WO2024183439A1 - Data processing method and apparatus, and computation device - Google Patents

Abstract

A data processing method and apparatus, and a computation device. The method comprises: a first blockchain node receives task information and sends the task information to a task execution device, wherein the task execution device is used for performing inference computation on a first model according to the task information to obtain an inference result for the first model; the task execution device sends the inference result to a trusted execution environment (TEE) for verification to obtain a verified inference result; and the node in a blockchain system performs on-chain storage on the inference result verified by the TEE. The method can improve the credibility of off-chain computation, and promote the convergence and development of the blockchain technology and the artificial intelligence technology.

Description

Data processing method, device and computing equipment

This application claims the priority of the Chinese patent application filed with the State Intellectual Property Office of China on March 9, 2023, with application number 202310226446.5 and application name “Method and computing device for smart contract computing based on a trusted execution environment”, and the priority of the Chinese patent application filed with the State Intellectual Property Office of China on April 20, 2023, with application number 202310432135.4 and application name “Method, device and computing device for data processing”, all of which are incorporated by reference into this application.

Technical Field

The present application relates to the field of cloud computing, and more specifically, to a data processing method, apparatus, and computing device.

Background Art

Since the birth of blockchain technology, after years of rapid development, it has been widely used in various industries such as finance, supply chain, and e-government. It has become the core technology to promote the transformation of information Internet to value Internet, and has attracted widespread attention from all over the world. Today, blockchain technology has become the focus of attention and research in countries around the world. Due to the characteristics of blockchain that cannot be tampered with and transparent development, blockchain-based artificial intelligence (BC-AI) is expected to further promote the training and reasoning of trusted distributed artificial intelligence. For example, blockchain technology is used to protect the data of neural network (NN) models from being tampered with, so promoting the integration and development of blockchain technology and artificial intelligence technology has become a new research hotspot. However, due to the lack of complex computing capabilities of existing mainstream smart contracts, blockchain nodes cannot handle complex tasks, resulting in the inference of neural network models (for example, deep neural network (DNN) models) cannot be directly executed in the blockchain network through smart contracts, which limits the application scope and further development of blockchain-based artificial intelligence.

In related technical solutions, since blockchain nodes cannot handle complex tasks, the model reasoning process is offloaded from the blockchain network to nearby edge servers to request the use of their powerful hardware to perform the model reasoning calculation process. This technology cannot guarantee the security and credibility of off-chain computing, the external platform for off-chain model reasoning is not trusted, and the credibility of the returned reasoning results cannot be guaranteed.

Therefore, how to improve the credibility of off-chain computing and promote the integrated development of blockchain technology and artificial intelligence technology has become a technical problem that needs to be solved urgently.

Summary of the invention

The present application provides a data processing method, apparatus, and computing device, which can improve the credibility of off-chain computing and promote the integrated development of blockchain technology and artificial intelligence technology.

In a first aspect, a method for data processing is provided, which is applied to a cloud blockchain system, wherein the cloud blockchain system includes multiple blockchain nodes, a cloud computing platform deploys the cloud blockchain system in the cloud computing resources it manages, and the cloud computing platform deploys blockchain services in the cloud computing resources. The method includes: a first blockchain node receives task information, and the first blockchain node is a node in the cloud blockchain system; the first blockchain node sends the task information to a task execution device, which is a server outside the cloud blockchain system, and the task execution device is used to perform inference calculation on a first model according to the task information to obtain an inference result of the first model, and the input of the first model includes the task information; the task execution device sends the inference result to a trusted execution environment TEE for verification to obtain a verified inference result; the first blockchain node obtains the verified inference result from the TEE and stores it on the chain; other nodes in the cloud blockchain system re-verify the verified inference result through their respective corresponding TEEs, and store the re-verified inference result on the chain.

In the above technical solution, the results of model inference performed on servers outside the blockchain network are verified through TEE, and the verified results are stored on the chain through blockchain nodes. In this way, blockchain technology can be used to protect the reasoning data of artificial intelligence from being tampered with, thereby promoting the integrated development of blockchain technology and artificial intelligence technology.

In combination with the first aspect, in certain implementations of the first aspect, the task execution device is a first server, which communicates with the first blockchain node. The first server is used to perform inference calculations on the first model based on the task information to obtain an inference result of the first model, and the first server sends the inference result to the TEE for verification.

In combination with the first aspect, in some implementations of the first aspect, the task execution device is the TEE, and the TEE communicates with the first server. The method also includes: the first server receives the task information sent by the first blockchain node; the first server sends the task information to the TEE, and the TEE is used to perform inference calculation on the first model according to the task information to obtain the inference result of the first model, and verify the inference result to obtain the verified inference result.

In combination with the first aspect, in certain implementations of the first aspect, the task execution device is an edge server, and the method also includes: the first server or the TEE sends the task information to the edge server, and the edge server performs inference calculations on the first model based on the task information to obtain an inference result of the first model; the edge server sends the inference result to the TEE for verification.

In combination with the first aspect, in certain implementations of the first aspect, the TEE is deployed on the first blockchain node.

In a second aspect, a method for data processing is provided, including: a first blockchain node receives task information, the first blockchain node is a node in the blockchain system; the first blockchain node sends the task information to a task execution device, the task execution device is a server outside the blockchain system, the task execution device is used to perform inference calculation on a first model according to the task information to obtain an inference result of the first model, and the input of the first model includes the task information; the task execution device sends the inference result to a trusted execution environment TEE for verification to obtain a verified inference result; the first blockchain node obtains the verified inference result from the TEE and stores it on the chain; other nodes in the blockchain system re-verify the verified inference result through their respective corresponding TEEs, and store the re-verified inference result on the chain.

In combination with the second aspect, in certain implementations of the second aspect, the task execution device is a first server, which communicates with the first blockchain node. The first server is used to perform inference calculations on the first model based on the task information to obtain an inference result of the first model, and the first server sends the inference result to the TEE for verification.

In combination with the second aspect, in certain implementations of the second aspect, the task execution device is the TEE, and the TEE communicates with the first server. The method also includes: the first server receives the task information sent by the first blockchain node; the first server sends the task information to the TEE, and the TEE is used to perform inference calculations on the first model based on the task information to obtain an inference result of the first model, and verify the inference result to obtain the verified inference result.

In combination with the second aspect, in certain implementations of the second aspect, the task execution device is an edge server, and the method also includes: the first server or the TEE sends the task information to the edge server, and the edge server performs inference calculations on the first model based on the task information to obtain an inference result of the first model; the edge server sends the inference result to the TEE for verification.

In combination with the second aspect, in certain implementations of the second aspect, the TEE is deployed on the first blockchain node.

In a third aspect, a data processing system is provided, which includes a cloud blockchain system, a task execution device and a trusted execution environment TEE. The cloud blockchain system includes multiple blockchain nodes, including a first blockchain node. The cloud computing platform deploys the cloud blockchain system in the cloud computing resources it manages, and the cloud computing platform deploys storage services in the cloud computing resources. The system includes: the first blockchain node is used to receive task information and send the task information to the task execution device, which is a server outside the cloud blockchain system. The task execution device is used to perform inference calculation on a first model according to the task information to obtain an inference result of the first model, and the input of the first model includes the task information; the task execution device is used to send the inference result to the trusted execution environment TEE; the TEE is used to verify the inference result to obtain the verified inference result; the first blockchain node is used to obtain the verified inference result from the TEE and store it on the chain; other nodes in the cloud blockchain system are used to re-verify the verified inference result through their respective corresponding TEEs, and store the re-verified inference result on the chain.

In combination with the third aspect, in certain implementations of the third aspect, the task execution device is a first server, which communicates with the first blockchain node. The first server is used to perform inference calculations on the first model based on the task information to obtain an inference result of the first model. The first server is specifically used to send the inference result to the TEE for verification.

In combination with the third aspect, in certain implementations of the third aspect, the task execution device is the TEE, which communicates with the first server, and the first server is used to receive the task information sent by the first blockchain node and send the task information to the TEE. The TEE is used to perform inference calculations on the first model based on the task information to obtain an inference result of the first model, and verify the inference result to obtain the verified inference result.

In combination with the third aspect, in certain implementations of the third aspect, the task execution device is an edge server, and the first server or the TEE is used to send the task information to the edge server; the edge server is used to perform inference calculations on the first model based on the task information, obtain the inference result of the first model, and send the inference result to the TEE for verification.

In combination with the third aspect, in certain implementations of the third aspect, the TEE is deployed on the first blockchain node.

In a fourth aspect, a computing device is provided, comprising a processor and a memory, and optionally, an input/output interface. The processor is used to control the input/output interface to send and receive information, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the method in the first aspect or any possible implementation of the first aspect is executed, or the method in the second aspect is executed. A method in any possible implementation manner of the first aspect or the second aspect.

Optionally, the processor may be a general-purpose processor, which may be implemented by hardware or software. When implemented by hardware, the processor may be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor may be a general-purpose processor implemented by reading software code stored in a memory, which may be integrated in the processor or located outside the processor and exist independently.

In a fifth aspect, a computing device cluster is provided, comprising at least one computing device, each computing device comprising a processor and a memory; the processor of the at least one computing device is used to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster executes the method in the first aspect or any possible implementation of the first aspect, or executes the method in the second aspect or any possible implementation of the second aspect.

In a sixth aspect, a chip is provided, which obtains instructions and executes the instructions to implement the method in the above-mentioned first aspect and any one of the implementations of the first aspect, or executes the method in the second aspect or any one of the possible implementations of the second aspect.

Optionally, as an implementation manner, the chip includes a processor and a data interface, and the processor reads instructions stored in the memory through the data interface to execute the method in the above-mentioned first aspect and any implementation manner of the first aspect.

Optionally, as an implementation method, the chip may also include a memory, in which instructions are stored, and the processor is used to execute the instructions stored in the memory. When the instructions are executed, the processor is used to execute the method in the first aspect and any one of the implementation methods of the first aspect.

In the seventh aspect, a computer program product comprising instructions is provided. When the instructions are executed by a computing device, the computing device executes the method in the first aspect and any one of the implementations of the first aspect, or executes the method in the second aspect or any one of the possible implementations of the second aspect.

In an eighth aspect, a computer program product comprising instructions is provided. When the instructions are executed by a computing device cluster, the computing device cluster executes the method in the first aspect and any one of the implementations of the first aspect, or executes the method in the second aspect or any one of the possible implementations of the second aspect.

In the ninth aspect, a computer-readable storage medium is provided, comprising computer program instructions. When the computer program instructions are executed by a computing device, the computing device executes the method in the first aspect and any one of the implementations of the first aspect, or executes the method in the second aspect or any one of the possible implementations of the second aspect.

As examples, these computer-readable storages include, but are not limited to, one or more of the following: read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), Flash memory, electrically EPROM (EEPROM), and hard drive.

Optionally, as an implementation manner, the above-mentioned storage medium may specifically be a non-volatile storage medium.

In the tenth aspect, a computer-readable storage medium is provided, comprising computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster executes the method in the first aspect and any one of the implementations of the first aspect, or executes the method in the second aspect or any one of the possible implementations of the second aspect.

As examples, these computer-readable storages include, but are not limited to, one or more of the following: read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), Flash memory, electrically EPROM (EEPROM), and hard drive.

Optionally, as an implementation manner, the above-mentioned storage medium may specifically be a non-volatile storage medium.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic block diagram of a cloud scenario applicable to an embodiment of the present application.

FIG. 2 is a schematic flow chart of a data processing method applicable to an embodiment of the present application.

FIG3 is a schematic block diagram of a relay server performing task scheduling provided in an embodiment of the present application.

FIG. 4 is a schematic block diagram of a data processing device 400 provided in an embodiment of the present application.

FIG5 is a schematic diagram of the architecture of a computing device 1500 provided in an embodiment of the present application.

FIG. 6 is a schematic diagram of the architecture of a computing device cluster provided in an embodiment of the present application.

FIG. 7 is a schematic diagram of a connection between computing devices 1500A and 1500B via a network provided in an embodiment of the present application.

DETAILED DESCRIPTION

The technical solution in this application will be described below in conjunction with the accompanying drawings.

The present application will present various aspects, embodiments or features around a system including multiple devices, components, modules, etc. It should be understood and appreciated that each system may include additional devices, components, modules, etc., and/or may not include all devices, components, modules, etc. discussed in conjunction with the figures. In addition, combinations of these schemes may also be used.

In addition, in the embodiments of the present application, words such as "exemplary" and "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present concepts in a concrete way.

In the embodiments of the present application, “corresponding” and “relevant” may sometimes be used interchangeably. It should be noted that when the distinction between them is not emphasized, the meanings they intend to express are consistent.

The business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. A person of ordinary skill in the art can appreciate that, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

References to "one embodiment" or "some embodiments" etc. described in this specification mean that a particular feature, structure or characteristic described in conjunction with the embodiment is included in one or more embodiments of the present application. Thus, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

In the present application, "at least one" means one or more, and "plurality" means two or more. "And/or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and/or B can mean: including the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character "/" generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, c can be single or multiple.

To facilitate understanding, relevant terms and concepts that may be involved in the embodiments of the present application are first introduced below.

1. Blockchain

Blockchain technology is a decentralized architecture and computing paradigm that uses block chain data structures to verify and store data, distributed node consensus algorithms to generate and update data, cryptography to ensure the security of data transmission and access, and smart contracts composed of automated script codes to program and operate data. Blockchain is a special distributed database with no central point, and information is stored in all nodes that join the blockchain network.

2. Blockchain Node

The nodes in the blockchain network can be called blockchain nodes, which can be a server, laptop, mobile phone, etc. Each blockchain node stores information in the form of blockchain, and the information stored in all nodes added to the blockchain network is consistent and synchronized. If one or two nodes are broken, the information will not be lost and can still be viewed on other nodes.

3. Trusted execution environment (TEE)

A system is deployed on a mobile device, and the system includes a trusted execution environment (TEE). TEE is an independent, isolated, secure operating environment within the mobile device (e.g., a smartphone, tablet, smart TV, etc.). Since TEE provides an isolated environment to store the user's sensitive information (e.g., the user's code and data), TEE provides a more secure space for the execution of code and data, and ensures the confidentiality and security of the user's sensitive information (e.g., the user's code and data).

Optionally, the mobile device may be a desktop computer, a notebook, a mobile phone, a tablet computer, a smart watch, a smart bracelet, etc., which is not specifically limited in this application.

Applications running on TEE are called trusted applications (TA). TEE divides independent trusted zones in the processor (e.g., central processing unit (CPU)) and memory, and isolates different TAs in the processor and memory to prevent different TAs from reading and accessing data from each other at will. TAs running in TEE can access the full functionality of the device's main processor and memory, while hardware isolation protects these components from being affected by user-installed applications running in the main operating system.

4. Software Guard Extension (SGX)

SGX is a new extension of Intel architecture, which adds a new set of instruction sets and memory access mechanisms to the original architecture. These extensions allow applications to implement a container called an enclave. In order to prevent different TAs from reading and accessing data at will, the basic input output system (BIOS) can be used to divide independent protected enclaves in the address space of the application. The area is used as an enclave. The data in the enclave is encrypted and cannot be viewed by the kernel or the hypervisor. Therefore, SGX can not only isolate the data of different TAs in memory, but also encrypt the data in the memory enclave. In this way, developers can divide applications into enclaves or executable protection areas in memory, which can improve security even in attacked platforms. Using this new application-layer trusted execution environment, developers can enable identity and record privacy, secure browsing and digital management protection (DRM), or any high-security application scenario that requires secure storage of secrets or protection of data.

The implementation of SGX requires the collaboration of hardware and software such as processors, memory management components, BIOS, drivers, and runtime environments.

5. Enclave

Encapsulate the security operations of legitimate software in an enclave to protect it from malware attacks, and neither privileged nor non-privileged software can access the enclave. In other words, once the software and data are in the enclave, even the operating system or virtual machine manager (VMM) cannot affect the code and data in the enclave.

6. Artificial Intelligence

Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making. Research in the field of artificial intelligence includes robotics, natural language processing, computer vision, decision-making and reasoning, human-computer interaction, recommendation and search, basic AI theory, etc.

7. Neural Networks

Neural networks (NN) are complex network systems formed by a large number of simple processing units (called neurons) that are widely interconnected. The neural network model is described based on the mathematical model of neurons. The neural network model is represented by network topology, node characteristics and learning rules.

Since the birth of blockchain technology, after years of rapid development, it has been widely used in various industries such as finance, supply chain, e-government, etc., becoming the core technology to promote the transformation of information Internet to value Internet, and has attracted widespread attention from all over the world. Today, blockchain technology has become the focus of attention and research in countries around the world.

Due to the characteristics of blockchain that it cannot be tampered with and is transparent to development, blockchain-based artificial intelligence (BC-AI) is expected to further promote the training and reasoning of trusted distributed artificial intelligence. For example, blockchain technology can be used to protect the data of neural networks (NN) models from being tampered with. Therefore, promoting the integration and development of blockchain technology and artificial intelligence technology has become a new research hotspot.

However, the existing mainstream smart contracts lack the ability to perform complex calculations, which makes it impossible for blockchain nodes to handle complex tasks. As a result, neural network model reasoning (for example, deep neural network (DNN) model) cannot be directly executed in the blockchain network through smart contracts, which limits the application scope and further development of blockchain-based artificial intelligence.

In related technical solutions, since blockchain nodes cannot handle complex tasks, the model reasoning process is offloaded from the blockchain network to nearby edge servers to request the use of their powerful hardware to perform the model reasoning calculation process. This technology cannot guarantee the security and credibility of off-chain computing, the external platform for off-chain model reasoning is not trusted, and the credibility of the returned reasoning results cannot be guaranteed.

In view of this, an embodiment of the present application provides a data processing method, which can verify the results of model reasoning performed on a server outside the blockchain network through TEE, and store the verified results on the chain through the blockchain node. In this way, it is possible to protect the reasoning data of artificial intelligence from being tampered with through blockchain technology, thereby promoting the integrated development of blockchain technology and artificial intelligence technology.

In a possible implementation, the method provided in the embodiment of the present application can be applied to a cloud service scenario, and the method is executed by a cloud management platform in the cloud service scenario. For ease of description, the cloud service scenario is described in detail below in conjunction with FIG.

Fig. 1 is a schematic block diagram of a cloud scenario applicable to an embodiment of the present application. As shown in Fig. 1 , the cloud scenario may include: a cloud management platform 110 , the Internet 120 , and a client 130 .

As shown in Fig. 1, the cloud management platform 110 is used to manage the infrastructure that provides multiple cloud services. The infrastructure includes multiple cloud data centers, each of which includes multiple servers, each of which includes cloud service resources to provide corresponding cloud services to tenants.

The cloud management platform 110 may be located in a cloud data center and may provide an access interface (such as an interface or an application program interface (API)). The tenant may operate the client 130 to remotely access the access interface to register a cloud account and password on the cloud management platform 110 and log in to the cloud management platform 110. After the cloud management platform 110 successfully authenticates the cloud account and password, the tenant may further pay to select and purchase a virtual machine with specific specifications (processor, memory, disk) on the cloud management platform 110. After the payment is successful, the cloud management platform 110 provides The client 130 can remotely log in to the virtual machine and install and run the tenant's application in the virtual machine. Therefore, the tenant can create, manage, log in and operate the virtual machine in the cloud data center through the cloud management platform 110. The virtual machine can also be called a cloud server (elastic compute service, ECS) or an elastic instance (different cloud service providers have different names).

It should be understood that tenants of cloud services can be individuals, enterprises, schools, hospitals, administrative agencies, etc.

The functions of the cloud management platform 110 include, but are not limited to, user console, computing management service, network management service, storage management service, authentication service, and image management service. The user console provides an interface or API to interact with tenants, the computing management service is used to manage servers running virtual machines and containers and bare metal servers, the network management service is used to manage network services (such as gateways, firewalls, etc.), the storage management service is used to manage storage services (such as data bucket services), the authentication service is used to manage tenant accounts and passwords, and the image management service is used to manage virtual machine images. Tenants can use the client 130 to log in to the cloud management platform 110 through the Internet 120 to manage the rented cloud services.

Fig. 2 is a schematic flow chart of a data processing method provided in an embodiment of the present application. As shown in Fig. 2, the method may include steps 210-260, and steps 210-260 are described in detail below.

Step 210: The blockchain network receives the task information submitted by the user.

As an example, a blockchain network may include multiple blockchain nodes, and the blockchain network may receive task information submitted by a user. Specifically, a blockchain node (e.g., a first blockchain node) in the blockchain network may receive task information submitted by a user. In a possible implementation, the task parameter may be, for example, input information of a model (e.g., a first neural network model).

The embodiments of the present application do not specifically limit the blockchain network (or blockchain platform), which may include but is not limited to: a public blockchain network, a private blockchain network, a consortium chain, etc.

Step 220: The blockchain network establishes a trusted connection with the external server and sends task information to the external server.

As an example, a blockchain network can establish a trusted connection with an external server, which can be a separate physical server outside the blockchain network. After the blockchain network and the external server establish a trusted connection, the blockchain network can send the task information received from the user to the external server for processing. Specifically, a blockchain node (e.g., a first blockchain node) that receives the task information in the blockchain network can establish a trusted connection with the external server, and the first blockchain node can send the task information to the external server for processing.

The embodiments of the present application do not specifically limit the communication method and communication protocol between the blockchain network and the external server. In one possible implementation, the communication between the blockchain network and the external server uses the Google Remote Procedure Call (gRPC) protocol, and the first blockchain node in the blockchain network sends the task information to the external server through the gRPC protocol.

For example, taking the blockchain network as a consortium chain and the external server as a relay server, the consortium chain code that writes the outsourced task in the first blockchain node acts as the client, and the relay server acts as the server, and the task information is transmitted through the gRPC protocol. For example, the task information includes task parameters. After the user submits the task parameters, the chain code client of the first blockchain node establishes a gRPC connection with the relay server, and serializes the task parameters and sends them to the relay server. After receiving the response message from the relay server, the chain code client of the first blockchain node ends the gRPC interaction and stores the task information on the chain.

Step 230: The external server performs inference calculation according to the task information to obtain the result of the inference calculation.

In the embodiment of the present application, after receiving the task information sent by the blockchain network, the external server can perform inference calculation based on the task information. For example, the task information can be used as an input parameter of a model (e.g., a first neural network model) and perform inference calculation of the model.

For ease of description, an external server is used as a relay server as an example for explanation below.

As an example, after the relay server receives the serialized task parameters sent by the blockchain network, it can deserialize the serialized task parameters, restore the task parameters, and perform inference calculations on a model (e.g., a first neural network model) based on the task parameters.

In one possible implementation, the relay server has a certain computing power, and the relay server can complete the inference calculation of the model (for example, the first neural network model) by itself. As an example, the relay server schedules the task and distributes it to the task execution device worker to perform the inference calculation of the model (for example, the first neural network model). For example, as shown in Figure 3, the relay server adds the Celery distributed asynchronous task framework to perform task scheduling. After the relay server receives the request submitted by the chain code, it deserializes the data to restore the task parameters, and then encapsulates the task request and puts it into the Celery message middleware (message broker) asynchronous queue. The task execution device worker takes the task from the broker queue to perform the inference calculation of the model (for example, the first neural network model). The worker here can be understood as a process.

In another possible implementation, if the computing power of the relay server is insufficient to support the complete reasoning of the deep neural network model, the relay server can outsource or delegate the task to other servers for processing. In one example, the relay server can establish a connection with the edge server and delegate the execution of the most time-consuming linear layer in the first neural network model to the edge server with faster processing speed for reasoning calculation, and At the same time, monitor the completion status of the task.

In another possible implementation, the relay server can also send the task to the TEE for execution. As an example, as shown in Figure 3, the task execution device worker takes the task from the broker queue and puts it into the trusted execution environment (TEE) for execution, for example, the task is divided into the enclave in the Intel SGX of the TEE for execution, and the relay server monitors the completion status of the task at the same time.

It should be understood that since TEE provides an isolated environment to store the user's sensitive information (e.g., the user's code and data), TEE provides a more secure space for the execution of code and data and ensures the confidentiality and security of the user's sensitive information (e.g., the user's code and data).

In another possible implementation, in order to solve the problem that the TEE memory is too small to complete the complex calculation of the model, as shown in Figure 3, the TEE can also outsource or delegate the task to other servers for processing. As an example, Intel SGX in TEE can protect selected code and data from being leaked and modified, but in order to solve the problem that its memory is small and insufficient to support the complete reasoning of the deep neural network model, the enclave in Intel SGX delegates the execution of the most time-consuming linear layer in the first neural network model to the edge server with faster processing speed for reasoning calculation through an outsourcing solution based on matrix multiplication, and monitors the completion status of the task at the same time.

Step 240: The person who completes the task sends the result of the inference calculation to the TEE for verification.

In the embodiment of the present application, there are multiple ways for the task completer to send the result of the reasoning calculation to the TEE for verification. The following is a detailed description of several possible implementation methods in conjunction with step 240.

In one possible implementation, the task is completed by a relay server, which can directly send the result of the inference calculation to the TEE for verification.

In another possible implementation, the task is completed by an edge server, which can directly send the result of the inference calculation to the TEE for verification, or the edge server can also send the result of the inference calculation to a relay server, and the relay server forwards the result of the inference calculation to the TEE for verification. This application does not make specific limitations on this.

There are many deployment forms of the above TEE, which are not specifically limited in the embodiments of the present application. In one example, TEE is deployed in the blockchain network, for example, TEE is deployed on each blockchain node. In another example, TEE is deployed on a separate server other than the blockchain network and the relay server.

Step 250: TEE verifies the result of the inference calculation.

In one possible implementation, TEE can obtain the real result based on the model reasoning, and compare the real result with the result it obtains to determine whether the reasoning result it obtains is credible. If the real result obtained by TEE reasoning is consistent with the result it obtains, it can be understood that the reasoning result it obtains is credible, and TEE can sign the result it obtains.

Step 260: The blockchain network uploads the inference results after TEE verification to the chain.

In an embodiment of the present application, the first blockchain node can obtain the result of reasoning verified by TEE, for example, the result of reasoning with TEE signature. There are many specific implementation methods, and the embodiment of the present application does not specifically limit this. In one example, TEE is deployed on the first blockchain node, and the first blockchain node can directly obtain the result of reasoning with TEE signature from TEE. In another example, TEE is deployed on other servers outside the blockchain network and relay server, and the first blockchain node can obtain the result of reasoning with TEE signature from the TEE deployed on the other server through communication with the other server.

In an embodiment of the present application, the first blockchain node obtains the result of the reasoning after TEE verification, and stores the result on the chain. After receiving the result of the reasoning after TEE verification sent by the first blockchain node, other nodes in the blockchain network can send their corresponding TEEs for verification again, and store the verified reasoning results on the chain. In one example, the TEEs corresponding to the other nodes in the blockchain network are deployed on their respective nodes, and the other nodes in the blockchain network verify the reasoning results through the TEEs deployed on their respective nodes. In another example, the TEEs corresponding to the other nodes in the blockchain network are deployed on other servers. The other nodes can send the reasoning results to the TEEs deployed on the other servers to verify the reasoning results, and obtain the reasoning results with TEE signatures through communication with other servers.

In the above technical solution, the results of model inference performed on servers outside the blockchain network can be verified through TEE, and the verified results can be stored on the chain through blockchain nodes. In this way, blockchain technology can be used to protect the reasoning data of artificial intelligence from being tampered with, thereby promoting the integrated development of blockchain technology and artificial intelligence technology.

The above describes in detail the method provided by the embodiment of the present application in conjunction with Figures 1 to 3, and the following describes in detail the embodiment of the device of the present application in conjunction with Figures 4 to 7. It should be understood that the description of the method embodiment corresponds to the description of the device embodiment, so the part not described in detail can refer to the previous method embodiment.

FIG4 is a schematic block diagram of a data identification device 400 provided in an embodiment of the present application. The device 400 can be implemented by software, hardware, The device 400 provided in the embodiment of the present application can implement the method flow shown in FIG. 2 of the embodiment of the present application, and the device 400 includes:

A receiving module 410, configured for a first blockchain node to receive task information, where the first blockchain node is a node in the blockchain system;

A sending module 420 is used for the first blockchain node to send the task information to a task execution device, where the task execution device is a server outside the blockchain system. The task execution device is used to perform inference calculation on the first model according to the task information to obtain an inference result of the first model, and the input of the first model includes the task information;

The sending module 420 is also used for the task execution device to send the reasoning result to the trusted execution environment TEE;

A verification module 430, used for the TEE to verify the reasoning result and obtain a verified reasoning result;

A storage module 440 is used for the first blockchain node to obtain the verified reasoning result from the TEE and store it on the chain;

The storage module 440 is also used for other nodes in the cloud blockchain system to re-verify the verified reasoning results through their respective corresponding TEEs, and store the re-verified reasoning results on the chain.

Optionally, the task execution device is a first server, which communicates with the first blockchain node. The first server is used to perform inference calculations on the first model according to the task information to obtain an inference result of the first model. The verification module 430 is specifically used for the first server to send the inference result to the TEE for verification.

Optionally, the task execution device is the TEE, which communicates with the first server, and the receiving module 410 is specifically used for the first server to receive the task information sent by the first blockchain node; the sending module 420 is specifically used for the first server to send the task information to the TEE, and the TEE is used to perform inference calculation on the first model according to the task information to obtain the inference result of the first model, and verify the inference result to obtain the verified inference result.

Optionally, the task execution device is an edge server, and the sending module 420 is specifically used for the first server or the TEE to send the task information to the edge server, and the edge server performs inference calculations on the first model based on the task information to obtain the inference result of the first model; the sending module 420 is specifically used for the edge server to send the inference result to the TEE for verification.

Optionally, the TEE is deployed on the first blockchain node.

The device 400 here can be embodied in the form of a functional module. The term "module" here can be implemented in the form of software and/or hardware, and is not specifically limited to this.

For example, a "module" can be a software program, a hardware circuit, or a combination of the two that implements the above functions. Exemplarily, the implementation of the receiving module 410 is described below by taking the receiving module 410 as an example. Similarly, the implementation of other modules, such as the sending module 420, the verification module 430, and the storage module 440, can refer to the implementation of the receiving module 410.

The receiving module 410 is taken as an example of a software functional unit, and the receiving module 410 may include code running on a computing instance. Among them, the computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the above-mentioned computing instance may be one or more. For example, the receiving module 410 may include code running on multiple hosts/virtual machines/containers. It should be noted that the multiple hosts/virtual machines/containers used to run the code may be distributed in the same region (region) or in different regions. Furthermore, the multiple hosts/virtual machines/containers used to run the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including one data center or multiple data centers with close geographical locations. Among them, usually a region may include multiple AZs.

Similarly, multiple hosts/virtual machines/containers used to run the code can be distributed in the same virtual private cloud (VPC) or in multiple VPCs. Usually, a VPC is set up in a region. For cross-region communication between two VPCs in the same region and between VPCs in different regions, a communication gateway needs to be set up in each VPC to achieve interconnection between VPCs through the communication gateway.

The receiving module 410 is taken as an example of a hardware functional unit, and the receiving module 410 may include at least one computing device, such as a server, etc. Alternatively, the receiving module 410 may also be a device implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

The multiple computing devices included in the receiving module 410 can be distributed in the same region or in different regions. The multiple computing devices included in the receiving module 410 can be distributed in the same AZ or in different AZs. Similarly, the multiple computing devices included in the receiving module 410 can be distributed in the same VPC or in multiple VPCs. The multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

Therefore, the modules of each example described in the embodiments of the present application can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

It should be noted that: when the device provided in the above embodiment executes the above method, only the division of the above functional modules is used as an example. In actual application, the above function allocation can be completed by different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. For example, the receiving module 410 can be used to execute any step in the above method, the sending module 420 can be used to execute any step in the above method, the verification module 430 can be used to execute any step in the above method, and the storage module 440 can be used to execute any step in the above method. The steps that the receiving module 410, the sending module 420, the verification module 430, and the storage module 440 are responsible for implementing can be specified as needed, and the receiving module 410, the sending module 420, the verification module 430, and the storage module 440 respectively implement different steps in the above method to realize all the functions of the above device.

In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation processes are detailed in the method embodiments above, which will not be repeated here.

The method provided in the embodiment of the present application can be performed by a computing device, which can also be referred to as a computer system. It includes a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system layer. The hardware layer includes hardware such as a processing unit, a memory and a memory control unit, and then the function and structure of the hardware are described in detail. The operating system is any one or more computer operating systems that implement business processing through a process, for example, a Linux operating system, a Unix operating system, an Android operating system, an iOS operating system, or a windows operating system. The application layer includes applications such as a browser, an address book, a word processing software, and an instant messaging software. In addition, optionally, the computer system is a handheld device such as a smart phone, or a terminal device such as a personal computer, which is not particularly limited in this application, as long as it can be provided by the method provided in the embodiment of the present application. The execution subject of the method provided in the embodiment of the present application can be a computing device, or a functional module in a computing device that can call a program and execute a program.

A computing device provided in an embodiment of the present application is described in detail below in conjunction with FIG. 5 .

FIG5 is a schematic diagram of the architecture of a computing device 1500 provided in an embodiment of the present application. The computing device 1500 may be a server or a computer or other device with computing capabilities. The computing device 1500 shown in FIG5 includes: at least one processor 1510 and a memory 1520.

It should be understood that the present application does not limit the number of processors and memories in the computing device 1500 .

The processor 1510 executes the instructions in the memory 1520, so that the computing device 1500 implements the method provided by the present application. Alternatively, the processor 1510 executes the instructions in the memory 1520, so that the computing device 1500 implements the functional modules provided by the present application, thereby implementing the method provided by the present application.

Optionally, the computing device 1500 further includes a communication interface 1530. The communication interface 1530 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 1500 and other devices or a communication network.

Optionally, the computing device 1500 further includes a system bus 1540, wherein the processor 1510, the memory 1520 and the communication interface 1530 are respectively connected to the system bus 1540. The processor 1510 can access the memory 1520 through the system bus 1540. For example, the processor 1510 can read and write data or execute code in the memory 1520 through the system bus 1540. The system bus 1540 is a peripheral component interconnect express (PCI) bus or an extended industry standard architecture (EISA) bus. The system bus 1540 is divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in FIG. 5, but it does not mean that there is only one bus or one type of bus.

In a possible implementation, the function of the processor 1510 is mainly to interpret the instructions (or codes) of the computer program and process the data in the computer software. The instructions of the computer program and the data in the computer software can be stored in the memory 1520 or the cache 1516.

Optionally, the processor 1510 may be an integrated circuit chip with signal processing capabilities. As an example and not limitation, the processor 1510 is a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. Among them, the general-purpose processor is a microprocessor, etc. For example, the processor 1510 is a central processing unit (CPU).

Optionally, each processor 1510 includes at least one processing unit 1512 and a memory control unit 1514 .

Optionally, the processing unit 1512 is also called the core or kernel, which is the most important component of the processor. The processing unit 1512 is made of single crystal silicon using a certain production process. All the calculations, command reception, command storage, and data processing of the processor are performed by the core. The processing units run program instructions independently and use the ability of parallel computing to speed up the program. Various processing units are It has a fixed logical structure. For example, the processing unit includes logical units such as a first-level cache, a second-level cache, an execution unit, an instruction unit, and a bus interface.

In one implementation example, the memory control unit 1514 is used to control data interaction between the memory 1520 and the processing unit 1512. Specifically, the memory control unit 1514 receives a memory access request from the processing unit 1512, and controls access to the memory based on the memory access request. As an example and not a limitation, the memory control unit is a device such as a memory management unit (MMU).

In one implementation example, each memory control unit 1514 addresses the memory 1520 through the system bus. An arbiter (not shown in FIG. 5 ) is configured in the system bus, and the arbiter is responsible for processing and coordinating contention accesses of multiple processing units 1512 .

In an implementation example, the processing unit 1512 and the memory control unit 1514 are connected to each other through connection lines inside the chip, such as address lines, so as to achieve communication between the processing unit 1512 and the memory control unit 1514.

Optionally, each processor 1510 also includes a cache 1516, wherein the cache is a buffer for data exchange (called cache). When the processing unit 1512 wants to read data, it will first search for the required data from the cache. If it is found, it will be executed directly. If it is not found, it will be searched from the memory. Since the running speed of the cache is much faster than the memory, the role of the cache is to help the processing unit 1512 run faster.

The memory 1520 can provide a running space for the processes in the computing device 1500. For example, the computer program (specifically, the code of the program) used to generate the process is stored in the memory 1520. After the computer program is executed by the processor to generate the process, the processor allocates a corresponding storage space for the process in the memory 1520. Furthermore, the above storage space further includes a text segment, an initialized data segment, a bit initialized data segment, a stack segment, a heap segment, etc. The memory 1520 stores the data generated during the running of the process in the storage space corresponding to the above process, such as intermediate data, process data, etc.

Optionally, the storage is also called memory, and its function is to temporarily store the operation data in the processor 1510 and the data exchanged with the external storage such as the hard disk. As long as the computer is running, the processor 1510 will transfer the data to be calculated to the memory for calculation, and when the calculation is completed, the processing unit 1512 will transmit the result.

As an example and not limitation, memory 1520 is a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory is a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory is a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory 1520 of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

The structure of the computing device 1500 listed above is only an exemplary description, and the present application is not limited thereto. The computing device 1500 of the embodiment of the present application includes various hardware in the computer system in the prior art. For example, the computing device 1500 also includes other memories other than the memory 1520, such as disk storage, etc. It should be understood by those skilled in the art that the computing device 1500 may also include other devices necessary for normal operation. At the same time, according to specific needs, it should be understood by those skilled in the art that the computing device 1500 may also include hardware devices for implementing other additional functions. In addition, it should be understood by those skilled in the art that the computing device 1500 may also include only the devices necessary for implementing the embodiment of the present application, without having to include all the devices shown in FIG. 5.

The embodiment of the present application also provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device may be a server. In some embodiments, the computing device may also be a terminal device such as a desktop computer, a laptop computer, or a smart phone.

As shown in Fig. 6, the computing device cluster includes at least one computing device 1500. The memory 1520 in one or more computing devices 1500 in the computing device cluster may store the same instructions for executing the above method.

In some possible implementations, the memory 1520 in one or more computing devices 1500 in the computing device cluster may also store partial instructions for executing the above method. In other words, the combination of one or more computing devices 1500 may jointly execute the instructions of the above method.

It should be noted that the memory 1520 in different computing devices 1500 in the computing device cluster may store different instructions, which are respectively used to execute part of the functions of the above-mentioned apparatus. That is, the instructions stored in the memory 1520 in different computing devices 1500 may implement the functions of one or more modules in the above-mentioned apparatus.

In some possible implementations, one or more computing devices in the computing device cluster may be connected via a network. The network may be a wide area network or a local area network, etc. FIG. 7 shows a possible implementation. As shown in FIG. 7 , two computing devices 1500A and 1500B are connected via a network. Specifically, the network is connected via a communication interface in each computing device.

It should be understood that the functionality of the computing device 1500A shown in FIG7 may also be implemented by multiple computing devices 1500. Similarly, the functionality of the computing device 1500B may also be implemented by multiple computing devices 1500.

In this embodiment, a computer program product including instructions is also provided. The computer program product may be a software or program product including instructions that can be run on a computing device or stored in any available medium. When the computer program product is run on a computing device, the computing device is caused to execute the method provided above, or the computing device is caused to implement the function of the apparatus provided above.

In this embodiment, a computer program product including instructions is also provided. The computer program product may be software or a program product including instructions that can be run on a computing device cluster or stored in any available medium. When the computer program product is run by a computing device cluster, the computing device cluster executes the method provided above, or the computing device cluster implements the function of the apparatus provided above.

In this embodiment, a computer-readable storage medium is also provided. The computer-readable storage medium may be any available medium that can be stored by a computing device or a data storage device such as a data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk). The computer-readable storage medium includes instructions. When the instructions in the computer-readable storage medium are executed on a computing device, the computing device executes the method provided above.

In this embodiment, a computer-readable storage medium is also provided, and the computer-readable storage medium may be any available medium that can be stored by a computing device or a data storage device such as a data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc. The computer-readable storage medium includes instructions, and when the instructions in the computer-readable storage medium are executed by a computing device cluster, the computing device cluster executes the method provided above.

It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the unit is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

If this function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims (21)

1. A method for data processing, characterized in that the method is applied to a cloud blockchain system, the cloud blockchain system includes multiple blockchain nodes, a cloud management platform deploys the cloud blockchain system on the cloud computing resources it manages, and the cloud management platform deploys blockchain services on the cloud computing resources, the method comprising:

   A first blockchain node receives task information, where the first blockchain node is a node in the cloud blockchain system;

   The first blockchain node sends the task information to a task execution device, which is a server outside the cloud blockchain system. The task execution device is used to perform inference calculation on a first model according to the task information to obtain an inference result of the first model, and the input of the first model includes the task information;

   The task execution device sends the reasoning result to the trusted execution environment TEE for verification, and obtains the verified reasoning result;

   The first blockchain node obtains the verified reasoning result from the TEE and stores it on the chain;

   The other nodes in the cloud blockchain system re-verify the verified reasoning results through their respective corresponding TEEs, and store the re-verified reasoning results on the chain.
2. The method according to claim 1 is characterized in that the task execution device is a first server, the first server communicates with the first blockchain node, and the first server is used to perform inference calculation on the first model according to the task information to obtain the inference result of the first model.

   The task execution device sends the reasoning result to the trusted execution environment TEE for verification, including:

   The first server sends the inference result to the TEE for verification.
3. The method according to claim 1, characterized in that the task execution device is the TEE, the TEE communicates with the first server, and the method further comprises:

   The first server receives the task information sent by the first blockchain node;

   The first server sends the task information to the TEE, and the TEE is used to perform inference calculation on the first model according to the task information to obtain the inference result of the first model, and verify the inference result to obtain the verified inference result.
4. The method according to claim 2 or 3, characterized in that the task execution device is an edge server, and the method further comprises:

   The first server or the TEE sends the task information to the edge server, and the edge server performs inference calculation on the first model according to the task information to obtain an inference result of the first model;

   The task execution device sends the reasoning result to the trusted execution environment TEE for verification, including:

   The edge server sends the inference result to the TEE for verification.
5. The method according to any one of claims 1 to 4, characterized in that the TEE is deployed on the first blockchain node.
6. A method for data processing, characterized in that the method comprises:

   A first blockchain node receives task information, where the first blockchain node is a node in the blockchain system;

   The first blockchain node sends the task information to a task execution device, which is a server outside the blockchain system. The task execution device is used to perform inference calculation on a first model according to the task information to obtain an inference result of the first model, and the input of the first model includes the task information;

   The task execution device sends the reasoning result to the trusted execution environment TEE for verification, and obtains the verified reasoning result;

   The first blockchain node obtains the verified reasoning result from the TEE and stores it on the chain;

   The other nodes in the blockchain system re-verify the verified reasoning results through their respective corresponding TEEs, and store the re-verified reasoning results on the chain.
7. The method according to claim 6 is characterized in that the task execution device is a first server, the first server communicates with the first blockchain node, and the first server is used to perform inference calculation on the first model according to the task information to obtain the inference result of the first model.

   The task execution device sends the reasoning result to the trusted execution environment TEE for verification, including:

   The first server sends the inference result to the TEE for verification.
8. The method according to claim 6, characterized in that the task execution device is the TEE, the TEE communicates with the first server, and the method further comprises:

   The first server receives the task information sent by the first blockchain node;

   The first server sends the task information to the TEE, and the TEE is used to perform inference calculation on the first model according to the task information to obtain the inference result of the first model, and verify the inference result to obtain the verified inference result.
9. The method according to claim 7 or 8, characterized in that the task execution device is an edge server, and the method further comprises:

   The first server or the TEE sends the task information to the edge server, and the edge server performs inference calculation on the first model according to the task information to obtain an inference result of the first model;

   The first server sends the inference result to the TEE for verification, including:

   The edge server sends the inference result to the TEE for verification.
10. The method according to any one of claims 6 to 9 is characterized in that the TEE is deployed on the first blockchain node.
11. A data processing system, characterized in that the system includes a cloud blockchain system, a task execution device and a trusted execution environment TEE, the cloud blockchain system includes multiple blockchain nodes, the multiple blockchain nodes include a first blockchain node, the cloud computing platform deploys the cloud blockchain system on the cloud computing resources it manages, the cloud computing platform deploys storage services on the cloud computing resources, and the system includes:

    The first blockchain node is used to receive task information and send the task information to a task execution device, wherein the task execution device is a server outside the cloud blockchain system, and the task execution device is used to perform inference calculation on a first model according to the task information to obtain an inference result of the first model, and the input of the first model includes the task information;

    The task execution device is used to send the reasoning result to the trusted execution environment TEE;

    The TEE is used to verify the reasoning result to obtain a verified reasoning result;

    The first blockchain node is used to obtain the verified reasoning result from the TEE and store it on the chain;

    The other nodes in the cloud blockchain system are used to re-verify the verified reasoning results through their respective corresponding TEEs, and store the re-verified reasoning results on the chain.
12. The system according to claim 11, characterized in that the task execution device is a first server, the first server communicates with the first blockchain node, and the first server is used to perform inference calculation on the first model according to the task information to obtain the inference result of the first model.

    The first server is specifically used to send the inference result to the TEE for verification.
13. The system according to claim 11, characterized in that the task execution device is the TEE, and the TEE communicates with the first server,

    The first server is used to receive the task information sent by the first blockchain node, and send the task information to the TEE. The TEE is used to perform inference calculation on the first model according to the task information to obtain the inference result of the first model, and verify the inference result to obtain the verified inference result.
14. The system according to claim 12 or 13, characterized in that the task execution device is an edge server,

    The first server or the TEE is used to send the task information to the edge server;

    The edge server is used to perform inference calculation on the first model according to the task information, obtain the inference result of the first model, and send the inference result to the TEE for verification.
15. The system according to any one of claims 11 to 14, characterized in that the TEE is deployed on the first blockchain node.
16. A computing device, characterized in that it comprises a processor and a memory, wherein the processor is used to execute instructions stored in the memory so that the computing device executes the method as described in any one of claims 1 to 5, or executes the method as described in any one of claims 6 to 10.
17. A computing device cluster, characterized in that it includes at least one computing device, each computing device includes a processor and a memory;

    The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster executes the method according to any one of claims 1 to 5, or executes the method according to any one of claims 6 to 10.
18. A computer program product comprising instructions, characterized in that when the instructions are executed by a computing device, the computing device executes the method as claimed in any one of claims 1 to 5, or executes the method as claimed in any one of claims 6 to 10.
19. A computer program product comprising instructions, characterized in that when the instructions are executed by a computing device cluster, the computing device cluster executes the method as claimed in any one of claims 1 to 5, or executes the method as claimed in any one of claims 6 to 10 method.
20. A computer-readable storage medium, characterized in that it includes computer program instructions. When the computer program instructions are executed by a computing device, the computing device executes the method as described in any one of claims 1 to 5, or executes the method as described in any one of claims 6 to 10.
21. A computer-readable storage medium, characterized in that it includes computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster executes the method as described in any one of claims 1 to 5, or executes the method as described in any one of claims 6 to 10.