Artificial intelligence as a management system for the circular economy

Abstract

An artificial intelligence-driven circular economy management system consisting of: a resource tracking unit configured to monitor and record data on the usage, status, and location of resources along the supply chain, the unit incorporating sensors and data interfaces to capture real-time data from multiple points within a company's operations; a lifecycle monitoring unit operationally coupled with the resource tracking unit and configured to analyze the lifecycle phase of products and materials using AI-driven predictive analytics to forecast deterioration, obsolescence, and remaining usability;a strategic recommendation module that is operationally coupled with the lifecycle monitoring unit and configured to analyze resource status and lifecycle data, the module using an AI-based inference engine to automatically generate strategies for reuse, recycling, refurbishment, and waste minimization of resources; an integration interface unit configured to connect the circular economy management system with existing supply chain and operating systems, the unit including API endpoints and data translation layers;a control processing unit that manages the data flow between the resource tracking unit, the life cycle monitoring unit, the strategic recommendation module, and the integration interface unit, and is configured to execute commands and control the operational states of the connected units based on a set of predefined sustainability targets; and a reporting and visualization unit that aggregates the data generated by the resource tracking unit, the life cycle monitoring unit, and the strategic recommendation module, and is configured to create real-time dashboards and sustainability reports.

Description

Field of the InventionThe present invention relates to a system for management of circulatory management using artificial intelligence that enables companies to deviate from and integrate circulatory management from a linearity-based business model as is currently common in the industry.BACKGROUND OF THE INVENTIONIn recent years there has been a marked conversion to persistent business practices that is driven by both regulatory requirements and by consumers' current expectation. Because of this linear, one-way movement of resources from production to disposal, traditional business models are not considered persistent in view of the waste inherent in their design. In contrast, circulatory economics maximize resource efficiency by being designed for scaling to extend product life cycles and minimize waste. However, current resource management systems do not have intelligence to automatically timely monitor resources during their life cycle and provide implementable strategies for cycle practices. The present disclosure fills in this gap by providing an artificial intelligence-controlled system that not only processes resource flow and lifecycle information, but also provides customized strategic recommendations based on instant analyses, thus allowing companies to shift sustain limits at minimum opportunistic costs.The proposed impact in the direction of circulatory business is in progress; companies and whole countries worldwide move away from linear business models and towards permanent alternatives. Linear Economic: Resources are recovered and then used to produce products which again terminate as waste after their consumption. This not only results in natural resources being exhausted, but at the same time has a very negative effect on the environmental destruction. In contrast, cycle management is designed to optimize resource efficiency by circulating products, materials, and components as long as possible (e.g., periodic use of products, recycling, workup, or reprocessing). Although the concept of circulatory management is not novel, its implementation on a reasonable scale presents considerable challenges, in particular with regard to supply chain management and operation.Existing mechanisms for promoting circulatory management include various resource management systems, ecobalance techniques (LCA), and waste minimization instruments. Some of the better solutions include a basic resource tracking system that enables companies to monitor inventory including garbage. Conventional identification methods such as bar codes and radio frequency identification (RFID) are used by these systems to monitor resources in certain sections of the supply chain. Although this information is valuable to provide insight into the availability and location of resources, it cannot provide real-time insight into the actual use or lifecycle status of resources. Moreover, they do not have the required predictive power to predict what you need when to take appropriate responsive actions.The desire for circulatory management requires the use of life cycle analysis (LCA) tools. These tools evaluate the environmental and life cycle effects of a product from its recovery to disposal. Each resident LCA tool provides an integral solution to the carbon, energy and waste contribution of a product. However, most tools today operate statically and in a retrospective manner and use historical data that no longer reflects the current status of the industry. Moreover, LCA applications are typically separate tools that are currently configured only in supply chain management or enterprise resource planning (ERP) systems. This fragmented type of discovery can prevent companies from developing an integral view, which complicates the development of integrated sustainability strategies.A limitation of most existing solutions is also how well they can be integrated into other business systems already used. The circular solution comprises all phases in the life cycle of a product: design, production, use and disposal. Unfortunately, many of the existing solutions operate in isolation and focus exclusively on certain areas of resource management without considering the overall operational context. This means that, although an LCA tool can provide detailed information on the environmental effects of a product, this information is lost in the decision framework if it cannot be integrated into its supply chain or ERP systems. The lack of integration results in piece goods that often do not conform to more comprehensive sustainability goals.Moreover, current solutions are not always scalable and flexible enough to adapt to already developed age supply chains of today. Conventional resource management systems are generally developed specifically for a particular application or industry and are therefore not suitable for companies with different business models, user-defined workflows or other operational requirements. This also applies to the way a retail waste reduction platform developed for manufacturing will not success where sources and generation will follow other patterns. Moreover, current solutions are not well scalable to the irregular new sets of metadata generated by IoT devices and other novel technologies, which prevents these emerging, but tight resource opportunities from providing real-time insights and only paying for what is actually used.A major limitation of the above solutions is that it cannot provide any recommendations for persistent practices that can be implemented thereby. Although LCA tools and waste reduction platforms may exhibit inefficiencies or wasteful areas, they do not have enough capabilities to provide strategies to combat these problems. For example, an LCA tool could notify them that their product has a high CO2 fuß, but they do not show how they can effectively reduce this footprint with other materials or design specifications and strategies for end-of-life recycling. Since there are no unique, specific and implementable recommendations for companies, many must perform their own sustainability plans; a time-consuming process, the scope of which is simply too large for each company without an entire division of experts dealing only with consumption.Moreover, current solutions typically use historical or incomplete data, resulting in unsatisfactory evaluation and arbitrary control. Most resource tracking and ecobalance tools are based on manually acquired data, while other historical data sets may not reflect actual conditions. A typical example: an ecobalance tool that uses less current emission data may result in underestimate of environmental effects associated with a product and, as a result, misrouted sustainability actions. Moreover, manual data collection is never error free or free from inconsistencies, which in turn leads to inaccuracies in the initiatives of resource management. From a philosophic point of view, this is in sharp contradiction to the circulatory business model, which requires fast and clear data for a far-ahead planning.Existing products do not have user-friendly interfaces and do not offer any adjustment possibilities. Most ecobalance tools and resource accounting systems are rather complex in application, which is a considerable hurdle for smaller companies that may not have their own sustainability experts. Moreover, these solutions are generally not adaptable to business requirements. For example, a waste reduction platform may provide standard reports to different waste streams, but does not allow users to change the report format or add metrics that are important to their business activity. Such inability of the system is problematic because companies do not find any urgent-required disclinic limits on the data provided and therefore have difficulty obtaining useful insight from their data, leading to inadequate environmental strategies.In view of these deficiencies, it is apparent that an AI-based model for cycle management can coherently solve all existing problems of such systems. This targeted system would provide real-time data processing and predictive analyses to provide proactive information for resource management.SUMMARY OF THE INVENTIONThe AI-controlled circulatory management system is a machine system that is intended to help companies and organizations find solutions to the conversion of their business models to circulatory management. This system includes a resource tracker, a life cycle monitor, a strategic recommendation module in the existing workpack tools, and an integration interface with control processing as a report visualization for adaptive method management. The parts cooperate to collect and process data on resources and life cycles so that recommendations can be issued that include AI-based practices such as reuse of materials or minimization of wastes. With the flexibility to always work well with existing supply chain and factory systems, real-time data exchange between different functions is facilitated to make optimal decisions to achieve sustainability objectives as well as to maintain winnings.The main aim of the invention is to provide the implementation of an AI-based management system for circulatory management, in which companies are given the possibility of deviating from the phase of linear management, which is common and entails many adverse effects on sustainability due to excessive resource consumption (which directly leads to depletion of resources) as well as economic losses; by circulating goods, until the irreversible residual inventory remains minimal. The system should support persistent resource management by offering cradle-to-cradle life cycle tracking from material purchase to disposal and recommendations to increase utility. The system may use AI to analyze data in progress and predict resource demand as needed, as well as perform life cycle analysis of products, followed by strategic advice for reduction, reuse, or recycling based on recommendations.Another object of the invention is seamless attachment to a growing number of supply chain and operating systems so that sustainability goals can be tracked in enterprise-wide institutions without compromising portability or operating efficiency. In this way, companies get a comprehensive survey of the resource flow and can closely associate sustainability institutions with the core business processes, e.g. with production planning, inventory management or logistics. Moreover, the decision process is to be better informed through data visualization by making the data available in real time and thus providing contextual results, e.g., insight into natural resource usage at a particular geographic location, environmental impact through resource usage, progress in achieving circulatory management goals, etc.Moreover, an object of the present solution is to overcome existing restrictions that invalidate known resource management solutions because they are generally nonpredictive (i.e., based on the past) and poorly integrated into other enterprise systems. To counteract these limitations, the AI-based circulatory management system utilizes innovative predictive analysis modules, so companies can predictively plan their resource requirements and inform them about persistent possibilities even before waste arises. Adaptive algorithms automatically refine life cycle predictions based on real-time data, so that companies have the most up-to-date and precise information to make decisions for resource planning.Another object of the invention is to provide a user-friendly and configurable platform that can be adapted to specific sustainability targets in different areas. This modularity in system architecture allows companies to optimize and reconfigure their own platform according to resource management requirements, also making them suitable for various applications such as manufacturing, retailing, or even waste management. The AI-controlled cycle management system provides a flexible and scalable solution that allows companies to achieve both ecological and economic advantages in their efforts to introduce a more durable and cycle oriented business model.Brief Description of the FigureFIG. 1 is a block diagram of a cycle management system according to an embodiment of the present invention.DETAILED DESCRIPTION OF THE INVENTIONFIG. 1 shows a block diagram of a circulatory management system, comprising: a resource tracking unit 102 configured to monitor and record data for usage, status, and location of resources along the supply chain, the unit comprising sensors and data interfaces for acquiring real-time data from multiple points within operations of a business; a life cycle monitoring unit 104 operatively coupled to the resource tracking unit and configured to analyze the life cycle state of products and materials using AI-controlled predictive analyses to predict wear, aging, and remaining utility; a strategic recommendation module 106 operatively coupled to the lifecycle monitoring unit and configured to analyze resource status and lifecycle data, the module using an AI-based inference engine to automatically generate strategies for re-use, recycling, workup, and waste minimization of resources; an integration interface unit 108 configured to associate the circulation management system with existing supply chain and operating systems, the unit including API endpoints and data translation levels to ensure compatibility and data exchange across multiple enterprise software platforms; a control processing unit 110 that manages the flow of data between the resource tracker, life cycle monitor, strategic recommendation module, and integration interface unit and is configured to execute instructions and control the operating states of the connected units based on a set of predefined sustainability targets; and a reporting and visualization unit 112 that aggregates the data generated by the resource tracker, life cycle monitor, and strategic recommendation module and is configured to generate real-time dashboards and sustainability reports for business partners, the unit providing insights into resource usage, waste reduction, and advances in achieving the goals of circulation management.In one embodiment, the resource tracker 102 includes radio frequency identification (RFID) sensors and Internet of Things (IoT) modules that enable continuous tracking and real-time updating of resource status at different geographic locations and improve data accuracy and updateability.In one embodiment, life cycle monitor 104 uses machine learning models that use historical material wear data, product usage patterns, and environmental impact factors to refine life cycle predictions, the models configured to adapt based on newly acquired real-time monitoring data.In one embodiment, strategic recommendation module 106 includes a resource optimization submodule that identifies synergies between different resources based on AI-controlled clustering algorithms, thus enabling optimized recycle and recycling paths that minimize waste output.In one embodiment, the integration interface unit 108 is also configured with data standardization protocols that convert data from multiple formats to a uniform format, thus facilitating interoperability with third party operating systems, including, but not limited to, enterprise resource planning (ERP) and product lifecycle management (PLM) systems.In one embodiment, the control processing unit 110 includes adaptive feedback mechanisms that continuously adjust the operating parameters of the system based on real-time inputs from the resource tracking unit and the life cycle monitoring unit, thus ensuring alignment with dynamically changing sustainability targets.In one embodiment, the reporting and visualization unit 112 includes interactive simulation tools that allow users to model potential effects of various circulatory management strategies on resource usage. This yields predictive findings about how different strategies can contribute to sustainability goals over specific periods of time.In one embodiment, the system also includes an AI-controlled decision support unit 114 configured to balance the economic and ecological tradeoffs of various strategies recommended by the strategic recommendation module, and to ensure that the proposed solutions maximize both portability and sustainability goals.In one embodiment, strategic recommendation module 106 uses a knowledge-based database that stores information about industry-specific recycling techniques, material properties, and waste processing options, thereby allowing customized recommendations to be created that are customized to the enterprise's unique operational context.In one embodiment, the integration interface unit 108 includes a real-time data synchronization submodule configured to synchronize data inputs from multiple operating systems with minimal latency, thereby allowing immediate updates across all connected systems and ensuring data consistency throughout the supply chain.The AI-controlled circulatory management system consists of a series of linked boxes, all of which cooperate to make operative decisions at the level (with highest cooperation) at which circulatory management is to be implemented. There is the resource tracking unit that draws all resources in the entire material supply chain with greatest attention. The unit comprises radio frequency identification (RFID) sensors and internet of things (IoT) modules that provide real-time location, status and usage patterns of the resources. This unit keeps track of resources from purchase to disposal so that the company can obtain detailed consumption data with it.A life cycle monitor connected to the resource tracker uses AI-based predictive analyses to analyze the life cycle of matters / activities / products and materials in different phases. The machine learning models are trained to evaluate wear, aging, etc., and help predict how long the product will be available. Over time, the life cycle monitor refines its predictions with new data collected from each resource tracking component so that companies can make informed decisions about when and how resources are reused or recycled.A strategic recommendation module runs on the resource tracker and is in constant communication with the life cycle monitoring system to inform companies how they can make decisions that take into account sustainability. Proposals are made primarily for ecological sustainability, economic advantages of the measure and adaptability to context. In addition, a module is proposed that includes a sub-module for resource optimization that uses clustering algorithms to discover synergies between different resources and offer optimal recycling paths that are cost effective, generate little waste, etc.The integration interface unit connects the circulatory management system to an enterprise supply chain and operative systems. It publishes API endpoints and translates data between their various enterprise softwares such as ERP, PLM, etc. In addition to data standardization protocols, the integration interface unit also performs a physical transformation of information from various sources to make it uniform and network capable for connection to external systems.The system includes an AI modeled as a decision support unit that trades strategic options. This unit utilized a knowledge-based database with material properties, recycling techniques, and Abfallbewirtschaftungspraktiken. The decision support unit uses this database to adapt its recommendations to the company's operating conditions, so that all suggested strategies remain financially viable and environmentally persistent.The AI-controlled CES platform has a dedicated hardware component that is integrated into the physical machine structure within the central unit. All communication at the POS intrasensor level is over high speed data buses, which allows for near perfect communication between components within the central enclosure unit and in fact supports the control processing unit, strategic recommendation module and integration interface units. The system has external ports for connecting RFID sensors, IoT modules and other peripheral devices that would basically aid in tracking resources. For extended use, the machine structure also includes a fully integrated cooling system to maintain peak performance in continuous operation environments.The device is based on a modular implementation that can replace parts and allow easy control over the installation of future technologies without price penalty. Such a machine structure is strong enough to support different business processes (from small and medium companies to large concerns) and can be scaled for many production nodes in complex supply chains.In one form of the present invention, an artificial intelligence automated circulatory management system is provided for operation in conjunction with sustained resource usage. Its resource tracker collects live data from resources along the entire supply chain. This device includes advanced sensors and RFID or IoT modules that also aid in controlling the availability, location of materials, and their usage pattern. In manufacturing environments, RFID sensors implanted in raw materials can constantly communicate their location and progress through the assembly process, thus accounting for all resources. This data is sent back to a central database which can inform downstream units within the same system.According to an embodiment, the lifecycle monitoring unit communicates with a resource tracking unit that evaluates the lifecycle of resources using AI-controlled predictive analytics. It uses machine learning models to understand both historical and real-time data for material degradation, usage patterns, and environmental impact. For example, the life cycle monitoring unit in a furniture manufacturer can predict when wear of the materials, e.g. wood or metal, is to be expected (based on their previous life cycle data and usage conditions). The AI models are able to adapt and improve their predictions based on new data as they arrive, thereby making this system much better over time. This predictive capability allows companies to predict the future re-useability of resources, thereby allowing them to be more proactive than reactive in resource management.According to one embodiment, the module that gives strategic recommendations is designed to send data from a life cycle monitor to generate AI-driven recommendations on which resources should be reused or recycled to avoid waste. This module includes a sub-module called resource optimization, which uses clustering algorithms to find the correlation between resources of different clusters. For example, a company manufacturing electronic modules like this could sort the remaining components due to disintegrated products and suggest which parts can best be combined with other parts for workup or recycling purposes, thereby minimizing waste production.In one example, the integration interface unit enables seamless operation with existing supply chain and operating systems (e.g., enterprise resource planning (ERP) platforms or product life cycle management systems). This particular device connects systems through the use of API endpoints and data translation levels to allow exchange between systems. An integration interface is used to allow information such as the number of resources used or the current phase of a product's life cycle to be easily transmitted between the application of the circulatory management system and, for example, an ERP system that helps a retail establishment manage inventory and thus allows more informed decisions to be made. This module also provides data standardization protocols that convert different data formats to a common format so that it can be integrated into third party systems and also maintain the integrity of its data set.According to an embodiment, the control processing unit is adapted to control the flow of data between the other units. In addition to controlling data transfer, this unit includes adaptive feedback mechanisms that adjust the parameters of the system as real-time inputs from resource tracking and life cycle monitoring units. In another example, should the system detect a rapid change in resource availability due to unexpected supply chain delays, the control processing unit may change operating conditions and prioritize important resources to ensure that alignment with the company's sustainability targets is maintained even during dynamic developments of circumstances.For example, the reporting and visualization unit may collect system-wide data to present dashboards and sustainability reports in real-time. The interactive simulation tools available in this module provide users with the ability to simulate how various interventions would optimally affect the flow metrics and thus resource usage and waste reduction. For example, a food processing company could use the simulation tools to model which effects of changing a type of packaging material would have on both resource usage and waste generation at various points in the production chain. By visualizing these potential future scenarios, participants may identify a number of circulatory management strategies that help them achieve their sustainability goals in a manner consistent with anticipation of future conditions.Viewed from the top, an AI-controlled decision support unit may be used to assess the economic and ecological advances and disadvantages of various strategies recommended by the strategic recommendation module. This is critical to finding the balance between the environmental advantages (achieved by recycling) and the costs that would arise from the degradation / production of these new materials, and also to achieve economic effects. An example could be a textile company that decides what to do with excess fabric - the use of the decision support unit would allow it to see what financially happens and at the same time to take a lecture of the environmental effects, which can ensure that it is responsible aware of and within its business goals by selecting this strategy.According to one embodiment, the strategic recommendation module of the system is a knowledge-based database that contains details of recycling technologies, material properties, and waste processing capabilities in its business domain. This database allows the module to provide fine tuned, operational context based recommendations. In the automotive sector, the module could for example propose recycling processes for aluminum and steel elements from old cars, which meet the local laws and industry standards and offer a possibility of achieving sustainability goals by the reuse of resources.Moreover, in one embodiment of the integration interface unit, a real-time data synchronization submodule guarantees minimum latencies with changes to each synchronized system. This makes data consistency indispensable throughout the supply chain, since immediate updates ensure timely decisions. Such a submodule would be the live update functionality that could allow a business to transfer its fleet of vehicles data into both its circulatory management system and any assets or resources software used by the same logistics business to track resources across multiple points during transport.All these units operate in a rationalized manner, thus establishing an effective and pragmatic AICE model of resource management in the interest of sustainability, enhanced by AI, but not at the expense of portability. The AI-based SCEMS not only offers companies the best tool to enable the transition from linear to circular processes, but also offers comprehensive sustainability advantages needed by both regulatory authorities and consumers through seamless integration opportunities into existing systems and implementable real-time findings.REFERENCES100 A system for managing circulation management. 102 Resource tracking unit 104 Life cycle monitoring unit 106 Strategic recommendation module 108 Integration interface unit 110 Control processing unit 112 Reporting and visualizing unit 114 Kl-Controlled Decision Support unit

Claims

An artificial intelligence controlled circulatory management system, comprising: a resource tracking unit configured to monitor and record data for use, status and location of resources along the supply chain, the unit comprising sensors and data interfaces for acquiring real-time data from multiple points within operations of a business; a life cycle monitoring unit operatively coupled to the resource tracking unit and configured to analyze the life cycle phase of products and materials using AI controlled predictive analyses to predict degradation, aging, and remaining utility; a strategic recommendation module operatively coupled to the lifecycle monitor and configured to analyze resource status and lifecycle data, the module using an AI-based inference engine to automatically generate strategies for resource reuse, recycling, workup, and waste minimization; an integration interface unit configured to connect the circulation management system to existing supply chain and operating systems, the unit comprising API endpoints and data translation levels; a control processing unit that manages the flow of data between the resource tracking unit, the life cycle monitoring unit, the strategic recommendation module, and the integration interface unit and is configured to execute instructions and control the operating states of the connected units based on a series of predefined sustainability targets; and a reporting and visualizing unit that aggregates the data generated by the resource tracking unit, the life cycle monitoring unit, and the strategic recommendation module and is configured to generate real-time dashboards and sustainability reports.The system of claim 1, wherein the resource tracker comprises radio frequency identification (RFID) sensors and internet of things (IoT) modules that enable continuous tracking and real-time updating of resource status at different geographic locations.The system of claim 1, wherein the life cycle monitor is configured to process historical data on material degradation, product usage patterns, and environmental impact factors to refine life cycle predictions, the models configured to adapt based on newly obtained data from the real-time monitor.The system of claim 1, wherein the strategic recommendation module comprises a resource optimization submodule that identifies synergies between different resources based on AI-driven clustering.The system of claim 1, wherein the control processing unit comprises adaptive feedback mechanisms that continuously adjust the operating parameters of the system based on real-time inputs from the resource tracking unit and the life cycle monitoring unit, thereby ensuring alignment with dynamically changing sustainability targets.The system of claim 1, wherein the reporting and visualization unit includes interactive simulation tools that allow users to model potential effects of different circulatory management strategies on resource usage and thus obtain predictive insights as to how different strategies may contribute sustainability goals over certain periods of time.The system of claim 1, wherein the strategic recommendation module uses a knowledge-based database that stores information about industry-specific recycling techniques, material properties, and waste processing options.The system of claim 1, wherein the integration interface unit comprises a real-time data synchronization submodule configured to synchronize data inputs from multiple operating systems with minimal latency, thereby allowing immediate updates across all connected systems and ensuring data consistency throughout the supply chain.

Images