A distributed virtual robot AI system

Abstract

The application relates to the technical field of artificial intelligence, in particular to a distributed virtual robot AI system. The distributed virtual robot AI system introduces a more advanced central management node, uses a machine learning algorithm to optimize coordination and resource management between nodes, establishes a virtual robot to process services, and reduces management complexity; the application realizes a dynamic resource allocation mechanism based on real-time load and capability evaluation, ensures optimal utilization of resources, and realizes replication and migration of the virtual robot, thereby improving overall system efficiency; the application provides an optimization strategy for cross-node service processing, and improves processing efficiency and reliability through introduction of a virtual robot alliance.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence technology, in particular to a distributed virtual robot AI system. BACKGROUND

[0002] Business audit is to check and verify the integrity, consistency and authenticity of business acceptance documents. The traditional audit is mainly manual, with huge labor cost and low efficiency. Taking a certain provincial company of an operator as an example, the annual audit work order exceeds 40 million, and the artificial audit cost of the whole business is nearly 100 million. Through the field of intelligent picture recognition, with the help of AI technology and combined with the characteristics of communication industry business, two capabilities of market business AI audit and government and enterprise business AI audit can be created to replace manual judgment operation and realize the comprehensive intelligent audit of market and government and enterprise basic business.

[0003] The AI audit business process is to return the AI recognition result after the combination service of AI audit preprocessing, AI audit rules and AI core algorithm on the input file transmitted by the application system.

[0004] By focusing on the audit business needs of government and enterprise and market fields, AI technology is applied to solve the intelligent bottleneck of audit. AI audit business has covered all high-sensitive business scenarios such as opening an account, replacing a card, password resetting, identity confirmation, transfer, and closing and reopening, which has significantly improved the digital level of government and enterprise and market fields.

[0005] With the rapid growth of business of enterprises, especially the popularity of online transactions and services, the number of business documents that enterprises need to handle has increased dramatically. These documents include but are not limited to account opening, transaction records, identity verification, etc., which need to go through strict audit processes to ensure compliance and accuracy. Traditional manual audit methods are not only time-consuming and labor-intensive, but also prone to errors, which cannot meet the needs of rapid response and large-scale processing.

[0006] To address this challenge, enterprises have begun to explore and implement automated audit solutions based on artificial intelligence (AI). AI audit business processing utilizes advanced technologies such as machine learning, natural language processing (NLP), and image recognition to automatically check the integrity, consistency, and authenticity of business documents. In this way, enterprises can improve audit efficiency, reduce labor costs, and reduce the risk of audit errors caused by human error.

[0007] To achieve efficient AI audit business processing, a distributed node deployment scheme is proposed and widely applied. In this scheme, the AI audit system is deployed on multiple nodes in different geographical locations, each of which is responsible for processing business documents of a specific region or type. This distributed architecture provides multiple advantages:

[0008] Load balancing: By distributing processing loads across different nodes, the system can more efficiently manage a large number of service requests, avoiding single-point overload.

[0009] Response speed: The proximity of geographically distributed nodes can reduce data transmission delays and improve response speed to local service requests.

[0010] Reliability and fault tolerance: Distributed architecture improves the stability of the system, even if a node fails, other nodes can continue to provide services.

[0011] Scalability: As the amount of business grows, the system's processing capacity can be expanded by adding new nodes without major changes to the existing architecture.

[0012] Data security and compliance: Distributed nodes can better comply with data privacy and compliance requirements, as data can be processed locally, reducing cross-regional transmission.

[0013] By implementing a distributed node deployment scheme for AI auditing business processing, enterprises can not only improve the efficiency and quality of business processing, but also better adapt to changing market environments and business demands.

[0014] However, the existing distributed node deployment scheme has the following problems:

[0015] 1. Node coordination and management complexity:

[0016] Although the distributed node deployment scheme improves processing capacity and response speed, as the number of nodes increases, coordination and management between nodes become more complex, requiring an efficient central management node to maintain the consistency and coordination of the entire system.

[0017] 2. Uneven resource allocation and efficiency problems:

[0018] The existing technology may not be able to dynamically allocate resources optimally based on business demand and node status, resulting in some nodes being overloaded while others have idle resources.

[0019] 3. Complexity of cross-node business processing:

[0020] When business processing needs to cross multiple nodes, the existing technology may lack effective mechanisms to manage and optimize these cross-node business processes. SUMMARY

[0021] To this end, the technical problem to be solved by the present application is to overcome the problems of node coordination and management, cross-node business processing complexity, and uneven resource allocation in the prior art.

[0022] To solve the above technical problems, the application provides a distributed virtual robot AI system, comprising:

[0023] An edge computing node for deploying a virtual robot, the virtual robot being a set of one or more AI auditing capabilities;

[0024] A central management node for creating, copying or migrating the virtual robot according to user requirements and in combination with multiple computing resource information of the edge computing node.

[0025] Preferably, the creation of the virtual robot according to user requirements and in combination with multiple computing resource information of the edge computing node comprises:

[0026] Obtaining a user virtual robot creation request message;

[0027] Sending a resource query request to one or more edge computing nodes in the location or area where the virtual robot is deployed according to the creation request message;

[0028] Determining one or more AI data models of the virtual robot according to the resource message returned by the edge computing node and sending the AI data models to the one or more edge computing nodes for deployment;

[0029] Sending a creation success notification to the user.

[0030] Preferably, the determination of one or more AI data models of the virtual robot according to the resource message returned by the edge computing node and the sending of the AI data models to the one or more edge computing nodes for deployment comprises:

[0031] Selecting an AI data model from a predefined AI model library according to the resource message returned by the edge computing node and the business requirements of the virtual robot and sending it to the edge computing node with matching resources for deployment;

[0032] After deployment, the AI data model is verified for performance to ensure that it meets the business requirements.

[0033] Preferably, the edge computing node is further configured to create a virtual robot in combination with multiple computing resource information of the node and register with the central management node.

[0034] Preferably, the creation of a virtual robot in combination with multiple computing resource information of the node and the registration with the central management node comprises:

[0035] Determining the type and capability of the virtual robot required to be created according to business requirements;

[0036] Judging whether the computing resources of the node can support the running of the virtual robot;

[0037] select an AI data model in a predefined AI template library according to a business demand analysis result and a resource evaluation result, and perform model training locally or in cooperation with other edge computing nodes;

[0038] integrate the trained AI data model into a virtual robot, and assign a unique identifier to the newly created virtual robot;

[0039] send registration information of the newly created virtual robot to a central management node.

[0040] Preferably, the replicating the virtual robot according to the user demand and in combination with multiple computing resource information of the edge computing nodes comprises:

[0041] obtaining a virtual robot replication request message;

[0042] sending a replicated virtual robot information query request to an edge computing node in a location or area where the replicated virtual robot is deployed according to ID information of the replicated virtual robot;

[0043] sending a resource query request to an edge computing node in a location or area where the new virtual robot is deployed according to location or area information where the new virtual robot is deployed and ID information of the edge computing node where the new virtual robot is deployed;

[0044] determining whether replication can be performed according to the returned information, and if so, performing replication and sending a replication success notification to the user.

[0045] Preferably, the migrating the virtual robot according to the user demand and in combination with multiple computing resource information of the edge computing nodes comprises:

[0046] obtaining a virtual robot migration request message;

[0047] sending a migrated virtual robot information query request to an edge computing node in a location or area where the migrated virtual robot is deployed according to ID information of the migrated virtual robot, source network location or area, and ID information of the edge computing node;

[0048] sending a resource query request to an edge computing node in a location or area where the new virtual robot is deployed according to location or area information where the new virtual robot is deployed and ID information of the edge computing node where the new virtual robot is deployed;

[0049] determining whether migration can be performed according to the returned information, and if so, performing migration;

[0050] sending a virtual robot information deletion request to an edge computing node in a source location or area where the migrated virtual robot is deployed;

[0051] After the deletion is successful, a migration success notification is sent to the user.

[0052] Preferably, the virtual robot is used for:

[0053] According to the business request message sent by the business client, the business is analyzed and processed, and if the processing is not successful, a virtual robot capability query message is sent to the center management node;

[0054] A backup virtual robot that meets the current business virtual robot capability requirement recommended by the center management node is sent a business analysis processing request;

[0055] The processing data of the backup virtual robot after completing the analysis is obtained and sent to the business client.

[0056] Preferably, the analysis and processing of the business include:

[0057] The received business data is preliminarily verified to ensure the integrity and correctness of the data, and image or document type data is preprocessed;

[0058] According to the business type and data content, the applicable audit rules are automatically matched from the pre-defined audit rule engine to preliminarily check the business data to check consistency and compliance;

[0059] The trained AI data model is used to identify abnormalities, risk points and inconsistencies in the business data;

[0060] The rule engine matching result and the AI data model analysis result are summarized to form an audit report.

[0061] Preferably, the center management node selects the backup virtual robot that meets the current business virtual robot capability requirement and has the highest priority from the alliance domain for recommendation, wherein the alliance domain is a virtual robot alliance generated by message indication in the virtual robot creation stage or an automatically generated virtual robot alliance.

[0062] The above technical solutions of the present application have the following advantages compared with the prior art:

[0063] The distributed virtual robot AI system of the present application introduces a more advanced center management node, uses machine learning algorithms to optimize coordination and resource management between nodes, establishes a virtual robot to process business, and reduces management complexity; The present application realizes a dynamic resource allocation mechanism based on real-time load and capability evaluation, ensures optimal utilization of resources, and realizes replication and migration of virtual robots to improve overall system efficiency; The present application provides an optimization strategy for cross-node business processing, and through the introduction of a virtual robot alliance, improves processing efficiency and reliability. Attached Figure Description

[0064] To make the content of this invention easier to understand, the invention will be further described in detail below with reference to specific embodiments and accompanying drawings, wherein:

[0065] Figure 1 This is a system architecture diagram of a distributed virtual robot AI system provided by the present invention;

[0066] Figure 2 This is a schematic diagram illustrating the process of creating a virtual robot at the central management node;

[0067] Figure 3 This is a schematic diagram illustrating the process of an edge computing node creating a virtual robot;

[0068] Figure 4 This is a diagram illustrating the virtual robot replication process.

[0069] Figure 5 This is a diagram illustrating the virtual robot migration process;

[0070] Figure 6 This is a diagram illustrating the process of virtual robots backing each other up. Detailed Implementation

[0071] The core of this invention is to provide a distributed virtual robot AI system that effectively improves the processing capacity of AI auditing business, reduces costs, enhances the system's flexibility and security, and better meets the needs of modern business.

[0072] To enable those skilled in the art to better understand the present invention, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0073] Please refer to Figure 1 , Figure 1 The present invention provides a system architecture diagram of a distributed virtual robot AI system; specifically including:

[0074] Edge computing nodes are used to deploy virtual robots, which are a collection of one or more AI auditing capabilities;

[0075] The central management node is used to create, copy, or migrate virtual robots based on user needs and by combining information from multiple computing resources on edge computing nodes.

[0076] The user is a distributed virtual robot AI system manager.

[0077] The central management node is a node in the distributed virtual robot AI system for unified management of virtual robots deployed in each network edge computing node in the system.

[0078] The virtual robot is a collection of one or more AI audit capabilities deployed in the edge computing node in the distributed virtual robot AI system. The virtual robot can be implemented by one or more AI data models. One or more AI audit capabilities of the virtual robot can be distributedly deployed in one or more physical edge computing nodes within the same network area. The virtual robot provides a unified input and output interface or a unified input and output management module for external nodes (such as the central management node, the business client, or other virtual robots). The virtual robot uses a unique ID in the distributed virtual robot AI system as an identifier in the distributed virtual robot AI system. Multiple virtual robots can share the same AI audit capability, that is, an edge computing node deploying an AI audit capability can be accessed by multiple virtual robots simultaneously. Multiple virtual robots can form a virtual robot alliance, that is, within the virtual robot alliance, the capabilities of the virtual robots can be shared entirely or a list of shareable capabilities can be determined by the virtual robot alliance. The virtual robot alliance is a logical organization of multiple virtual robots, which can not be bound to the physical deployment location of the virtual robots, that is, multiple virtual robots not deployed in adjacent physical network locations can form a virtual robot alliance according to negotiated rules and determine a list of shareable capabilities within the alliance. The same virtual robot can be included in different virtual robot alliances.

[0079] Based on the above embodiments, in the distributed virtual robot AI system architecture, the central management node maintains one or more virtual robot information, including virtual robot ID information, AI audit capability information, resource information, network topology information, etc. The virtual robot needs to deploy an AI data model supporting the AI audit capability, and the central management node can not need to deploy an AI data model supporting the AI audit capability. The virtual robot needs to report an AI audit capability release / update notification to the central management node when actively updating the AI audit capability or the AI data model. The virtual robot can indicate the list of AI audit capabilities disclosed within different virtual robot alliances and the list of AI audit capabilities disclosed outside the virtual robot alliance to the central management node when reporting the AI audit capability release / update notification to the central management node. The virtual robot needs to interact with other virtual robots, and can query virtual robot information through the central management node.

[0080] The distributed virtual robot AI system comprises the following stages and edge computing node interaction processes: creation of a virtual robot, replication and migration of the virtual robot, and cooperation services such as mutual assistance and backup provided by the virtual robot through an alliance domain.

[0081] Based on the above embodiments, the creation of a virtual robot is described in detail as shown in Figure 2

[0082] The creation of the virtual robot according to the user demand and in combination with the multiple computing resource information of the edge computing node comprises the following steps:

[0083] A user virtual robot creation request message is obtained. The request message carries the type of the virtual robot and / or the service type information of the service, the traffic demand information, the position / region where the virtual robot is deployed, the ID of the edge computing node where the virtual robot is deployed, the virtual robot capability list information, the ID information of the virtual robot alliance to which the virtual robot applies to join, the capability list information shared by the virtual robot in each virtual robot alliance, and the capability list information shared by the virtual robot outside the virtual robot alliance. The type of the virtual robot includes a network detection robot (facing network management and maintenance) and a service robot (facing customer service). The service type of the virtual service robot includes account opening, card replacement, password resetting, identity confirmation, transfer, and account cancellation and reopening. The traffic demand information is, for example, x single A service per day or y bps service transmission. The position / region where the virtual robot is deployed includes network region ID information, network device ID information, and location GPS information. One virtual robot creation request message can apply to create one or more virtual robots.

[0084] A resource query request is sent to one or more edge computing nodes in the position or region where the virtual robot is deployed according to the creation request message. If the virtual robot creation request message carries one or more edge computing node IDs indicated by the user where the virtual robot is deployed, the central management node sends a resource request message to the one or more edge computing nodes where the virtual robot is deployed carried in the virtual robot creation request message. If the virtual robot creation request message does not carry the edge computing node ID information indicated by the user where the virtual robot is deployed, the central management node sends a resource request message to one or more edge computing nodes in the position / region where the virtual robot is required to be deployed carried in the virtual robot creation request message. The resource request message carries GPU resource information, CPU resource information, memory information, and resource cost information.

[0085] ​According to the resource message returned by the edge computing node, one or more AI data models of the virtual robot are determined, and the AI data models are sent to one or more edge computing nodes for deployment; wherein each AI data model can support the provision of one or more capabilities of the virtual robot. One AI data model is downloaded and installed by one edge computing node. The set of capabilities provided by the AI data models installed by one or more edge computing nodes constitutes the total set of capabilities of the virtual computing person.

[0086] A creation success notification is sent to the user. The message carries the ID of the virtual robot, the capabilities provided by the virtual robot, the AI data model deployment topology information of each capability of the virtual robot, etc.

[0087] Based on the above embodiments, the AI data models of the virtual robot are determined according to the resource message returned by the edge computing node, and the AI data models are sent to one or more edge computing nodes for deployment, which includes:

[0088] According to the resource message returned by the edge computing node and the business requirements of the virtual robot, AI data models are selected from a pre-defined AI model library and sent to edge computing nodes matching their resources for deployment;

[0089] After deployment is completed, the performance of the AI data models is verified to ensure that they meet the business requirements.

[0090] Specifically, the center management node determines the AI data model method as follows:

[0091] 1) Demand analysis: The center management node first analyzes the virtual robot creation request submitted by the user, including business type, business volume requirement, expected performance indicators, etc.

[0092] 2) Resource evaluation: The center management node sends a resource query request to the corresponding edge computing node according to the deployment location / region specified in the request, and collects available computing resource information such as GPU, CPU, memory, etc.

[0093] 3) Model selection: According to the results of demand analysis and resource evaluation, the center management node selects the most suitable AI data model from a pre-defined AI model library. These models may be optimized for specific business scenarios, or they may be general models that can be customized according to requirements.

[0094] 4) Model customization: If necessary, the center management node can customize the selected AI data model to meet specific business requirements. This may include adjusting model parameters, selecting training data sets, or modifying model structures.

[0095] 5) Model Deployment: The central management node sends the selected and customized AI data model to the designated edge computing node for deployment. The deployment process may include installation, configuration, and initialization of the model.

[0096] 6) Model Testing: After deployment, the central management node runs a series of test cases to verify whether the AI data model meets the expected performance indicators and ensures its stability and reliability in the actual environment.

[0097] 7) Feedback and Optimization: The test results are fed back to the central management node, which may make further optimization adjustments if the model does not meet the expected results.

[0098] In summary, the specific process of creating a virtual robot by the central management node is as follows:

[0099] 1) Receive resource information: The central management node receives resource information from edge computing nodes, including available computing resources and storage resources.

[0100] 2) Resource matching: The central management node evaluates which resources are most suitable for deploying the requested AI data model based on resource information and the business needs of the virtual robot.

[0101] 3) Model deployment decision: Based on the results of resource matching, the central management node decides which AI data models to deploy on which edge computing nodes and develops a deployment plan.

[0102] 4) Deployment instruction issuance: The central management node sends deployment instructions to the selected edge computing nodes, including model files, configuration parameters, and deployment guidelines.

[0103] 5) Monitor the deployment process: The central management node monitors the deployment process of the AI data model to ensure that the deployment proceeds as planned and handles any problems that may arise.

[0104] 6) Performance verification: After deployment, the central management node monitors the performance of the virtual robot to ensure that it meets business needs.

[0105] 7) User notification: Once the AI data model is deployed and passes the test, the central management node sends a successful notification to the user, including the ID of the virtual robot and the provided capabilities, etc.

[0106] Through this series of steps and processes, the central management node ensures that the AI data model of the virtual robot can be efficiently and accurately deployed in a distributed system, meeting business needs and providing stable services.

[0107] Based on the above example, the creation of a virtual robot can also be implemented by an edge computing node:

[0108] As Figure 3 , the edge computing node combines the information of multiple computing resources of the node to create a distributed functional virtual robot, and registers with the central management node. Compared with the creation process of the virtual robot described above, this embodiment is a decentralized process, in which the edge computing node independently creates a virtual robot using its own computing resources, and joins it to the system maintained by the central management node through the registration process.

[0109] Edge computing nodes play a crucial role in the distributed virtual robot AI system. They are usually located at the edge of the network, close to data sources such as user devices or sensors. The purpose of edge computing nodes is to provide computing and storage capabilities at the data source, thereby reducing the need for data transmission to the central data center, reducing latency, and improving processing speed and efficiency.

[0110] Characteristics of edge computing nodes:

[0111] Near-user computing: Edge computing nodes are usually deployed near users, providing fast response and real-time data processing.

[0112] Resource limitations: Compared with central data centers, edge computing nodes may have limitations in computing power and storage resources.

[0113] Autonomy: Edge computing nodes can operate independently and handle tasks without direct intervention from the central management node.

[0114] Distributed processing: Edge computing nodes can work together with other edge computing nodes to complete tasks or optimize resource usage.

[0115] Combining the information of multiple computing resources of the node to create a virtual robot and registering with the central management node includes:

[0116] 1. One or more edge computing nodes create a virtual robot through model training in the autonomous domain, where the capabilities of the virtual robot can be provided by one or more AI data models, and one AI data model is downloaded and installed by one edge computing node. The set of capabilities provided by the AI data models installed by one or more edge computing nodes constitutes the total set of capabilities of the virtual robot. The edge computing node determines the ID of the virtual robot.

[0117] The creation steps of the edge computing node virtual robot include:

[0118] 1) Demand analysis: The edge computing node first analyzes the business requirements and determines the type and capabilities of the virtual robot to be created.

[0119] 2) Resource Assessment: The edge computing node assesses its computing resources, including CPU, GPU, memory, and storage, to determine whether there are sufficient resources to support the operation of the virtual robot.

[0120] 3) Model Selection and Training: Based on the demand analysis, the edge computing node can select appropriate AI models from the AI model library and perform model training locally or in collaboration with other edge computing nodes. The pre-configuration of the AI model library and the training method of the AI model are not limited by the present application.

[0121] 4) Virtual Robot Construction: The edge computing node integrates the trained AI model into the virtual robot, constructing a virtual robot with the required capabilities.

[0122] 5) ID Allocation: A unique identifier (ID) is assigned to the newly created virtual robot for identification and management in the system.

[0123] 6) Registration Preparation: The edge computing node prepares a registration message containing detailed information about the virtual robot, such as type, service type, deployment location, capability list, etc.

[0124] 2、The edge computing node sends a virtual robot registration message to the central management node. The registration message carries information such as the type of virtual robot and / or the service type it serves, the location / region where the virtual robot is deployed, the ID of the edge computing node where the virtual robot is deployed, the virtual robot capability list information, the ID information of the virtual robot alliance that the virtual robot applies to join, the shared capability list information of the virtual robot in each virtual robot alliance, and the shared capability list information of the virtual robot outside the virtual robot alliance.

[0125] 3、The central management node records and maintains virtual robot registration information and sends a registration success message to the edge. Once confirmed, the edge computing node receives the registration success message, and the virtual robot becomes an official part of the system.

[0126] Through the above steps, the edge computing node can autonomously create and manage virtual robots, thereby improving the performance and efficiency of the entire system while reducing dependence on the central data center.

[0127] As shown in Figure 4 based on the above embodiment, the virtual robot is replicated according to user demand and in combination with multiple computing resource information of the edge computing node, which includes:

[0128] Obtaining a virtual robot replication request message; wherein the virtual robot replication request message can come from a user's virtual robot replication request message, or the central management node determines a virtual robot that can be deployed by replication for an area where no virtual robot is deployed according to big data algorithm. The virtual robot replication request message carries virtual robot ID information, the position / area where the virtual robot is deployed, and the edge computing node ID of the virtual robot deployment, etc.

[0129] According to the virtual robot ID information to be replicated, send a replicated virtual robot information query request to the edge computing node of the position or area where the replicated virtual robot is deployed; when the central management node itself maintains all the information (including virtual robot AI data model information, the topology of the node required by the innovative virtual robot, and the GPU resource information, CPU resource information, and memory information of each node) required to create the virtual robot indicated by the virtual robot ID information, and the central management node determines that the information it maintains is the latest version of the virtual robot indicated by the virtual robot ID information, this step can be omitted.

[0130] The edge computing node where the virtual robot indicated by the virtual robot ID information is located replies to the central management node with the information of the virtual robot, including virtual robot AI data model information, the topology of the node required by the innovative virtual robot, and the GPU resource information, CPU resource information, and memory information of each node.

[0131] According to the position or area where the new virtual robot is deployed and the edge computing node ID information of the new virtual robot deployment, send a resource query request to the edge computing node of the position or area where the new virtual robot is deployed; if the virtual robot creation request message carries one or more edge computing node IDs indicated by the user for virtual robot deployment, the central management node sends a resource request message to the edge computing node where one or more virtual robots indicated by the user are deployed. If the virtual robot creation request message does not carry the edge computing node ID information indicated by the user for virtual robot deployment, the central management node sends a resource request message to one or more edge computing nodes in the position / area where the virtual robot is required to be deployed as carried in the virtual robot creation request message. The resource request message carries GPU resource information, CPU resource information, memory information, resource cost information, etc.

[0132] According to the returned information, it is judged whether the copy operation can be performed. If yes, the copy is performed. If the copy condition can be met, the center management node sends one or more AI data models of the virtual robot to one or more edge computing nodes of the target area network. Each AI data model can support the provision of the capability of one or more virtual robots. One AI data model is downloaded and installed by one edge computing node. The set of capabilities provided by the AI data model installed by one or more edge computing nodes constitutes the total set of capabilities of the virtual computing person.

[0133] The center management node feeds back a virtual robot copy success response message to the user. The message carries the ID of the virtual robot, the capabilities provided by the virtual robot, the AI data model deployment topology information of each capability of the virtual robot, etc.

[0134] As shown in FIG. 5, based on the above embodiment, the migration of the virtual robot according to the user demand and in combination with the plurality of computing resource information of the edge computing node includes:

[0135] A virtual robot migration request message is obtained. The virtual robot migration request message can be a virtual robot migration request message from the user, or the center management node migrates a virtual robot from a source network area to a new network area for deployment according to other trigger conditions. The virtual robot migration request message carries the virtual robot ID information, the source network location / area / edge computing node ID, the target network location / area / edge computing node ID, etc.

[0136] According to the migrated virtual robot ID information, the source network location or area, and the edge computing node ID information, a migrated virtual robot information query request is sent to the edge computing node of the location or area where the migrated virtual robot is deployed. When the center management node itself maintains all the information (including the virtual robot AI data model information, the topology of the node required by the innovative virtual robot, and the GPU resource information, CPU resource information, and memory information of each node) required for creating the virtual robot indicated by the virtual robot ID information, and the center management node determines that the information it maintains is the latest version of the virtual robot indicated by the virtual robot ID information, this step can be omitted.

[0137] The edge management node where the virtual robot indicated by the virtual robot ID information is located replies to the center management node with the information of the virtual robot, including the virtual robot AI data model information, the topology of the node required by the innovative virtual robot, and the GPU resource information, CPU resource information, and memory information of each node.

[0138] According to the location or area where the new virtual robot is deployed and the edge computing node ID information of the new virtual robot deployment, a resource query request is sent to the edge computing node in the location or area where the new virtual robot is deployed; if one or more virtual robot deployment edge computing node IDs are carried in the virtual robot creation request message, the central management node sends a resource request message to the one or more virtual robot deployment edge computing nodes carried in the virtual robot creation request message. If the virtual robot creation request message does not carry the user-indicated virtual robot deployment edge computing node ID information, the central management node sends a resource request message to one or more edge computing nodes in the location / area where the virtual robot is required to be deployed, which is carried in the virtual robot creation request message. The resource request message carries GPU resource information, CPU resource information, memory information, resource cost information, etc.

[0139] According to the return information, it is judged whether the migration operation can be performed, and if so, the migration is performed; if the migration condition can be met, the central management node sends one or more AI data models of the virtual robot to one or more edge computing nodes of the target area network. Each AI data model can support the provision of one or more capabilities of the virtual robot. One AI data model is downloaded and installed by one edge computing node. The set of capabilities provided by the AI data model installed by one or more edge computing nodes constitutes the total set of capabilities of the virtual computer.

[0140] A virtual robot information deletion request is sent to the edge computing node of the source location or area where the migrated virtual robot is deployed; the message carries the ID of the virtual robot.

[0141] After deletion is successful, a migration success notification is sent to the user. The message carries the ID of the virtual robot (the same ID as before migration or a new ID allocated after migration), the capabilities provided by the virtual robot, the AI data model deployment topology information of each capability of the virtual robot, etc.

[0142] As Figure 6 , based on the above embodiments, the virtual robot is used for:

[0143] According to the business request message sent by the business client, the business is analyzed and processed (the message carries the business type, business ID, and data content involved in the business (such as file, photo, signature, etc.). When the business client and the virtual robot are co-located on a physical device, this step can be omitted.

[0144] If the processing is successful, the business response is directly performed, and if the processing is not successful (i.e., the business request information is not within the capability range that the virtual robot 1 can provide or the virtual robot 1 needs to use a backup virtual robot service due to reasons such as maintenance, current processing overload, etc.), a virtual robot capability query message is sent to the center management node; the message carries information such as business type, business ID, virtual robot capability requirement, etc.

[0145] A business analysis processing request is sent to the backup virtual robot recommended by the center management node to meet the current business virtual robot capability requirement; the message carries information such as business type, business ID, data content involved in the business (such as file, photo, signature, etc.).

[0146] The processing data after the backup virtual robot completes the analysis is obtained and sent to the business client.

[0147] Based on the above embodiment, the analysis and processing of the business include:

[0148] The received business data is preliminarily verified to ensure the integrity and format correctness of the data, and image or document type data is preprocessed;

[0149] According to the business type and data content, the applicable audit rules are automatically matched from the pre-defined audit rule engine, and the business data is preliminarily checked to check consistency and compliance;

[0150] The trained AI data model is used to identify abnormalities, risk points, and inconsistencies in the business data;

[0151] The rule engine matching result and the AI data model analysis result are summarized to form an audit report.

[0152] Specifically:

[0153] 1) Data verification and preprocessing:

[0154] The virtual robot 1 preliminarily verifies the received business data to ensure the integrity and format correctness of the data. Necessary preprocessing is performed on image or document type data, such as image cropping, rotation correction, denoising, etc., OCR recognition and structuring of text data.

[0155] 2) Rule engine matching:

[0156] The pre-defined audit rule engine is applied to automatically match the applicable audit rules according to the business type and data content.

[0157] 3) AI model analysis:

[0158] Virtual robots 1 use trained AI models (such as machine learning, deep learning models) to conduct in-depth analysis of data, identify abnormal patterns, potential risks and inconsistencies.

[0159] 4) Result summary and decision suggestion:

[0160] The rule engine matching results and AI model analysis results are summarized to form an audit report.

[0161] Provide decision suggestions based on the analysis results to help business personnel respond and handle quickly.

[0162] Based on the above embodiments, when there are multiple virtual robots that meet the virtual robot capability requirements, the center management node feeds back the ID list of the virtual robots to the virtual robot 1, which can be sorted according to the recommended priority. Different virtual robots can form a virtual robot alliance (the composition conditions of the virtual robot alliance are, for example, virtual robots with close physical locations of edge computing nodes or virtual robots with data sharing contracts, etc.).

[0163] When prioritizing, the center management node needs to consider business needs to ensure that the selected virtual robots best meet the specific requirements of the current business. The following are examples of business demand factors that the center management node may consider when prioritizing:

[0164] Business type matching: The center management node will prioritize virtual robots designed or optimized to handle similar businesses according to the type of business request.

[0165] Business urgency: For urgent or time-sensitive business requests, the center management node will prioritize virtual robots that can respond and handle quickly.

[0166] Business complexity: For complex or require specific expertise of the business, the center management node will prioritize virtual robots with expertise in the relevant field.

[0167] Business data security: For businesses involving sensitive information, the center management node will consider the data security record and security measures of the virtual robot, and prioritize virtual robots with good reputation and high security performance.

[0168] Business historical performance: The center management node will refer to the historical performance of virtual robots in handling similar businesses in the past, including success rate, customer satisfaction, etc., to predict their future performance.

[0169] Business-specific rules: If the business has specific processing rules or standards, the center management node will prioritize virtual robots that can comply with these rules.

[0170] Business cost-effectiveness: While meeting business needs, the central management node also considers cost-effectiveness, prioritizing cost-effective virtual robots to optimize overall costs.

[0171] Through such comprehensive considerations, the central management node can ensure that the selected virtual robots not only have the ability to handle specific businesses, but also can efficiently, safely, and economically complete tasks, thereby improving the overall business processing capacity and customer satisfaction of the system. This detailed priority ranking mechanism is an important improvement of the present invention over existing technical solutions, making the collaboration of virtual robots more intelligent and business-oriented.

[0172] Based on the above embodiments, the central management node selects the backup virtual robot with the highest priority that meets the current business virtual robot capability requirements from the alliance domain, which is a virtual robot alliance generated by message indication in the virtual robot creation stage or an automated intelligent virtual robot alliance.

[0173] The method of virtual robots forming an alliance domain can be determined by the "I, virtual robot creation" method of the present invention, in which the user carries "ID information of the virtual robot alliance to which the virtual robot applies to join, and capability list information shared by the virtual robot in each virtual robot alliance" and other indication information in the virtual robot creation request message sent to the central management node, or in method two, the edge computing node carries "ID information of the virtual robot alliance to which the virtual robot applies to join, and capability list information shared by the virtual robot in each virtual robot alliance" and other indication information in the virtual robot registration message sent to the central management node.

[0174] In addition to being generated by message indication in the "virtual robot creation" stage, the virtual robot alliance domain can also be automatically generated based on the AI system architecture of distributed virtual robots.

[0175] The alliance domain formed by virtual robots can be managed by the alliance initiator (which can be one or more influential virtual robots) or the central management node, with the following specific methods:

[0176] 1) Goal and condition setting

[0177] Automatic target identification: Determine the goals of the alliance through algorithm analysis, such as optimizing resource utilization, improving task processing speed, complementary capabilities, load balancing, etc.

[0178] Condition definition algorithm: Use pre-set standards and algorithms to automatically set the conditions for joining the alliance, such as computing power threshold, storage requirements, etc.

[0179] 2) Strategy and rule automation formulation

[0180] Automated Interaction Rules: Utilize machine learning models to automatically generate resource sharing protocols and task scheduling mechanisms based on historical data and performance metrics.

[0181] Dynamic Role Assignment: Dynamically assign virtual robots' roles and responsibilities based on real-time performance data and load conditions.

[0182] 3) Automated Member Recruitment

[0183] Intelligent Identification of Potential Members: Automatically identify suitable virtual robots for joining the alliance by analyzing network topology and performance logs.

[0184] Automated Invitation Process: The system automatically sends invitations to potential members and provides necessary alliance information.

[0185] 4) Automated Registration and Verification

[0186] Automatic Registration: Potential members automatically submit registration information and capability proofs through API interfaces.

[0187] Intelligent Verification: The central management node uses automated verification algorithms to verify the accuracy and completeness of registration information.

[0188] 5) Alliance Establishment and Information Synchronization

[0189] Automatic Confirmation of Membership: Once the registration verification is passed, the system automatically updates the member status and grants corresponding permissions.

[0190] Real-time Information Synchronization: The capabilities and resource status of new members are shared with existing members through real-time data synchronization mechanisms.

[0191] 6) Efficient Alliance Operation

[0192] Automatic Resource Sharing: Based on pre-set resource sharing protocols, the system automatically allocates and adjusts resources.

[0193] Dynamic Task Scheduling: Based on real-time load and priority, the system automatically schedules tasks to the most suitable virtual robots.

[0194] Collaborative Execution Mechanism: Through API and message queues, efficient collaboration and data backup between members are achieved.

[0195] 7) Maintenance and Performance Evaluation

[0196] Real-time Performance Monitoring: Use monitoring tools to track virtual robots' performance indicators in real time.

[0197] Periodic Evaluation: Regularly run evaluation algorithms to adjust alliance configurations based on performance data and business requirements.

[0198] 8) Expansion and Dissolution Mechanisms

[0199] Intelligent Expansion Analysis: Based on business growth and market trends, the system automatically analyzes and proposes expansion suggestions.

[0200] Condition-driven Dissolution: Pre-set dissolution conditions such as target achievement or performance decline, the system automatically executes the dissolution process.

[0201] Through these optimized steps, the establishment and operation of the virtual robot alliance domain will be more automated and intelligent, reducing human intervention, improving efficiency and reliability.

[0202] Taking AI auditing business as an example, the specific operation steps of "virtual robots providing mutual assistance, backup and other collaborative services through alliance domain" are as follows:

[0203] 1) Business request reception and verification: Virtual robot 1 receives requests from business clients and verifies the validity of the request, including business type, ID and data integrity.

[0204] 2) Data preprocessing and feature extraction: Preprocess the received data, such as image enhancement, text structuring, etc., and extract key features for subsequent analysis.

[0205] 3) AI rule matching and preliminary verification: Apply the built-in AI auditing rule engine to perform preliminary verification on the data, checking consistency and compliance.

[0206] 4) Deep learning model analysis: Use deep learning models to analyze data in depth, identify abnormal patterns, risk points and potential inconsistencies.

[0207] 5) Alliance domain collaboration request: When virtual robot 1 encounters processing bottlenecks or specific business requirements exceed its capabilities, it initiates a collaboration request to the central management node.

[0208] 6) Central management node coordination: The central management node selects the most suitable virtual robot 2 from the alliance domain based on the virtual robot's capabilities, load and geographic location, and alliance open capability list.

[0209] 7) Task distribution and execution: Virtual robot 1 forwards the business request to the selected virtual robot 2, which executes specific auditing tasks based on its professional capabilities.

[0210] 8) Result aggregation and report generation: After virtual robot 2 completes the task, it feeds back the results to virtual robot 1, which aggregates all information and generates a detailed auditing report.

[0211] 9) Decision support and response: Virtual robot 1 provides decision support based on the aggregated results and returns the final processing results to the business client in a timely manner.

[0212] Improvements of the present invention:

[0213] 1) Improved collaboration efficiency: Through collaboration within the alliance domain, virtual robots can quickly respond to complex business needs, shorten processing time, and improve overall efficiency.

[0214] 2) Optimal resource utilization: The dynamic task allocation and resource scheduling mechanism of the alliance domain ensures that the computing resources of each virtual robot are optimally utilized, reducing system resource waste.

[0215] 3) Enhanced system reliability: The alliance domain provides multi-level backup and disaster recovery mechanisms, so that the system can remain stable even in the event of partial node failure.

[0216] 4) Flexibility and scalability of business processing: Virtual robots can be dynamically expanded or reduced according to business needs, and the resource sharing and complementary capabilities within the alliance domain enable the system to adapt flexibly to changing business environments.

[0217] 5) Depth and breadth of data processing: Virtual robots within the alliance domain can share advanced AI models and processing strategies, enabling the system to handle more complex data and business scenarios.

[0218] In summary, the present invention not only improves the automation level of AI audit business, but also enhances the intelligent collaboration capabilities of the system, providing a more efficient, reliable and intelligent audit solution for enterprises.

[0219] The present invention proposes that in a distributed virtual robot AI system, based on edge computing node collaboration and center management node collaboration, iterative completion of virtual robot installation upgrade, replication migration, and mutual backup, while realizing flexible invocation of system capabilities, the impact of single point failure on the system is avoided. The distributed virtual robot AI system is suitable for AI audit systems and can also be used for other AI data processing systems.

[0220] The distributed virtual robot AI system described in the application optimizes coordination and resource management between nodes using machine learning algorithms by introducing a more advanced central management node, establishes virtual robots to process services, and reduces management complexity; The application realizes a dynamic resource allocation mechanism based on real-time load and capacity assessment, ensures optimal utilization of resources, and realizes replication and migration of virtual robots to improve overall system efficiency; The application provides an optimization strategy for cross-node service processing, and improves processing efficiency and reliability through the introduction of a virtual robot alliance. Through these improvements, the application aims to solve the problems in the existing distributed node deployment scheme, and provide more efficient, reliable and intelligent AI audit business processing capabilities; The distributed virtual robot system proposed in the application can also solve the cost problem in existing AI audit services: the existing node deployment scheme requires a large amount of hardware and maintenance costs. Virtual robots can utilize existing computing resources to reduce additional hardware investment. Through these improvements, the distributed virtual robot system not only improves the processing capacity of AI audit services, but also reduces costs, enhances system flexibility and security, and better meets the needs of modern services.

[0221] The application proposes to complete virtual robot installation, upgrade, replication, migration and mutual backup in a distributed virtual robot AI system based on edge computing node cooperation and central management node cooperation iteration, which realizes flexible invocation of system capacity while avoiding the impact of single point failure on the system. Its technical advantages are as follows:

[0222] 1. In the AI system architecture based on distributed virtual robots, the central management node only needs to maintain one or more virtual robot information, and does not need to deploy an AI data model supporting AI audit capability. Avoid the waste of data processing load and network transmission resources caused by centralized AI audit capability deployment.

[0223] 2. Deploying distributed virtual robots using edge devices can fully integrate and utilize the computing resources of edge computing nodes, and because edge computing nodes are closer to users in the transmission path, data transmission latency is saved.

[0224] 3. Virtual robots can be updated, upgraded and maintained independently without affecting the business processing capacity of the entire system.

[0225] 4. Virtual robots can be flexibly replicated and migrated in the distributed virtual robot AI system to realize the large-scale promotion of personalized AI audit capabilities in the network.

[0226] 5. Virtual robots can back up each other to prevent single point failure.

[0227] Obviously, the above embodiments are merely example for clearly illustrating, and are not limitation to the embodiments. Other different forms of changes or variations can be made on the basis of the above description for those skilled in the art. Here, all the embodiments need not and can not be exhausted. The obvious changes or variations derived therefrom are still within the protection scope of the present application.

Claims

1. A distributed virtual robot AI system, characterized by, Comprise: An edge computing node for deploying a virtual robot, the virtual robot being a set of one or more AI auditing capabilities; A central management node for creating, copying or migrating the virtual robot according to user requirements and in combination with multiple computing resource information of the edge computing node; The creating of the virtual robot according to user requirements and in combination with multiple computing resource information of the edge computing node comprises: Obtaining a virtual robot creation request message from a user; Sending a resource query request to one or more edge computing nodes in the location or area where the virtual robot is deployed according to the creation request message; Selecting an AI data model from a predefined AI model library according to the resource message returned by the edge computing node and the business requirements of the virtual robot, and sending it to the edge computing node with matching resources for deployment; After deployment, the performance of the AI data model is verified to ensure that it meets the business requirements; Send a creation success notification to the user.

2. The distributed virtual robotic Al system of claim 1, wherein, The edge computing node is also used to create a virtual robot in combination with multiple computing resource information of the node, and register with the central management node.

3. The distributed virtual robotic Al system of claim 2, wherein, The creating of the virtual robot in combination with multiple computing resource information of the node and the registration with the central management node comprises: Determine the type and capability of the virtual robot to be created according to the business requirements; Determine whether the computing resources of the node can support the running of the virtual robot; Select an AI data model from a predefined AI model library according to the business requirement analysis result and the resource evaluation result, and perform model training locally or in cooperation with other edge computing nodes; Integrate the trained AI data model into the virtual robot, and assign a unique identifier to the newly created virtual robot; Send the registration information of the newly created virtual robot to the central management node.

4. The distributed virtual robotic Al system of claim 1, wherein, The copying of the virtual robot according to user requirements and in combination with multiple computing resource information of the edge computing node comprises: Obtaining a virtual robot copy request message; According to the ID information of the copied virtual robot, send a copied virtual robot information query request to the edge computing node in the location or area where the copied virtual robot is deployed; According to the location or area where the new virtual robot is deployed and the edge computing node ID information of the new virtual robot, send a resource query request to the edge computing node in the location or area where the new virtual robot is deployed; Determine whether the copy operation can be performed according to the returned information, and if so, perform the copy and send a copy success notification to the user.

5. The distributed virtual robotic Al system of claim 1, wherein, The migration of the virtual robot according to user requirements and in combination with multiple computing resource information of the edge computing node comprises: Obtaining a virtual robot migration request message; According to the ID information of the migrated virtual robot, the source network location or area, and the edge computing node ID information, send a migrated virtual robot information query request to the edge computing node in the location or area where the migrated virtual robot is deployed; According to the location or area where the new virtual robot is deployed and the edge computing node ID information of the new virtual robot deployment, a resource query request is sent to the edge computing node of the location or area where the new virtual robot is deployed; According to the return information, it is judged whether the migration operation can be performed, and if so, the migration is performed; A virtual robot information deletion request is sent to the edge computing node of the source location or area where the migrated virtual robot is deployed; After successful deletion, a migration success notification is sent to the user.

6. The distributed virtual robotic Al system of claim 1, wherein, The virtual robot is used for: According to the business request message sent by the business client, the business is analyzed and processed, and if the processing is not successful, a virtual robot capability query message is sent to the center management node; Send a business analysis processing request to the backup virtual robot recommended by the center management node to meet the current business virtual robot capability requirements; Get the processing data of the backup virtual robot after completing the analysis and send it to the business client.

7. The distributed virtual robotic Al system of claim 6, wherein, The analysis and processing of the business include: Preliminary verification of the received business data to ensure data integrity and format correctness, and preprocessing of image or document data; According to the business type and data content, automatically match the applicable audit rules from the pre-defined audit rule engine to perform preliminary verification on the business data to check consistency and compliance; Abnormal identification, risk point identification and inconsistency identification of business data are performed using trained AI data models; The rule engine matching results and AI data model analysis results are summarized to form an audit report.

8. The distributed virtual robotic Al system of claim 6, wherein, The center management node selects the backup virtual robot with the highest priority that meets the current business virtual robot capability requirements from the alliance domain for recommendation, wherein the alliance domain is a virtual robot alliance generated by message indication in the virtual robot creation stage or an automatically generated virtual robot alliance.

Images