A method for integrating intelligent information systems for artificial intelligence systems in the production field

Abstract

This invention discloses an intelligent information system integration method for artificial intelligence systems in the production field, relating to the field of information integration technology in intelligent industrial production. It aims to address the pain points of existing integration methods, such as poor compatibility and insufficient flexibility. The method includes: building a four-level integration architecture; constructing a "general interface + customized interface" adaptation platform to achieve compatible docking of multi-source heterogeneous systems; cleaning, standardizing, and fusing multi-source data, and using a hybrid storage mode to ensure data quality; achieving deep integration and collaborative linkage between the artificial intelligence system and the integration architecture; and building a monitoring platform to complete real-time monitoring, fault early warning, and dynamic optimization, while coordinating debugging and maintenance to ensure system stability. This invention enables unified management, intelligent analysis, and collaborative scheduling of production data, breaks down data barriers between systems, allows for flexible deployment, and possesses dynamic scheduling and self-optimization capabilities. It is particularly suitable for multi-system integration and intelligent decision support in complex manufacturing environments.

Description

Technical Field

[0001] This invention relates to the field of information integration technology in intelligent industrial production, and specifically to an intelligent information system integration method for artificial intelligence systems in the production field. Background Technology

[0002] With the deepening of the "Smart Enterprises" initiative, the application of artificial intelligence technology in the production field is becoming increasingly widespread. Various production enterprises are gradually introducing artificial intelligence systems (such as intelligent inspection, quality testing, process optimization, and equipment operation and maintenance systems) to achieve intelligent upgrades in the production process. However, the current information systems in the production field generally suffer from the problem of "information silos." Information systems for different production links (such as raw material procurement, production and processing, quality testing, warehousing and logistics, and equipment operation and maintenance) are developed by different vendors, using different hardware architectures, data formats, and communication protocols, resulting in the inability of multi-source data to be efficiently interconnected and collaboratively linked.

[0003] Existing information integration methods mostly adopt traditional interface docking modes, which have the following drawbacks:

[0004] First, poor compatibility. For heterogeneous systems with different protocols and formats, separate interfaces need to be developed, which is costly and time-consuming, and it is difficult to adapt to the high requirements of real-time performance and accuracy of artificial intelligence systems in the production field.

[0005] Second, the integration flexibility is insufficient. When the production process is adjusted, new artificial intelligence application modules are added, or the information system is replaced, the interface needs to be re-debugged. The scalability is poor and it cannot quickly respond to the dynamic changes in the production scenario.

[0006] Third, the data processing efficiency is low. During the integration process, multi-source production data is not cleaned, merged and standardized in a targeted manner, resulting in inconsistent data quality obtained by the artificial intelligence system, which affects the model training accuracy and decision reliability, making it difficult to give full play to the core role of artificial intelligence technology in production optimization.

[0007] Fourth, the lack of a unified integration management and control mechanism makes it impossible to monitor and provide fault warnings in real time for data transmission, interface operation, and system collaboration during the integration process, resulting in poor stability and maintainability of the integrated system.

[0008] For example, during the deployment of the intelligent inspection system, Daqing Oilfield faced the problem of inefficient connection between the equipment data collected by the inspection robot and the pump station system data. This required a significant investment of manpower for data format conversion and manual input, which not only reduced inspection efficiency but also affected the timeliness of equipment optimization and operation management. When the digital platform of Sany Heavy Energy's wind turbine blade factory was integrated with various production monitoring equipment, the lack of unified interfaces resulted in delays in real-time monitoring of production parameters, making it difficult to achieve lean management throughout the entire process.

[0009] Therefore, there is an urgent need for an integration method that adapts to the needs of artificial intelligence systems in the production field, enables efficient compatibility, flexible expansion, high-quality data, and intelligent management of multi-source heterogeneous information systems, addresses the pain points of existing integration technologies, and promotes the large-scale and in-depth application of artificial intelligence systems in the production field. Summary of the Invention

[0010] To address the shortcomings of the aforementioned technologies, this invention provides an intelligent information system integration method for artificial intelligence systems in the production field. This method breaks down data barriers, enables flexible deployment, and possesses dynamic scheduling and self-optimization capabilities. It is particularly suitable for multi-system integration and intelligent decision support in complex manufacturing environments.

[0011] The technical solution adopted by the present invention to achieve the above-mentioned technical effects is as follows:

[0012] A method for integrating intelligent information systems for artificial intelligence systems in the production field includes the following steps:

[0014] Step S1: Integration Requirements Analysis and Architecture Construction: Clarify the core requirements of the artificial intelligence system in the production field, sort out the multi-source heterogeneous information systems in the production process, and build a four-level integrated architecture of "perception layer - transmission layer - processing layer - application layer".

[0015] Step S2, Compatibility and Adaptation of Multi-Source Heterogeneous Information Systems: Construct a unified interface adaptation platform, adopting a combination of "general interface + customized interface" to develop standardized general interfaces to adapt to common production information systems, and develop customized interfaces to adapt to special types of information systems. Through interface adaptive matching, achieve compatibility and docking between multi-source heterogeneous information systems and the integrated architecture.

[0016] Step S3: Standardization and Fusion Processing of Multi-Source Production Data: This involves cleaning, standardizing, and fusing the accessed multi-source heterogeneous data to construct a hybrid distributed data storage system, enabling categorized storage and efficient retrieval of the data.

[0017] Step S4: Deep integration of artificial intelligence system and integrated architecture: Connect the artificial intelligence system in the production field to the processing layer to realize two-way data interaction and collaborative operation. Input the standardized fusion dataset of the processing layer into the artificial intelligence system and feed back the decision results of the artificial intelligence system to the corresponding production information system and production equipment to realize system collaborative linkage.

[0018] Step S5: Intelligent monitoring and optimization of the integrated system: Construct an integrated system monitoring platform to monitor the interface operation status, data transmission rate, data processing efficiency, and system collaboration in real time. Use an artificial intelligence fault prediction model to achieve fault early warning and use an adaptive optimization algorithm to dynamically optimize the system.

[0019] Preferably, in the above-mentioned intelligent information system integration method for artificial intelligence systems in the production field, in step S1, the perception layer is used to collect multi-source data in the production process, the transmission layer is used to realize data transmission between layers and complete protocol conversion, the processing layer is used to perform standardized processing, fusion analysis and storage of multi-source data, and the application layer includes artificial intelligence systems in the production field and various production management applications.

[0020] Preferably, in the above-mentioned intelligent information system integration method for artificial intelligence systems in the production field, in step S1, the multi-source data includes equipment operating parameters, production process parameters, quality inspection data, and environmental data; the transmission layer adopts a hybrid communication protocol, integrating 5G, industrial Ethernet, and LoRa protocols, and sets up a protocol conversion module to achieve adaptive conversion of different communication protocols; the processing layer uses artificial intelligence algorithms to process the data, and the application layer realizes intelligent data analysis, decision output, and system collaborative scheduling.

[0021] Preferably, in the above-mentioned intelligent information system integration method for artificial intelligence systems in the production field, in step S2, the interface adaptation platform is equipped with an interface detection module to detect the interface type, communication protocol and data format of the access system in real time, and automatically match the corresponding general interface or customized interface to realize the plug-and-play interface; the customized interface is developed after obtaining the data transmission protocol and data format of the target system through interface reverse parsing technology.

[0022] Preferably, in the above-mentioned intelligent information system integration method for artificial intelligence systems in the production field, in step S3, the data cleaning adopts an artificial intelligence cleaning algorithm that integrates outlier detection, missing value filling, and duplicate data deduplication; the data standardization formulates data standardization specifications for the production field to achieve the unification of data format, unit, and encoding; the data fusion adopts a multi-source data fusion algorithm to extract the correlation features in the data and form a structured fusion dataset; the hybrid distributed data storage system adopts "time-series database + relational database + non-relational database" to store time-series data, structured data, and unstructured data respectively.

[0023] Preferably, in the above-mentioned intelligent information system integration method for artificial intelligence systems in the production field, in step S4, the artificial intelligence system includes one or more of the following: intelligent decision-making module, equipment fault early warning module, production process optimization module, and quality prediction module; the collaborative linkage includes: when the artificial intelligence system detects abnormal equipment operation, it automatically triggers an alarm mechanism and links with the equipment operation and maintenance system to generate a maintenance work order.

[0024] Preferably, in the above-mentioned intelligent information system integration method for artificial intelligence systems in the production field, in step S5, the integrated system monitoring platform is used to realize the visualization display of monitoring data; the equipment fault early warning module is used to identify potential faults such as interface abnormalities, data transmission interruptions, and substandard data quality, and issue early warning signals and provide fault handling suggestions in advance; the adaptive optimization algorithm adjusts interface parameters, data processing strategies, and system collaboration mechanisms according to changes in monitoring data and production scenarios.

[0025] Preferably, in the above-described intelligent information system integration method for artificial intelligence systems in the production field, the production field includes one or more of the following: machinery manufacturing, chemical production, oil and gas extraction, and new energy production; the multi-source heterogeneous information system includes one or more of the following: production equipment monitoring system, quality inspection system, warehouse management system, order management system, and equipment operation and maintenance system.

[0026] Preferably, the above-mentioned intelligent information system integration method for artificial intelligence systems in the production field also includes a security sandbox mechanism. The security sandbox mechanism is used to monitor the runtime behavior of all integrated third-party AI algorithm packages. Once abnormal memory access or unauthorized network requests are detected, the microservice instance is immediately isolated.

[0027] The beneficial effects of this invention are as follows:

[0028] High compatibility and wide adaptability: This invention combines a "general interface + customized interface" approach with a protocol conversion module and an interface adaptive matching function, enabling rapid access to various multi-source heterogeneous information systems in the production field. It eliminates the need to develop a large number of interfaces for different systems, reducing integration costs and time. It is adaptable to various production scenarios such as machinery manufacturing, chemical production, and oil and gas extraction, solving the pain point of poor compatibility of existing integration methods.

[0029] High flexibility and good scalability: The interface adaptation platform supports plug-and-play interfaces. When the production process is adjusted, new artificial intelligence application modules are added, or the information system is replaced, there is no need to re-debug the entire integration architecture. Only the corresponding interfaces need to be matched or a few customized interfaces need to be developed. It can quickly respond to the dynamic changes in the production scenario, has strong scalability, and meets the iterative upgrade needs of artificial intelligence systems in the production field.

[0030] High data quality and strong support capabilities: Through artificial intelligence cleaning algorithms, standardization processing, and multi-source data fusion algorithms, multi-source heterogeneous data is comprehensively processed, invalid data is eliminated, data standards are unified, and data correlation is strengthened. This provides high-quality, structured fusion datasets for artificial intelligence systems, effectively improving the training accuracy and decision reliability of artificial intelligence models. It solves the problems of low data processing efficiency and poor data quality in existing integration methods, and can better leverage the core role of artificial intelligence technology in production optimization, such as improving equipment inspection accuracy, reducing product defects, and shortening delivery time.

[0031] Intelligent management and control with high stability: An integrated system monitoring platform is built, which uses an artificial intelligence fault prediction model to achieve early warning of faults. Combined with an adaptive optimization algorithm, the system can be dynamically optimized. At the same time, a normalized operation and maintenance mechanism is established, which can monitor the operating status of the integrated system in real time, handle faults in a timely manner, improve the stability and maintainability of the integrated system, reduce the impact of system faults on production, and ensure the coordinated and efficient operation of the artificial intelligence system and the production information system. Attached Figure Description

[0032] Figure 1 This is an overall flowchart of the method described in this invention;

[0033] Figure 2 This is a schematic diagram illustrating the process of compatibility and adaptation of multi-source heterogeneous information systems as described in this invention;

[0034] Figure 3 This is a schematic diagram of the process for standardizing and fusion processing of multi-source production data as described in this invention;

[0035] Figure 4 This is a schematic diagram illustrating the deep integration of the artificial intelligence system and the integrated architecture described in this invention.

[0036] Figure 5 This is a schematic diagram of the intelligent monitoring and optimization process of the integrated system described in this invention. Detailed Implementation

[0037] To provide a further understanding of the present invention, the invention will be further described below with reference to the accompanying drawings and specific embodiments:

[0038] In the description of this invention, it should be noted that the terms "vertical," "upper," "lower," and "horizontal," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, "first," "second," "third," and "fourth" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0039] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or a connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0040] Please see Figure 1 As shown in the figure, an embodiment of the present invention proposes an artificial intelligence method for use in the production field.

[0041] The intelligent information system integration method for energy systems includes the following steps:

[0042] Step S1: Integration Requirements Analysis and Architecture Construction: Clarify the core requirements of the artificial intelligence system in the production field, sort out the multi-source heterogeneous information systems in the production process, and build a four-level integrated architecture of "perception layer - transmission layer - processing layer - application layer".

[0043] The core requirements include data collection scope, real-time data transmission requirements, artificial intelligence model training data requirements, and system collaboration scenarios. The multi-source heterogeneous information systems include industrial production systems such as production equipment monitoring systems, quality inspection systems, warehouse management systems, order management systems, and equipment operation and maintenance systems.

[0044] Step S2, Compatibility and Adaptation of Multi-Source Heterogeneous Information Systems: Based on the integrated architecture built in Step S1, a unified interface adaptation platform is constructed. A combination of "general interfaces + customized interfaces" is adopted to achieve compatible connection between multi-source heterogeneous information systems and the integrated architecture.

[0045] Step S3, Standardization and Fusion Processing of Multi-Source Production Data: Perform data cleaning, standardization and fusion processing on the accessed multi-source heterogeneous data to build a hybrid distributed data storage system, and realize the classified storage and efficient retrieval of data.

[0046] Step S4: Deep integration of the artificial intelligence system and the integrated architecture: Connect the artificial intelligence system in the production field to the processing layer to realize two-way data interaction and collaborative operation. Input the standardized fusion dataset of the processing layer into the artificial intelligence system, and feed back the decision results of the artificial intelligence system to the corresponding production information system and production equipment to achieve system collaboration and linkage.

[0047] The artificial intelligence system includes one or more of the following: intelligent decision-making module, equipment fault early warning module, production process optimization module, and quality prediction module; the collaborative linkage includes: when the artificial intelligence system detects abnormal equipment operation, it automatically triggers an alarm mechanism and links with the equipment operation and maintenance system to generate a maintenance work order.

[0048] Step S5: Intelligent monitoring and optimization of the integrated system: Construct an integrated system monitoring platform to monitor the interface operation status, data transmission rate, data processing efficiency, and system collaboration in real time. Use an artificial intelligence fault prediction model to achieve fault early warning and use an adaptive optimization algorithm to dynamically optimize the system.

[0049] Specifically, in a preferred embodiment of the present invention, in step S1, the sensing layer is used to collect multi-source data during the production process. This multi-source data includes equipment operating parameters, production process parameters, quality inspection data, environmental data, etc. The aforementioned multi-source data uses a standardized acquisition module adapted to different types of sensors, production equipment, and information systems. The transmission layer is used to realize data transmission between the sensing layer and the processing layer, and between the processing layer and the application layer. It adopts a hybrid communication protocol (integrating 5G, Industrial Ethernet, LoRa, etc.) and sets up a protocol conversion module to achieve adaptive conversion between different communication protocols. The processing layer uses artificial intelligence algorithms to standardize, fuse, analyze, and store the collected multi-source data, providing high-quality data support for the artificial intelligence system. The application layer includes artificial intelligence systems in the production field and various production management applications, used to realize intelligent data analysis, decision output, and system collaborative scheduling.

[0050] Specifically, in a preferred embodiment of the present invention, such as Figure 2 As shown, the multi-source heterogeneous information system compatibility adaptation mentioned in step S2 includes the following steps:

[0051] Step S21, General Interface Development: For common information systems in the production field (such as PLC control systems, SCADA systems, MES systems), develop standardized general interfaces to support the parsing and conversion of mainstream data formats (such as JSON, XML, CSV) and reduce redundant development;

[0052] Step S22, Custom Interface Development: For special types of information systems or devices from niche manufacturers, use interface reverse parsing technology to obtain their data transmission protocols and data formats, and develop customized interfaces to ensure that all heterogeneous systems can be connected to the integrated architecture.

[0053] Step S23, Interface Adaptive Matching: Set up an interface detection module in the interface adaptation platform to detect the interface type, communication protocol and data format of the access system in real time, and automatically match the corresponding general interface or customized interface to achieve plug-and-play interface and improve integration flexibility.

[0054] In embodiments of the present invention, standardized general interfaces are used to adapt to common production information systems, while customized interfaces are used to adapt to special types of information systems. Through adaptive matching of interfaces, the compatibility and docking of multi-source heterogeneous information systems with the integrated architecture can be achieved.

[0055] Specifically, in a preferred embodiment of the present invention, such as Figure 3 As shown, the multi-source production data standardization and fusion processing described in step S3 includes the following steps:

[0056] Step S31, Data Cleaning: The collected raw data is processed using artificial intelligence cleaning algorithms to remove abnormal data, supplement missing data, and delete duplicate data, so as to avoid invalid data affecting the training of artificial intelligence models.

[0057] Step S32, Data Standardization: Formulate data standardization specifications for the production field, unify the format, units, and codes of the cleaned data, and convert heterogeneous data from different systems into standardized data to ensure data consistency and comparability;

[0058] Step S33, Data Fusion: A multi-source data fusion algorithm is used to fuse data from different information systems and different collection dimensions, extract the correlation features in the data, and form a structured fusion dataset to provide comprehensive and accurate data support for the artificial intelligence system. At the same time, an improved simulated annealing algorithm is used to optimize the fusion process, improve fusion efficiency and data correlation.

[0059] Step S34, Data Storage: Construct a distributed data storage system, adopting a hybrid storage mode of "time-series database + relational database + non-relational database". The time-series database is used to store real-time time-series data such as equipment operating parameters, the relational database is used to store structured data such as production orders and quality inspection results, and the non-relational database is used to store unstructured data such as images and videos, so as to realize the classified storage and efficient retrieval of data.

[0060] Specifically, in the embodiments of the present invention, the artificial intelligence cleaning algorithm adopts mature technologies in the prior art, including outlier detection, missing value imputation, and deduplication. Through the data processing in step S3 above, it can be ensured that the data quality meets the application requirements of the artificial intelligence system.

[0061] Specifically, in a preferred embodiment of the present invention, such as Figure 4 As shown, the deep integration of the artificial intelligence system and the integrated architecture in step S4 includes the following steps:

[0062] Step S41, Data Input Integration: The standardized fusion dataset output by the processing layer is input into the artificial intelligence system through a dedicated data interface to provide data support for the training and inference of the artificial intelligence model and ensure the real-time and accuracy of data transmission.

[0063] Step S42, Decision Output Integration: The decision results of the artificial intelligence system (such as equipment maintenance suggestions, production process adjustment parameters, quality anomaly warnings, etc.) are fed back to the processing layer, which then distributes them to the corresponding production information system and production equipment to achieve rapid implementation of decisions;

[0064] Step S43, Collaborative Control Integration: Build a system collaborative control module to realize the collaborative linkage between the artificial intelligence system, the production information system, and the production equipment. For example, when the artificial intelligence system detects abnormal equipment operation, it automatically triggers the alarm mechanism of the equipment monitoring system and links the equipment operation and maintenance system to generate maintenance work orders, so as to realize the rapid handling of abnormalities.

[0065] Specifically, in a preferred embodiment of the present invention, such as Figure 5 As shown, the intelligent monitoring and optimization of the integrated system in step S5 includes the following steps:

[0066] Step S51, Real-time monitoring: Monitor the interface operation status, data transmission rate, data processing efficiency, and system collaboration in real time, collect monitoring data and visualize it to facilitate staff to keep track of the system operation status in real time;

[0067] Step S52, Fault Early Warning: Using an artificial intelligence fault prediction model, the monitoring data is analyzed to identify potential faults such as interface anomalies, data transmission interruptions, and substandard data quality. Early warning signals are issued in advance, and fault handling suggestions are given to reduce the impact of faults on production.

[0068] Step S53, Dynamic Optimization: Based on changes in monitoring data and production scenarios, an adaptive optimization algorithm is used to dynamically adjust interface parameters, data processing strategies, and system collaboration mechanisms to improve the operating efficiency and adaptability of the integrated system. At the same time, based on feedback from the application of the artificial intelligence system, the data fusion algorithm and data standardization specifications are continuously optimized to improve data quality.

[0069] Furthermore, in a preferred embodiment of the present invention, the production field includes one or more of machinery manufacturing, chemical production, oil and gas extraction, and new energy production; the multi-source heterogeneous information system includes one or more of production equipment monitoring system, quality inspection system, warehouse management system, order management system, and equipment operation and maintenance system.

[0070] Furthermore, in a preferred embodiment of the invention, a safety sandbox mechanism is also included, wherein the safety sandbox...

[0071] The box mechanism is used to monitor the runtime behavior of all integrated third-party AI algorithm packages. Once abnormal memory access or unauthorized network requests are detected, the microservice instance is immediately isolated.

[0072] This invention simplifies the integration process, reduces the workload of interface development and debugging, and lowers integration costs. At the same time, through unified data management and system collaboration, it improves the utilization efficiency of production data, helps artificial intelligence systems achieve functions such as production process optimization, equipment fault early warning, and precise quality control, effectively improving production efficiency, reducing production costs, and improving product quality. It has strong practicality and promotional value and can drive the transformation of traditional production models to intelligent models.

[0073] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claims. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A method for integrating intelligent information systems for artificial intelligence systems in the production field, characterized in that, Includes the following steps: Step S1: Integration Requirements Analysis and Architecture Construction: Clarify the core requirements of the artificial intelligence system in the production field, sort out the multi-source heterogeneous information systems in the production process, and build a four-level integrated architecture of "perception layer - transmission layer - processing layer - application layer"; Step S2, Compatibility and Adaptation of Multi-Source Heterogeneous Information Systems: Construct a unified interface adaptation platform, adopting a combination of "general interfaces + customized interfaces" to achieve compatible docking between multi-source heterogeneous information systems and the integrated architecture; Step S3, Standardization and Fusion Processing of Multi-Source Production Data: Data cleaning, standardization, and fusion processing are performed on the accessed multi-source heterogeneous data to build a hybrid distributed data storage system, enabling classified storage and efficient retrieval of data; Step S4: Deep integration of artificial intelligence system and integrated architecture: Connect the artificial intelligence system in the production field to the processing layer to realize two-way data interaction and collaborative operation. Input the standardized fusion dataset of the processing layer into the artificial intelligence system and feed back the decision results of the artificial intelligence system to the corresponding production information system and production equipment to realize system collaborative linkage. Step S5: Intelligent monitoring and optimization of the integrated system: Construct an integrated system monitoring platform to monitor the interface operation status, data transmission rate, data processing efficiency, and system collaboration in real time. Use an artificial intelligence fault prediction model to achieve fault early warning and use an adaptive optimization algorithm to dynamically optimize the system.

2. The intelligent information system integration method for artificial intelligence systems in the production field according to claim 1, characterized in that, In step S1, the perception layer is used to collect multi-source data in the production process, the transmission layer is used to realize data transmission between layers and complete protocol conversion, the processing layer is used to standardize, fuse, analyze and store multi-source data, and the application layer includes artificial intelligence systems in the production field and various production management applications.

3. The intelligent information system integration method for artificial intelligence systems in the production field according to claim 2, characterized in that, In step S1, the multi-source data includes equipment operating parameters, production process parameters, quality inspection data, and environmental data; the transmission layer adopts a hybrid communication protocol, integrating 5G, industrial Ethernet, and LoRa protocols, and sets up a protocol conversion module to achieve adaptive conversion of different communication protocols; the processing layer uses artificial intelligence algorithms to process the data, and the application layer realizes intelligent data analysis, decision output, and system collaborative scheduling.

4. The intelligent information system integration method for artificial intelligence systems in the production field according to claim 1, characterized in that, In step S2, the interface adaptation platform sets up an interface detection module to detect the interface type, communication protocol and data format of the access system in real time, and automatically match the corresponding general interface or customized interface to achieve plug-and-play interface; the customized interface is developed after obtaining the data transmission protocol and data format of the target system through interface reverse parsing technology.

5. The intelligent information system integration method for artificial intelligence systems in the production field according to claim 1, characterized in that, In step S3, the data cleaning adopts an artificial intelligence cleaning algorithm that integrates outlier detection, missing value imputation, and deduplication of duplicate data; the data standardization formulates data standardization specifications for the production field to achieve uniformity in data format, units, and encoding; the data fusion adopts a multi-source data fusion algorithm to extract correlation features in the data and form a structured fusion dataset; the hybrid distributed data storage system adopts "time-series database + relational database + non-relational database" to store time-series data, structured data, and unstructured data respectively.

6. The intelligent information system integration method for artificial intelligence systems in the production field according to claim 1, characterized in that, In step S4, the artificial intelligence system includes one or more of the following: intelligent decision-making module, equipment fault early warning module, production process optimization module, and quality prediction module; the collaborative linkage includes: when the artificial intelligence system detects abnormal equipment operation, it automatically triggers an alarm mechanism and links with the equipment operation and maintenance system to generate a maintenance work order.

7. The intelligent information system integration method for artificial intelligence systems in the production field according to claim 6, characterized in that, In step S5, the integrated system monitoring platform is used to realize the visualization of monitoring data; the equipment fault early warning module is used to identify potential faults such as interface abnormalities, data transmission interruptions, and substandard data quality, and issue early warning signals and provide fault handling suggestions in advance; the adaptive optimization algorithm adjusts interface parameters, data processing strategies, and system collaboration mechanisms according to changes in monitoring data and production scenarios.

8. The intelligent information system integration method for artificial intelligence systems in the production field according to claim 1, characterized in that, The production field includes one or more of the following: machinery manufacturing, chemical production, oil and gas extraction, and new energy production; the multi-source heterogeneous information system includes one or more of the following: production equipment monitoring system, quality inspection system, warehouse management system, order management system, and equipment operation and maintenance system.

9. The intelligent information system integration method for an artificial intelligence system in the production field according to any one of claims 1 to 8, characterized in that, It also includes a security sandbox mechanism, which is used to monitor the runtime behavior of all integrated third-party AI algorithm packages. Once abnormal memory access or unauthorized network requests are detected, the microservice instance is immediately isolated.

Images