Data processing method and device, readable storage medium and computer program product

Abstract

The embodiment of the invention provides a data processing method and device, a readable storage medium and a computer program product. A control system is connected with a processing system through a gateway. A client is deployed in an artificial intelligence module of the control system based on the target communication protocol, the client is connected with a server, an operator can establish connection with the server in a registration mode, and the operator is accessed to the artificial intelligence module. When the artificial intelligence module executes the data processing task, the artificial intelligence module can quickly interact with the operator according to the target communication protocol so as to perform auxiliary processing through the corresponding operator, thereby completing the data processing task. Through a standardized interface, plug-and-play and distributed deployment of operators are realized, multi-source heterogeneous data are quickly and conveniently accessed to an artificial intelligence model, a data islanding effect is avoided, and the complexity of heterogeneous system integration is reduced. The development process is simple, the artificial intelligence model can quickly and accurately complete tasks by means of operators, and the data processing efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a data processing method, device, readable storage medium, and computer program product. Background Art

[0002] In the industrial sector, processing systems enabled by IoT technologies have emerged to enable control functions such as equipment testing, maintenance, and process optimization. These systems connect to industrial equipment and data collection devices and provide computing tools to implement these control functions. These computing tools, also known as operators, can implement analytical capabilities such as equipment control, data acquisition, and signal processing based on specific algorithms or models.

[0003] However, how to use operators to achieve accurate and efficient data processing has become a technical problem that needs to be solved. Summary of the Invention

[0004] The embodiments of the present application provide a data processing method, device, readable storage medium, and computer program product, which can achieve accurate and efficient data processing with the help of operators.

[0005] In a first aspect, embodiments of the present application provide a data processing method applied to an artificial intelligence module in a control system, wherein the artificial intelligence module integrates a client configured according to a target communication protocol; the client establishes a connection with a server configured according to the target communication protocol, the method comprising: Invoking the client to obtain registration information of at least one operator from the server; the registration information is obtained by registering according to the target communication protocol; In response to a data processing task, selecting at least one target operator that meets task requirements from the at least one operator according to registration information of the at least one operator; Sending a corresponding task request to the at least one target operator according to the target communication protocol; the task request is used to trigger the target operator to perform a corresponding task operation and obtain an operation result; Obtaining, according to the target communication protocol, an operation result returned by each of the at least one target operators; The data processing task is executed in combination with the operation results of the at least one target operator.

[0006] In a second aspect, an embodiment of the present application provides a data processing method, which is applied to a server integrated in a gateway device or a processing system; the gateway device is connected to the processing system; the processing system is connected to at least one operator; the server is connected to the client according to the target communication protocol; the client is an artificial intelligence module configured according to the target communication protocol and integrated into the control system; the method includes: sending registration information of at least one operator registered according to the target communication protocol to the artificial intelligence module; receiving, in accordance with the target communication protocol, a task request corresponding to at least one target operator sent by the client, and sending the corresponding task request to the at least one target operator; the at least one target operator is an operator selected by the artificial intelligence module in response to a data processing task, based on registration information of the at least one operator, from among the at least one operator that meets the task requirements of the data processing task; the task request is used to trigger the target operator to perform a corresponding task operation and obtain an operation result; Receive operation results respectively sent by the at least one target operator according to the target communication protocol, and send the operation results to the artificial intelligence module, so that the artificial intelligence module combines the operation results to perform the data processing task.

[0007] In a third aspect, an embodiment of the present application provides a data processing method, which is applied to a target operator connected to a processing system; the processing system is integrated with a server or a gateway device connected to the processing system is integrated with a server; the server is connected to a client according to a target communication protocol; the client is configured according to the target communication protocol and is an artificial intelligence module integrated into a control system; the method includes: receiving a task request sent by the server; the task request is sent by the artificial intelligence module in response to a data processing task in accordance with the target communication protocol; the target operator is an operator that meets the task requirements of the data processing task; Execute the task operation corresponding to the task request and obtain the operation result; According to the target communication protocol, the operation result is sent to the server, so that the server sends the operation result to the artificial intelligence module, and the artificial intelligence module performs the data processing task in combination with the operation result sent by the target operator.

[0008] In a fourth aspect, an embodiment of the present application provides an electronic device comprising: a memory, a processor, and a communication interface; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the data processing method as described in the first aspect.

[0009] In a fifth aspect, an embodiment of the present application provides an electronic device comprising: a memory, a processor, and a communication interface; wherein, the memory stores executable code, and when the executable code is executed by the processor, the processor executes the data processing method as described in the second aspect.

[0010] In a sixth aspect, an embodiment of the present application provides an electronic device comprising: a memory, a processor, and a communication interface; wherein, the memory stores executable code, and when the executable code is executed by the processor, the processor executes the data processing method as described in the third aspect.

[0011] In the seventh aspect, an embodiment of the present application provides a non-temporary machine-readable storage medium, on which executable code is stored. When the executable code is executed by a processor of an electronic device, the processor can at least implement the data processing method described in the first aspect.

[0012] In an eighth aspect, an embodiment of the present application provides a non-temporary machine-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor can at least implement the data processing method described in the second aspect.

[0013] In the ninth aspect, an embodiment of the present application provides a non-temporary machine-readable storage medium, on which executable code is stored. When the executable code is executed by a processor of an electronic device, the processor can at least implement the data processing method described in the third aspect.

[0014] In a tenth aspect, an embodiment of the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it can implement the data processing method described in the first aspect.

[0015] In an eleventh aspect, an embodiment of the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it can implement the data processing method described in the second aspect.

[0016] In the twelfth aspect, an embodiment of the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it can implement the data processing method described in the third aspect.

[0017] In the data processing solution provided in the embodiment of the present application, various operators in the processing system are connected to the artificial intelligence module in the control system through registration through the target communication protocol. When the artificial intelligence module performs data processing tasks, it can quickly interact with the operator through the target communication protocol to perform auxiliary processing through the corresponding operator, thereby completing the data processing task. Thus, various operators, including operators in heterogeneous processing systems, can be quickly and conveniently connected to the artificial intelligence model through the interface of the standardized target communication protocol. The development process is simple, and plug-and-play and distributed deployment of operators are realized. Multi-source heterogeneous data can be quickly and conveniently connected to the artificial intelligence model, avoiding the data island effect and reducing the complexity of heterogeneous system integration. The artificial intelligence model can use operators to quickly and accurately complete data processing tasks, thereby improving the efficiency of data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, a brief introduction will be given below to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 An architectural diagram of a target communication protocol provided in an embodiment of the present application; Figure 2 A system architecture diagram of a data processing system provided in an embodiment of the present application; Figure 3 An interactive schematic diagram of a data processing method provided in an embodiment of the present application; Figure 4 An interactive schematic diagram of another data processing method provided in an embodiment of the present application; Figure 5 An interactive schematic diagram of another data processing method provided in an embodiment of the present application; Figure 6 An interactive schematic diagram of another data processing method provided in an embodiment of the present application; Figure 7 An interactive schematic diagram of another data processing method provided in an embodiment of the present application; Figure 8 A schematic diagram of the principle of a data processing system provided in an embodiment of the present application; Figure 9 This is a schematic structural diagram of an electronic device provided in this embodiment. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. In addition, the step timing in the following method embodiments is only an example and not a strict limitation.

[0021] It should be noted that when the embodiments of this application involve user information, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation portals for users to choose to authorize or refuse. In addition, the various models involved in this application (including but not limited to large language models or other models) are in compliance with relevant laws and standards.

[0022] First, the terms or concepts involved in the embodiments of this application are explained: Operators: These are computing tools that implement analytical capabilities based on specific algorithms or models. In industrial scenarios, they are also called industrial operators. Industrial operators are core components of industrial systems.

[0023] Artificial Intelligence: is a technology that aims to automate tasks and make decisions by simulating human intelligent behavior through computers.

[0024] Artificial intelligence model: refers to a model trained based on deep learning and artificial intelligence technologies, such as an artificial intelligence-based language model (LM), image recognition model, or multimodal model (MM). It has great generalization and intelligence capabilities, and thus has the ability to handle multiple tasks, such as language understanding, generation, image recognition, etc.

[0025] Model Context Protocol (MCP): is a standardized communication protocol used to integrate artificial intelligence language models with external data sources and tools. It is used to establish a secure two-way connection between the model and the data source, ensuring the security of data transmission and the flexibility of operation.

[0026] Multi-source heterogeneous data: Data from different sources, formats, and structures in industrial scenarios, such as sensor data, equipment logs, and video streams, need to be integrated and processed to support intelligent decision-making.

[0027] Data island effect: The phenomenon of data sharing and integration being difficult in industrial scenarios due to decentralized data storage or lack of a unified interface hinders the implementation of intelligent applications.

[0028] Local sensitive data: data with high privacy and strict security requirements stored in industrial sites or local environments, such as equipment operating parameters and production process information.

[0029] In the industrial sector, operators are often needed to achieve accurate and efficient data processing. For example, in smart manufacturing scenarios, it is necessary to optimize existing production processes based on production data from multiple factories to improve production efficiency.

[0030] With the development of artificial intelligence (AI), AI models can automate tasks, improve efficiency and decision-making capabilities, and are already being applied in a variety of scenarios. If AI can be applied to the industrial sector, it will greatly facilitate data processing in the industrial sector.

[0031] The artificial intelligence model involved in the embodiments of the present application can be an artificial intelligence-based language model (LM) or a large model (LM). The embodiments of the present application do not limit the number of model parameters supported by the model, and the goal is to meet actual needs. If the model parameters are relatively large, the scale of the model will be relatively large, and the model performance will be relatively better. Of course, it will consume more time and resources during the reasoning or training process; if the model parameters are relatively small, the scale of the model will be relatively small. If the performance meets the requirements, the model will be more lightweight and consume relatively less time and resources during the reasoning or training process. The artificial intelligence model can be a deep learning model used to process and generate natural language text or multimodal data. It can be implemented based on a neural network architecture, which can be pre-trained on a large amount of data. In an optional implementation, the artificial intelligence model may include an encoder, a decoder, a self-attention layer, and a feed-forward neural network. The encoder is mainly used to convert input data (usually in sequence form) into vector representation. This process can capture the semantic features of the input data. The decoder is responsible for converting the intermediate representation generated by the encoder into output data (usually in sequence form). The self-attention layer is a mechanism that allows the model to pay attention to other positions in the sequence to better encode the current position information. The feedforward neural network can perform nonlinear transformations on the output of the self-attention layer to enhance the model's expressiveness. The various parts work together to enable the models built on them to perform well in various complex processing tasks, such as natural language processing, computer vision, speech recognition, machine translation, text summarization, and intelligent question answering.

[0032] The following introduces two implementation methods of the artificial intelligence model provided by this application in the industrial field for complex data processing.

[0033] An embodiment of the present application provides a data processing method. Various operators in the processing system can be encapsulated as an application programming interface (API), for example, an API designed in the REST (Representational State Transfer) architectural style, to access the artificial intelligence model. Optionally, a loosely coupled interaction between the artificial intelligence model and the processing system can be achieved through an HTTP service link constructed using retrieval augmentation generation (RAG) technology. However, the HTTP interface is not developed for the characteristics of artificial intelligence model communication, and it is impossible to form a unified standard interface for accessing the artificial intelligence model. The operators in the processing system may be deployed on different platforms or frameworks, and compatibility development is usually required.

[0034] The present application provides another data processing method. An AI model can call operators through function calls to complete data processing tasks. Alternatively, operators can be encapsulated as JSON Schema standard interfaces, and a function call mapping table can be established by fine-tuning the AI model. However, this typically only supports simple operator calls, which can lead to the AI model accidentally triggering sensitive operations, and the corresponding database requires continuous updating.

[0035] In summary, the two data processing methods provided above in the embodiments of the present application have their own shortcomings. In order to overcome these shortcomings, the embodiments of the present application propose a method for implementing accurate and efficient data processing by calling operators through an artificial intelligence model. Through the target communication protocol, various operators in the processing system are connected to the artificial intelligence module in the control system by registration. When the artificial intelligence module performs data processing tasks, it can quickly interact with the operators through the target communication protocol to perform auxiliary processing through the corresponding operators, thereby completing the data processing tasks. Thus, various operators, including operators in heterogeneous processing systems, can be quickly and conveniently connected to the artificial intelligence model through the interface of the standardized target communication protocol. The development process is simple, and the artificial intelligence model can use the operators to quickly and accurately complete data processing tasks, thereby improving the efficiency of data processing.

[0036] The following is an introduction to the new data processing solution provided in the embodiments of the present application.

[0037] The target communication protocol mentioned in the embodiments of this application can establish a communication channel between the artificial intelligence model and the operator, enabling interaction between the artificial intelligence model and the operator, and solving the problem that the artificial intelligence model cannot fully realize its potential due to data island limitations. Exemplarily, the target communication protocol can be the MCP protocol. The architecture of the target communication protocol is introduced below using the MCP protocol as an example.

[0038] See also Figure 1 , Figure 1 This is an architectural diagram of a target communication protocol provided in an embodiment of the present application. The MCP protocol divides the communication between an AI model and an operator into three main parts: the client, the server, and the operator. The client connects to the operator through the server. Typically, the client can be set up within a host program, which can refer to the application program of the AI model. Figure 1 In the example, three servers are shown, namely the first server 102, the second server 103 and the third server 104. It can be understood that the number of servers can be more or less. Figure 1 The number of servers in the example is only an example and does not constitute a limitation of this application. Optionally, the server can be a lightweight service component, also known as a lightweight server. Operators can register with the server through registration to enable operator access. Figure 1 In the example, three operators are shown, namely the first operator 105, the second operator 106 and the third operator 107. It can be understood that in actual applications, the number of operators can be more or less. Figure 1 The number of operators is only an example and does not constitute a limitation of this application. The server provides tools, resources, and functions to the client. Among them, an operator can be a tool, a resource, such as a database resource, or a processing function.

[0039] In a possible embodiment, the connected operators can be compatible with multiple data types, such as structured data, time series data, images, text, etc., to meet the needs of diversified data processing.

[0040] In actual use, the client connects to the AI model, which then obtains information about the currently connected operator from the server through the client. When the AI model requires an operator's assistance in completing a data processing task, it determines the operator to use and the task operation that requires its assistance based on the obtained operator information. It then sends a task request to the operator through the client and server. After the operator performs the corresponding task operation, it obtains the operation result and sends it to the server. The server then sends the operation result to the AI model through the client. This completes the communication between the AI model and the operator via the MCP protocol.

[0041] The following is based on Figure 1 The architecture of the target communication protocol, combined with Figure 2 The architecture of the data processing system used in the data processing method of this application is introduced.

[0042] Figure 2A system architecture diagram of a data processing system provided in an embodiment of the present application, such as Figure 2 As shown, the data processing system may include a control system device, a gateway device and a processing system device. The control system device is connected to the processing system device via the gateway device.

[0043] The control system runs in the control system device, which can be a computer or server, or a cluster of multiple computers and / or servers. Optionally, the control system can be an Internet of Things platform system, a distributed control system (DCS), etc. The control system device integrates an artificial intelligence module, which integrates a client configured according to the target communication protocol. The client can be the above-mentioned Figure 1 In the illustrated embodiment, the client artificial intelligence module can call an artificial intelligence model to complete data processing tasks.

[0044] Gateway devices are used to implement data conversion between control systems and processing systems.

[0045] The processing system device may be a single computer or server, or a cluster consisting of multiple computers and / or servers. Figure 2 In the figure, three processing system devices are shown as an example, namely a first processing system device 203, a second processing system device 204 and a third processing system device 205. It can be understood that in actual applications, the number of processing system devices can be more or less. Figure 2 The number of processing system devices is only an example and does not constitute a limitation to this application. A processing system runs in a processing system device. A processing system can run in one or more processing system devices, and a processing system device can also run one or more processing systems. The processing system can be a data acquisition and monitoring system, a production process management system, a data statistical analysis system, etc. The server can be the above-mentioned Figure 1 The server in the illustrated embodiment can be integrated into a gateway device or a processing system device. Each operator accesses the server by registering.

[0046] Operators can be deployed in processing systems or in cloud devices. For example, operators involving sensitive data can be deployed in processing systems to ensure data security. For example, operators that consume a large amount of transmission resources, such as operators that require GPU resources, can be deployed in processing systems, thereby saving a large amount of network transmission resources compared to deploying operators in cloud devices. For example, deploying operators that require complex computing power in cloud devices can enable operators to execute corresponding tasks more quickly. In addition, if operators that require complex computing power cannot be deployed in the processing system, they can be deployed in cloud devices to provide more capabilities for artificial intelligence models.

[0047] Furthermore, operators deployed in cloud devices can communicate with edge servers deployed in the processing system through the Secure Sockets Layer (SSL) protocol to ensure data security.

[0048] In an optional embodiment, the artificial intelligence model can be deployed in a control system device or a cloud server. In this case, the execution process of the above-mentioned data processing method may be as follows: the artificial intelligence module in the control system receives a data processing task, where the data processing task may be user-input, set in the control system to be completed at a preset time, or obtained in some other way. The artificial intelligence module calls the client to obtain the registration information of at least one operator registered according to the target communication protocol from the server. In response to the data processing task, the artificial intelligence module selects at least one target operator from the at least one operator that meets the task requirements based on the registration information of the at least one operator. Then, according to the target communication protocol, the artificial intelligence module sends a corresponding task request to the at least one target operator via the client and the server. After receiving the task request, the target operator performs the corresponding task operation, obtains the operation result, and sends the operation result to the artificial intelligence module via the server and the client according to the target communication protocol. The artificial intelligence module combines the operation results of the at least one target operator to execute the data processing task. After completing the data processing task, the artificial intelligence module outputs the task result of the data processing task.

[0049] The data processing system and data processing method provided in the embodiments of the present application can be applied in a variety of industrial scenarios. The following examples illustrate applicable industrial scenarios. In intelligent manufacturing scenarios, by integrating artificial intelligence models and operators, production processes can be optimized, equipment utilization and product quality can be improved. Predictive maintenance based on real-time data analysis can be achieved to reduce equipment failures and downtime. In energy management scenarios in the fields of electricity, oil, and natural gas, operators can be called through artificial intelligence models to analyze multi-source heterogeneous data and optimize energy scheduling and consumption. The operating status of key equipment can be monitored to promptly identify potential risks and take measures. In logistics and supply chain scenarios, operators and artificial intelligence models are combined to achieve upgrades in warehouse automation, route optimization, and inventory management. Accurate demand forecasts and resource allocation recommendations are provided to improve supply chain efficiency. In quality inspection scenarios, image recognition models are combined with operators to perform automated quality inspections on products, improving inspection accuracy and efficiency. It also supports defect identification and classification in complex scenarios, reducing the cost of manual intervention.

[0050] The following describes in detail the execution process of the data processing method provided by the embodiment of the present application in conjunction with the accompanying drawings. Optionally, the data processing method can be applied to the above Figure 2 The data processing system shown, wherein the control system in the data processing method can be the above Figure 2 The control system in the data processing system shown in the figure, the artificial intelligence module in the data processing method can be the above Figure 2 The artificial intelligence module in the data processing system shown in the figure, the client in the data processing method can be the above Figure 2 The client in the data processing system shown in the figure, the processing system in the data processing method can be the above Figure 2 The processing system in the data processing system shown in the figure, the server in the data processing method can be the above Figure 2 In the server of the data processing system shown in FIG, the operator and the target operator in the data processing method can be the above Figure 2 Operators in the data processing system shown.

[0051] Figure 3 This is an interactive diagram of a data processing method provided in an embodiment of the present application, such as Figure 3 As shown, the method includes the following steps: 301. The artificial intelligence module calls the client to obtain registration information of at least one operator from the server. The registration information is obtained by registering according to the target communication protocol.

[0052] 302. The artificial intelligence module selects, in response to the data processing task, at least one target operator from the at least one operator according to the registration information of the at least one operator, which meets the task requirements of the data processing task.

[0053] 303. The artificial intelligence module sends a corresponding task request to at least one target operator according to the target communication protocol; the task request is used to trigger the target operator to perform the corresponding task operation and obtain the operation result.

[0054] 304. The target operator executes the task operation corresponding to the task request and obtains the operation result.

[0055] 305. The target operator sends the operation result to the artificial intelligence module according to the target communication protocol.

[0056] 306. The artificial intelligence module performs a data processing task based on the operation results of at least one target operator.

[0057] In this embodiment, if an operator is required to assist the AI model in completing the corresponding function, the operator can be registered based on the target communication protocol. Typically, based on the target communication protocol, the server can register the operator based on the operator's registration information. The operator's registration information is formed based on the content and format of the registration information specified in the target communication protocol. Optionally, the server can form an operator list based on the registration information of the registered operator, so as to more clearly know the currently registered operators, that is, the operators that have been connected.

[0058] The operator registration information refers to the descriptive information that the operator needs to provide during registration, in accordance with the target communication protocol. For example, in accordance with the requirements of the target communication protocol, the registration information may include, but is not limited to, at least one of functional description information, input format, output format, and supported operation types. For example, for a material layer thickness operating status detection operator, its functional description information may include: The operator can query various status detection indicator information, such as "material layer thickness status amplitude indicator, furnace pressure status amplitude indicator, CO (carbon monoxide) content status amplitude indicator."

[0059] Among them, one possible implementation method for registering an operator may be: the server receives the input registration information of the operator to complete the registration of the operator. Usually, the user may input the registration information of the corresponding operator on the server, and the server registers the operator based on the registration information. Another possible implementation method for registering an operator may be: the operator to be connected sends a registration request to the server, the registration request includes the registration information of the operator to be connected, and the registration request is used to instruct the server to complete the registration of the operator to be connected based on the registration information. The operator is usually integrated in the processing system device, and the registration request can be sent to the server through the processing system device. After receiving the registration request, the server completes the registration of the operator according to the registration information.

[0060] Optionally, when registering an operator, authorization from a user with the corresponding permissions is required to complete the registration. This prevents misoperation and ensures the security of accessing the operator.

[0061] In practical applications, the AI module can acquire data processing tasks and invoke an AI model to complete them. The AI module can acquire data processing tasks by receiving them through the AI module's human-computer interface, from a device connected to the control system, or through a scheduled data processing task. The AI module can integrate a human-computer interface to receive user input for data processing tasks that the AI module must complete, and display the results of the data processing tasks after the AI module completes them.

[0062] After receiving a data processing task, the AI module calls the AI model to process it. The following details the data processing process. Hereinafter, the AI module calling the AI model to process the data is referred to as the AI module's processing.

[0063] In response to a data processing task, the artificial intelligence module selects at least one target operator from the at least one operator that meets the task requirements of the data processing task based on the registration information of at least one currently registered operator. Task requirements refer to the required information required to complete the task as indicated by the data processing task. For example, this may include the data range required to execute the data processing task, the format of the task results, the content requirements of the task results, or other information related to the data processing task.

[0064] Optionally, the registration information of at least one operator can be obtained from the server by calling the client after the artificial intelligence module receives the data processing task; or the server can send the registration information to the client each time there is a registered operator, and the client saves the registration information of the operator. When the artificial intelligence module needs the registration information of the operator, it directly calls the client to obtain it.

[0065] The at least one target operator selected can be one target operator or multiple target operators. Figure 3The example in the figure shows a target operator, which does not constitute a limit on the number of target operators. In addition, when processing a data processing task, the artificial intelligence module may not be able to determine all target operators at once, and may also determine the target operators at different times. If all target operators are determined at one time, corresponding task requests are sent to the target operators respectively. If the target operators are determined at different times, the corresponding task requests can be sent to the target operators after the target operators are determined. Regardless of how the target operators are determined, interaction with the target operators can be performed in the manner described in this embodiment. The following details the process of interaction between the artificial intelligence module and the operators.

[0066] The AI module then sends a task request to at least one target operator, triggering it to execute the corresponding task and obtain the result, according to the target communication protocol. According to the target communication protocol, when the AI module needs to interact with an operator, it calls the client, which then interacts with the server.

[0067] In an optional embodiment, the task request may include task parameters, which are used to indicate the task operation to be performed by the target operator and the required operation result.

[0068] It is understandable that different target operators may be able to implement different functions. In the process of processing data processing tasks, the artificial intelligence module may need one or more target operators to assist in obtaining the corresponding operation results. When multiple target operators are required to assist in obtaining the corresponding operation results, corresponding task requests need to be sent to the multiple target operators respectively. For example, two target operators are determined, namely target operator A and target operator B. Target operator A is required to assist in completing task operation C, and target operator B is required to assist in completing task operation D. Then, a task request for instructing the completion of task operation C is sent to target operator A, and a task request for instructing the completion of task operation D is sent to target operator B.

[0069] In an optional embodiment, if the artificial intelligence module determines that multiple target operators are required to assist in obtaining the corresponding operation result, and that the multiple target operators have a certain order in which to execute the task request, priority information may be included in the task request. The priority information is used to indicate the order in which the target operators execute the task request.

[0070] After receiving a task request, the target operator completes the task operation specified in the request and obtains the result. A task operation can be anything the target operator can perform, such as acquiring sampled data, predicting data trends, or other operations. The result is the result obtained from executing the task operation—the information that the target operator needs to return to the AI module, as specified in the task request.

[0071] The target operator sends the operation result to the AI module according to the target communication protocol. According to the target communication protocol, when the operator sends data to the AI module, it must transmit the data through both the server and the client. Here, the target operator sends the operation result to the server, which then sends it to the client, and the AI module receives the operation result.

[0072] The artificial intelligence module combines the received operation results, performs data processing tasks, and obtains data processing results.

[0073] In an optional embodiment, after the artificial intelligence module obtains the data processing result, it can output the data processing result.

[0074] For example, a user at a manufacturing company wants to use an AI model to optimize the predictive maintenance process for production line equipment. This can be done by registering an operator in an existing equipment monitoring system on the server. The operator in the equipment monitoring system can obtain real-time monitoring data from production line equipment provided by the industrial data acquisition and control terminal and perform functions such as vibration signal analysis. Hereinafter, operators in the equipment monitoring system are referred to as industrial operators. The user enters the command "Optimize the predictive maintenance process for production line equipment" into the AI module's human-computer interface. The AI module obtains a list of currently registered industrial operators using the MCP protocol, selects industrial operator E from this list, and sends a task request to industrial operator E via the MCP protocol, instructing it to provide an optimized solution for the predictive maintenance process for production line equipment. After receiving the task request, industrial operator E performs fault prediction operations based on the real-time monitoring data obtained from the production line equipment, obtains optimized control parameters, and feeds these optimized control parameters back to the AI module via the MCP protocol. After receiving the optimized control parameters, the AI module continues executing the task based on them. Later, the AI module needs the assistance of industrial operators to complete the corresponding operations during the execution of the task. Therefore, it selects industrial operators F and G from the industrial operator list and sends task requests to them respectively via the MCP protocol. The task requests instruct industrial operators F and G to perform predictive maintenance on the equipment. This process enables the industrial operators to respond quickly.

[0075] In summary, through the solution provided by the above-mentioned embodiment of the present application, in the industrial field, the control system is connected to the processing system through a gateway. Based on the target communication protocol, a client is deployed in the artificial intelligence module of the control system, and a server is deployed in the processing system or gateway. The operator can establish a connection with the server by registration, thereby connecting the operator to the artificial intelligence module. The artificial intelligence module can call the client and obtain the registration information of at least one currently connected operator from the server. In the process of performing a data processing task, if the artificial intelligence module needs an operator to assist in completing the data processing task, at least one target operator is selected from at least one operator based on the registration information of at least one operator obtained, and a task request for instructing the corresponding task operation is sent to the target operator through the client and the server in accordance with the target communication protocol. After the target operator performs the corresponding task operation, it obtains the operation result and sends the operation result to the server in accordance with the target communication protocol. The server sends the operation result to the client. The artificial intelligence module combines the operation results of at least one target operator to perform the data processing task. As a result, various operators, including those in heterogeneous processing systems, can quickly and easily connect to AI models through standardized target communication protocol interfaces. This standardized interface enables plug-and-play and distributed deployment of operators, effectively integrating multi-source heterogeneous data. This allows for quick and convenient integration of multi-source heterogeneous data into AI models, avoiding data silos and reducing the complexity of heterogeneous system integration. Cross-platform operator integration reduces system transformation costs. When AI modules perform data processing tasks, they can decompose the tasks into multiple subtasks. Through the target communication protocol, they can quickly interact with operators, assisting in completing subtasks with the assistance of operators. This improves task execution efficiency and simplifies the development process. AI models can leverage operators to quickly and accurately complete data processing tasks, improving data processing efficiency and the ability to execute complex data processing tasks.

[0076] In an optional embodiment, when the artificial intelligence module issues a task request to the target operator, it can convert the task request into an input format that the target operator can receive, and send it to the target operator through the server.

[0077] See also Figure 4 , Figure 4 This is an interactive diagram of another data processing method provided in an embodiment of the present application. Figure 4 As shown, the method includes the following steps: 401. The artificial intelligence module calls the client to obtain registration information of at least one operator from the server. The registration information is obtained by registering according to the target communication protocol.

[0078] 402. The artificial intelligence module selects at least one target operator that meets the task requirements from at least one operator in response to the data processing task and based on the registration information of at least one operator.

[0079] 403. The artificial intelligence module converts the format of the task request corresponding to the at least one target operator according to the target communication protocol and the registration information of the at least one target operator to obtain the task request after the format conversion, where the registration information includes the input format.

[0080] 404. The artificial intelligence module calls the client and sends the corresponding format-converted task request to the server; the format-converted task request is used to trigger the target operator to perform the corresponding task operation and obtain the operation result.

[0081] 405. The server sends the corresponding format-converted task request to at least one target operator.

[0082] 406. The target operator executes the task operation corresponding to the received format-converted task request and obtains the operation result.

[0083] 407. The target operator sends the operation result to the artificial intelligence module according to the target communication protocol.

[0084] 408. The artificial intelligence module performs the data processing task based on the operation results of at least one target operator.

[0085] It should be noted that the execution process of steps 401, 402, 406 and 407 is similar to that of the above embodiment and will not be repeated here.

[0086] In this embodiment, the registration information of the operator may include the input format of the operator. The input format of the operator refers to the format of the input task request that can be recognized and executed by the operator.

[0087] After determining at least one target operator, the artificial intelligence module converts the task request into the input format of the at least one target operator according to the target communication protocol and the input format included in the registration information of the at least one target operator, thereby obtaining a converted task request. The artificial intelligence module invokes the client to send the converted task request corresponding to the at least one target operator to the server. The server then sends the converted task request to the corresponding target operator.

[0088] Based on the target communication protocol, when the artificial intelligence module sends a task request to the operator, the task request is formatted and converted into a task request in an input format that the operator can recognize and execute, and then sent to the corresponding operator, so that the operator can accurately and quickly execute the task assigned by the artificial intelligence module, thereby quickly realizing the interaction between the artificial intelligence module and the operator through the target communication protocol.

[0089] In an optional embodiment, the artificial intelligence module may convert the received operation results into context information that can be received by the artificial intelligence model, and send it to the artificial intelligence model for processing.

[0090] See also Figure 5 , Figure 5 This is an interactive diagram of another data processing method provided in an embodiment of the present application. Figure 5 As shown, the method includes the following steps: 501. The artificial intelligence module calls the client to obtain registration information of at least one operator from the server; the registration information is obtained by registering according to the target communication protocol.

[0091] 502. The artificial intelligence module responds to the data processing task and selects at least one target operator that meets the task requirements from at least one operator based on the registration information of at least one operator.

[0092] 503. The artificial intelligence module calls the client according to the target communication protocol and sends a task request to the server. The task request is used to trigger the target operator to perform the corresponding task operation and obtain the operation result.

[0093] 504. The server sends a corresponding task request to at least one target operator.

[0094] 505. The target operator executes the task operation corresponding to the task request and obtains the operation result.

[0095] 506. The target operator sends the operation result to the artificial intelligence module through the server.

[0096] 507. The artificial intelligence module converts the operation results into model context information.

[0097] 508. The artificial intelligence module performs the data processing task in combination with the model context information of at least one target operator.

[0098] It should be noted that the execution process of steps 501-506 is similar to that of the above embodiment and will not be repeated here.

[0099] In this embodiment, after the target operator obtains the operation result, it sends the operation result to the server. The server sends the operation result to the artificial intelligence module through the client.

[0100] The AI module converts the operation result into model context information that the AI model can understand and sends the model context information to the AI model. The AI module obtains the model context information by calling the client and performs data processing tasks.

[0101] Based on the target communication protocol, after the operator sends the operation result to the artificial intelligence module, the artificial intelligence module converts the format of the operation result into model context information that the artificial intelligence model can understand, and sends it to the artificial intelligence module to perform data processing tasks, thereby quickly realizing the interaction between the operator and the artificial intelligence module through the target communication protocol.

[0102] In industrial scenarios, when using AI models to solve given data processing tasks, they often lack a good understanding of the various data processing tasks, resulting in unsatisfactory results. Therefore, when executing data processing tasks, AI models can obtain the corresponding task operation flow and execute the data processing tasks according to this task operation flow.

[0103] In a possible implementation of obtaining the task operation process, the task operation process can be obtained at the same time as the data processing task is obtained. Figure 6 The illustrated embodiment is described in detail.

[0104] See also Figure 6 , Figure 6 This is an interactive diagram of another data processing method provided in an embodiment of the present application. Figure 6 As shown, the method includes the following steps: 601. The artificial intelligence module calls the client to obtain registration information of at least one operator from the server; the registration information is obtained by registering according to the target communication protocol.

[0105] 602. The artificial intelligence module obtains the data processing task and obtains the operation process information corresponding to the data processing task.

[0106] 603. The artificial intelligence module responds to the data processing task and selects at least one target operator that meets the task requirements from at least one operator according to the operation process information.

[0107] 604. The artificial intelligence module calls the client according to the target communication protocol and sends a task request to the server; the task request is used to trigger the target operator to perform the corresponding task operation and obtain the operation result.

[0108] 605. The server sends a corresponding task request to at least one target operator.

[0109] 606. The target operator executes the task operation corresponding to the task request and obtains the operation result.

[0110] 607. The target operator sends the operation result to the artificial intelligence module according to the target communication protocol.

[0111] 608. The artificial intelligence module performs the data processing task based on the operation results of at least one target operator.

[0112] It should be noted that the execution process of step 601 and steps 604-608 is similar to that of the above embodiment and will not be repeated here.

[0113] In this embodiment, the operational process information is used to indicate the process for executing a data processing task. For example, the operational process information may be the content of the operational steps listed in the order in which they are to be executed. The artificial intelligence module obtains the data processing task and obtains the operational process information corresponding to the data processing task. For example, a user enters a data processing task and the operational process information corresponding to the data processing task in the human-computer interaction interface. The artificial intelligence module executes the data processing task based on the operational process information. For another example, when another device sends a data processing task to the artificial intelligence module, it also sends the operational process information corresponding to the data processing task.

[0114] The artificial intelligence module executes the data processing task according to the process indicated by the operation process information.

[0115] The method provided in this embodiment, by issuing corresponding operation process information while issuing data processing tasks to the artificial intelligence module, the artificial intelligence model refers to the operation process information to perform data processing tasks, so that the artificial intelligence model can better understand the data processing tasks in the industrial field, save the computing power of the artificial intelligence model to process data processing tasks, improve the efficiency of data processing, and make the obtained data processing results more in line with industrial scenarios, thereby improving the accuracy and ease of use of the data processing results.

[0116] In another possible implementation of obtaining the task operation process, the task operation process can also be obtained through one or more operators, and the operators are connected to the artificial intelligence module. Figure 7 The illustrated embodiment is described in detail.

[0117] See also Figure 7 , Figure 7 This is an interactive diagram of another data processing method provided in an embodiment of the present application. Figure 7 As shown, the method includes the following steps: 701. The artificial intelligence module calls the client to obtain registration information of at least one operator from the server; the registration information is obtained by registering according to the target communication protocol.

[0118] 702. The artificial intelligence module selects at least one target operator from at least one operator in response to the data processing task based on registration information of at least one operator; the target operator is used to provide operation flow information of the data processing task.

[0119] 703. The artificial intelligence module calls the client according to the target communication protocol and sends a task request to the server. The task request is used to trigger the target operator to return the operation flow information of the data processing task.

[0120] 704. The server sends a corresponding task request to at least one target operator.

[0121] 705. The target operator executes the task operation corresponding to the task request and obtains the operation result; the operation result is used to indicate the operation flow information of the data processing task.

[0122] 706. The device where the target operator is located sends the operation result to the artificial intelligence module according to the target communication protocol.

[0123] 707. The artificial intelligence module performs the data processing task based on the operation results of at least one target operator.

[0124] In this embodiment, in the industrial field, a control system is connected to a processing system via a gateway. Based on the target communication protocol, a client is deployed in the control system's artificial intelligence module, and a server is deployed in the processing system or gateway. Operators can establish a connection with the server through registration, thereby connecting the operators to the artificial intelligence module. Operators can include those that provide operational process information.

[0125] When the artificial intelligence module calls the artificial intelligence model to process a data processing task, if the artificial intelligence model needs to obtain the operational process information corresponding to the data processing task, it can call the client and obtain the registration information of at least one currently connected operator from the server. Based on the obtained registration information of the at least one operator, the artificial intelligence model selects at least one target operator from the at least one operator for providing the operational process information. Then, according to the target communication protocol, the artificial intelligence model sends a task request to the selected target operator via the client and the server, instructing the operator to obtain the operational process information for the data processing task.

[0126] The target operator obtains the operation result indicating the operation flow information of the data processing task and sends the operation result to the server according to the target communication protocol. For example, the target operator can be a vector database, which stores the operation flow information as vectors. Based on the data processing task, the target operator obtains the corresponding operation flow information from the vector database as the operation result.

[0127] The server sends the operation result to the client. The artificial intelligence module combines the operation result of at least one target operator, that is, the operation process information, to perform the data processing task.

[0128] In an optional embodiment, the number of operation results returned by at least one target operator may be one or more, that is, the operation process information may be one or more. For example, the number of target operators may be one, and the target operator returns one or more operation process information for the task request; the number of target operators may be multiple, and each target operator returns one or more operation process information for each received task request. The artificial intelligence model can then perform the data processing task in combination with one or more operation process information. For example, if the artificial intelligence model receives multiple operation process information, it can select a target operation process information from the multiple operation process information and perform the data processing task according to the target operation process information.

[0129] In this embodiment, the artificial intelligence module obtains the operation process information corresponding to the data processing task from the operator during the process of processing the data processing task. The artificial intelligence model refers to the operation process information to perform the data processing task, so that the artificial intelligence model can better understand the data processing tasks in the industrial field, save the computing power of the artificial intelligence model to process the data processing tasks, improve the efficiency of data processing, and make the obtained data processing results more in line with the industrial scenario, thereby improving the accuracy and ease of use of the data processing results.

[0130] In an optional embodiment, the artificial intelligence module determines that a function currently requires the assistance of an operator to implement, and multiple operators can implement it. The artificial intelligence module can then determine at least one operator as the target operator from multiple operators that have the ability to implement the function, that is, determine to implement the function with the assistance of the target operator.

[0131] In an optional embodiment, the number of AI models that can be called by the AI module can be one or more. If there is only one AI model, then that AI model can be directly called to perform the data processing task. If there are multiple AI models, then after obtaining the data processing task, an AI model can be selected from the multiple AI models to perform the data processing task.

[0132] In one possible implementation of selecting an artificial intelligence model, the identification information of the target artificial intelligence model corresponding to the data processing task can be obtained when obtaining the data processing task. The identification information of the artificial intelligence model is used to indicate that the data processing task is executed by the target artificial intelligence model corresponding to the identification information. For example, when the user enters the data processing task in the human-computer interaction interface, the target artificial intelligence model is selected from the callable artificial intelligence models so that the currently input data processing task is executed by the target artificial intelligence model. For another example, the artificial intelligence module is set to a default artificial intelligence model. When the user enters the data processing task in the human-computer interaction interface, the user does not select an artificial intelligence model. In this case, the artificial intelligence module calls the default artificial intelligence model to execute the data processing task.

[0133] In another possible implementation method of selecting an artificial intelligence model, after the artificial intelligence module obtains the data processing task, it can determine the target artificial intelligence model corresponding to the data processing task from multiple artificial intelligence models based on the data processing task, so as to execute the data processing task through the target artificial intelligence model.

[0134] Furthermore, because AI models typically require significant computing power, local control systems, such as edge devices within them, have limited computing resources, making it difficult to deploy complex AI models. Locally deployed AI models may struggle to support complex data processing tasks. Edge devices are widely distributed in industrial systems, and deploying AI models on edge devices requires significant investment in both manpower and material resources for upgrades and maintenance. Furthermore, using AI models deployed on cloud devices relies on network stability, and industrial scenarios may involve sensitive local data. Data leakage can easily occur during transmission to cloud devices and processing by cloud devices, posing data security risks. Long-term use of AI models deployed on cloud devices will also increase costs.

[0135] Considering the aforementioned factors, AI models can be deployed in cloud devices and / or control systems. For example, when data processing tasks involve sensitive data, AI models deployed in the control system can be invoked to ensure the security of local sensitive data. For example, when complex data processing tasks involve AI models deployed in cloud devices, the higher capabilities of these models can be leveraged to complete these complex data processing tasks.

[0136] By selecting different AI models, it is possible to dynamically switch between them to adapt to the execution of different data processing tasks. If one AI model is not suitable, there are multiple other options, which reduces dependence on a single AI model and reduces the risk of technology lock-in.

[0137] In an optional embodiment, in actual applications, accessing various operators through the target communication protocol can embed industrial domain expertise, such as process flows, equipment characteristics, and industry standards, into AI models, enhancing the models' understanding and reasoning capabilities for specific industrial scenarios. By executing data processing tasks, the AI module can learn from the operator's operational data and dynamically optimize its decision-making strategies, forming a knowledge update system that enhances system robustness and improves accuracy.

[0138] In an optional embodiment, the control system can store logs that record the interactions between the AI module and operators during the completion of data processing tasks. This allows for full traceability of the task execution process, facilitating troubleshooting and performance optimization.

[0139] The following combination Figure 8 , taking the target communication protocol as the MCP protocol as an example, the principle of a data processing system provided by an embodiment of the present application is introduced.

[0140] Figure 8 A schematic diagram of a data processing system provided in an embodiment of the present application is shown in FIG. Figure 8As shown, the data processing system provided in this embodiment includes a control system 801, an artificial intelligence module 802, an MCP server 803, a first artificial intelligence model 804, a second artificial intelligence model 805, a first operator resource 806, and a second operator resource 807. Control system 801 corresponds to the control system in the aforementioned embodiment. Control system 801 can integrate artificial intelligence module 802, and control system 801 can also access operator resource 806 via protocols such as HTTP. Artificial intelligence module 802 corresponds to the artificial intelligence module in the aforementioned embodiment. Artificial intelligence module 802 integrates an MCP client, which corresponds to the client in the aforementioned embodiment. MCP server 803 is integrated into artificial intelligence module 802. MCP server 803 corresponds to the server in the aforementioned embodiment. Artificial intelligence module 802 can call either the first artificial intelligence model 804 deployed in the public cloud or the second artificial intelligence model 805 deployed in an industrial field environment, enabling flexible model switching. MCP server 803 can connect to the second operator resource 807 deployed in the public cloud via SSL and Post Office Protocol (POP) to ensure data communication security. It can also connect to a first operator resource 806 deployed in an industrial field environment. The first operator resource 806 and the second operator resource 807 can respectively include operators constituting an industrial IoT model and operators constituting a dataset. Thus, through this deployment, the threshold for operator integration is lowered through service openness, enabling the integration of operators with artificial intelligence models via the MCP protocol. The artificial intelligence module can then call operators for rapid data processing.

[0141] The MCP protocol has built-in data encryption and access control mechanisms to ensure the security of industrial data during transmission and processing, meeting compliance requirements in the industrial field.

[0142] Based on the above data processing system and in accordance with the MCP protocol, the integration process of industrial operators and artificial intelligence models can include the following steps: Step 1: System initialization.

[0143] System initialization includes operator registration and model configuration. Operator registration means that each operator registers with the MCP protocol server at startup, providing its functional description (such as input and output formats, supported operation types, etc.). Model configuration means that the AI model obtains a list of available operators through the MCP protocol and selects the appropriate operator based on the data processing task.

[0144] Step 2: Distribution and execution of data processing tasks.

[0145] When processing data tasks, the AI model sends a task request to the operator via the MCP protocol. The task request contains task parameters and priority information. After receiving the task request, the operator performs calculations based on its internal logic to obtain the operation result.

[0146] Step 3: Result feedback and optimization After the operator completes the task, it returns the operation results to the artificial intelligence model through the MCP protocol.

[0147] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 9 As shown, in practice, the electronic device includes: a memory 21 and a processor 22.

[0148] The memory 21 is used to store computer programs and can be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, data structures, contact data, phone book data, messages, images, videos, etc.

[0149] The processor 22 is coupled to the memory 21 and is used to execute the computer program in the memory 21 to implement the data processing method provided in the above embodiment.

[0150] Further, if Figure 9 As shown, the electronic device also includes: a communication component 23, a display 24, a power component 25, an audio component 26 and other components. Figure 9 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 9 The electronic device of this embodiment can be implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone or an IOT device, or a server device such as a conventional server, a cloud server or a server array.

[0151] The above-mentioned memory can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random-access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0152] The communication component is configured to facilitate wired or wireless communication between the device in which the communication component resides and other devices. The device in which the communication component resides can access a wireless network based on a communication standard, such as a 2G, 3G, 4G / LTE, 5G, or other mobile communication network, or a combination thereof. In an exemplary embodiment, the communication component receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel.

[0153] The display includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, it may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensors can detect not only the boundaries of a touch or slide action, but also the duration and pressure associated with the touch or slide operation.

[0154] The power supply assembly provides power to various components of the device in which the power supply assembly is located. The power supply assembly may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which the power supply assembly is located.

[0155] The above-mentioned audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC). When the device where the audio component is located is in an operating mode, such as call mode, recording mode, and voice recognition mode, the microphone is configured to receive external audio signals. The received audio signal can be further stored in the memory or sent via the communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0156] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to implement each step in the above-mentioned method embodiment. The computer-readable storage medium includes volatile or non-volatile storage, or a combination thereof, and may be removable or non-removable. Examples of computer-readable storage media include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape, disk storage or other magnetic storage devices, or any other non-transmission medium.

[0157] Accordingly, an embodiment of the present application further provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the processor is enabled to implement the steps in the above-mentioned method embodiment. It should be understood that each process or a combination of multiple processes in the above-mentioned method flow can be implemented by a computer program or instruction. In addition, these computer programs or instructions can be applied to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device, so that the processor of the general-purpose computer, the special-purpose computer, the embedded processor or other programmable data processing device can be implemented as a device for implementing the corresponding functions in the above-mentioned method embodiment.

[0158] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A data processing method, characterized in that: An artificial intelligence module used in a control system, wherein the artificial intelligence module integrates a client configured according to a target communication protocol; The client establishes a connection with a server configured according to the target communication protocol, the method comprising: Invoking the client to obtain registration information of at least one operator from the server; the registration information is obtained by registering according to the target communication protocol; In response to a data processing task, selecting at least one target operator that meets a task requirement of the data processing task from the at least one operator according to registration information of the at least one operator; Sending a corresponding task request to the at least one target operator according to the target communication protocol; the task request is used to trigger the target operator to perform a corresponding task operation and obtain an operation result; Obtaining, according to the target communication protocol, an operation result returned by each of the at least one target operators; The data processing task is executed in combination with the operation results of the at least one target operator.

2. The method according to claim 1, characterized in that The sending a corresponding task request to the at least one target operator includes: According to the registration information of the at least one target operator, format conversion is performed on the task request corresponding to the at least one target operator to obtain a task request after format conversion; the registration information includes an input format; The client is called to send the format-converted task request to the server, so that the server sends the format-converted task request to the at least one target operator.

3. The method according to claim 1 or 2, characterized in that After obtaining the at least one operation result returned by each, the method further includes: The operation results returned by each of the at least one target operator are converted into model context information respectively.

4. The method according to claim 1 or 2, characterized in that The method further comprises: Obtaining the data processing task; Determining a target artificial intelligence model corresponding to the data processing task from a plurality of artificial intelligence models; the plurality of artificial intelligence models are respectively deployed in a cloud device and / or a control system; The step of selecting, in response to the data processing task, at least one target operator that meets task requirements from the at least one operator according to registration information of the at least one operator includes: In response to a data processing task, at least one target operator that meets the task requirements is selected from the at least one operator based on the registration information of the at least one operator through the target artificial intelligence model.

5. The method according to claim 1 or 2, characterized in that The method further comprises: Obtaining the data processing task and obtaining the operation process information corresponding to the data processing task; The step of selecting, in response to the data processing task, at least one target operator that meets task requirements from the at least one operator according to registration information of the at least one operator includes: In response to the data processing task, at least one target operator that meets the task requirements is selected from the at least one operator according to the operation flow information and the registration information of the at least one operator.

6. The method according to claim 1 or 2, characterized in that The at least one target operator is used to provide operation flow information of the data processing task; and the operation result includes the operation flow information of the data processing task.

7. A data processing method, characterized in that: Applied to a server integrated in a gateway device or a processing system; the gateway device is connected to the processing system; the processing system is connected to at least one operator; the server is connected to the client according to the target communication protocol; The client is configured according to the target communication protocol and integrated into an artificial intelligence module in the control system; the method includes: sending registration information of at least one operator registered according to the target communication protocol to the artificial intelligence module; receiving, in accordance with the target communication protocol, a task request corresponding to at least one target operator sent by the client, and sending the corresponding task request to the at least one target operator; the at least one target operator is an operator selected by the artificial intelligence module in response to a data processing task, based on registration information of the at least one operator, from among the at least one operator that meets the task requirements of the data processing task; the task request is used to trigger the target operator to perform a corresponding task operation and obtain an operation result; Receive operation results respectively sent by the at least one target operator according to the target communication protocol, and send the operation results to the artificial intelligence module, so that the artificial intelligence module combines the operation results to perform the data processing task.

8. The method according to claim 7, characterized in that The method further comprises: Receive a registration request; the registration request includes registration information of the target operator; Complete the registration of the target operator according to the registration information.

9. A data processing method, characterized in that: A target operator connected to a processing system; a server integrated in the processing system or integrated in a gateway device connected to the processing system; the server connecting to the client according to the target communication protocol; The client is configured according to the target communication protocol and integrated into an artificial intelligence module in the control system; the method includes: receiving a task request sent by the server; the task request is sent by the artificial intelligence module in response to a data processing task in accordance with the target communication protocol; the target operator is an operator that meets the task requirements of the data processing task; Execute the task operation corresponding to the task request and obtain the operation result; According to the target communication protocol, the operation result is sent to the server, so that the server sends the operation result to the artificial intelligence module, and the artificial intelligence module performs the data processing task in combination with the operation result sent by the target operator.

10. The method according to claim 9, characterized in that The method further comprises: Sending a registration request to the server; the registration request includes registration information of the target operator, so that the server completes the registration of the target operator based on the registration information.

11. An electronic device, characterized in that: include: A memory, a processor, and a communication interface; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the method according to any one of claims 1 to 10.

12. A non-transitory machine-readable storage medium, characterized in that The non-transitory machine-readable storage medium stores executable code, and when the executable code is executed by a processor of an electronic device, the processor is caused to perform the method according to any one of claims 1 to 10.

13. A computer program product, characterized in that include: A computer program, when executed by a processor of an electronic device, causes the processor to perform the method according to any one of claims 1 to 10.

Images