockchain, significantly reducing computational complexity and bridging the gap between real-time big data processing and blockchain performance, achieving millisecond-level real-time computation and analysis of massive amounts of risk data. Through the automatic construction, fusion optimization, and automated deployment of multi-dimensional intelligent rules, combined with real-time and trusted data, it significantly improves the accuracy and intelligence level of risk identification, assessment, prediction, and early warning. While realizing data value mining and sharing, it effectively prevents data leakage and misuse by employing various technologies such as encryption, distributed storage, and privacy computing, protecting data privacy and security.

[0028] Optionally, the method further includes: in response to the decision information involving multi-departmental cooperation, providing cross-departmental data sharing and information interaction based on a blockchain-based distributed digital identity system and privacy-preserving data sharing technology.

[0029] This provides a secure, reliable, and efficient data sharing platform, breaking down information barriers between departments and regions, and promoting cross-organizational business collaboration and joint risk prevention and control.

[0030] Furthermore, a universal basic platform that deeply integrates multiple technologies will be built to provide unified technical support and interfaces for different types of risk prevention and control applications, and to provide technical support for the rapid development, deployment and expansion of applications.

[0031] Optionally, the device for collecting multimodal raw data includes one or more of the following: environmental sensors, surveillance cameras, mobile terminals, financial transaction terminals, and network behavior collection devices; the multimodal raw data includes one or more of the following: environmental monitoring data, public safety data, equipment operation data, economic activity data, and network behavior data.

[0032] This ensures the diversity and coverage of data collection sources.

[0033] Optionally, the method further includes storing the aggregated intermediate data into the blockchain base layer.

[0034] Therefore, by using intermediate data expression and computation modes, the amount of data that needs to be processed and uploaded to the blockchain is significantly reduced, computational complexity is significantly reduced, the gap between real-time big data processing and blockchain performance is bridged, and millisecond-level real-time computation and analysis of massive risk data is achieved.

[0035] Optionally, the preset risk indicators are matched with the rule model; and the step of performing real-time calculations on intermediate data based on the preset risk indicators to generate risk indicator values ​​includes: performing real-time calculation and analysis on the generated intermediate data stream to generate risk indicator values, wherein the real-time calculation and analysis includes at least one of the following: cascading merging, incremental calculation, distributed caching, and merging of associated timestamps.

[0036] Therefore, the required real-time analysis methods can be flexibly set according to the specific application scenarios corresponding to the application services, thereby improving the accuracy and flexibility of technical analysis.

[0037] Optionally, the subject dimension is defined as the entity from which the data originates, including the device number, user account, or organization identifier; the time dimension indicates the data window to be divided into slices according to a preset time unit; and the operator dimension indicates the calculation method used for the calculation.

[0038] Optionally, the method further includes: automatically deploying multiple rule models based on smart contracts and on-chain / off-chain collaboration models; wherein the number of parameters of the rule models deployed based on smart contracts is less than the number of parameters of the rule models deployed based on on-chain / off-chain collaboration models.

[0039] Therefore, depending on the different properties of the rule model, a suitable method can be flexibly selected between smart contract mechanisms (more accurate, less efficient) and on-chain / off-chain mechanisms (requires off-chain deployment, more efficient).

[0040] As an example scenario, an exemplary process can be provided here for applying the risk prevention and control method of the present invention, which integrates blockchain, artificial intelligence, big data, and the Internet of Things, to risk prevention and control.

[0041] Step 1, Trusted Data Collection and Identity Authentication: Collect multimodal risk data through IoT devices and the Internet, and at the same time use distributed digital identity (DID) management at the blockchain layer to authenticate the data source (device, user).

[0042] Step 2, Data Aggregation and Intermediate State Transformation: The collected raw time-series risk data is aggregated into intermediate state data in real time through the engine of the calculation and analysis layer according to predefined rules (based on subject, time, and operator dimensions).

[0043] Step 3, Real-time Calculation of Intermediate Data: Perform real-time incremental calculation and correlation analysis on the generated intermediate data stream, and calculate various risk indicators and characteristics according to the needs of the intelligent decision-making layer.

[0044] Step 4, Intelligent Rule Construction and Loading: The intelligent decision-making layer continuously learns and optimizes multi-risk rules from various data sources, and loads the optimized rules (or rule models) into the rule engine through an automated deployment mechanism.

[0045] Step 5, Intelligent Decision-Making and Risk Warning: The rule engine matches and infers the risk indicators calculated in real time with the loaded intelligent rules to determine the risk level and generate risk assessment, prediction or warning results.

[0046] Step Six: Result Storage and Trusted Sharing: Key intermediate data, risk warning results, decision logs, etc., are stored in a trusted manner through the blockchain infrastructure layer. If cross-departmental collaborative processing is required, relevant information is securely and reliably shared with authorized agencies through a privacy-preserving data sharing mechanism.

[0047] Step 7, Traceability and Auditing: Utilizing the immutability and traceability of blockchain, the entire process of risk event occurrence and handling is recorded and audited, supporting post-event analysis and accountability.

[0048] The above exemplary process can achieve the following beneficial technical effects:

[0049] (1) Improve data credibility and full traceability

[0050] Based on blockchain trust, and combined with distributed digital identity (DID) management and trusted evidence storage, the entire process from data source, processing to final result is trusted, tamper-proof, and traceable, effectively solving the trust deficiency problem in existing technologies.

[0051] (2) Achieve efficient and real-time data processing and analysis

[0052] By using intermediate-state data representation and computation modes, the amount of data that needs to be processed and uploaded to the blockchain is significantly reduced, computational complexity is significantly reduced, the gap between real-time big data processing and blockchain performance is bridged, and millisecond-level real-time computation and analysis of massive risk data is achieved.

[0053] (3) Enhance the accuracy and intelligence of risk prevention and control

[0054] By automatically constructing, integrating, optimizing, and deploying multiple intelligence rules, and combining them with real-time and reliable data, the accuracy and intelligence of risk identification, assessment, prediction, and early warning can be significantly improved.

[0055] (4) Protecting data security and privacy

[0056] While realizing the value mining and sharing of data, various technical means such as encryption, distributed storage, and privacy computing are used to effectively prevent data leakage and abuse, and protect data privacy and security.

[0057] (5) Break down information silos and promote collaborative governance.

[0058] It provides a secure, reliable, and efficient data sharing platform to break down information barriers between departments and regions, and promote cross-organizational business collaboration and joint risk prevention and control.

[0059] (6) Provide a unified and scalable infrastructure framework

[0060] Build a universal basic platform that deeply integrates multiple technologies, providing unified technical support and interfaces for different types of risk prevention and control applications, and providing technical support for the rapid development, deployment and expansion of applications.

[0061] like Figure 2 As shown, it illustrates an exemplary structure of an embodiment of a risk control system integrating blockchain, artificial intelligence, big data, and the Internet of Things according to the present invention. Figure 2 The risk control system shown is a blockchain-integrated artificial intelligence, big data, and Internet of Things system, comprising: a data perception layer 201, a blockchain layer 202, an analysis and computing layer 203, and a decision-making layer 204.

[0062] Optionally, it may include an application service layer 205. Application service layer 205 is used to build applications for specific social risk scenarios based on the capabilities provided by the underlying layer, such as anti-money laundering, anti-telecom fraud, network information content risk prevention and control, public safety incident early warning, and financial risk monitoring. It provides unified data interfaces, rule base interfaces, engine interfaces, and on-chain evidence storage interfaces for different applications, supporting rapid application construction and deployment.

[0063] The data sensing layer, comprising various IoT devices and the internet, is used to collect multimodal raw data. It is structured based on Internet of Things (IoT) technology. This layer can include various sensors, monitoring equipment, mobile terminals, etc., to broadly collect multimodal and heterogeneous data related to risks in social operations. Data sources can include environmental monitoring data, equipment operation data, network behavior data, public safety data, economic activity data, etc., ensuring the diversity and coverage of data collection sources.

[0064] The blockchain layer includes a distributed digital identity system and a blockchain infrastructure layer. The distributed digital identity system is used to authenticate the source of data.

[0065] The analysis and calculation layer is used to aggregate the raw data into intermediate data according to the dimensions of subject, time, and operator; and to perform real-time calculations on the intermediate data based on preset risk indicators to generate risk indicator values.

[0066] The steps to aggregate raw data into intermediate data by subject, time, and operator dimensions. For example, the results of a certain subject (such as device or account) for a certain risk calculation operator (such as summation, count, or variance) within a specific time slice (such as minute or hour) are aggregated and stored.

[0067] The method involves calculating intermediate data in real time based on preset risk indicators to generate risk indicator values. For example, the number of requests initiated by a terminal device to a server every 12 hours can be used as a risk indicator value.

[0068] The decision-making layer is used to: match the generated risk indicator values ​​with multiple rule models generated based on artificial intelligence to generate risk assessment results; and to select key intermediate data based on the risk assessment results, establish a correlation between the key intermediate data and the corresponding risk indicator values, risk assessment results, and decision information, and to perform trusted storage through the blockchain infrastructure layer.

[0069] Optionally, the blockchain layer is also used to: in response to the decision information involving multi-departmental cooperation, provide cross-departmental data sharing and information interaction based on a distributed digital identity system and privacy-preserving data sharing technology.

[0070] Optionally, the blockchain layer is also used to: automatically deploy multiple rule models based on smart contracts and on-chain / off-chain collaboration models.

[0071] The number of parameters in the rule model deployed based on smart contracts is less than the number of parameters in the rule model deployed based on the on-chain / off-chain collaboration model.

[0072] As an example, the application of the method or system provided by this invention in social governance and risk prevention and control can be introduced here. Social governance and risk prevention and control simultaneously meet the multi-objective requirements of high reliability, high real-time performance, high accuracy, and intelligence, which cannot be achieved by relying solely on single technologies such as blockchain, big data, and artificial intelligence.

[0073] Therefore, in response to the core problems existing in the social risk prevention and control system, such as insufficient credibility, lagging real-time performance, limited intelligence level, and obstacles to the integration of multiple technologies, this paper proposes a social risk prevention and control method and system that takes blockchain technology as the core and deeply integrates artificial intelligence, big data, and Internet of Things technologies.

[0074] The method or system provided by this invention effectively integrates technologies such as big data, blockchain, and artificial intelligence, and leverages the synergistic effect of these technologies to support the multi-objective requirements of social risk governance and prevention for high reliability, high real-time performance, high accuracy, and intelligence.

[0075] The Internet of Things (IoT) technology enables the automatic collection and transmission of social risk data; blockchain technology can solve the problems of full traceability and authenticity after data is uploaded to the chain; big data technology can enable the dynamic processing and analysis of massive heterogeneous social risk data; the application research of artificial intelligence technology in the multi-level construction, integration optimization and automatic deployment of multi-dimensional and heterogeneous risk prevention and control rules is still imperfect, and it is necessary to combine blockchain, big data and other technologies to further improve the credibility of social risk data and the interpretability of risk prevention and control rules; the Internet of Things (IoT) technology enables the automatic collection and transmission of social risk data.

[0076] Optionally, a trusted data sharing mechanism across departments and regions can be built using blockchain to break down information silos between traditional systems and ensure the authenticity, integrity, and traceability of data throughout its entire lifecycle.

[0077] Optionally, distributed digital identity, encryption algorithms, and privacy computing technologies can be used to achieve secure protection and controllable sharing of data throughout the entire process.

[0078] Optionally, to address the challenge of processing massive heterogeneous data, an innovative intermediate data processing mode based on the dimensions of subject, time, and operator is designed. Combined with incremental computing technology, it effectively bridges the performance gap between blockchain and big data and AI, achieving millisecond-level response for risk monitoring.

[0079] Optionally, at the intelligent decision-making level, a multi-dimensional intelligent rule system, including knowledge rules, feature rules, neural rules, and graph rules, can be integrated to construct a dynamically optimized intelligent engine, significantly improving the accuracy of risk identification and prediction.

[0080] Through architecture-level converged design, the real-time sensing of the Internet of Things, the efficient processing of big data, and the intelligent analysis capabilities of AI are integrated on the trusted foundation of blockchain to form a mutually empowering collaborative technology framework. This provides support for building a highly reliable, real-time, and accurate unified and scalable social risk prevention and control platform, and effectively solving the problem of functional fragmentation and performance overlap of multiple technology systems.

[0081] The social risk prevention and control system proposed in this invention is based on blockchain as its core and trust foundation. It can be roughly divided into a data perception layer, a blockchain foundation layer, a computing and analysis layer, an intelligent decision-making layer, and an application service layer from bottom to top.

[0082] (1) Data perception layer

[0083] Utilizing Internet of Things (IoT) technology, including various sensors, monitoring devices, and mobile terminals, we extensively collect multimodal and heterogeneous data related to risks in social operations. Data sources can include environmental monitoring data, equipment operation data, network behavior data, public safety data, and economic activity data. The key is to ensure the diversity and coverage of data collection sources.

[0084] (2) Blockchain Foundation Layer

[0085] Build an independent and controllable (consortium) blockchain platform as the trusted infrastructure for the entire system.

[0086] Distributed Digital Identity (DID) management provides blockchain-based distributed digital identity registration, verification, and management services for various entities (individuals, devices, and organizations) participating in the system, solving the problem of identity theft and ensuring the trustworthiness of interacting entities.

[0087] This privacy-preserving data sharing mechanism combines cryptographic techniques such as zero-knowledge proofs and secure multi-party computation with access control strategies to achieve secure, usable, but invisible sharing of data across entities and departments, breaking down data silos while protecting data privacy. Data interaction records are uploaded to the blockchain to ensure transparency and traceability throughout the process.

[0088] Trusted evidence storage provides tamper-proof and traceable on-chain evidence storage services for critical data (or its hash), risk events, processing logs, rule models, etc.

[0089] (3) Calculation and Analysis Layer

[0090] The computational analysis layer is a key layer connecting massive amounts of data with the blockchain, and its core lies in an innovative intermediate data processing model.

[0091] The intermediate-state data representation model addresses the massive amounts of raw risk data generated by the Internet of Things (IoT) by not directly uploading all of it to the blockchain. Instead, it designs a novel "intermediate-state" data representation structure. This structure extracts and aggregates features from the raw data across three dimensions: subject, time, and operator. For example, it aggregates and stores the results of a specific risk calculation operator (such as summation, counting, or variance) for a particular subject (e.g., device, account) within a specific time slice (e.g., minute, hour).

[0092] The intermediate-state data real-time computing engine, based on an intermediate-state representation model, achieves efficient real-time computation. Utilizing techniques such as cascading merging, incremental computation, distributed caching, and associated timestamp merging, it supports real-time (sub-second) computation and dynamic tracking of arbitrary time windows and complex risk operators. Computation results or their summary information are uploaded to the blockchain.

[0093] (4) Intelligent Decision-Making Layer

[0094] By integrating artificial intelligence technology, we can achieve intelligent risk analysis and decision-making.

[0095] Multiple intelligence rule construction automatically extracts and expresses diverse risk prevention and control rules, such as knowledge rules, feature rules, neural rules, and graph rules, from expert knowledge, machine learning models, deep learning models, and temporal correlation graphs through induction and learning.

[0096] Rule fusion and optimization employs methods such as ensemble learning to intelligently fuse and combine diverse rules adapted to different data types and scenarios to achieve optimal results, eliminating ambiguity and conflict, and forming the optimal set of decision rules.

[0097] This research focuses on automated rule deployment and execution, exploring mechanisms based on smart contracts (suitable for low-parameter rules) and on-chain / off-chain collaboration (suitable for high-parameter, complex models, such as off-chain fine-tuning of pre-trained models using privacy data). The rule engine performs online inference based on intermediate data provided by the real-time computing layer and the fused rules, enabling real-time risk assessment, prediction, and early warning.

[0098] (5) Application Service Layer

[0099] Based on the underlying capabilities, applications can be built for specific social risk scenarios, such as anti-money laundering, anti-telecom fraud, online information content risk prevention and control, public safety incident early warning, and financial risk monitoring. Unified data interfaces, rule base interfaces, engine interfaces, and on-chain evidence storage interfaces are provided for different applications, supporting rapid application construction and deployment.

[0100] The foregoing description of specific exemplary embodiments of the invention is for illustrative and explanatory purposes. These descriptions are not intended to limit the invention to the precise forms disclosed, and it will be apparent that many changes and variations can be made in accordance with the foregoing teachings. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application, thereby enabling those skilled in the art to implement and utilize various different exemplary embodiments of the invention, as well as various different choices and variations. The scope of the invention is intended to be defined by the claims and their equivalents.

Claims

1. A risk prevention and control method integrating blockchain, artificial intelligence, big data, and the Internet of Things, characterized in that, Includes the following steps: Collect multimodal raw data through IoT devices and the Internet, and use blockchain's distributed digital identity system to authenticate the data source; The multimodal raw data is aggregated into intermediate data according to the dimensions of subject, time, and operator; Based on preset risk indicators, intermediate data are calculated in real time to generate risk indicator values. The generated risk indicator values ​​are matched with multiple rule models generated based on artificial intelligence to generate risk assessment results, wherein the risk assessment results include one or more of the following: risk level labels, probability values ​​and disposal recommendations; Based on the risk assessment results, key intermediate data are selected, and a correlation is established between the key intermediate data and the corresponding risk indicator values, risk assessment results, and decision information. The data is then stored in a trusted manner through the blockchain infrastructure layer.

2. The risk prevention and control method integrating blockchain, artificial intelligence, big data, and the Internet of Things as described in claim 1, characterized in that, The method further includes: In response to the fact that the decision-making information involves cooperation among multiple departments, a distributed digital identity system based on blockchain and privacy-preserving data sharing technology provides data sharing and information interaction between cross-departmental entities.

3. The risk prevention and control method integrating blockchain, artificial intelligence, big data, and the Internet of Things as described in claim 1, characterized in that, The devices for collecting multimodal raw data include one or more of the following: environmental sensors, surveillance cameras, mobile terminals, financial transaction terminals, and network behavior acquisition devices; The multimodal raw data includes one or more of the following: environmental monitoring data, public safety data, equipment operation data, economic activity data, and network behavior data.

4. The risk prevention and control method for blockchain integration with artificial intelligence, big data, and the Internet of Things as described in claim 1, characterized in that, The method further includes: The aggregated intermediate data is stored in the blockchain base layer.

5. The risk prevention and control method for blockchain integration with artificial intelligence, big data, and the Internet of Things as described in claim 4, characterized in that, The preset risk indicators are matched with the rule model; as well as The step of generating risk indicator values ​​by real-time calculation of intermediate data based on preset risk indicators includes: The generated intermediate data stream is subjected to real-time calculation and analysis to generate risk indicator values. The real-time calculation and analysis includes at least one of the following: cascading merging, incremental calculation, distributed caching, and merging of associated timestamps.

6. The risk prevention and control method for blockchain integration with artificial intelligence, big data, and the Internet of Things as described in claim 1, characterized in that, The subject dimension is defined as the entity from which the data originates, including device number, user account, or organization identifier; The time dimension indicates that the data window is divided into slices based on preset time units; Operator dimension indicates the computational method used.

7. The risk prevention and control method for blockchain integration with artificial intelligence, big data, and the Internet of Things as described in claim 1, characterized in that, The method further includes: Based on smart contracts and on-chain / off-chain collaboration models, multiple rule models are automatically deployed. The number of parameters in the rule model deployed based on smart contracts is less than the number of parameters in the rule model deployed based on the on-chain / off-chain collaboration model.

8. A risk prevention and control system integrating blockchain, artificial intelligence, big data, and the Internet of Things, characterized in that, include: The data sensing layer includes various IoT devices used to collect multimodal raw data; The blockchain layer includes a distributed digital identity system and a blockchain infrastructure layer. The distributed digital identity system is used to authenticate the source of data. The analysis and calculation layer is used to aggregate raw data into intermediate data according to the dimensions of subject, time, and operator; and to perform real-time calculations on the intermediate data based on preset risk indicators to generate risk indicator values. The decision-making layer is used to: match the generated risk indicator values ​​with multiple rule models generated based on artificial intelligence to generate risk assessment results; and to select key intermediate data based on the risk assessment results, establish a correlation between the key intermediate data and the corresponding risk indicator values, risk assessment results, and decision information, and to perform trusted storage through the blockchain infrastructure layer.

9. The risk prevention and control system integrating blockchain, artificial intelligence, big data, and the Internet of Things as described in claim 8, characterized in that, The blockchain layer is also used to: in response to the decision information involving cooperation among multiple departments, provide cross-departmental data sharing and information interaction based on a distributed digital identity system and privacy-preserving data sharing technology.

10. The risk prevention and control system integrating blockchain, artificial intelligence, big data, and the Internet of Things as described in claim 8, characterized in that, The blockchain layer is also used to: automatically deploy multiple rule models based on smart contracts and on-chain / off-chain collaboration models; The number of parameters in the rule model deployed based on smart contracts is less than the number of parameters in the rule model deployed based on the on-chain / off-chain collaboration model.

Images