Generating digital assets for supply chain products

Abstract

The disclosure relates to the field of generative artificial intelligence in track and trace applications for decentral networks, in particular for the selection of decentral networks, respective semantic models and data points associated with a supply chain product. Disclosed are methods, apparatuses, systems, computing nodes, computer elements for generating an digital assets associated with supply chain products.

Description

[0001] GENERATING DIGITAL ASSETS FOR SUPPLY CHAIN PRODUCTS

[0002] TECHNICAL FIELD

[0003] The disclosure relates to the field of generative artificial intelligence in track and trace applications for decentral networks, in particular for the selection of decentral networks, respective semantic models and data points associated with a supply chain product. Disclosed are methods, apparatuses, systems, computing nodes, computer elements for generating digital assets associated with supply chain products.

[0004] TECHNICAL BACKGROUND

[0005] In the supply and production of products multiple regulatory requirements need to be met, which differ depending on the product. To fulfil such regulatory requirements, data on such products may need to be exchanged between different participants involved in the production and use of such products. Such data may be exchanged in a secure and controlled manner within a decentral network connecting different participants involved in the production and / or recycling of the product.

[0006] SUMMARY

[0007] The disclosure relates to an operating system configured for configuration of data exchange via decentral network and selection of product data for data exchange via decentral networks.

[0008] In one aspect disclosed is a method for generating a digital asset associated with at least one supply chain product, wherein the digital asset is configured to exchange product data associated with the at least one supply chain product, the method comprising: providing at least one user and / or system interaction relating to a request to provide the digital asset by generating the digital asset and / or by accessing the generated digital asset; generating at least one selection instruction for selecting at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product based on accessing a configuration data base and at least in part based on the at least one user and / or system interaction, wherein the configuration data base provides access to configuration data including at least decentral network protocols and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol, selecting at least one decentral network protocol and / or at least one data model based on the at least one selection instruction, generating the digital asset based on the selected at least one decentral network protocol and / or at least one data model, wherein the digital asset is generated by generating at least one product data set according to the selected at least one data model by generating at least one selection instruction for selecting at least one data point from a product data base based on the selected at least one data model and / or at least in part based on the at least one user and / or system interaction, wherein the product data base provides product data associated with the at least one supply chain product, generating the digital asset by providing one or more decentral identifier(s) uniquely associated with the supply chain product based on the selected decentral network protocol and by providing a locator to the generated product data set, providing the digital asset for access by one or more data consuming node(s) according to at least one decentral network protocol, in particular according to the selected at least one decentral network protocol.

[0009] In another aspect disclosed is an apparatus for generating a digital asset associated with at least one supply chain product, wherein the digital asset is configured to exchange product data associated with the at least one supply chain product, the method comprising: an input interface configured to provide at least one user and / or system interaction relating to a request to provide the digital asset by generating the digital asset and / or by accessing the generated digital asset, a selection component configured to generate at least one selection instruction for selecting at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product based on accessing a configuration data base and at least in part based on the at least one user and / or system interaction, wherein the selection component is configured to select at least one decentral network protocol and / or at least one data model based on the at least one selection instruction, a configuration data base configured to provide access to configuration data including at least decentral network protocols and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol, an asset generation component configured to generate the digital asset based on the selected at least one decentral network protocol and / or at least one data model, wherein asset generation component is configured to execute the steps of generating at least one product data set according to the selected at least one data model by generating at least one selection instruction for selecting at least one data point from a product data base based on the selected at least one data model and / or at least in part based on the at least one user and / or system interaction, wherein the product data base provides product data associated with the at least one supply chain product, generating the digital asset by providing one or more decentral identifier(s) uniquely associated with the supply chain product based on the selected decentral network protocol and by providing a locator to the generated product data set, 231228

[0010] 3 an output interface configured to provide the digital asset for access by one or more data consuming node(s) according to at least one decentral network protocol in particular according to the selected at least one decentral network protocol.

[0011] The disclosure relates to an operating system configured for configuration of data exchange via decentral network.

[0012] In yet another aspect disclosed is a method for generating a digital asset associated with at least one supply chain product, wherein the digital asset is configured to exchange product data associated with the at least one supply chain product, the method comprising: providing at least one user and / or system interaction relating to a request to provide the digital asset by generating the digital asset and / or by accessing the generated digital asset, generating at least one selection instruction for selecting at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product based on accessing a configuration data base and at least in part based on the at least one user and / or system interaction, wherein the configuration data base provides access to configuration data including at least decentral network protocols and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol, selecting at least one decentral network protocol and / or at least one data model based on the at least one selection instruction, generating and / or providing a request to generate the digital asset(s) generated based on the at least one selected decentral network protocol and / or at least one selected data model and / or to provide access to the digital asset(s) generated based on the at least one selected decentral network protocol and / or at least one selected data mode.

[0013] In yet another aspect disclosed is apparatus for generating a digital asset associated with at least one supply chain product, wherein the digital asset is configured to exchange product data associated with the at least one supply chain product, the method comprising: an input interface configured to provide at least one user and / or system interaction relating to a request to provide the digital asset by generating the digital asset and / or by accessing the generated digital asset, a selection component configured to generate at least one selection instruction for selecting at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product based on accessing a configuration data base and at least in part based on the at least one user and / or system interaction, wherein the selection component is configured to select at least one decentral network protocol and / or at least one data model based on the at least one selection instruction, 231228

[0014] 4 a configuration data base configured to provide access to configuration data including at least decentral network protocols and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol, an output interface configured to generate and / or provide a request to generate the digital asset(s) based on the at least one selected decentral network protocol and / or at least one selected data model and / or to provide access to the digital asset(s) generated based on the at least one selected decentral network protocol and / or at least one selected data mode.

[0015] The disclosure relates to an operating system configured for selection of product data for data exchange via decentral networks.

[0016] In yet a further aspect disclosed is method for generating a digital asset associated with at least one supply chain product, wherein the digital asset is configured to exchange product data associated with the at least one supply chain product, the method comprising: providing at least one user and / or system interaction, at least one decentral network protocol e.g. based on at least one selection instruction and / or at least one data model e.g. based on at least one selection instruction, generating the digital asset based on the at least one decentral network protocol and / or at least one data model, wherein generating the digital asset includes generating at least one product data set according to the selected at least one data model by generating at least one selection instruction for selecting at least one data point from a product data base based on the provided at least one data model and / or at least in part based on the at least one user and / or system interaction, wherein the product data base provides product data associated with the at least one supply chain product, generating the digital asset by providing one or more decentral identifier(s) uniquely associated with the supply chain product based on the decentral network protocol and by providing a locator to the generated product data set, providing the digital asset for access by one or more data consuming node(s) according to the at least one decentral network protocol.

[0017] In yet another aspect disclosed is an apparatus for generating a digital asset associated with at least one supply chain product, wherein the digital asset is configured to exchange product data associated with the at least one supply chain product, the method comprising: an input interface configured to provide at least one user and / or system interaction, at least one decentral network protocol e.g. based on at least one selection instruction and / or at least one data model e.g. based on at least one selection instruction, an asset generation component configured to generate the digital asset based on the at least one decentral network protocol and / or at least one data model, wherein asset generation component is configured to execute the steps of 231228

[0018] 5 generating at least one product data set according to the at least one data model by generating at least one selection instruction for selecting at least one data point from a product data base based on the at least one data model and / or at least in part based on the at least one user and / or system interaction, wherein the product data base provides product data associated with the at least one supply chain product, generating the digital asset by providing one or more decentral identifier(s) uniquely associated with the supply chain product based on the decentral network protocol and by providing a locator to the generated product data set, an output interface configured to provide the digital asset for access by one or more data consuming node(s) according to the at least one decentral network protocol.

[0019] The disclosure relates to uses of data bases and digital assets generated for exchange of product data via decentral networks.

[0020] In yet another aspect disclosed is the use of the configuration data base storing configuration data including at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product and / or the product data base storing product data associated with the at least one supply chain product for generating a digital asset associated with at least one supply chain product as disclosed by the methods and apparatuses herein.

[0021] In yet another aspect disclosed is the use of the digital asset associated with at least one supply chain product generated as disclosed by the methods or apparatuses disclosed herein for providing the product data set generated according to the selected or provided at least one data model for access by or via a pee-to-peer communication according to the selected or provided at least one decentral network protocol for exchanging product data associated with the supply chain product.

[0022] In yet another aspect disclosed is the use of the digital asset associated with at least one supply chain product generated as disclosed by the methods or apparatuses disclosed herein for accessing the product data set generated according to the selected or provided at least one data model by or via a pee-to-peer communication according to the selected or provided at least one decentral network protocol for exchanging product data associated with the supply chain product.

[0023] The disclosure relates to configuration data base for digital asset generation, product data base for digital asset generation, digital asset generated for exchange of product data via decentral network, supply chain products associated with the digital asset, decentral network nodes configured for exchanging product data and computer elements configured to carry out the method steps disclosed herein. 231228

[0024] 6

[0025] In yet another aspect disclosed is a configuration data base storing configuration data including at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product and / or a product data base storing product data associated with the at least one supply chain product for generating a digital asset associated with at least one supply chain product as disclosed by the methods and apparatuses herein.

[0026] In yet another aspect disclosed is a digital asset associated with at least one supply chain product generated as disclosed by the methods or apparatuses disclosed herein for providing the product data set generated according to the selected at least one data model for access by or via a pee-to-peer communication according to the selected at least one decentral network protocol for exchanging product data associated with the supply chain product.

[0027] In yet another aspect disclosed is a digital asset associated with at least one supply chain product generated as disclosed by the methods or apparatuses disclosed herein for accessing the product data set generated according to the selected at least one data model by or via a pee-to-peer communication according to the selected at least one decentral network protocol for exchanging product data associated with the supply chain product.

[0028] In yet another aspect disclosed is a supply chain product associated with a digital asset generated according to the method(s) disclosed herein or by the apparatus(es) disclosed herein.

[0029] In yet another aspect disclosed is a decentral network node associated with or related to the configuration data base storing configuration data including at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product and / or the product data base storing product data associated with the at least one supply chain product for generating a digital asset associated with at least one supply chain product as disclosed by the methods and apparatuses herein.

[0030] In yet another aspect disclosed is a decentral network node configured to provide the digital asset associated with at least one supply chain product generated as disclosed by the methods or apparatuses disclosed herein for providing the product data set generated according to the selected at least one data model for access by or via a pee-to-peer communication according to the selected at least one decentral network protocol for exchanging product data associated with the supply chain product.

[0031] In yet another aspect disclosed is a decentral network node configured to access the digital asset associated with at least one supply chain product generated as disclosed by the methods or apparatuses disclosed herein for accessing the product data set generated according to the selected at least one data model by or via a pee-to-peer communication according to the selected at least one decentral network protocol for exchanging product data associated with the supply chain product. In yet another aspect disclosed is a computer element, such as a computer program product or a machine-readable medium, with instructions, which when executed on one or more computing node(s) or processor(s) is / are configured to carry out the steps of the method(s) disclosed herein or configured to be carried out by the apparatus(es) disclosed herein.

[0032] Any disclosure, embodiments and examples described herein relate to the methods, the systems, apparatuses, uses, databases, digital assets, supply chain products, decentral network nodes and computer elements lined out above and below. Advantageously, the benefits provided by any of the embodiments and examples equally apply to all other embodiments and examples.

[0033] EMBODIMENTS

[0034] In the following, embodiments of the present disclosure will be outlined by ways of embodiments and / or examples. It is to be understood that the present disclosure is not limited to said embodiments and / or examples.

[0035] Various units, entities, nodes or other computing components may be described as "configured to” perform a task or tasks. Configured to shall recite structure meaning "having circuitry that” performs the task or tasks on operation. The units, circuits, entities, nodes or other computing components can be configured to perform the task even when the unit / circuit / component is not operating. The units, circuits, entities, nodes or other computing components that form the structure corresponding to "configured to” may include hardware circuits and / or memory storing program instructions executable to implement the operation. The units, circuits, entities, nodes or other computing components may be described as performing a task or tasks, for convenience in the description. Such descriptions shall be interpreted as including the phrase "configured to.”

[0036] In general, the methods, apparatuses, systems, computer elements, nodes or other computing components described herein may include memory, software components and hardware components. The memory can include volatile memory such as static or dynamic random-access memory and / or nonvolatile memory such as optical or magnetic disk storage, flash memory, programmable read-only memories, etc. The hardware components may include any combination of combinatoric logic circuitry, clocked storage devices such as flops, registers, latches, etc., finite state machines, memory such as static random-access memory or embedded dynamic random-access memory, custom designed circuitry, programmable logic arrays, etc.

[0037] Owing to the transfer of highly standardized data packages within decentral networks connecting multiple supply chain participants producing and / or providing supply chain products, generation of such data packages is cumbersome in handling, especially when providing products to various supply chain participants participating in multiple decentral networks. Hence, there is a need to simplify generation of data packages, in particular for production input used to produce the product, which can be exchanged via a decentral network while at the same time ensuring transfer of all data packages required for further processing. 231228

[0038] 8

[0039] The methods, the systems, supply chain products, passports, digital assets and the computer elements disclosed herein provide an efficient, secure and robust way for sharing or exchanging product or property data across different participant nodes in value chains. In particular, by providing supply chain product specific data via the supply chain product specific passport or digital asset, properties like environmental impact can be shared and made transparent from the material to the product produced from such material. The passport or digital asset enables secure data exchange, since data access can be controlled by the supply chain product provider. The exchanges of data assets can be specific to the supply chain product as produced and tailored to the needs of the supply chain product user. This way an improved tracking and tracing of supply chain products can be achieved by securely providing product or property data in diverse and highly complex value chains. The properties can hence be tracked leading to simpler, more efficient and sustainable handling of supply chain products by value chain participants.

[0040] The disclosure particularly relates to the use of generative artificial intelligence in the context of decentral networks. As more and more supply chains move towards decentral data transfers multiple decentral network protocols emerge. The decentral network protocols may be specific for the supply chain, the tier of the supply chain, the industry, the supply chain products, the end products of the supply chain or any intermediate product of specific supply chains. In essence these protocols define communication standards that may differ depending on the decentral network. One part of the communication standard may relate to data models for describing the digital twin of the respective supply chain product. The supply chain product may relate to physical products produced by the supply chain players. The supply chain product may also relate to intangible products such as energy that is distributed over the grid and where energy provided to the grid may be tracked in a book and claim manner.

[0041] To orchestrate or manage the multiple protocol standards and to reliably track and trace these supply chain products across their respective supply chain, multiple communication protocols need to be fulfilled by the digital assets generated for such supply chain products. The diversity and regular changes make reliable operation according to such protocol standards cumbersome. In particular, the choice of decentral network, the data model or even individual data points to generate the digital assets for the supply chain products and the use of current versions of the standards, lead to high complexity for users of such systems. Owing to the regulatory need to provide supply chain products with their unique digital assets, reliability to orchestrate or manage the multiple protocol standards becomes even more important.

[0042] By generating selection instruction configured to select at least one decentral network, at least one data model and / or at least one product data point for generating the digital asset, the diversity of protocol standards can be handled in a more reliable way. A rule-based selection from a configuration data base that is regularly updated directly from the standard source in the web ensures up to date configuration data for digital asset generation. A Large Language Model (LLM) based selection further enhances the flexibility of the system, since the selection from the configuration base can be executed even if the user of the system cannot accurately specify the decentral network and / or data model to be selected or multiple systems interact based on different protocols. By integrating the product 231228

[0043] 9 database with the LLM even the data point selection may be simplified for the users and systems. Lastly, the up-to- date configuration data base for standard protocols, the LLM integration for decentral network and / or data model, the LLM integration with product data base holding the data points and the stepwise enabled selection makes operating in multiple decentral networks with diverse protocols simpler and hence product tracking in multiple supply chains more reliable.

[0044] The decentral network may include participant nodes configured to perform data transactions or data exchanges between participant nodes, e.g. via peer-to-peer communication between participant nodes. The participant nodes may be associated with producers or user of supply chain products, such as chemical product producers, intermediate product producers, end product producers or end product users. The data transactions or exchanges may be based on a decentral network protocol establishing peer-to-peer communication between participant nodes. The participant nodes of the decentral network may be configured to provide data consuming component(s) and / or data providing component(s). A data providing component may be configured to provide or send product data to another participant node of the decentral network. A data consuming component may be configured to ingest or receive product data from another participant node of the decentral network. Providing product data to the data providing component for access by the data consuming component may include indirect or direct access of the data consuming component to the product data.

[0045] The decentral network protocol may relate to decentral identifier(s) identifying the at least one supply chain product and / or the at least one participant node and / or authentication and / or authorization mechanism(s) authentication and / or authorizing the at least one participant node for data exchange.

[0046] The data transactions or exchanges may be based on a decentral network protocol including decentral identifier(s) associated with at least one supply chain product and / or at least one participant node. Based on the decentral identi- fier(s) of the participant nodes the participant nodes for peer-to-peer communication may be identified. Based on the decentral identifier(s) of the supply chain products the product data associated with the supply chain product for peer-to-peer data exchange may be identified.

[0047] The data transactions or exchanges may be based on a decentral network protocol including authentication and / or authorization mechanism(s). Based on the authentication and / or authorization mechanism(s) a peer-to-peer network between participant nodes of the decentral network may be established. The one or more authentication mecha- nism(s) may be associated with or linked to the decentral identifier(s) related to participant nodes of the decentral network. The one or more authentication mechanism(s) associated with the decentral identifier(s) may be provided to participant node(s) for authenticating the peer-to-peer communication between respective participant nodes. The one or more authentication mechanism(s) associated with the decentral identifier(s) may be accessible by the data providing component and / or the data consuming component of respective participant node. The one or more authorization mechanism(s) may include at least one authorization rule for providing and / or consuming and / or accessing product data. The one or more authorization mechanism(s) may be associated with or linked to the decentral identifier(s) associated with the participant node and / or the supply chain product. The one or more authorization mechanism(s) may be associated with or linked to the decentral identifier(s) related to product data to be accessed and / or exchanged. The decentral configuration allows for more efficient use of computing resources and strengthens control by each data owner of the decentral network.

[0048] The digital asset associated with at least one supply chain product may relate to the digital twin of the supply chain product. Digital twin in this context may relate to product data associated with the supply chain product, such as property data associated with the supply chain product. The digital asset associated with at least one supply chain product may relate to data points related to one or more properties of the supply chain product. The data points related to one or more properties of the supply chain product may relate to properties measured or derived from data measured before, during and / or after production of the supply chain product.

[0049] The digital asset may include at least one decentral identifier and at least one locator to or digital representation locating the product data associated with the supply chain product. The digital asset may include at least one decentral identifier and at least one locator to the data points related to one or more properties of the supply chain product. The digital asset may be provided to the decentral network to be discoverable and / or accessible by the participant nodes. The digital asset may be provided to the decentral network to provide access to the product data associated with the supply chain product e.g. via the locator. The digital asset may be provided to the decentral network to provide access to the data points related to one or more properties of the supply chain product. The digital asset may be provided to the decentral network to provide the locator for accessing to the product data associated with the supply chain product. The digital asset may be provided to the decentral network to provide the locator for accessing to the data points related to one or more properties of the supply chain product. The digital asset may be provided to the decentral network in relation to, linked to or including authentication and / or authorization information. The digital asset may be provided to the decentral network to provide the locator for accessing to the product data associated with the supply chain product after authentication and / or authorization of the by the participant node(s) requesting access. The digital asset may be provided to the decentral network to provide the locator for access to the data points related to one or more properties of the supply chain product by the participant node(s) after authentication and / or authorization of the by the participant node(s) requesting access.

[0050] The digital asset may include the decentral identifier(s) associated with the supply chain product and the decentral identifier(s) may be linked to one or more product data points associated with the supply chain product. The decentral identifier(s) may be linked to the one or more product or property data points. The one or more product data points or property data points may be linked to the decentral identifier included in the digital asset. The one or more product data points, or one or more property data points may be stored in a data base of the supply chain product producer for access by supply chain product user(s), e.g. authenticated and / or authorized for such access. The one or more product data points, or one or more property data points may be stored in a data base of the supply chain product producer for transfer to the supply chain product user e.g. when accessed or on providing the supply chain product. 231228

[0051] 11

[0052] The decentral identifier(s) may comprise any unique identifier uniquely associated with the participant node of the supply chain product producer, the supply chain product producer, the physical entity of the supply chain product, product data sets associated with the supply chain product such as properties of the supply chain product and / or any subset or combination thereof. The decentral identifier(s) may include a Universally Unique IDentifier (UUID) or a Digital IDentifier (DID). The decentral identifier(s) may be issued by a central or decentral identity issuer of the decentral network according to the decentral network protocol. The decentral identifier(s) may be discoverable and or accessible to participant nodes of the decentral network according to the decentral network protocol. The decentral identifier(s) may be linked to authentication and / or authorization information. Via the decentral identifier(s) and the unique association with the participant node of the supply chain product producer, the supply chain product producer, the physical entity of the supply chain product, product data sets associated with the supply chain product such as properties of the supply chain product and / or any subset or combination thereof, access to the supply chain product data may be controlled by the supply chain product producer. This contrasts with central authority schemes, where identifiers are provided by such central authority and access to data is controlled by such central authority. Decentral in this context refers to the usage of the identifier in implementation as controlled by the data owner, such as the supply chain product producer.

[0053] The decentral identifier may be uniquely associated with the supply chain product or the physical entity of the supply chain product, e.g. as packaged for transportation to the supply chain product user. The decentral identifier may be uniquely associated with the digital asset providing access to the product data associated with the supply chain product. The supply chain product digital asset may include one or more digital representation (s) or locator(s) pointing to supply chain product data including the properties or parts thereof. The digital representation or locator may relate to at least one interface to a data providing component. It may further relate to at least one interface to a data consuming comment. It may include an endpoint for data exchange or sharing (resource endpoint) or an endpoint for component interaction (component endpoint), that is uniquely identified via the decentral network protocol. The digital representations) or locator pointing to supply chain product data or parts thereof may be uniquely associated with the decentral identifier(s).

[0054] The decentral network protocol may specify a communication protocol for peer-to-peer communication according to a communication standard defined for the decentral network. For example, some decentral networks may define fully decentral protocols using trust systems based on distributed ledgers such as blockchain implementations. Further for example, other decentral networks may define partially decentral protocols using trust systems that are only partially based on distributed ledgers such as blockchain implementations. For example, verifiable credentials used to verify product data by an issuer node may be implemented based on distributed ledger for the verification information such as blockchain implementations. Further for example, management and orchestration of decentral identifiers associated with participant nodes and / or supply chain products may be implemented based on central management and orchestration systems. The decentral network protocol may differ between different decentral networks. Participant nodes may participate in multiple decentral networks with different decentral network protocols. 12

[0055] The decentral network protocol may include one or more data model(s) defining product data, such as property data points, associated with the supply chain product. The one or more data model(s) may relate to one or more supply chain products and / or supply chain product class(es). The data model may be or may relate to specific supply chain product(s) or class(es).The data model(s) may contain a semantic description of the respective product data set associated with the supply chain product. The semantic description may include the structure of at least a portion of the product data set, and / or properties of the product data set. The data model may define or specify at least types of product data, such as property data points, that relate to properties of the supply chain product. The data model may define or specify at least a context or descriptions of the product data, such as property data points, that relate to properties of the supply chain product. The data model may define or specify key-value pairs for product data, such as property data points, that relate to properties of the supply chain product. The data model may define or specify the digital twin of the supply chain product by product data, such as property data points, that relate to properties of the supply chain product. The data model may be defined or specified per decentral network and / or per supply chain product(s) or class(es).

[0056] The user and / or system interaction may relate to a request to provide the digital asset by generating the digital asset and / or by accessing the generated digital asset. The user and / or system interaction may include one or more indica- tion(s) with respect to the supply chain product, the decentral network and / or the data model. The user and / or system interaction may specify the supply chain product, the decentral network and / or the data model. The user and / or system interaction may relate to the supply chain product, the decentral network and / or the data model. The user interaction may be provided from interaction with a user. The user interaction may include indication(s) with respect to the supply chain product, the decentral network and / or the data model based on natural language or text. The system interaction may be provided from interaction with local and / or decentral computing environment. The system interaction may include indication(s) with respect to the supply chain product, the decentral network and / or the data model based on one or more decentral network protocols.

[0057] The user and / or system interaction may indirectly or semantically relate to the supply chain product, the decentral network and / or the data model. The user and / or system interaction may correspond to the one or more indication(s) as provided by one or more decentral network protocols and / or as stored by a local data base associated with single participant nodes such as the configuration data base or the product data base. The user and / or system interaction may provide context or descriptions in natural language relating to the supply chain product, the decentral network and / or the data model as provided by one or more decentral network protocols and / or as stored by a local data base associated with single participant nodes such as the configuration data base or the product data base.

[0058] The selection instruction may be configured to select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product. The selection instruction may include at least one instruction configured to interact with or access the configuration data base. The selection instruction may include at least one instruction based on the user 13 and / or system interaction. The selection instruction may include at least one instruction configured to search the configuration data base based on the user and / or system interaction. The selection instruction may include at least one instruction configured to retrieve configuration data from the configuration data base based on the user and / or system interaction. The selection instruction may include at least one instruction configured to interact with a template data base storing template instructions for interaction with a general-purpose data driven model or Large Language Model (LLM). The selection instruction may include at least one instruction configured to retrieve at least one template instruction from the template data base storing template instructions for interaction with a general-purpose data driven model or Large Language Model (LLM). The selection instruction may include at least one instruction configured to interact with a general-purpose data driven model or Large Language Model (LLM). The selection instruction may include at least one instruction configured to retrieve a selection from the general-purpose data driven model or Large Language Model (LLM).

[0059] The selection instruction may be configured to select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product based on an instruction chain including multiple sub-instructions to be executed for multiple stages. The selection instruction may include search instruction(s), data base retrieval instruction(s) and / or LLM retrieval instructions. The selection instruction may include sub-instructions with staged instruction(s) per stage. The selection instruction may include a data base retrieval stage, a search stage including a data base retrieval stage and / or a LLM retrieval stage. The data base retrieval stage, the search stage and / or the LLM retrieval stage may be executed based on the user and / or system interaction. If the user and / or system interaction indicates search or retrieval from data base, the search and / or data base retrieval stage may be initiated. In the data base retrieval stage, the data base retrieval instructions may be configured to select the configuration data from the configuration data base based on the user and / or system interaction. In the search stage, one or more search instructions may be configured to search the configuration data base based on the user and / or system interaction, e.g. by semantic search. If the user and / or system interaction indicates LLM retrieval, the LLM retrieval stage may be initiated. In the LLM retrieval stage, the LLM retrieval instructions may be configured to select the configuration data based on the user and / or system interaction, one or more instruction template(s), one or more data base retrieval instructions for retrieving context or descriptions and / or LLM interaction including request and retrieval. If the user and / or system interaction does not indicate search, retrieval from data base or retrieval from LLM, the selection instruction maybe configured to execute a chain of sub-instructions including data base retrieval instruction, which in case of failed selection may be followed by a semantic search retrieval instruction, which in case of failed selection may be followed by the LLM retrieval instruction.

[0060] The configuration data base may provide access to configuration data including at least decentral network protocols and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. The configuration data base may store configuration data including at least decentral network protocols and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol(s). The configuration data base 231228

[0061] 14 may store configuration data in key value pairs including decentral network protocols and per decentral network protocol one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. The configuration data base may store configuration data in key value pairs including decentral network protocols, per decentral network protocol one or more data model(s) and context or descriptions in natural language of data points stored as configuration data.

[0062] The product data set may be generated according to at least one selected or provided data model. The product data may relate to properties of the supply chain product. The product data may include multiple data points relating to properties of the supply chain product. The product data may relate to specific supply chain product(s) or product class(es). The product data set may include a subset of the product data as defined by the at least one selected or provided data model.

[0063] The selection instruction may be configured to select at least one data point from a product data base e.g. based on the provided or selected at least one data model. The selection instruction may include at least one instruction configured to interact with or access the product data base. The selection instruction may include at least one instruction based on the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product. The selection instruction may include at least one instruction configured to search the product data base based on the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product. The selection instruction may include at least one instruction configured to retrieve product data from the product data base based on the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product. The selection instruction may include at least one instruction configured to interact with a template data base storing template instructions for interaction with a general-purpose data driven model or Large Language Model (LLM). The selection instruction may include at least one instruction configured to retrieve at least one template instruction from the template data base storing template instructions for interaction with a general-purpose data driven model or Large Language Model (LLM). The selection instruction may include at least one instruction configured to interact with a general-purpose data driven model or Large Language Model (LLM). The selection instruction may include at least one instruction configured to retrieve a selection from the general-purpose data driven model or Large Language Model (LLM).

[0064] The selection instruction may be configured to select to select at least one data point from a product data based on an instruction chain including multiple sub-instructions to be executed for multiple stages. The selection instruction may include search instruction(s), data base retrieval instruction(s) and / or LLM retrieval instruction(s). The selection instruction may include sub-instructions with staged instruction(s) per stage. The selection instruction may include a data base retrieval stage, a search stage including a data base retrieval stage and / or a LLM retrieval stage. The data 231228

[0065] 15 base retrieval stage, the search stage and / or the LLM retrieval stage may be executed based on the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product. If the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product indicates search or retrieval from data base, the search and / or data base retrieval stage may be initiated. In the data base retrieval stage, the data base retrieval instructions may be configured to select the product data from the product data base based on the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product. In the search stage, one or more search instructions may be configured to search the product data base based on the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product, e.g. by semantic search. If the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product indicates LLM retrieval, the LLM retrieval stage may be initiated. In the LLM retrieval stage, the LLM retrieval instructions may be configured to select the product data based on the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product, one or more instruction template(s), one or more data base retrieval instructions for retrieving context or descriptions and / or LLM interaction including request and retrieval. If the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product does not indicate search, retrieval from data base or retrieval from LLM, the selection instruction maybe configured to execute a chain of sub-instructions including data base retrieval instruction, which in case of failed selection may be followed by a semantic search retrieval instruction, which in case of failed selection may be followed by the LLM retrieval instruction.

[0066] The product data base may provide access to product data including property data associated with the supply chain product to be exchanged by the decentral network protocol. The product data base may store product data including at least property data points signifying properties of the supply chain product. The product data base may store product data in key value pairs including property data associated with the supply chain product to be exchanged by the decentral network protocol. The product data base may store product data in key value pairs including supply chain products, per supply chain product one or more property data point(s) and context or descriptions in natural language of data points stored as product data.

[0067] The digital asset generated based on the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one 231228

[0068] 16 data model related to product data associated with the supply chain product may include at least one or more decentral identifier(s) uniquely associated with the supply chain product based on the selected decentral network protocol and a locator to the generated product data set. The digital asset including one or more decentral identifier(s) uniquely associated with the supply chain product based on the selected decentral network protocol and a locator to the generated product data set may be provided to the decentral network to be discovered and accessed by one or more data consuming node(s) according to the selected at least one decentral network protocol. The digital asset including one or more decentral identifier(s) uniquely associated with the supply chain product based on the selected decentral network protocol, the locator to the generated product data set may be provided to the decentral network to be discovered and accessed by one or more data consuming node(s) according to the selected at least one decentral network protocol and the product data set may be stored in a target data base for digital assets to be discovered and accessed by one or more data consuming node(s).

[0069] In one embodiment the user and / or system interaction relates to at least one decentral network protocol for exchanging product data associated with the supply chain product, at least one data model related to product data associated with the supply chain product and / or a product data set to be generated according to the provided or selected at least one data model. The user and / or system interaction may be provided in one step on starting the method. The user and / or system interaction may be provided prior to each step generating selection instructions. The user and / or system interaction may be provided in one step on starting the method and / or prior to each step generating selection instructions. The user and / or system interaction may be provided prior to the generation of at least one selection instruction for selecting at least one decentral network protocol and / or at least one data model. The user and / or system interaction may be provided prior to the generation of at least one product data set according to the selected or provided at least one data model.

[0070] In another embodiment the user and / or system interaction relates to a request for providing the digital asset by generating the digital asset and / or by accessing the generated digital asset by one or more participant(s) of one or more decentral network(s) and / or for one or more supply chain product(s). The user and / or system interaction may include a request for providing the digital asset by generating the digital asset and / or by accessing the generated digital asset from a specific participant node of a specific decentral network. The user and / or system interaction may specify the specific participant node of a specific decentral network, e.g. by the decentral identifier(s) related to the specific participant node of a specific decentral network. The user and / or system interaction may include a request for providing the digital asset by generating the digital asset and / or by accessing the generated digital asset for a specific supply chain product. The user and / or system interaction may specify the specific supply chain product, e.g. by the decentral identifier(s) related to the specific supply chain product e.g. for a specific decentral network.

[0071] In another embodiment the user interaction may include a prompt instruction in natural language indicating a request to provide the digital asset by generating the digital asset and / or by accessing the generated digital asset. The system interaction may include a system request according to a decentral network protocol indicating a request to provide the digital asset by generating the digital asset and / or by accessing the generated digital asset. The system 231228

[0072] 17 interaction may include the user interaction. The user interaction may include the system interaction. The system interaction may include the selection of at least one decentral network and / or at least one data model based on the at least one selection instruction. On selecting at least one product data point from a product data base the selected at least one decentral network and / or at least one data model may relate to a system interaction.

[0073] In another embodiment the selection instruction includes at least one instruction configured to search the product data base and / or the configuration data base, at least one instruction configured to retrieve configuration data from the configuration data and / or product data from the product data base, at least one instruction configured to interact with a template data base storing template instructions for interaction with a Large Language Model (LLM), at least one instruction configured to interact with the Large Language Model (LLM), at least one instruction configured to retrieve a selection from the Large Language Model (LLM) or any combinations or subsets thereof.

[0074] In another embodiment the selection instruction may include multiple sub-instructions to be executed for one or more stages. The one or more stages may include a retrieval stage, a semantic search stage and / or a LLM retrieval stage. Multiple stages may be staggered, wherein depending on successful or failed selection per stage the retrieval stage may be followed by the semantic search stage and / or the LLM retrieval stage, e.g. the semantic search stage may be followed by the LLM retrieval stage, or the retrieval stage may be followed by the LLM retrieval stage. The selection instruction may include search instruction(s), data base retrieval instruction(s) and / or LLM retrieval instruction(s). The data base retrieval stage, the search stage and / or the LLM retrieval stage may be executed based on the user and / or system interaction and / or the provided or select at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product.

[0075] In another embodiment the configuration data base stores configuration data in key value pairs including decentral network protocols and per decentral network protocol one or more data model (s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. The selection instruction may be configured to retrieve and / or search configuration data from the configuration data base based on the at least one user and / or system interaction and based on the key-value pairs. The at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product may be selected based on the key-value pairs.

[0076] In another embodiment the configuration data base stores configuration data including descriptions in natural language of configuration data points stored as configuration data. The selection instruction may be configured to retrieve configuration data by interaction with a LLM based on the at least one user and / or system interaction and based on the descriptions in natural language of configuration data points stored as configuration data. The at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product may be selected based on the descriptions in natural language of configuration data points stored as configuration data. 231228

[0077] 18

[0078] In another embodiment the configuration database is populated and / or updated based on web data provided for or related to the one or more decentral networks. Web data may relate to decentral network specifications, decentral network identifiers, decentral network context data, data models per decentral network, data models per supply chain product, data model context data or any combinations or subsets thereof. Context data may relate to descriptions in natural language of respective data. Web data may be retrieved by or via a web interface configured to access web repositories and / or scrape webpages. Web data may be retrieved by or via a web interface configured to access web repositories and / or scrape webpages based on an update event received by the web repositories and / or scrape webpages. Web data may be mapped to configuration data for populating and / or updating the configuration data base. Web data may be mapped to the data structure the configuration data is stored in by the configuration data base. Web data may include or relate to public data such as publicly accessible over the internet.

[0079] In another embodiment the product data base stores product data in key value pairs including property data related to properties associated with the supply chain product and to be exchanged by the decentral network protocol. The selection instruction may be configured to retrieve and / or search product data from the product data base based on the selected at least one data model and / or at least in part based on the at least one user and / or system interaction and based on the key-value pairs. The at least one at least one product data set according to the provided or selected at least one data model may be selected based on the key-value pairs. The product data points stored by the product data base may in this embodiment correspond to the data points defined by the selected or provided data model. The product data points may be selected based on selected data model. The product data points stored by the product data base may in this embodiment have one-to-one correspondence or at least semantic correspondence to the data points defined by the selected or provided data model. The product data points may be selected based on selected data model.

[0080] In another embodiment the product data base stores product data including descriptions in natural language of product data points stored as product data. The selection instruction may be configured to retrieve product data by interaction with a LLM based on the selected at least one data model and / or at least in part based on the at least one user and / or system interaction and based on the descriptions in natural language of configuration data points stored as product data. The at least one at least one product data set according to the provided or selected at least one data model may be selected based may be selected based on the descriptions in natural language of product data points stored as product data.

[0081] Generating selection instructions may include retrieving instruction template relating to selection of at least one decentral network, at least one data model and / or at least one data point. The instruction template may be provided to general purpose data driven model to provide at least one decentral network, at least one data model and / or at least one data point to be selected. Selection instructions may include task instruction related to the task to be executed by general purpose data driven model. The selection instructions may include context instructions relating to context of decentral network, at least one data model and / or at least one data point, wherein context is retrieved from the 231228

[0082] 19 configuration and / or product data base. The product data set may be generated according to data model, wherein data points may be retrieved from the product data base, wherein the product data set may be stored in a target product data base in relation to decentral identifier for the selected decentral network that is uniquely associated with the supply chain product and a locator to the generated product data set.

[0083] In another embodiment the product database is related to the decentral network node associated with a decentral network participant producing the at least one supply chain product. The product database may be directly or indirectly communicatively connected to the decentral network node associated with a decentral network participant producing the at least one supply chain product. The product database may store product data for one or more supply chain product(s). The product database may be populated and / or updated based on product data retrieved from the production of the one or more supply chain product(s). The digital assets generated from such product data may be stored by or in a target product data base. The product database may be directly or indirectly communicatively connected to a target data base for storing generated digital assets. The target data base for storing generated digital assets may be directly or indirectly communicatively connected to the decentral network node associated with a decentral network participant producing the at least one supply chain product. The target data base may store the digital asset including decentral identifier(s), product data set related to the decentral identifier(s) and / or the locator to the product data set related to the decentral identifier(s). The digital asset including the decentral identifier(s), and / or the locator to the product data set related to the decentral identifier(s) and stored by the target data base may be provided to decentral network for discovering the digital asset and / or accessing the data set.

[0084] In another embodiment the configuration database is associated with or related to at least one operating system orchestrating decentral network data exchange in multiple decentral networks and / or digital asset generation for orchestrating decentral network data exchange in multiple decentral networks. The configuration database may be associated with or related to the decentral network node associated with a decentral network participant producing the at least one supply chain product.

[0085] BRIEF DESCRIPTION OF DRAWINGS

[0086] In the following, the present disclosure is further described with reference to the enclosed figures. The figures illustrate embodiments as examples. The following embodiments are mere examples for implementing methods, apparatuses, systems, clients or application devices disclosed herein and shall not be considered limiting.

[0087] Fig. 1 a illustrates an example of a participant network of a product ecosystem including a material loop and being associated with a decentral peer-to-peer network for exchange of data associated with raw materials, chemical product(s), discrete product(s), end product(s) and recycled material(s). 231228

[0088] 20

[0089] Fig. 1b illustrates an example of a participant network of a battery ecosystem including a material loop and being associated with a decentral peer-to-peer network for exchange of data associated with raw materials, chemical product(s), batteries, end product(s) and recycled material(s).

[0090] FIG. 2 illustrates an example system and associated methods for generating digital assets associated with supply chain product(s) and providing access to the generated digital assets(s).

[0091] Fig. 3a illustrates an example of an operating system communicatively coupled or connected to multiple data spaces.

[0092] Fig. 3b illustrates another example of an operating system associated with each node connecting multiple nodes in data spaces.

[0093] Fig. 4a illustrates an example of the operating system including a configuration data base that is updated through a configuration data collection and used for generating supply chain product specific digital assets.

[0094] Fig. 4b illustrates the decentral network, data model and / or data point selection based on context stored in relation to respective decentral networks, data models and / or data points.

[0095] Fig. 4c, d illustrates data structures and related processing of descriptions as context.

[0096] Fig. 5 illustrates an example method for generating digital assets for a specific supply chain product.

[0097] Fig. 6 illustrates another example method for generating digital assets for a specific supply chain product.

[0098] Fig. 7a-c illustrates example user interfaces for user interaction to execute the methods for generating digital assets for a specific supply chain product.

[0099] Figs. 8-11 illustrate an example transformer architecture of a general-purpose model. Specifically, FIG. 8 illustrates an embodiment of training an embedding layer. FIG. 9A illustrates an embodiment of a transformer encoder architecture. FIG. 9B illustrates an embodiment of a transformer decoder architecture. FIG. 9C illustrates an embodiment of a transformer encoder-decoder architecture. FIG. 9D illustrates another example architecture. Fig. 10 illustrates an embodiment of training and / or deploying the transformer encoder, the transformer decoder and / or the transformer encoder-decoder. FIG. 11 illustrates an embodiment of input embedding.

[0100] Figs. 12a to 12c illustrate different computing environments, central, decentral and distributed. 231228

[0101] 21

[0102] DETAILED DESCRIPTION OF DRAWINGS

[0103] Fig. 1 a illustrates an example of a participant network of a product ecosystem including a material loop and being associated with a decentral peer-to-peer network for exchange of data associated with raw materials, chemical produces), discrete product(s), end product(s) and recycled material(s).

[0104] The decentral participant network 130 may include one or more decentral network participants, such as decentral participant 102 to 114. The decentral network participants may be part of a product ecosystem including chemical products. The product ecosystem may include production chains to produce an end-product. The product ecosystem may include recycling chains to recycle at least part of an end-of-life product resulting from the use of the end product. The product ecosystem may include a raw material producer 104, a chemical product producer 102, a chemical product user 106, an end-product producer 108, an end-product user 110 an EOL product collector 112 and a recycler 114. The decentral participant network 130 may include a chemical supply chain. The product ecosystem may allow to use of recycled materials resulting from recycling of end-of-life products to produce new products, such as chemical products. The product ecosystem may be associated with the production and / or recycling of physical products. The product may be a chemical product, an intermediate chemical product, a component, a component assembly, an end product, an end-of-life product or a recycled material.

[0105] At least a part of the participant(s) of the decentral participant network 130 may be associated with the production of the product and / or the recycling of end-of-life products resulting from the use of the product by product users, such as end-product users 110. The decentral network participant 102 to 114 may refer to a manufacturer of physical products, such as raw material producer 104, chemical product producer 102, chemical product user 106, end-product producer 108, a user of physical goods, such as end-product user 110, and / or a participant of a recycling chain associated with the physical product, such as EOL product collector 112 and recycler 114. The decentral network participant may be associated with a decentral participant identifier. The decentral participant identifier may uniquely identify the decentral network participant within the decentral participant network 130.

[0106] At least a further part of the participant(s) of the decentral participant network 130 may be associated with the generation of product passport(s). Such decentral participants may not be associated with the production of the product and / or the recycling of the end-of-life products. Such decentral participants may gather input material data, for example as described in the context of FIG. 14 and may generate product passports using at least a part of the gathered input material data. The generated product passports may be provided by such participants for access via the decentral network 130. For instance, recycler 114 may access such product passports to determine the composition of the end-of-life product, allowing adaption of the recycling process to the determined composition.

[0107] The partici pant(s) of the decentral participant network 130 may be connected via material flows. The material flow may be a loop material flow 136. The loop material flow 136 may be a closed loop material flow. A closed loop 22 material flow may refer to a material loop where recycled material is used to produce the same end products the recycled material is obtained from via recycling. The loop material flow 136 may be an open loop material flow. An open loop material flow may refer to a material loop where recycled material is used to produce different end products than the one the recycled material is obtained from. The material flow may be a linear material flow (e.g. not including recycling). The material flow 136, 138 may correspond to the flow of product from one participant of the decentral participant network 130 to the downstream participant of the decentral participant network 130. The material flow 136, 138 may refer to a continuous or a discontinuous flow of product. The flow of product may include any means of transportation suitable to transport the product from a participant to the downstream participant. The means of transportation may include pipes, containers, barrels, packages. The material flow 138 may be associated with raw materials used to produce a chemical product, such as virgin raw materials. The raw materials may be provided to chemical product producer 102 for producing chemical product(s) and / or intermediate chemical product(s) (not shown). The loop material flow 136 may be associated with chemical product(s) and discrete product(s). The chemical product(s) may be provided from chemical product producer 102 to chemical product user 106 for producing discrete product(s). In contrast to chemical production, the discrete products being produced are distinct units sold as individual products. The loop material flow 136 may be associated with recycled material. The recycled material may be provided from recycler 114 to chemical product producer 102 for the production of chemical product(s) using the recycled material.

[0108] At least part of the participants of the decentral participant network 130 may be associated with decentral participant network nodes 116 to 128. The decentral participant nodes 116 to 128 may be under control of the respective decentral participant associated with the respective decentral participant node. The decentral participant nodes 116 to 128 may form decentral network 134. The decentral network 134 may be a peer-to-peer communication network. The decentral network 134 may be configured to perform data transactions 132. The data transactions 132 may be based on a transaction protocol including authentication and / or authorization mechanism(s). Based on the authentication and / or authorization mechanism(s) a peer-to-peer communication between decentral network nodes 116 to 128 associated with decentral network participants 102 to 114 may be established. The one or more authentication mecha- nism(s) may be associated with or linked to an identifier as described in the context of FIG. 8. The one or more authentication mechanism(s) associated with the identifier may be accessible by the decentral participant nodes as described in the context of FIG. 8. The decentral configuration allows for more efficient use of computing resources and strengthens control by the data owners of the decentral network.

[0109] Data transactions between decentral network participant nodes may be based on an identifier associated with respective data to be accessed, for example as described in the context of FIG. 8. The identifier may be uniquely associated with the physical entity of the respective product and associated product data. The identifier may be a decentral identifier uniquely identifying the product within the decentral network. The identifier may be a local identifier used by the respective product producer to uniquely identify the respective product. The identifier may be associated with further identifier(s), such as identifier(s) of production input(s) (e.g. input materials) used to produce the output product. This may allow to track the product input(s) used to produce a product, such as an end-product. 23

[0110] The data flow 132 (e.g. transactions) between decentral network participant nodes may be directly or indirectly associated with the material flow 136, 138 between the decentral network participants. For instance, data flow 132 may be directly associated with material flow 136, 138 if data associated with an input material provided from the raw material producer 104 to the chemical product producer 102 is accessed by decentral participant node 118 associated with said chemical product producer 102. For instance, data flow 132 may be indirectly associated with material flow 136, 138 if data associated with a chemical product produced by chemical product producer 102 is accessed by decentral participant node 128 associated with recycler 114.

[0111] The decentral participant nodes 116 to 128 may be decentral computing nodes. The decentral computing node may be any device or system that includes at least one physical and tangible processor, and a physical and tangible memory capable of having thereon computer-executable instructions that are executed by a processor. The memory may take any form and depends on the nature and form of the computing node.

[0112] At least part of the decentral participant nodes 116 to 128 may be decentral data providing network nodes. At least part of the participant nodes 116 to 128 may be decentral data consuming network nodes. A participant of the decentral participant network 130 may be associated with a decentral data providing network node and / or a decentral data consuming network node depending on whether data is provided to downstream participants and / or consumed from upstream participants. For instance, end-product producer 108 may be associated with a decentral data providing network node configured to provide product data to a downstream participant (e.g. recycler 114). In addition to or alternatively, end-product producer 108 may be associated with a decentral data consuming network node configured to access data associated with a discrete product produced by an upstream participant (e.g. chemical product user 106).

[0113] The decentral network 134 may include further decentral network nodes. The further decentral network nodes may be decentral infrastructure component nodes (not shown in FIG. 1). The decentral infrastructure component nodes may not be associated with a participant of the product ecosystem. The decentral infrastructure component nodes may provide components for decentral participant nodes 116 to 128, such as verifying the identity of the decentral network participant nodes 116 to 128 prior to performing a data exchange. The decentral network participant nodes 116 to 128 may be associated with or include certificate , such as X.509 certificate®. The certificate® may be associated with decentral infrastructure component node(s) including e.g. a certificate issuing component and / or a dynamic provisioning component providing dynamic attribute tokens (e.g. OAuth Access Tokens). This way the decentral network participant nodes 116 to 124 possess a unique identifier embedded in a X.509 certificate that identifies the respective decentral network participant node 116 to 128. The information required to verify the certificate may be provided via an authentication registry associated with the certificate issuing component and / or a dynamic provisioning component. For instance, in the IDSA Reference Architecture Model, Version 3.0 of April 2019, a decentral data providing network node associated with a data owner, a Certification Authority (CA), a Dynamic Attribute 24

[0114] Provisioning Component (DAPS) and a decentral data consuming network node associated with a data consumer are used to verify the identity prior to performing a data exchange.

[0115] Fig. 1 b illustrates an example of a participant network of a battery ecosystem including a material loop and being associated with a decentral peer-to-peer network for exchange of data associated with raw materials, chemical produces), batteries, end product(s) and recycled material(s).

[0116] The decentral participant network 216 may include one or more decentral network participants, such as decentral network participants 108, 112 and 202 to 212. The battery ecosystem may include production chains to produce an end product, such as a machine containing a battery. The battery ecosystem may include recycling chains to recycle at least part of an end-of-life battery resulting from the use of the end product. The battery ecosystem may include a miner 202, a refiner 204, a precursor cathode active material (PCAM) and cathode active material (CAM) producer 206, a battery producer 208, an end-product producer 108, an EOL product collector 112, a black mass producer 210 and a metal extractor 212. The battery ecosystem may allow to use recycled materials, such as recycled metals and metal salts, resulting from recycling of end-of-life batteries or components thereof to produce new products, such as PCAM and CAM. The product ecosystem may be associated with the production and / or recycling of batteries.

[0117] The partici pant(s) of the decentral participant network 216 may be associated with the production of a battery containing end product and / or recycling of end-of-life batteries or components thereof. The decentral network participant may be a manufacturer of physical products, such as miner 202, refiner 204, PCAM & CAM producer 206 chemical product producer 102, chemical product user 106, end-product producer 108 and / or a participant of a recycling chain associated with the end-of-life batteries or components thereof, such as EOL product collector 112, black mass producer 210 and metal extractor 212. For instance, the metal extractor 212 and the PCAM & CAM producer 206 may be a single entity performing recycling operations to obtain recycled material, such as recycled metals and / or metal salts, and producing new chemical product(s), such as PCAM and / or CAM using the recycled metal and / or metal salts. The decentral network participant may be associated with a decentral participant identifier. The decentral participant identifier may uniquely identify the decentral network participant within the decentral participant network 216.

[0118] At least a further part of the participant(s) of the decentral participant network 130 may be associated with the generation of battery passport(s). Such decentral participants may not be associated with the production of the battery containing end product and / or the recycling of the end-of-life batteries or components. Such decentral participants may gather input material data and may generate battery passports using at least a part of the gathered input material data. The generated battery passports may be provided by such participants for access via the decentral network 130. For instance, recycler 114 may access such battery passports to determine the chemical composition of the end-of-life batteries or components thereof, allowing adaption of the recycling process to the determined composition. 231228

[0119] 25

[0120] The partici pant(s) of the decentral participant network 216 may be connected via material flows as described in the context of FIG. 1 . The raw materials, such as metals, may be provided to refiner 204 for refinement. The refined metals may be provided to PCAM & CAM producer 206 for the production of cathode active material. The CAM may be used, for example by battery producer 208, to produce battery cell. The battery cells may be used to produce batteries or battery packs. The batteries or battery packs may be provided to end-product producer 108 to produce battery containing end products, such as electric vehicles. Scrape from battery production may be provided to black mass producer 210.

[0121] At least a part of the participants of the decentral participant network 216 may be associated with decentral participant network nodes 218 to 232 as described in the context of FIG. 1 . The decentral participant nodes 218 to 232 may form decentral network 208. The decentral network 208 may be a peer-to-peer communication network as described in the context of FIG. 1 . The decentral configuration allows for more efficient use of computing resources and strengthens control by the data owners of the decentral network.

[0122] Data transactions between decentral network participant nodes may be based on an identifier associated with respective data to be accessed. The identifier may be uniquely associated with the physical entity of the respective product and associated product data. The identifier may be a decentral identifier uniquely identifying the product within the decentral network. The identifier may be a local identifier used by the respective product producer to uniquely identify the respective product. The identifier may be associated with further identifier(s), such as identi- fier(s) of production input(s) (e.g. input materials) used to produce the output product. This may allow to track the product input(s) used to produce a product, such as an end-product. The identifier may, for example, be included in input material data associated with input materials.

[0123] The data flow 132 (e.g. transactions) between decentral network participant nodes may be directly or indirectly associated with the material flow 136, 138 between the decentral network participants as described in the context of FIG.

[0124] 1 . The decentral participant nodes 218 to 232 may be decentral computing nodes as described in the context of FIG. 1 . At least part of the decentral participant nodes 218 to 232 may be decentral data providing network nodes. At least part of the participant nodes 116 to 128 may be decentral data consuming network nodes. A participant of the decentral participant network 130 may be associated with a decentral data providing network node and / or a decentral data consuming network node depending on whether data is provided to downstream participants and / or consumed from upstream participants (see also FIG. 1). The decentral network 134 may include further decentral network nodes as described in the context of FIG. 1 .

[0125] FIG. 2 illustrates an example system and associated methods for generating digital assets associated with supply chain product(s) and providing access to the generated digital assets(s).

[0126] The example system and methods illustrated in Fig. 2 relate to one example participant of the product ecosystem illustrated in Figs. 1a and b. The example participants chosen is the chemical product producer that produced chemical products to be provided to the chemical product user. 231228

[0127] 26

[0128] The chemical producer may produce one or more output product(s) 706 using one or more input material(s). The output product may comprise or be any product produced by the production and provided at any exit point of the production. The input material may include starting material used in a production process performed within production to produce the output product. An input material can be used in any process step of the production process. This means, the intermediate output product of the one production plant of production can correspond to the input material of a subsequent production plant of production. Input material may include recycled material. The input material may comprise or be any input material entering the production. The input material may comprise or be any input material provided at any entry point of the production.

[0129] The output product may be produced via one or more process steps from the input material(s) within production. The process steps may involve chemical reactions and / or physical processes and / or assembly processes involving the assembly of different discrete input mate-rial(s) and / or processes involving chemical input materials and discrete input materials, such as filling processes. The input material may be used in one or more of such production step(s). The input materials may enter the system boundary of the production at the entry point, such as a production plant or a material storage associated with the production. The amount of input material entering the system boundary of the production may be measured, for example using sensor. Sensors include sensors configured to measure an amount of input material, such as a weight and / or a volume. Chemical and / or physical properties of the input material may be measured, for example using sensor, upon passing system boundary of the production. The measured data may be used to determine at least one chemical and / or physical property of the respective input material. Examples of chemical properties include heat of combustion, enthalpy of formation, toxicity, chemical stability in a given environment, flammability, oxidation state(s), ability to corrode, combustibility, acidity and basicity, chemical composition, recyclate content used for producing or manufacturing the input material, bio-based content used for producing or manufacturing the input material, renewable content used for producing or manufacturing the input material, biodegradability, and / or pH value. Examples of physical properties include absorption, brittleness, boiling point, capacitance, color, concentration, density, ductility, distribution, efficacy, elasticity, electric charge, electrical conductivity, electrical impedance, electric potential, flow rate, fluidity, hardness, heat capacity, inductance, intrinsic impedance, luminance, luminescence, luster, mass, melting point, opacity, permeability, permittivity, plasticity, pressure, radiance, resistivity, reflectivity, refractive index, solubility, specific heat, strength, stiffness, temperature, tension, thermal conductivity, thermal resistance, viscosity, volume and / or wave impedance.

[0130] An operating system of the production may monitor and / or control the production based on operating parameters of the different processes. The operating system may receive production demand data associated with the production planning for the production. The production demand data may be produced from target production capacities for one or more out-put product(s) produced by the production. The production demand data may be produced from pre-defined production capacities or data-driven models that relate production capacities to market demand data or quantities consumed at the consumption location. The production demand data may include target capacities for output products produced by the production. The operating system may further receive a bill of materials associated with 231228

[0131] 27 output products to be produced. The bill of materials may include material data associated with the input materials used to produce the output product, process data associated with the production chain for producing the output product and / or output product data associated with the output product, such as a product specification data or data on the amount of output product to be produced.

[0132] Based on the received production demand data and the bill of materials, material demand data may be determined. The material demand data may include data on the amount of input material required to produce the target capacities of output product. The material demand data may include input material identifiers associated with input materials required to produce the output product and data on amounts of input material for respective input materials. The material demand data may include one or more material specifier(s) per input material identifier signifying the material specification. The material demand data may include data on the material amount per input material identifier signifying the amount of material to be supplied. The material demand data may specify the production chain(s) of the production. The material demand data may include a bill of materials for one or more production chain(s) of the production. The material demand data may include one or more recipe(s) specifying one or more material(s) for production process(es) of the production. The determined material demand data may be provided for access by a supplier system associated with a supplier outside the physical system boundary of the production. Material supply may be triggered by the supplier system accessing the mate-rial demand data.

[0133] The amount of output product(s) resulting from processes performed within production 704 may be measured using a sensor, such as sensor. The measured data may be stored in one or more databases associated with operating system. Moreover, processes performed within production may be monitored using sensors, such as sensors, and the generated monitoring data may be stored in one or more databases associated with operating system. The monitoring data may be interrelated with a digital output product identifier associated with the respective output product. Physical and / or chemical properties of produced output products may be measured by sensors, such as sensors. Physical and / or chemical properties may include the properties previously described. The measured and / or determined chemical and / or physical properties of the produced output products may be stored in one or more databases as-sociated with operating system. The measured and / or determined chemical and / or physical properties of the produced output products may be interrelated with a digital output product identifier associated with the respective output product.

[0134] The produced output products may be provided at one or more exit points of the production. The output product may exit the system boundary of the production.

[0135] The operating system for digital asset generation and transfer may be communicatively connected or coupled to at least one decentral network node associated with the supply chain producer such as the chemical producer. The operating system may include components configured to generate a digital asset(s) associated with at least one supply chain product produced by the chemical production. The digital asset may be configured to exchange product data or parts thereof associated with the at least one supply chain product via the decentral network. 28

[0136] The tenant environment associated with the chemical production may include an operating system for digital asset generation and / or transfer. Tenant environment may relate to a local compute and / or storage environment associated with the chemical production. The local compute and / or storage environment may include a distributed compute and / or storage environment accessible by the chemical production. The operating system for digital asset generation and / or transfer may be communicatively connected or coupled to the production systems. The operating system may include or may be communicatively connected or coupled to product data storage storing product data gathered in association with at least one supply chain product produced by the chemical production or produced supply chain product(s) e.g. from or by the production system. The operating system may include one or more component(s) configured to generate and / or provide digital asset(s) associated with at least one supply chain product produced by the chemical production or produced supply chain product(s). The operating system may include or may be communicatively connected or coupled to digital asset storage storing the generated digital asset(s) associated with the at least one supply chain product produced by the chemical production or produced supply chain product(s).

[0137] The operating system may be configured to gather or fetch product data in association with at least one supply chain product produced by the chemical production or produced supply chain product(s) e.g. from or by the production system. The operating system may be configured to provide product data for storing in the product data base or storage. The operating system may be configured to generate and / or provide digital asset(s) by providing at least one decentral identifier associated with at least one supply chain product produced by the chemical production or produced supply chain product(s), e.g. uniquely associated with supply chain product produced by the chemical production or produced supply chain product. The operating system may be configured to generate and / or provide digital asset(s) by selecting at least part of the product data associated with the supply chain product produced by the chemical production or produced supply chain product(s). The operating system may be configured to generate and / or provided digital assets by linking or relating the provided decentral identifier(s) with the selected product data associated with the supply chain product, e.g. uniquely associated with supply chain product produced by the chemical production or produced supply chain product. The operating system may be configured to generate and / or provide digital assets by storing the decentral identifier, the linked or related product data selected and at least one locator for such data such as the storage address of a data base, e.g. in a digital asset data base associated with the operating system of the supply chain production such as the chemical production. The locator(s) may relate to the storage location or address of the digital asset data base or storage accessible by the operation system.

[0138] The operating system may be configured to generate and / or provide digital assets by providing the decentral identi- fier(s) and at least one locator, such as a url, a uri, an endpoint and / or a path, related to or pointing to the selected product data stored in association with the decentral identifier(s) in the digital asset storage associated with the operating system of the supply chain production to a decentral data provider node and / or a decentral digital twin registry. The locator(s) may relate to a link and / or endpoint to the digital asset data base or storage associated with the operating system of the supply chain production such as the chemical production. The operating system may be configured to transfer digital assets to the decentral data provider node for further transfer to the decentral data consuming 29 node, e.g. through a decentral data communication protocol or a decentral network protocol. The operating system may be configured to at least initiate transfer of digital assets or product data sets with selected product data points from the decentral data provider node to a decentral data consuming node via a peer-to-peer communication channel.

[0139] The transfer of product data sets as selected on digital asset generation may be initiated by the decentral data provider or consumer node. The data consumer node may request one or more digital asset(s) from the data provider node e.g. on entry of the output product provided by the chemical producer as input for the production of the output product user by the chemical product user. To establish a pee-to-peer communication channel, the decentral data consumer node and consumer node may request connection based on the data provider node ID, e.g. as provided by the digital asset information of the output product, and / or the locator linked to the output product. The decentral data provider node and consumer node may initiate an authentication process based on one or more authentication mechanism(s) such as exchange of data encrypted with private key on one side and decrypted with public key on the other side. Once the authentication process is successful the peer-to-peer communication channel may be established. Based on the digital asset information including the decentral identifier(s) associated with the output product and accessible by the data consumer node, the data consumer node may request transfer of selected product data as provided by or linked to the digital asset. The data provider node may authorize the request, gather the selected product data as provided by or linked to the digital asset from the digital asset storage and transfer the selected product data to the data consumer node. The data consumer node may store the decentral identifier(s) associated with the output product, the linked or related product data selected and at least one locator for such data such as the storage address of a data base, e.g. in a digital asset data base associated with the chemical product user production.

[0140] In particular, the operating system for generating and / or providing digital asset(s) may include a configuration data component configured to generate at least one selection instruction for selecting at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product and to select at least one decentral network and / or at least one data model based on the at least one selection instruction. Further in particular, the operating system for generating and / or providing digital asset(s) may include a digital asset generation component configured to generate the digital asset based on the selected and / or provided at least one decentral network and / or at least one data model. Further in particular, the operating system for requesting a digital asset or generation of a digital asset, e.g. from a data consumer to a data provider, may include a digital asset preparation component configured to generate at least one selection instruction for selecting at least one product data point or set to be exchanged in association with the supply chain product according to selected at least one decentral network and / or at least one data model. Further in particular, the operating system for validating a digital asset may include a digital asset preparation component configured to validate based on at least one selection instruction for selecting at least one validation rule dependent on the product data point or set to be exchanged in association with the supply chain product according to selected at least one decentral network and / or at least one data model. The operating system including the different components and / or their functionalities will be described in more details below e.g. in relation to the following Figures. 231228

[0141] 30

[0142] Fig. 3a illustrates an example of an operating system communicatively coupled or connected to multiple data spaces or decentral networks as illustrated in Figs. 1a and b.

[0143] The system architecture illustrated in Fig. 3a relates to a central system architecture for orchestrating and managing data spaces 1, 2, ...n. The data spaces 1, 2...n may include multiple participating node(s) configured for data exchange between participants of the decentral network. The participants of the decentral network may include supply chain participants producing and providing supply chain products for example as illustrated in Figs. 1 and 2. The participants of the decentral network may be associated with participant nodes configured for data exchange between participants of the decentral network.

[0144] The participants may participate in one or more decentral networks. The decentral networks may be associated with different supply chains and / or supply chain products. The decentral networks may define one or more unique decentral identifier(s) related to the different participant nodes e.g. associated to the supply chain participants. Per decentral network the participant nodes may be related to one or more decentral identifier(s) associated with the participant of the respective decentral network. Per participant node one or more unique decentral identifier(s) for different decentral networks may be defined.

[0145] The decentral networks may define different data exchange protocols related to the different supply chains and / or supply chain products. Per decentral network one or more exchange protocol(s) related to the different supply chains of participants and / or supply chain products of the participants of the respective decentral network may be pre-defined. Per decentral network one or more exchange protocol(s) related to the one supply chain of participants and / or supply chain products of the respective supply chain may be pre-defined.

[0146] To enable data exchange between nodes associated with participants of one or more decentral network(s), the decentral network and associated protocols for data exchange need to be determined or provided. Multiple different decentral networks, e.g. in relation to different end product types such as automotive, health, semiconductor, energy or the like, may implement different or at least partially different protocols including semantic data models which may be pre-defined as part of the communication protocol per decentral network. The multiple different decentral networks may also be referred to as different data spaces, e.g. in relation to different end product types or supply chains such as automotive, health, semiconductor or the like.

[0147] An operating system may be configured to manage and / or orchestrate the data exchange between participant node(s) participating in one or more data space(s) or decentral network(s). The operating system may be configured to select the decentral network type or data space type, decentral network protocols, supply chain product specific data models and / or supply chain product specific data points to be entered into the data model. The operating system may be configured to manage and / or orchestrate data exchange based on the selected decentral network type 31 or data space type, decentral network protocol (s), supply chain product specific data model(s) and / or supply chain product specific data point(s) to be entered into the data model.

[0148] Fig. 3b illustrates another example with operating systems communicatively coupled or connected to multiple data spaces.

[0149] The system architecture illustrated in Fig. 3n relates to a decentral system architecture for orchestrating and managing data spaces 1 , 2, ...n. In contrast to Fig. 3a the operating system(s) may be associated with one or more participant nodes of different data spaces 1 ... n. The illustration of Fig. 3b illustrates a decentral architecture of the operating system(s) by running the operating system(s) as described in the context of Fig. 3a for individual nodes. The operating system may be configured to manage and / or orchestrate the data exchange between participant node(s) participating in one or more data space(s) or decentral network(s). The operating system may be configured to select the decentral network type or data space type, decentral network protocols, supply chain product specific data models and / or supply chain product specific data points to be entered into the data model. The operating system may be configured to manage and / or orchestrate data exchange based on the selected decentral network type or data space type, decentral network protocol (s), supply chain product specific data model(s) and / or supply chain product specific data point(s) to be entered into the data model.

[0150] Figs. 3a and 3b are only illustrative for the potential architectures of using the functionalities of the operating system®. This shall not be considered limiting. Any combination of central and decentral architectures may be possible with operating systems running centrally for some node(s) and / or data space(s) and / or running decentrally for other node(s) and / or data space(s). Also sub-functionalities of the operating system may run centrally or decentrally as case may be.

[0151] Fig. 4a illustrates an example of the operating system including a configuration data base that is updated through a configuration data collection and used for generating supply chain product specific digital assets.

[0152] The operating system may be configured to fetch web data including data related to decentral network protocols for exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. The operating system may include a web interface configured to fetch web data based on one or more Uniform Resource Locators (URLs) or application programming interfaces associated with a path to a web repository e.g. / re- pos / {owner} / {repo}. The operating system may include a configuration data component communicatively coupled or connected to the web interface. The configuration data component may include a web scraping component configured to receive and / or fetch web data including configuration data through the web interface based on web protocols such as html or xhtml data, metadata or semantic markups and annotations defined by web protocols such as Cascading Style Sheets (CSS) standard as defined by W3C, Selectors Level 4, W3C Working Draft, 11 November 2022. The configuration data component may include web repository component configured to receive and / or fetch web 32 data including configuration data through the web interface from internet repositories accessible through an application programming interface such as REST APIs. The web repositories or the URLs may provide access to web data including configuration data related to decentral networks, decentral network protocols for respective decentral networks, supply chain product specific data models and / or context information for the respective decentral networks, protocols and / or data models based on web data. The web repositories or the URLs may provide the web data including configuration data related to decentral networks, decentral network protocols for respective decentral networks, supply chain product specific data models and / or context information for the respective decentral networks, protocols and / or data models.

[0153] The web data may be fetched in response to update event(s) provided by web components configured to notify subscribers when web content is updated. The configuration data component may be configured to update the configuration data base storing configuration data related to decentral networks, decentral network protocols for respective decentral networks, supply chain product specific data models and / or context information for the respective decentral networks, protocols and / or data models based on web data. The configuration data collection component may be configured to receive update event(s) via the web interface e.g. by connection to web repositories accessible through application programming interface such as REST APIs.

[0154] The configuration data component may be connected, e.g. via an API, to pre-defined paths for accessing pre-defined web repositories storing web data including configuration data related to one or more decentral network(s), decentral network protocol(s) for respective decentral network(s), supply chain product specific data model(s) for respective decentral network(s), and / or context information for the respective decentral networks, protocols and / or data models, such as semantic models stored on GitHub. For example, the configuration data component may be configured to access such pre-defined web repositories. Further for example, the configuration data component may be configured to receive updates from such pre-defined web repositories. The configuration data component may receive notifications when one of the pre-defined web repositories is updated and may collect updated configuration data in response to such notification(s). The configuration data collection component may receive updated configuration data when one of the pre-defined web repositories is updated.

[0155] The web data may be fetched based on one or more lists including pre-defined paths to web content relating to decentral network protocols for exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. The configuration data component may be configured to provide paths or representations such as urls locating the web content to be scraped e.g. to the web interface. For example, the configuration data collection component may be configured to access and / or provide to the web interface one or more pre-defined lists of urls related to one or more decentral network(s), decentral network protocol(s) for respective decentral network(s), supply chain product specific data model(s) for respective decentral network(s), and / or context information for the respective decentral networks, protocols and / or data models and to be scraped. The web data may be fetched based on one or more pre-defined search terms for searching web content related to decentral network protocols for 231228

[0156] 33 exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. For example, the configuration data collection component may be configured to access and / or provide to the web interface one or more pre-defined search terms for searching content related to one or more decentral network(s), decentral network protocol(s) for respective decentral network(s), supply chain product specific data model(s) for respective decentral network(s), and / or context information for the respective decentral networks, protocols and / or data models and locating respective urls to be scraped.

[0157] The configuration data component may be configured to receive web repository and / or web data including configuration data related to decentral networks, decentral network protocols for respective decentral networks, supply chain product specific data models and / or context information for the respective decentral networks, protocols and / or data models. The configuration data component may be configured to receive configuration data related to decentral networks, decentral network protocols for respective decentral networks, supply chain product specific data models and / or context information for the respective decentral networks, protocols and / or data models. The configuration data may include as for example illustrated in Fig. 5a the specification of the decentral network, respective decentral network protocols defined for the specified decentral network, supply chain product specific data models defined for the specified decentral network and / or context information for the specified decentral network, protocols and / or data models.

[0158] The operating system may be configured to generate configuration data by mapping the fetched web data to a configuration data structure as stored by a configuration data base. The configuration data base may store key-value pairs of decentral network protocols and respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. The web repositories, or the URLs may provide web data that may be mapped to the configuration data as stored by the configuration data base. The configuration data component may be configured to receive web repository and / or web data and extract configuration data in a structured format such as table formats or semi-structured format such as JSON or JSON Lines. This may include cleansing of HTML data, validating scraped data e.g. by checking that the data items contain certain fields or checking for duplicates and dropping them. The configuration data component may be configured to receive configuration data in a structured format such as table formats or semi-structured format such as JSON or JSON Lines. Further details of the processing will be described in the context of Fig. 4b. The processing and the storing of the configuration data may be logged and stored in a documentation storage. Configuration data may be updated frequently in preset or dynamic time intervals. The configuration data component may be configured to store configuration data in a structured format such as table formats or semi-structured format such as JSON or JSON Lines.

[0159] Descriptions of the decentral network protocols for exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol may be extracted from the fetched web data. The configuration data component may be configured to receive context information for the specified decentral network, protocols and / or 231228

[0160] 34 data models e.g. in natural language e.g. from html content of webpages or web repositories. The configuration data base may store descriptions in natural language for configuration data points stored as key-value pairs.

[0161] The configuration data component may be configured to generate context information for the specified decentral network, protocols and / or data models e.g. by using a data-driven general-purpose model such as a Large Language Model (LLM) e.g. as described in the context of Fig. 8-11 . The data-driven model may be general purpose in the sense that it was trained or is pre-trained on unstructured natural language data and is configured to process natural language. The data-driven model may be general purpose in the sense that is not trained for a specific task. The data-driven model may include a general-purpose model trained at least on unstructured data.

[0162] Descriptions of the decentral network protocols for exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol may be generated using a data-driven general-purpose model such as a Large Language Model (LLM) e.g. as described in the context of Fig. 8-11. One or more instruction(s) may be generated and provided to the data-driven general-purpose model such as a Large Language Model (LLM) e.g. as described in the context of Fig. 8-11. The instructions may include at least one task instruction specifying the task to generate descriptions of the decentral network protocols for exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged. The instructions may include fetched web data as context, wherein the instructions may indicate the key-value pair(s) of configuration data structure to be described. One or more instruction (s) may be provided to the data driven model e.g. together with configuration parameters for the data-driven model such as maximal token specification or authentication / authorization parameters. The data-driven model may be selected from one or more data-driven models based on a functionality, a sensitivity and / or confidentiality level of processing by the data- driven model. The data-driven model may generate and / or provide context descriptions for the specified decentral network, protocols and / or data models. The context descriptions may be stored in relation to or for the specified decentral network, protocols and / or data models. The context descriptions for the specified decentral network, protocols and / or data models may be provided in natural language or text and stored as metadata in association with the specified decentral network, protocols and / or data models in the configuration data base e.g. as illustrated in the context of Fig. 5a. The configuration data collection component may be communicatively coupled or connected to the configuration data base.

[0163] The operating system may be configured for storing the generated configuration data in a configuration database. The configuration data base may store configuration data in key-value pairs including decentral network protocols and per decentral network protocol one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. The configuration data base may store configuration data including descriptions in natural language of configuration data points stored as configuration data. The configuration data component may be configured to select decentral network and respective protocols and / or data models based on the configuration data stored in the configuration data base. The configuration data component 231228

[0164] 35 may be configured to select decentral network and respective protocols and / or data models by using a data-driven general-purpose model e.g. as described above and will be described in more detail below.

[0165] The passport generation component may be configured to generate a digital asset specific to one or more supply chain products based on user and / or system interaction. The configuration data base and / or the configuration data component may be communicatively coupled or connected to a passport generation component. The passport generation component may be configured to generate a digital asset specific to one or more supply chain products based on the selected decentral network and respective protocols and / or data models. The passport generation component and / or the configuration data component may be configured to retrieve at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product based on the key-value pairs stored as configuration data in the configuration data base. The passport generation component and / or the configuration data component may be configured to retrieve at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product based on the descriptions in natural language of configuration data points stored as configuration data in the configuration data base.

[0166] The passport generation component may be communicatively coupled or connected to a product data base. The passport generation component may be configured to generate a digital asset specific to one or more supply chain products based on the selected decentral network and respective protocols and / or data models. The passport generation component and / or the configuration data component may be configured to generate the digital asset based on the retrieved decentral network protocol and / or at least one data model by generating at least one product data set according to the retrieved at least one data model by retrieving one or more product data points from a product data base based on the retrieved at least one data model, wherein the product data base provides product data associated with the at least one supply chain product. The passport generation component and / or the configuration data component may be configured to generate the digital asset based on the retrieved decentral network protocol and / or at least one data model by providing one or more decentral identifier(s) uniquely associated with the supply chain product based on the retrieved decentral network protocol and by providing a locator to the generated product data set. The selection of decentral network protocols, data models and product data points as well as the generation of digital assets will be described in more detail below:

[0167] The configuration data component and / or the passport generation component may be configured to receive one or more triggers or requests for passport generation. The trigger or request may be based on user interaction such as a prompt in natural language and / or system interaction such as a request received by a node of one of the decentral networks. For example, a user may provide a user instruction to generate a passport or digital asset for the supply chain product in natural language. Further for example, a participating node of one decentral network may request the generation of the digital asset of the supply chain product. 231228

[0168] 36

[0169] The configuration data component and / or the passport component may be configured to route the user and / or system interaction for selection of the decentral network and / or the data model. The configuration data component and / or the passport generation component may be configured to determine if a decentral network and / or data model selection is required. The configuration data component and / or the passport generation component may be configured to determine if a decentral network is indicated by the user and / or system interaction e.g. if a decentral network is specified as provided by the user and / or system interface. The determination may be based on the configuration data stored in the configuration data base and / or the decentral network specification included in the user and / or system interaction. The configuration data component and / or the passport generation component may be configured to determine if a data model is indicated by the user and / or system interaction e.g. if a data model is specified as provided by the user and / or system interface. The determination may be based on the configuration data stored in the configuration data base and / or the data model specification included in the user and / or system interaction. If no decentral network protocol and / or data model is specified, the passport generation component may be configured to request selection of the decentral network and / or the data model by the configuration data component.

[0170] DECENTRAL NETWORK SELECTION

[0171] The configuration data component and / or the passport component may be configured to select the decentral network based on user and / or system interaction e.g. as provided by the user and / or system interface. The selection may be based on the configuration data stored in the configuration data base and / or a decentral network specification included in the user and / or system interaction.

[0172] For example, the decentral network specification of the user and / or system interaction may be equal or correspond to the decentral network specification stored in the configuration database. In such case the selection may include checking for the decentral network specification in the configuration data base and confirming that the decentral network specification is stored in relation to data models and supply chain products related to the specified decentral network.

[0173] Further for example, the decentral network specification may be different to the decentral network specification stored in the configuration database. The decentral network specification may semantically correspond to the decentral network specification stored in the configuration database. In such case the selection may include a semantic search in the configuration database and confirming that the decentral network specification is stored in relation to data models related to the decentral network specification provided by the user and / or system interaction. Further a user confirmation may be requested and / or provided confirming that the decentral network specification semantically correlating to the decentral network specification provided by the user and / or system interaction is stored in relation to data models and supply chain products related to the specified decentral network in the configuration data base.

[0174] Further for example, the user and / or system interaction may include context relating to the decentral network specification. In such case the selection may include interaction with a data-driven general-purpose model as described 231228

[0175] 37 above and will be described in more detail below. The selection may include retrieval of at least one prompt template with instructions for selecting the decentral network and / or decentral network specification. The instructions may include at least one task instruction for the general-purpose data-driven model relating to the task of selecting the decentral network and / or decentral network specification. The instructions may include at least one context instruction for the general-purpose data-driven model relating to context data for the network as stored in the configuration data base e.g. by providing decentral network specifications and / or context for the network stored in the configuration data base to be selected from. The selection instructions may be provided to the general-purpose data driven model to generate decentral network specification to be selected. The general-purpose data driven model may generate and provide decentral network specification to be selected. Further a user confirmation may be requested and / or provided confirming that the decentral network specification conforms with the decentral network intended by the user and / or system interaction.

[0176] DATA MODEL SELECTION

[0177] Based on the system and / or user interaction and / or the selected decentral network specification the data model may be selected. For example, if the decentral network specification as stored in the configuration data base or corresponding to the configuration database is selected, the data model selection may include the selected decentral network specification. If the system and / or user interaction provides indication of the data model related to the supply chain product as stored in the configuration data base or the supply chain product corresponding to the configuration data stored in the configuration data base, the data model may be selected based on such system and / or user interaction as described above either by string or semantic search in the configuration data base.

[0178] Further for example, if no decentral network specification as stored in the configuration data base or corresponding to the configuration database is selected, the data model selection may be based on the user and / or system interaction. If the system and / or user interaction provides indication of the data model related to the supply chain product, the data model may be selected based on such system and / or user interaction as described above either by string or semantic search in the configuration data base. The decentral network specification may be selected based on the selected data model.

[0179] Further for example, the user and / or system interaction may include context relating to the data model. In such case the selection may include interaction with a data-driven general-purpose model as described above and will be described in more detail below. The selection may include retrieval of at least one prompt template with instructions for selecting the data model. The instructions may include at least one task instruction for the general-purpose data- driven model relating to the task of selecting the data model. The instructions may include at least one context instruction for the general-purpose data-driven model relating to context data for the data model as stored in the configuration data base e.g. by providing data models and / or context for the data models stored in the configuration data base to be selected from. The selection instructions may be provided to the general-purpose data driven model to generate data model to be selected. The general-purpose data driven model may generate and provide data model 231228

[0180] 38 to be selected. Further a user confirmation may be requested and / or provided confirming that the data model and related decentral network specification conform with the supply chain product and the decentral network intended by the user and / or system interaction.

[0181] DATA SELECTION

[0182] Based on the system and / or user interaction, the selected decentral network specification and / or the data model the data points related to the specific supply chain product may be selected. The data points related to the specific supply chain product may be stored in a private product data base associated with the participant producing the respective supply chain product. The data points associated with the specific supply chain product may be stored in relation to context data specifying the respective data points associated with the supply chain product in natural language.

[0183] For example, if the selected data model specifies the data points as stored in the product data base or corresponding to the product database, the data point selection may include selection according to the data model. If the selected data model specifies the data points without one-to-one correspondence to the data points stored in the product database, the data points may be selected according to the data model based on string or semantic search in the product data base.

[0184] Further for example, if the selected data model does not specify the data points as stored in the product data base or corresponding to the product database, the data point selection may include selection based on the data model and context of the data model and / or data points. In such case the selection may include interaction with a data-driven general-purpose model as described above and will be described in more detail below. The selection may include retrieval of at least one prompt template with instructions for selecting the data points. The instructions may include at least one task instruction for the general-purpose data-driven model relating to the task of selecting the data points according to the data model. The instructions may include at least one context instruction for the general-purpose data-driven model relating to context data for the data model as stored in the configuration data base and / or context data for the data points as stored in the product data base. The selection instructions may be provided to the general-purpose data driven model to generate data points to be selected. The general-purpose data driven model may provide data points to be selected. Further a user confirmation may be requested and / or provided confirming that the data points and related data model conform with the supply chain product and the decentral network intended by the user and / or system interaction.

[0185] VALIDATION

[0186] The selection of decentral network, data model and / or data points may be provided. The provided selection may be validated by using a general-purpose data driven model e.g. as described in the context of Fig. 8-11. For validation a validation templates may be provided. The validation template may include in natural language task instructions for the data-driven model to validate the selection. The validation template may include at least one placeholder for the 231228

[0187] 39 selection to be validated. The validation template may relate to rules to be checked on validation provided in natural language or text. The validation template may relate to correction instructions in case at least one error is found upon validation. The validation instruction may include selection instructions relating to the output structure or conditions to be fulfilled by the output or the instruction to restrict execution to fully defined attribute sets. The validation template may depend on the type of selection generated, which may depend on the task instruction provided to the data- driven model for selection instruction generation. Depending on the task instruction used for generation of the selection instruction the validation template may be selected. The validation template may be used to generate one or more instruction(s) to be provided to the data-driven model. Upon receipt of the response from the data-driven model a validated selection instruction may be provided.

[0188] Fig. 4b illustrates the decentral network, data model(s) and / or data point(s) selection based on context stored in relation to respective decentral networks, data models and / or data points.

[0189] For selection of the decentral network, data model(s) and / or data point(s), the configuration data base and or the product data base may be filled with structured data including context as illustrated in Figs 4c and d. For example, the data structure of the configuration data base may include a decentral network identifier, context describing the decentral network based on text data, data models and / or data model identifiers, context describing the data models based on text data, supply chain products and / or supply chain product identifiers, context describing the supply chain products based on text data or the like.

[0190] The configuration data may be gathered from public or private web resources such as described in the context of Fig. 4a via web scraping and / or APIs to repositories with respective content. The scraped or received web data may be cleansed and / or structured according to the data structure for configuration data as stored by the configuration data base. E.g. as illustrated in Fig. 4c the configuration data may be structured according to the illustrated data structure for configuration data. Fig. 4c illustrates an example of a data model schema for battery passport. The context or description of individual schema sections may be extracted to fill the respective elements of the configuration data structure as indicated by the arrows. This may also be referred to as chunking of the web data to extract the configuration data.

[0191] To build up the configuration data base the extracted values of configuration data may be stored according to the configuration data structure. The chunks of text or descriptions may be embedded by way of an embedding layer or model as described e.g. in more detail in the context of Figs. 8-11, for example Fig. 8 describing the CBOW embedding. The embedding may be done by description section, sentence or parts of sentences such as words. The embedding layer may map the natural language or text to numeric vectors in an embedding space. By doing so the natural language or text may be mapped to numeric representation(s) that may be used for similarity searches in the vector space. The extracted chunks of text or descriptions may be stored together with their respective embedding vectors. The configuration data base may hence store the extracted chunks of text or descriptions in relation to respective embedding vectors. Similarly, the product data base may be built up based on descriptions of the supply 231228

[0192] 40 chain products produced by the supply chain product producer. Such descriptions may be generated as described in the context of Fig. 4a in interaction with the data driven model such as the LLM or any models e.g. as described in the context of Fig. 8-11 . An example of the product data base structure is illustrated in Fig. 4c. The configuration and / or product data base may store structured or semi-structured data such as JSON files or SQL queries.

[0193] With continued reference to Fig. 4b, the data structure stored in the configuration and / or product data base may be used in a Retrieval Augmented Generation (RAG) framework. The user interaction and / or system interaction may be received in unstructured or semi structured text as e.g. described in the context of Fig. 4a. The user and / or system interaction may be embedded by way of an embedding layer or model as described e.g. in more detail in the context of Figs. 8-13, for example Fig. 8 describing the CBOW embedding. The embedding may be done by description section, sentence or parts of sentences such as words. The embedding layer basically maps the natural language or text to numeric vectors in an embedding space. By doing so the natural language or text may be mapped to numeric representation (s) that may be used for similarity searches in the vector space.

[0194] Based on the embedded user and / or system interaction the configuration and / or product data base may be searched for similar context in the stored descriptions. Similar context may refer to embedding vectors with distance closest to the embedded user and / or system interaction. This way configuration data and / or product data based on context may be retrieved. In addition an instruction template for the data-driven general purpose model e.g. as described in the context of Fig. 8-11 may be retrieved based on the requested task of the user and / or system interaction. The template may include placeholders for filling the configuration data and or product data context. The thus generated instruction set based on instruction template may be used for instructing the LLM to fulfill a task as e.g. described in the context of Fig. 4a. Fig. 4c illustrates in the bottom section the interplay between embedding vectors and natural language instruction generation by searching the embedding space.

[0195] Fig. 4a may be viewed as illustrating a schematic example of the agent setup for selecting decentral network, data models and / or data points to generate digital assets associated with supply chain products. The passport generation component may interact with one or more general purpose data driven models as described above and will be described in more detail below. The interaction may include retrieval of task specific instruction templates, completion of the instruction templates based on stored context and providing such templates to the general-purpose data driven model. These individual processing steps may be viewed as an agent executing on one or more specific tasks as specified by the instruction template. The prompt templates are illustrated for different scenarios described herein including selection of decentral network or data model, selection of data points and validation. Decentral network selection agent may be configured to retrieve the instruction template for network selection and interact with the general-purpose data driven model accordingly. Data model selection agent may be configured to retrieve the instruction template for data model selection and interact with the general-purpose data driven model accordingly. Data selection agent may be configured to retrieve the instruction template for data point selection and interact with the general- purpose data driven model accordingly. 231228

[0196] 41

[0197] Fig. 5 illustrates an example method for generating digital assets for a specific supply chain product.

[0198] Web data including data related to decentral network protocols for exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol may be fetched. The web data may be fetched based on one or more lists including pre-defined paths to web content relating to decentral network protocols for exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. The web data may be fetched based on one or more pre-defined search terms for searching web content related to decentral network protocols for exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol.

[0199] Configuration data may be generated by mapping the fetched web data to a configuration data structure as stored by a configuration data base, wherein the configuration data base stores key value pairs of decentral network protocols and respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. The configuration data base may store configuration data in key-value pairs including decentral network protocols and per decentral network protocol one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. The at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product are retrieved based on the key-value pairs. The configuration data base may store configuration data including descriptions in natural language of configuration data points stored as configuration data, wherein the at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product are retrieved based on the descriptions in natural language of configuration data points stored as configuration data. The web data may be fetched in response to update event(s) provided by web components configured to notify subscribers when web content is updated.

[0200] Values related to the decentral network protocols for exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol may be extracted from the fetched web data. The configuration data base may store values for configuration data points stored as key-value pairs.

[0201] Descriptions of the decentral network protocols for exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol may be extracted from the fetched web data. The configuration data base may store descriptions in natural language for configuration data points stored as key-value pairs. Descriptions related to or of the decentral network protocols for exchanging product data associated with the supply chain product 231228

[0202] 42 and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol may be generated using a Large Language Model. One or more instruction may be generated and provided to the Large Language Model, wherein the instructions may include at least one task instruction specifying the task to generate descriptions of the decentral network protocols for exchanging product data associated with the supply chain product and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged, wherein the instructions may include fetched web data as context, wherein the instructions may indicate the key-value pair(s) of configuration data structure to be described.

[0203] The generated configuration data may be stored in a configuration database in configuration data structure.

[0204] A request to provide the digital asset by generating the digital asset and / or by accessing the generated digital asset may be provided. The request may include at least one indication of the decentral network protocol for exchanging product data associated with the supply chain product and / or of the data model related to product data associated with the supply chain product to be exchanged by the decentral network protocol.

[0205] The digital asset may be generated by retrieving the configuration data from the configuration data base based on the request. The digital asset may be generated based on the retrieved decentral network protocol and / or at least one data model includes generating at least one product data set according to the retrieved at least one data model by retrieving one or more product data points from a product data base based on the retrieved at least one data model, wherein the product data base provides product data associated with the at least one supply chain product. The digital asset may be generated based on the retrieved decentral network protocol and / or at least one data model includes providing one or more decentral identifier(s) uniquely associated with the supply chain product based on the retrieved decentral network protocol and by providing a locator to the generated product data set.

[0206] The generated digital asset may be provided for access by one or more data consuming node(s) according to the decentral network protocol.

[0207] Fig. 6 illustrates an example method for generating digital assets for a specific supply chain product.

[0208] The method of Fig. 6 illustrates the method of operation including the complexity induced by (a) the system interaction stemming from different nodes following different decentral network protocols, (b) the decentral network protocol, the data model and / or the product data points stored in the configuration data base or the product data base not corresponding to the user and / or system interaction. The method for generating a digital asset associated with at least one supply chain product may be executed in stages including the determination of the decentral network and / or the data model followed by the selection of product or property data related to the supply chain product. 231228

[0209] 43

[0210] At least one user and / or system interaction relating to a request to provide the digital asset the digital asset by generating the digital asset and / or by accessing the generated digital asset may be provided. The user and / or system interaction may be based on a user interaction such as a prompt in natural language and / or system interaction such as a request received by a node of one of the decentral networks. For example, a user may provide a user instruction to generate a passport or digital asset for the supply chain product in natural language. Further for example, a participating node of one decentral network may request the generation of the digital asset of the supply chain product. The user and / or system interaction may relate to at least one decentral network protocol for exchanging product data associated with the supply chain product, at least one data model related to product data associated with the supply chain product and / or a product data set to be generated according to the provided or selected at least one data model. The user and / or system interaction may relate to a request for providing the digital asset by generating the digital asset and / or by accessing the generated digital asset by one or more participant(s) of one or more decentral network(s) and / or for one or more supply chain product(s).

[0211] The selection instructions as used herein may include at least one instruction configured to search the product data base and / or the configuration data base, at least one instruction configured to retrieve configuration data from the configuration data and / or product data from the product data base, at least one instruction configured to interact with a template data base storing template instructions for interaction with a Large Language Model (LLM), at least one instruction configured to interact with the Large Language Model (LLM), at least one instruction configured to retrieve a selection from the Large Language Model (LLM) or any combinations or subsets thereof. The selection instructions as used herein may include multiple sub-instructions to be executed for one or more stages, wherein the one or more stages include a retrieval stage, a semantic search stage and / or a LLM retrieval stage, wherein the multiple stages are staggered, wherein depending on successful or failed selection per stage the retrieval stage may be followed by the semantic search stage and / or the LLM retrieval stage.

[0212] At least one selection instruction for selecting at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product based on accessing a configuration data base and at least in part based on the at least one user and / or system interaction may be generated. The configuration data base may provide access to configuration data including at least decentral network specifications and / or one or more data model(s) associated with the at least one supply chain product related to the specified decentral networks. The configuration data base may store configuration data in key value pairs including decentral network protocols and per decentral network protocol one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol. The at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product may be selected based on the key-value pairs. The configuration data base may store configuration data including descriptions in natural language of configuration data points stored as configuration data. The at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product may be selected based on the descriptions in 231228

[0213] 44 natural language of configuration data points stored as configuration data. The configuration database may be populated and / or updated based on web data related to the one or more decentral networks, wherein web data is retrieved by a web interface configured to access web repositories and / or scrape webpages. The web data may be mapped to configuration data for populating and / or updating the configuration data base. The configuration database may be related to at least one operating system orchestrating decentral network data exchange in multiple decentral networks and / or digital asset generation for orchestrating decentral network data exchange in multiple decentral networks and / or the configuration database may be related to the decentral network node associated with a decentral network participant producing the at least one supply chain product.

[0214] At least one decentral network and / or at least one data model based on the at least one selection instruction may be selected. The decentral network and / or the data model may be indicated by the user and / or system interaction as specified by the configuration data stored by the configuration data base. In such case the decentral network and associated data models may be retrieved from the configuration data base based on the user and / or system interaction.

[0215] The decentral network and / or the data model may not be indicated by the user and / or system interaction as specified by the configuration data stored by the configuration data base. The decentral network and / or the data model as specified by the user and / or system interaction may not be identical as specified by the configuration data stored by the configuration data base. The decentral network specification as indicated by the user and / or system interaction may be different to the decentral network specification stored in the configuration database. The decentral network specification as indicated by the user and / or system interaction may correspond to the decentral network specification stored in the configuration database. In such case the selection may include a semantic search in the configuration database and confirming that the decentral network specification is stored in relation to data models related to the decentral network specification provided by the user and / or system interaction. Further a user confirmation may be requested and / or provided confirming that the decentral network specification semantically correlating to the decentral network specification provided by the user and / or system interaction is stored in relation to data models and supply chain products related to the specified decentral network in the configuration data base.

[0216] The decentral network specification as indicated by the user and / or system interaction may be different to the decentral network specification stored in the configuration database and may not correspond to the decentral network specification stored in the configuration database. In such case the decentral network and associated data models may be retrieved from the configuration data base in interaction with a LLM. the user and / or system interaction may include context relating to the decentral network specification. In such case the selection may include interaction with a data-driven general-purpose model as described above and will be described in more detail below. The selection may include retrieval of at least one prompt template with instructions for selecting the decentral network and / or decentral network specification. The instructions may include at least one task instruction for the general-purpose data- driven model relating to the task of selecting the decentral network and / or decentral network specification. The instructions may include at least one context instruction for the general-purpose data-driven model relating to context 231228

[0217] 45 data for the network as stored in the configuration data base e.g. by providing decentral network specifications and / or context for the network stored in the configuration data base to be selected from. The selection instructions may be provided to the general-purpose data driven model to generate decentral network specification to be selected. The general-purpose data driven model may generate and provide decentral network specification to be selected. Further a user confirmation may be requested and / or provided confirming that the decentral network specification conforms with the decentral network intended by the user and / or system interaction.

[0218] At least one decentral network and / or at least one data model may be selected and provided for generating the digital asset associated with the supply chain product.

[0219] The digital asset may be generated based on the provided based on the at least one decentral network and / or at least one data model. A data set may be generated according to the selected at least one data model by generating at least one selection instruction for selecting at least one data point from a product data base based on the data model. The product data base may provide product or property data associated with the at least one supply chain product. The product data base may store product data in key value pairs including product or property data related to properties associated with the supply chain product and to be exchanged by the decentral network protocol. The at least one at least one product data set according to the selected at least one data model may be selected based on the key-value pairs. The product data base may store product data including descriptions in natural language of product data points stored as product data. The at least one at least one product data set according to the selected at least one data model may be selected based may be selected based on the descriptions in natural language of product data points stored as product data. The product database may be related to the decentral network node associated with a decentral network participant producing the at least one supply chain product, wherein the product database is directly or indirectly communicatively connected to a target data base for storing generated digital assets. The target data base for storing generated digital assets may be directly or indirectly communicatively connected to the decentral network node associated with a decentral network participant producing the at least one supply chain product.

[0220] The product data associated with the supply chain product may be indicated by the user and / or system interaction as specified by the product or property data stored by the product data base. In such case the product or property data associated with the supply chain product may be retrieved from the product data base based on the user and / or system interaction. The product or property data associated with the supply chain product may not be indicated by the user and / or system interaction as specified by the product or property data stored by the product data base. In such case the product or property data associated with the supply chain product may be retrieved from the product data base in interaction with a LLM.

[0221] For example, if the selected data model specifies the data points as stored in the product data base or corresponding to the product database, the data point selection may include selection according to the data model. If the selected data model specifies the data points without one-to-one correspondence to the data points stored in the product 231228

[0222] 46 database, the data points may be selected according to the data model based on string or semantic search in the product data base.

[0223] Further for example, if the selected data model does not specify the data points as stored in the product data base or corresponding to the product database, the data point selection may include selection based on the data model and context of the data model and / or data points. In such case the selection may include interaction with a data-driven general-purpose model as described above and will be described in more detail below. The selection may include retrieval of at least one prompt template with instructions for selecting the data points. The instructions may include at least one task instruction for the general-purpose data-driven model relating to the task of selecting the data points according to the data model. The instructions may include at least one context instruction for the general-purpose data-driven model relating to context data for the data model as stored in the configuration data base and / or context data for the data points as stored in the product data base. The selection instructions may be provided to the general-purpose data driven model to generate data points to be selected. The general-purpose data driven model may provide data points to be selected. Further a user confirmation may be requested and / or provided confirming that the data points and related data model conform with the supply chain product and the decentral network intended by the user and / or system interaction.

[0224] The digital asset may be generated by providing one or more decentral identifier(s) uniquely associated with the supply chain product based on the selected decentral network and by providing a locator to the generated data set.

[0225] The digital asset for access by one or more data consuming node(s) of the selected decentral network may be provided.

[0226] Figs. 7a-c illustrate screens with entry masks for the user to specify the data model, the product data and / or properties of the digital asset.

[0227] Figs. 8-11 illustrate an example transformer architecture of a general-purpose model. Fig. 8 illustrates an embodiment of training an embedding layer.

[0228] An input embedding may be obtained by training for example a continuous bag of words model (CBOW) or a skipgram model. The embedding layer may be suitable for generating embedded input data based on input data. Generating embedded input data may refer to embedding input data. Embedding input data may result in a representation associated with the input data. Thus, the embedded input 114 may be the representation associated with the input data. The input data may comprise one or more elements. The one or more elements may be represented by the input vector 106. In particular, the embedded input 114 and / or the input vector 106 may be machine- readable and / or processable by a processor. For this purpose, the embedded embedded input 114 and / or the input vector 106 may be a tensor, in particular a first-rank tensor. Specifically, the input vector 106 may be a one-hot vector or a summation of a plurality of one-hot vectors. A one-hot vector may be a vector with one entry unequal to zero. Examples for 231228

[0229] 47 one-hot vectors may be 108, 110 and 112. The entries unequal to zero in the one-hot vector and / or in the input vector 106 may indicate the element. For example, a lookup table may define the relation between the position of the entries unequal to zero and the element indicated by the one-hot vector. The lookup table may specify a plurality of different elements. The number of different elements may be equal to the number of entries in the one-hot vector. The number of different elements may be referred to as vocabulary size. In an example, the elements may be represented by tokens and a sequence of elements may refer to at least a part of a sentence. The at least a part of the sentence may be represented by a plurality of tokens. A token may represent at least a part of the element and / or word.

[0230] The embedded input 114 may be a lower-dimensional representation than the input vector 106. For example, typical embedded inputs 114 may comprise some hundreds of different entries. Followingly, the embedded inputs 114 constitute a densified representation of one or more elements using less computational resources. More than that, the embedded input 114 may represent a relation between two or more elements. For example, the words "Italy” and "Germany” may be similar or may be more closely related since they both define european countries, whereas the the word "embodiment” may be very different from the two respective words. The smaller the dot product between two embedded inputs 114 may be the more similar the two elements associated with the embedded inputs 114 may be.

[0231] For transforming the input vector 106 into the embedded input 114, the embedding layer may comprise a number of neurons equal to the number of entries in the embedded input 114. Based on the embedded inputs 114, the output layer may generate the output vector 116. The output vector may be a vector and / or may indicate one or more elements. The output vector 116 may indicate one or more elements different from the input vector 106 and / or the one- hot vectors associated with the input vector 106. For this purpose, the output layer may comprise a number of neurons equal to the number of entries of the input vector 106 and / or the output vector 116. The output layer may apply a softmax function to the embedded inputs 114. By doing so, the output vector may comprise the probabilities associated with the elements associated with the entries of the output vector 116 unequal to zero. By defining a threshold to which the probability may be compared, the selection of the corresponding elements may be tailored to the needs of the user. The elements generated by the model comprising the embedding layer 102 and the output layer 104 may refer to the most probable elements indicated by the output vector 116. Hence, the model depicted in FIG. 8 may generate the element associated with the vector 118 with a confidence score of 71 %.

[0232] The model of FIG. 8 may be continuous bag of words (CBOW) model. The CBOW model may be trained based on a training data set comprising a plurality of input vectors and corresponding output vectors. As the training data set may not be labeled, the training of the CBOW model may be referred to as self-supervised. Before training of the CBOW model, the CBOW model may be initialized with random values assigned to the weights of the neurons. During the training of the CBOW model, the input vectors may be passed through the initialized embedding layer and the output layer and a loss may be determined by comparing the output vector obtained by passing the input vector 106 through the model to the output vector corresponding to the input vector 106 as specified by the training data set. 231228

[0233] 48

[0234] Based on the determined loss, backpropagation may be applied to determine the gradients associated with the neurons of the embedding layer 102 and the output layer 104 to lower the loss. According to the determined gradients, the weights of the neurons may be updated by using a gradient descent algorithm. If a predetermined loss may be achieved by the CBOW model, the training may be terminated and a trained CBOW model may be obtained. From the trained CBOW model, the embedding layer 102 may be suitable for embedding input data comprising one or more elements. This embedding layer 102 may be used in other machine-learning architectures requiring an embedding layer 102 such as a transformer encoder, transformer decoder or transformer encoder decoder architecture as described within the context of FIG. 9A, 9B, 9C and 9D. Hence, a model such as a CBOW model may be trained prior to training the transformer encoder, transformer decoder or transformer encoder decoder architecture.

[0235] Fig. 9A illustrates an embodiment of a transformer encoder architecture.

[0236] The transformer encoder comprises an encoder input 278, one or more encoder blocks 274, 214 and an encoder output. A plurality of transformer encoder architectures may be available in the art such as the bi-directional encoder representations from transformers (BERT) or ELECTRA.

[0237] The input data may be received at the encoder input 278. The input data may comprise at least one of text data, numerical data, tabular data, image data or the like. Where the input data may comprise one of text data, numerical data, tabular data, image data or the like. Input embedding of a type corresponding to the type of input data may be applied. The type of the input data may be text data, numerical data, tabular data, image data or the like. In an embodiment, the input data may be associated with two or more types of input data. The input embedding may be associated with the two or more types of input embedding, in particular according to the input data. Hence, the input embedding may be configured to map text data, numerical data, tabular data, image data or the like to a numerical representation of the input data. Per type of input data, the corresponding input embedding may be applied to at least a part of the input data associated with the type of input data. A model processing numerical representations of different types of data may be referred to as a multimodal model. The type of the input data may correspond to a modality. An example of input embedding associated with text data can be found in the context of FIG. 8. An example of input embedding associated with numerical and / or tabular data can be found in the context of FIG. 11.

[0238] Receiving and / or providing the input data may comprise identifying two or more elements of the input data. This may be referred to as tokenization. For this purpose, a vocabulary may be available. The vocabulary may specify a plurality of elements, in particular elements typically repeating in data of the type of the input data. For example, where the input data may be text data, the vocabulary may comprise several endings and / or word stems. In an embodiment, the elements of the input data may be specified by a selection indicative of the plurality of elements provided.

[0239] The encoder input 278 may be configured to perform any one of 702 to 708 or a combination thereof. 231228

[0240] 49

[0241] Further, the encoder input 278 may be configured to perform 710, ie apply positional encoding 204. Applying positional encoding 204 may refer to adding a positional factor to the embedded input obtained via input embedding. Preferably, the input data may specify a sequence of elements. The positional factor pposmay be indicative of the position of the elements within the sequence. For example, the positional factor may be obtained based on the following equation: where pos may refer to the position of the element within the sequence, i may refer to the dimension associated with the input embedding and d may refer to the dimension of the model, eg transformer decoder, transformer encoder or transformer encoder-decoder. This may be referred to as absolute positional embeddings. Alternatively, the positional encoding may be based on rotary positional embeddings (RoPE). Positional encoding is beneficial since it enables the processing of sequential data without requiring further dimensions indicating the position of each element. Followingly, the positional encoding 204 reduces the computational resources needed for embedding the input data. By passing the input data through the encoder input, the input data may be transformed into a second-rank tensor representing the sequence of elements. This second-rank tensor may be referred to as embedded input data.

[0242] The encoder block may be configured to perform any one of 712 to 716 or a combination thereof, he embedded input data may be provided to the layer normalization 208 by a residual connection. 712 and 714 may be referred to as applying multi-head self-attention 206. Multi-head self-attention 206 may comprise the two components multi-head and self-attention. Self-attention may be understood as being a filter applied to the embedded input data and correspond to 714. Applying the filter may be referred to as weighting the elements associated with the embedded input data. This is advantageous specifically regarding long sequences of elements. The filter may be learned and improved during the training by learning to identify the contribution of elements associated with the embedded input data. Self-attention may refer to attention generated based on the input data. Hence, the filter may be determined based on the input data, preferably the embedded input data. The embedded input data may serve as query Q, key K and value V with respect to the self-attention operation. The self-attention may refer to attention based on the received input data. Hence, the filter may be calculated based on the following formula by inserting the respective tensors based on the embedded input data: where dk corresponds to the dimension of the key.

[0243] For improving the efficiency of the transformer encoder further, the multiple heads are used to apply the filter resulting in the multi-head self attention 906. Multi-head self attention 906 may comprise applying the filter to 231228

[0244] 50 two or more parts of the embedded input data. Hence, the tensor may be split into two or more parts and the filter may be applied to the two or more parts separately by two or more heads according to the following equa-tion :head i = Attention (QWiQ, KW{K, VWiV) with parameter matrices may refer to the number of heads, may refer to the dimensions of the value, key and query. The result of the two or more head may be concatenated according to the following equation: MultiHead Q, K, V) = Concat (head 1, . . . , headh) WQwhere pe^hdv*d and h may refer to the number of heads.

[0245] The embedded input data may be transformed via the multi-head self-attention 206 into a context tensor. The context tensor may represent the sequence of elements and the relation between two or more elements of the input data. The context tensor may be a second rank tensor and / or may comprise one or more first rank tensors). After the multi-head self-attention 206 layer normalization 208 may be applied based on the context tensor and / or the embedded input data from the residual connection. Applying layer normalization 208 may refer to normalizing the context tensor. Normalizing the context tensor may lower the values of the entries of the context tensor. This reduces the computational cost associated with processing the context tensor. Further, it improves the training by contributing the loss to converge and preventing instabilities.

[0246] Layer normalization 208 may be followed by passing the context tensor to a feed-forward layer 210 again followed by layer normalization 212 based on the residual connection to the context tensor and / or the output of the feed-forward layer 210. The feed-forward layer 210 may be a feed-forward neural network. The feed-forward neural network may comprise of a plurality of fully connected neurons. Passing the context tensor through the feed-forward neural network may result in transforming the context tensor linearly. Additionally or alternatively, the neural network may comprise one or more activation functions such as a rectified linear unit (ReLU). Hence, the neural network may be configured for performing one or more non-linear operations to the context tensor and / or transforming the context tensor non-linearly. After the context tensor has been transformed and / or normalized by the feed-forward layer 210 and the layer normalization 212, the context tensor may be provided to one or more further encoder blocks 214. Having passed the context tensor through the feed-forward layer 210 may adapt the context tensor for the processing by a further attention layer of the one or more further encoder blocks 214 for applying a self-attention filter, preferably multi-head self-attention 206. The context vector after being transformed by the layer normalization 212 and the feed-forward layer 210 may be referred to as hidden state.

[0247] The encoder output 276 comprises of a linear layer 216 and a softmax layer 218. The linear layer 216 may transform the context vector into a logits vector. The linear layer may be fully connected. The logits vector obtained by passing the context tensor through the linear layer 216 may be passed through the softmax layer 218. Passing the logits vector through the softmax layer 218 may refer to applying the softmax function to the 231228

[0248] 51 logits vector. Applying the softmax function to the logits vector may result in a probability distribution of one or more elements corresponding to the sequence of elements in the input data. From the probability distribution based on predefined selection criteria, one or more elements may be chosen. The one or more chosen elements may be referred to as the one or more elements generated by the transformer encoder. The one or more generated elements may be provided to the encoder input for generating further one or more elements corresponding to the sequence of the input data and the one or more elements generated by the transformer encoder as described within the context of FIG. 10.

[0249] Hence, processing the numerical representation of the two or more elements and the relation between the two or more elements by the data-driven model may comprise at least one of 708 to 720 or a combination thereof. Applying self-attention may comprise modifying the two or more numerical representation of the two or more elements and the relation between the two or more elements by applying a filter to the two or more numerical representations of the two or more elements and the relation between the two or more elements , wherein the filter may be configured to modify the contribution of the two or more elements to the numerical representations of the two or more elements and the relation between the two or more elements. The filter may be obtained during training of the data-driven model. The filter may be obtained based on, in particular related to the input data. Multi-head self-attention may comprise generating two or more numerical representations of the two or more elements and the relation between the two or more elements from the numerical representation of the two or more elements and the relation between the two or more elements, modifying the two or more numerical representation of the two or more elements and the relation between the two or more elements by applying a filter to the two or more numerical representations of the two or more elements and the relation between the two or more elements , wherein the filter may be configured to modify the contribution of the two or more elements to the numerical representations of the two or more elements and the relation between the two or more elements and / or concatenating the two or more numerical representations of the two or more elements and the relation between the two or more elements.

[0250] The encoder output may be configured to map the concatenated numerical representation of the two or more elements and the relation between the two or more elements to a numerical representation of the output data. The numerical representation of the output data may be mapped to output data, eg by providing a vocabulary indicative of a relation between numerical representations and data of a type according to the input data. Additionally or alternatively, a decoding model may be used to map the concatenated numerical representation of the two or more elements and the relation between the two or more elements to a numerical representation of the output data. The decoding model may be trained to relate a numerical representation of data of a type according to the input data.

[0251] FIG. 9B illustrates an embodiment of a transformer decoder architecture. Input data, embedded input data, context tensor and / or output data may be as defined within the context of FIG. 9A. 231228

[0252] 52

[0253] The transformer decoder comprises a decoder input 284, one or more decoder blocks 280, 232 and a decoder output 292. The transformer decoder architecture may be derived from the transformer encoder-decoder architecture as shown in FIG. 9C. The transformer decoder may be referred to as X-former. The transformer decoder architecture may correspond to the decoder architecture associated with the transformer encoder-decoder architecture independent of receiving one or more hidden states from the encoder of the transformer encoderdecoder. A plurality of transformer decoder architectures are available in the art such as the generative pretrained transformers (GPT).

[0254] The decoder input 284 may apply input embedding 220 and positional encoding 222 analogous to analogous to the input embedding 202 and the positional encoding 204 as described within the context of FIG. 9A.

[0255] The decoder block 280 may comprise the layer normalizations 226, the masked multi-head self-attention 224, the feed-forward layers 228 and / or the layer normalization 230. The embedded input data resulting from passing the input data through the decoder input 284 may be provided to the layer normalization 226 via a residual connection. Further, masked multi-head self-attention 224 may be applied to the embedded input data. Masked multi-head self-attention 224 corresponds to the multi-head self-attention 206 as described within the context of FIG. 9A with additionally masking a part of the embedded input data associated with elements later in the sequence than the element to be generated. Additionally or alternatively, the part of the input data associated with elements later in the sequence than the element to be generated may not be received and / or transformed into the embedded input data. Thus, the transformer decoder may be suitable for generating a subsequent element to a sequence, whereas the transformer encoder may be suitable for generating a missing element in within one sequence and / or between two or more sequences. Therefore, the transformer encoder may be configured for classification tasks. The transformer decoder may be configured for text generation. Masked multihead self-attention may comprise applying a filter obtained based on elements of the sequence of the input data appearing previously to the to be generated part of the sequence. Similar to the transformer encoder as described within the context of FIG. 9A, a context tensor may be generated by applying the masked multi-head self-attention 224 and the layer normalization 226. The context tensor may be provided to the layer normalization 230 via a residual connection. Further, the feed-forward layer 228 and the layer normalization 230 may be analogous to the feed-forward layer 210 and the layer normalization 212 as described within the context of FIG. 9a. The context tensor may be provided to one or more further decoder blocks 232.

[0256] The decoder output 292 may comprise of a linear layer 234 and a softmax layer 236. The linear layer 234 and the softmax layer 236 may be analogous to the linear layer 216 and the softmax layer 218 as described within the context of FIG. 9A.

[0257] FIG. 9C illustrates an embodiment of a transformer encoder-decoder architecture. The transformer encoderdecoder may comprise the encoder input 288, the one or more encoder blocks 286, 264, the decoder input 294, the decoder block 290 and the decoder output 292. The encoder input 288 may correspond to the encoder input 231228

[0258] 53

[0259] 278 of FIG. 9A. The one or more encoder block 286, 264 may correspond to the one or more encoder blocks

[0260] 274, 214 of FIG. 9A. The decoder input 294 may correspond to the decoder input 284 of FIG. 9B.

[0261] The decoder block 290 may comprise a masked multi-head self-attention 270, a layer normalization 272, a feedforward layer 238 and a layer normalization 240 analogous to the masked multi-head self-attention 224, the layer normalization 226, the feed-forward layer 228 and the layer normalization 230 as described within the context of FIG. 9B. The decoder block 290 may further comprise a multi-head self-attention 250 and a layer normalization 248. Analogous to the description of FIG. 9B, the context tensor may be obtained from the masked multi-head self-attention 270 and the layer normalization 272. Multi-head self-attention 250 analogous to the multi-head self-attention 206 of FIG. 9A may be applied to the context vector obtained from the layer normalization 272 and the hidden states of the one or more encoder blocks 286, 264. Layer normalization 248 may be applied to the context vector obtained from the multi-head self-attention 250 and the context vector obtained from the layer normalization 272 provided via a residual connection. The context vector resulting from the layer normalization 248 may be processed via the feed-forward layer 238 and the layer normalization 240 analogous to the description of FIG. 9B. The context vector resulting from the layer normalization 240 may be provided to further decoder blocks 242 analogous to the decoder block 290. The context vector obtained from the one or more decoder blocks 290, 242 may be provided to the decoder output 292. The decoder output 292 may correspond to the decoder output 282 of FIG. 9B.

[0262] With the above-described example architectures, the transformer encoder-decoder may receive and process input data at the encoder input 288 and the one or more encoder blocks 286, 264 and the decoder block 290 and the decoder output 292. Based on the input data, the transformer encoder-decoder may generate output data part by part or sequentially. The sequentially generated output data may be provided to and / or may be processed by the decoder input 294, the one or more decoder blocks 290, 242 and the decoder output 292. Preferably, a sequence may be provided to the encoder input 288 and after having generated at least a part of the output data, the decoder input 294 may be provided with at least the part of the elements of the output data already generated. By doing so, the next elements of the output data may be generated with a higher accuracy by taking the input data and the generated output data into account since more data is received by the transformer encoder-decoder may be received over time.

[0263] Because of the transformer encoder-decoder architecture, the transformer encoder-decoder may be configured for transforming a sequence into another representation of the sequence. An example for transforming one sequence into another representation may be translation of one sentence into another language. A plurality of transformer encoder-decoders are available in the art such as BART, T5 or the like. 231228

[0264] 54

[0265] In an embodiment, the layer normalization 208, 212 may be applied prior to the masked multi-head self-attention 224, multi-head self-attention 206 and / or the feed-forward layer 210 in the transformer decoder, the transformer encoder and / or the transformer encoder-decoder. By doing so, the computational resources for applying the multi-head self-attention 206 and / or the feed-forward layer 210 to the embedded input data and / or the context tensor may be decreased as the entries of the respective tensors may be lower after normalization.

[0266] In an embodiment, the decoder output 292 may comprise of a classification neural network, further feedforward layers, convolutional layers, fully connected layers or the like. For example, the transformer encoder-decoder may be configured for choosing between a plurality of options. For this purpose, the transformer encoder-decoder may be provided with three different input data sets and may classify the context vectors obtained from the one or more decoder blocks 290 via one or more linear layers. Followingly, the architecture may be extended depending on the use case to be solved.

[0267] FIG. 9d illustrates an embodiment of a Mamba architecture. The mamba architecture may be used as data- driven model. A Mamba architecture may enhance inference speed in relation to a transformer-based model.

[0268] The Mamba architecture with its layered structure may be similar to the transformer decoder architecture discussed in relation to FIG. 9D. However, instead of decoder blocks mamba blocks 332, 304 are stacked. Mamba block 332 may be based on a selective space state sequence model (S6).

[0269] An input token may be linearly projected via linear layer 312, 320 into an expanded latent space (which may allow to capture more information during processing in the selective state space layer 310), followed by a convolution via a convolutional layer 314 and a non-linear function (e.g. a sigmoid linear unit (SiLu) or swish activation function). The convolution before the selective state space layer 310 may prevent independent token calculations. The selective state space layer 310 performs a selective state space operation. Further, a learnable skip connection may be provided via linear layer 320, this may use a linear transformation to map the input to the output, similar to a residual connection in a transformer model this may help to mitigate vanishing gradient effects.

[0270] A selective state space layer 310 may be a linear recurrent network that selectively process data based on the input token, which may allow to focus on relevant data and discard irrelevant data. For instance in each step a separate weight vector may be determined based on the respective input token. The determined weight vector may then be used in a selective scan. 231228

[0271] 55

[0272] A selective state space layer 310 may be used in a convolutional mode e.g. for parallelizable training and a recurrent mode for near-constant time generation of output data. A state space operation may be based on solving the state and output equations, wherein a state equation may describe how a state changes based on how the input influences the state and an output equation may describe how the state is translated to the output. Further how the input influences the output may be represented by a learnable linear transformation, e.g. a matrix D, used in a learnable skip connection.

[0273] The state equation for a hidden state may be (in discretized form): hk— Ahk■> ~F Bxk

[0274] The output may be expressed by (in discretized form): yk= Chk

[0275] This discretized space state model may be unfolded into a recurrent form similar to a recurrent network, exemplifying that a selective state space model may be or comprise a linear recurrent model. However, here matrices A, B, and C may also be used as a kernel of a convolution of the state space model. Kernel K for this may e.g. be: which may allow to determine an output:

[0276] So, in this representation of the state space model training may be performed in a parallel manner like in convolutional neural networks.

[0277] Matrix A may be a matrix that represents recent tokens well and decays older tokens and may be initialized using HIPPO: where every entry below the diagonal is set to 0. This may allow to create a long-term memory for the selective state space model.

[0278] For a Mamba block 332, the matrices B and C as well as the step size A used for discretization of the matrices may be dependent on the input token and may be trained during training, so that for each input token different matrices B and C are determined, which may enhance the content-awareness and may act similar to a multihead self-attention in a transformer model. However, unlike in space state models with fixed matrices A, B, and C, here the convolutional representation may not be easily determined. Hence, to operate the selective state space layer 310 in convolutional mode a selective scan may be applied utilizing associative properties of the 231228

[0279] 56 hidden states calculation, allowing parallel determination of the sequence in parts and iteratively combining them, so that parallel training may be used. Further reading and writing operations may be decreased by using kernel fusion of the described step size, the selective scan, and the multiplication with C.

[0280] Linear layer 302 may project the generated output back into the same dimension as the input.

[0281] Mamba blocks may be used together with transformer decoder blocks or mixture of expert blocks (e.g. decoder blocks wherein the feed-forward layer is exchanged for a gating network and a number of parallel feed-forward layers, wherein the gating network switches between the feed-forward layers depending on the input), which may allow leveraging advantages of the different architectures.

[0282] An example of the architecture of a mamba block may be found in "Mamba: Linear-Time Sequence Modeling with Selective State Spaces” by Albert Gu and Tri Dao arXiv:2312.00752v2 [cs.LG] 31 May 2024, , which is incorporated herein by reference.

[0283] FIG. 10 illustrates an embodiment of training and / or deploying the transformer encoder, the transformer decoder and / or the transformer encoder-decoder.

[0284] The data-driven model 402 may correspond to the transformer decoder, the transformer encoder, the Mamba architecture and / or the transformer encoder-decoder as described within the context of FIGs. 9 A-D.

[0285] The output data generated by the data-driven model 402 may comprise of one or more elements, in particular a sequence of elements. The previously generated elements of the output data may be provided as input for generating the next element in the sequence of the output data.

[0286] In the example of FIG. 10, the input data may comprise of N elements, in particular input tokens. An input token may be a token dedicated to be inputted into the data-driven model. The output data to be generated may comprise of M elements. The data-driven model 402 may generate one element of the output data based on receiving the input data and optionally previously generated elements of the output data at a timestep. Hence, for generating M elements M time steps are required. A time step comprises of providing input 410, 412, 414 to the data-driven model 402 and receiving output data 404, 408, 406 from the data-driven model 402. In a first timestep, the input 410 may comprise of N input tokens. One or more input tokens may specify the beginning of the sequence of tokens and / or the end of the sequence of tokens. The input 410 may be processed by the data-driven model 402. Based on the input 410 at least a part of the output data 404 may be generated, eg a first output token. In the next timestep, the generated first output token may be provided together with the input 412. This process may be repeated until a token indicating an end of generating tokens may be generated by the data-driven model. 231228

[0287] 57

[0288] Similarly, to the data processing during deployment of the data-driven model 402, the data-driven model 402 may be trained. The training data set may comprise a plurality of sequences comprising a plurality of elements and / or tokens. The sequences may be associated with the input data and / or the output data. Additionally or alternatively, the sequences may be independent of the input data and / or the output data.

[0289] The training may be initialized by initializing the data-driven model 402. In an embodiment, the parameters associated with the data-driven model 402 may be initialized randomly. Additionally or alternatively, the input embedding of the data-driven model 402 may be obtained by training a CBOW model or a skip gram model as described within the context of FIGs 9A-D. The trained embedding layer may be used during training. The parameters associated with the embedding layer may be kept constant and / or may be updated after a predefined number of training epochs. By doing so, the number of parameters to be updated is lower enabling a faster and less computational resources-consuming training. Further, the accuracy associated with the embedding layer may be constant and / or may be increased by avoiding error compensation in relation to the just initialized data-driven model 402.

[0290] During the training of the data-driven model 402, at least a part of the sequences of the training data set may be provided to the data-driven model 402 one by another and one or more elements may be generated based on the sequences of the training data set one by another. The elements generated based on the sequences may follow the elements of the parts of sequences the data-driven model 402 may have been provided with. The generated one or more elements may be compared to the one or more elements following the at least a part of the sequences provided to the data-driven model 402 as specified by the training data set. Hence, during the training the data-driven model 402 may generate a guess on the next element and the guess on the next element in a sequence may be compared to the ground truth specifying the actual next element according to the training data set. Based on the guess on the next element and the ground truth a loss may be determined. The loss may define the similarity between the guess on the next element and the ground truth. The loss may be determined by forming a vector dot product between the token associated with the one or more elements and the token associated with the ground truth. A loss unequal to zero may result in updating the parameters associated with data-driven model 402. Preferably the parameters associated with the data-driven model 402 may be independent of the embedding layer. For example, the parameters associated with the data-driven model 402 may be weights of the neurons of the data-driven model 402.

[0291] Based on the determined loss, backpropagation may be applied to determine the gradients associated with the parameters of the parameters associated with data-driven model 402 to lower the loss. According to the determined gradients, the parameters associated with the data-driven model 402, preferably the weights of the neurons associated with the data-driven model 402, may be updated by using a gradient descent algorithm. 231228

[0292] 58

[0293] The training data set may be unlabeled. The sequences of elements within the training data set may inherently comprise the ground truth for determining the loss with respect to the one or more elements generated during the training of the data-driven model 402. Hence, the data-driven model 402 may be trained self-supervised.

[0294] The data-driven model may be configured to perform few shot or even zero shot predictions with respect to a plurality of use cases after pretraining. The performance of the data-driven model may be increased further by an additional training referred to as finetuning. Finetuning may refer to training a pretrained data-driven model for a concrete task, eg by providing task instructions to the pretrained data-driven model and adapting the parameters of the pretrained data-driven model to decrease the distance of the generated output data by the pretrained data-driven model in response to receiving the task instructions from predefined output data corresponding to the provided task instructions.

[0295] Models based on the architecture according to FIGs. 9A-D and / or pretrained data-driven model(s) and / or finetuned data-driven model(s) may be referred to as large language models. Famous examples include GPT models, BERT models or the like. Such models have been tested. Testing data-driven model(s), in particular pretrained and / or finetuned data-driven model(s), may include comparing output data generated by the one or more data-driven model(s) in response to receiving the input data with target data, eg obtained from domain experts. These domain experts may be a current bar for performing tasks the data-driven model(s) may be parametrized and / or trained for. The target data may specify output data desired to be generated in response to receiving the input data. In an example, Bran et al evaluated use of GPT-4 for chemical tasks such as organic synthesis tasks, molecular design tasks and / or chemical logic and knowledge tasks in the publication "Augmenting large language models with chemistry tools” (doi 10.48550 / arXiv.2304.05376). Bran et al showed that a model such as GPT-4 can solve chemical tasks.

[0296] FIG. 11 illustrates an embodiment of input embedding. Where the sequence of elements associated with the input data, preferably comprised in the input data, may be of one type, the input embedding 202, 220, 252, 266 as described within the context of FIG. 9A-D may be used. For example, a type of input data may be text where the elements may be associated with at least a part of a word, a punctuation character, a start token specifying the beginning of one or more sequences associated with the input data and / or the end token. In another example, the input data may be at least partially numerical. Hence, the input data may comprise a plurality of numbers. Numerical input data may be for example tabular data. Tabular data may specify one or more rows and / or one or more columns. Hence, the tabular data may comprise one or more cells, wherein the cells may be associated with one or more numerical values.

[0297] Numerical input data may require a different embedding than text input data. Input embeddings for numerical input data may comprise a token embedding, a positional embedding, a column embedding, a row embedding or a combination thereof. 231228

[0298] 59

[0299] Applying a token embedding to one or more elements, in particular tokens associated with the input data may result in a machine-processable representation associated with the one or more elements, in particular tokens. Applying the token embedding to one or more elements may refer to passing the one or more elements through the embedding layer, eg as described within the context of FIGs. 8, 9A-D. Hence, token embeddings may specify the one or more elements, in particular tokens in a machine-processable representation. For example, the token embedding may transform a numerical value into a vector. This is advantageous since this representation can be enriched by further information such as the position of the token within the sequence and / or within a table associated with the sequence of tokens. The positional embedding may be analogous to the positional embedding as described within the context of FIGs. 8, 9A-D. Where the input data may be tabular data, column embedding may be applied. Applying a column embedding to one or more elements, in particular tokens associated with the input data may result in a machine-processable representation specifying the location of the one or more elements within a table 502, preferably within the columns of the table 502. Applying the column embedding may refer to adding a column factor to the input data embedded via token embeddings, in particular the embedded input data. The column factor may be the same for elements associated with the same column and / or may differ between two or more elements associated with different columns.

[0300] Analogous, row embeddings may be applied where the input data may be tabular data. Applying a row embedding to one or more elements, in particular tokens associated with the input data may result in a machine-processable representation specifying the location of the one or more elements within a table 502, preferably within the rows of the table 502. Applying the row embedding may refer to adding a column factor to the input data embedded via token embeddings, in particular the embedded input data. The row factor may be the same for elements associated with the same row and / or may differ between two or more elements associated with different rows.

[0301] In an embodiment, input data may be at least partially numerical and at least partially text. Hence, the input data may comprise two or more types of data. A type of data may refer to a modality. Followingly, different embeddings may be applied to the input data. To parts of the input data comprising text the input embedding referred to in 8, 9A-D may be applied. To parts of the input data being numerical token embeddings, positional embeddings, column embeddings and row embeddings may be applied. Further, segment embeddings may be applied to the input data independent of the type of input data. The segment embedding may specify the type of input data one or more elements may be associated to. For example, if the input data comprises of text and numbers, the input data may comprise of two types of input data. Applying the segment embedding to the input data may refer to adding a segment factor to the input data, preferably the embedded input data and / or the input data after having applied the token embedding. The segment factor may specify the type of data associated with the one or more elements. The segment factor may be the same for one or more elements associated with the same type of input data and / or may differ between two or more elements associated with different types of input data. 231228

[0302] 60

[0303] Applying the token embedding, the positional embedding, the segment embedding, the column embedding, the row embedding or a combination thereof may result in embedded input data and / or may be the output of any one of the encoders input 278, 284, 288 or decoder input 284, 294. The data obtained by applying the token embedding, the positional embedding, the segment embedding, the column embedding, the row embedding or a combination thereof may be processed by the encoder block 274, 286, decoder block 280, 290, encoder output 276, decoder output 292, 282.

[0304] Figs. 12a to 12c illustrate different computing environments, central, decentral and distributed. The methods, apparatuses, computer elements of this disclosure may be implemented in decentral or at least partially decentral computing environments. In particular, for data sharing or exchange in ecosystems of multiple players different challenges exist. Data sovereignty may be viewed as a core challenge. It can be defined as a natural person's or corporate entity's capability of being entirely self-determined with regard to its data. To enable this particular capability related aspects, including requirements for secure and trusted data exchange in business ecosystems, may be implemented across the chemical value chain. In particular, chemical industry requires tailored solutions to deliver chemical products in a more sustainable way by using digital ecosystems.

[0305] Fig. 12a illustrates an example embodiment of a centralized computing system 1200 comprising a central computing node 1201 (filled circle in the middle) and several peripheral computing nodes 1201.1 to 1201.n (denoted as filled circles in the periphery). The term "computing system” is defined herein broadly as including one or more computing nodes, a system of nodes or combinations thereof. The term "computing node” is defined herein broadly and may refer to any device or system that includes at least one physical and tangible processor, and a physical and tangible memory capable of having thereon computer-executable instructions that are executed by a processor. Computing nodes are now increasingly taking a wide variety of forms. Computing nodes may, for example, be handheld devices, production facilities, sensors, monitoring systems, control systems, appliances, laptop computers, desktop computers, mainframes, data centers, or even devices that have not conventionally been considered a computing node, such as wearables (e.g., glasses, watches or the like). The memory may take any form and depends on the nature and form of the computing node.

[0306] In this example, the peripheral computing nodes 1201.1 to 1201.n may be connected to one central computing system (or server). In another example, the peripheral computing nodes 1201.1 to 1201. n may be attached to the central computing node via e.g. a terminal server (not shown). The majority of functions may be carried out by, or obtained from the central computing node (also called remote centralized location). One peripheral computing node 1201.n has been expanded to provide an overview of the components present in the peripheral computing node. The central computing node 1201 may comprise the same components as described in relation to the peripheral computing node 1201. n.

[0307] Each computing node 1201, 1201.1 to 1201. n may include at least one hardware processor 1202 and memory 1204. The term "processor” may refer to an arbitrary logic circuitry configured to perform basic operations of a computer or 231228

[0308] 61 system, and / or, generally, to a device which is configured for performing calculations or logic operations. In particular, the processor, or computer processor may be configured for processing basic instructions that drive the computer or system. It may be a semi-conductor based processor, a quantum processor, or any other type of processor configures for processing instructions. As an example, the processor may comprise at least one arithmetic logic unit ("ALU"), at least one floating-point unit ("FPU)", such as a math coprocessor or a numeric coprocessor, a plurality of registers, specifically registers configured for supplying operands to the ALU and storing results of operations, and a memory, such as an L1 and L2 cache memory. In particular, the processor may be a multicore processor. Specifically, the processor may be or may comprise a Central Processing Unit ("CPU"). The processor may be a ("GPU”) graphics processing unit, (“TPU”) tensor processing unit, ("CISC") Complex Instruction Set Computing microprocessor, Reduced Instruction Set Computing ("RISC") microprocessor, Very Long Instruction Word ("VLIW") microprocessor, or a processor implementing other instruction sets or processors implementing a combination of instruction sets. The processing means may also be one or more special-purpose processing devices such as an Application-Specific Integrated Circuit ("ASIC"), a Field Programmable Gate Array ("FPGA"), a Complex Programmable Logic Device ("CPLD"), a Digital Signal Processor ("DSP"), a network processor, or the like. The methods, systems and devices described herein may be implemented as software in a DSP, in a micro-controller, or in any other side-processor or as hardware circuit within an ASIC, CPLD, or FPGA. It is to be understood that the term processor may also refer to one or more processing devices, such as a distributed system of processing devices located across multiple computer systems (e.g., cloud computing), and is not limited to a single device unless otherwise specified.

[0309] The memory 1204 may refer to a physical system memory, which may be volatile, non-volatile, or a combination thereof. The memory may include non-volatile mass storage such as physical storage media. The memory may be a computer-readable storage media such as RAM, ROM, EEPROM, CD-ROM, or other optical disk storage, magnetic disk storage, or other magnetic storage devices, or any other physical and tangible storage medium which can be used to store desired program code means in the form of computer-executable instructions or data structures and which can be accessed by the computing system. Moreover, the memory may be a computer-readable media that carries computer- executable instructions (also called transmission media). Further, upon reaching various computing system components, program code means in the form of computer-executable instructions or data structures can be transferred automatically from transmission media to storage media (or vice versa). For example, computer-executable instructions or data structures received over a network or data link can be buffered in RAM within a network interface module (e.g., a "NIC”), and then eventually transferred to computing system RAM and / or to less volatile storage media at a computing system. Thus, it should be understood that storage media can be included in computing components that also (or even primarily) utilize transmission media.

[0310] The computing nodes 1201, 1201.1 ...1201. n may include multiple structures 106 often referred to as an "executable component or computer-executable instructions”. For instance, memory 104 of the computing nodes 1201, 1201.1 ...1201. n may be illustrated as including executable component 106. The term "executable component” may be the name for a structure that is well understood to one of ordinary skill in the art in the field of computing as being a structure that can be software, hardware, or a combination thereof or which can be implemented in software, 231228

[0311] 62 hardware, or a combination. For instance, when implemented in software, one of ordinary skill in the art would understand that the structure of an executable component include software objects, routines, methods, and so forth, that is executed on the computing nodes 101, 1201 .1 ... 1201 ,n, whether such an executable component exists in the heap of a computing node 1201, 1201 .1 ... 1201 ,n, or whether the executable component exists on computer-readable storage media. In such a case, one of ordinary skill in the art will recognize that the structure of the executable component exists on a computer-readable medium such that, when interpreted by one or more processors of a computing node 1201, 1201.1...1201. n (e.g., by a processor thread), the computing node 1201, 1201.1 ...1201n is caused to perform a function. Such a structure may be computer-readable directly by the processors (as is the case if the executable component were binary). Alternatively, the structure may be structured to be interpretable and / or compiled (whether in a single stage or in multiple stages) so as to generate such binary that is directly interpretable by the processors. Such an understanding of example structures of an executable component is well within the understanding of one of ordinary skill in the art of computing when using the term "executable component”. Examples of executable components implemented in hardware include hardcoded or hard-wired logic gates, that are implemented exclusively or near-exclusively in hardware, such as within a field- programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or any other specialized circuit. In this description, the terms "component”, "agent”, "manager”, "service”, "engine”, "module”, "virtual machine” or the like are used synonymous with the term "executable component.

[0312] The processor 1202 of each computing node 1201, 1201 .1 ...1201 ,n direct the operation of each computing node

[0313] 1201. 1201.1 ...1201. n in response to having executed computer- executable instructions that constitute an executable component. For example, such computer-executable instructions may be embodied on one or more computer- readable media that form a computer program product. The computer-executable instructions may be stored in the memory 1204 of each computing node 1201, 1201.1... 1201. n. Computer-executable instructions comprise, for example, instructions and data which, when executed at a processor 1201, cause a general purpose computing node 1201, 1201.1 ...1201.n, special purpose computing node 1201, 1201 .1 ...1201 ,n, or special purpose processing device to perform a certain function or group of functions. Alternatively or in addition, the computer-executable instructions may configure the computing node 1201, 1201.1... 1201. n to perform a certain function or group of functions. The computer executable instructions may be, for example, binaries or even instructions that undergo some translation (such as compilation) before direct execution by the processors, such as intermediate format instructions such as assembly language, or even source code.

[0314] Each computing node 1201, 1201 .1 ... 1201 ,n may contain communication channels 1208 that allow each computing node 1201.1... 1201. n to communicate with the central computing node 101, for example, a network (depicted as solid line between peripheral computing nodes and the central computing node in Fig. 1a). A "network” may be defined as one or more data links that enable the transport of electronic data between computing nodes 1201,

[0315] 1201.1 ...1201. n and / or modules and / or other electronic devices. When information is transferred or provided over a network or another communications connection (either hardwired, wireless, or a combination of hardwired or wireless) to a computing node 1201, 1201.1... 1201. n, the computing node 1201, 1201.1... 1201. n properly views the 231228

[0316] 63 connection as a transmission medium. Transmission media can include a network and / or data links which can be used to carry desired program code means in the form of computer-executable instructions or data structures and which can be accessed by a general-purpose or special-purpose computing nodes 1201, 1201 .1 ... 1201 ,n. Combinations of the above may also be included within the scope of computer-readable media.

[0317] The computing node(s) 1201, 1201.1 to 1201.n may further comprise a user interface system 1210 for use in interfacing with a user. The user interface system 110 may include output mechanisms 1210A as well as input mechanisms 1210B. The principles described herein are not limited to the precise output mechanisms 1210A or input mechanisms 110B as such will depend on the nature of the device. However, output mechanisms 1210A might include, for instance, displays, speakers, displays, tactile output, holograms and so forth. Examples of input mechanisms 110B might include, for instance, microphones, touchscreens, holograms, cameras, keyboards, mouse or other pointer input, sensors of any type, and so forth.

[0318] Fig. 12b illustrates an example embodiment of a decentralized computing environment 100' with several computing nodes 1201. T to 1201. n' denoted as filled circles. In contrast to the centralized computing environment 100 illustrated in Fig. 1a, the computing nodes 12201. T to 101. n' of the decentralized computing environment are not connected to a central computing node 1201 and are thus not under control of a central computing node. Instead, resources, both hardware and software, may be allocated to each individual computing node 1201. T... 1201. n' (local or remote computing system) and data may be distributed among various computing nodes 1201. T...1201. n’ to perform the tasks. Thus, in a decentral system environment, program modules may be located in both local and remote memory storage devices. One computing node 10T has been expanded to provide an overview of the components present in the computing node 10T. In this example, the computing node 101’ comprises the same components as described in relation to Fig. 12a.

[0319] Fig. 12c illustrates an example embodiment of a distributed computing environment 1203. In this description, "distributed computing” may refer to any computing that utilizes multiple computing resources. Such use may be realized through virtualization of physical computing resources. One example of distributed computing is cloud computing. "Cloud computing” may refer a model for enabling on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services). When distributed, cloud computing environments may be distributed internationally within an organization and / or across multiple organizations. In this example, the distributed cloud computing environment 1203 may contain the following computing resources: mobile device(s) 1214, applications 1216, databases 1218, data storage 1220 and server(s) 1222. The cloud computing environment 1203 may be deployed as public cloud 1224, private cloud 1226 or hybrid cloud 1228. A private cloud 1224 may be owned by an organization and only the members of the organization with proper access can use the private cloud 1226, rendering the data in the private cloud at least confidential. In contrast, data stored in a public cloud 1226 may be open to anyone over the internet. The hybrid cloud 128 may be a combination of both private and public clouds 1224, 1226 and may allow to keep some of the data confidential while other data may be publicly available. 231228

[0320] 64

[0321] The present disclosure has been described in conjunction with preferred embodiments and examples as well. However, other variations can be understood and effected by those persons skilled in the art and practicing the claimed subject-matter, from the studies of the drawings, this disclosure and the claims.

[0322] Notably, in particular, any steps presented can be performed in any order, i.e. the present disclosure is not limited to a specific order of these steps. Moreover, it is also not required that the different steps are performed at a certain place or at one node of a distributed system, i.e. each of the steps may be performed at different nodes using different equipment / data processing. The sequence of all method steps presented above is not mandatory, also alternative sequences may be possible. Nevertheless, the specific sequence of method steps shown as examples in the figures shall be considered as one possible sequence of method steps, e.g. for the respective embodiment described by the respective figure or an embodiment comprising at least some of the steps described by the respective figure.

[0323] Any steps presented herein can be performed in any order. The methods disclosed herein are not limited to a specific order of these steps. It is also not required that the different steps are performed at a certain place or in a certain computing node of a distributed system, i.e. each of the steps may be performed at different computing nodes using different equipment / data processing.

[0324] As used herein ..determining" also includes ..initiating or causing to determine", "generating" also includes ..initiating and / or causing to generate" and "providing” also includes "initiating or causing to determine, generate, select, send and / or receive”. "Initiating or causing to perform an action” includes any processing signal that triggers a computing node or device to perform the respective action.

[0325] In the claims as well as in the description the word "comprising” does not exclude other elements or steps and the indefinite article "a” or "an” does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in the mutual different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation. In the claims as well as in the description the word "comprising” or "including” or similar wording does not exclude other elements or steps and shall not be construed limiting to the elements or steps lined out. The indefinite article "a” or "an” does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in the mutual different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation or further elements may be included.

[0326] Providing in the scope of this disclosure may include any interface configured to provide data. This may include an application programming interface, a human-machine interface such as a display and / or a software module interface. 231228

[0327] 65

[0328] Providing may include communication of data or submission of data to the interface, in particular display to a user or use of the data by the receiving node, entity or interface.

[0329] Various units, circuits, entities, nodes or other computing components may be described as "configured to” perform a task or tasks. Configured to shall recite structure meaning "having circuitry that” performs the task or tasks on operation. The units, circuits, entities, nodes or other computing components can be configured to perform the task even when the unit / circuit / component is not operating. The units, circuits, entities, nodes or other computing components that form the structure corresponding to "configured to” may include hardware circuits and / or memory storing program instructions executable to implement the operation. The units, circuits, entities, nodes or other computing components may be described as performing a task or tasks, for convenience in the description. Such descriptions shall be interpreted as including the phrase "configured to.” Any recitation of "configured to” is expressly intended not to invoke 35 U.S.C. § 112(f) interpretation.

[0330] In general, the methods, apparatuses, systems, computer elements, nodes or other computing components described herein may include memory, software components and hardware components. The memory can include volatile memory such as static or dynamic random-access memory and / or nonvolatile memory such as optical or magnetic disk storage, flash memory, programmable read-only memories, etc. The hardware components may include any combination of combinatorial logic circuitry, clocked storage devices such as flops, registers, latches, etc., finite state machines, memory such as static random-access memory or embedded dynamic random-access memory, custom designed circuitry, programmable logic arrays, etc.

[0331] Moreover, any of the methods, method steps, processes and actions described or illustrated herein may be implemented using executable instructions in a general-purpose or special-purpose processor and stored on. A processor may be a processor of any suitable type such as a processor configured for parallel processing of at least a hundred or a at least a thousand threads in parallel, e.g. a graphical processing unit (GPU). For instance, the processor comprises at least a hundred or a at least a thousand parallel processing cores. In particular, the processor may comprise at least one (preferably at least a thousand) compute unified device architecture (CUDA) core(s), which may allow for using a graphical processing unit as the processor, which may increase computational efficiency. For instance, the processor may comprise at least one (e.g. at least a hundred) streaming multiprocessor cores, which may allow for increasing the data throughput. As a further example, the processor may comprise one or more (e.g. at least a hundred) tensor core(s). A tensor core may be specifically adapted to perform matrix operations and may allow to accelerate large matrix operations. A tensor core may be configured to perform mixed-precision matrix multiply and accumulate calculations in a single operation. For instance, a tensor core may perform mixed-precision floatingpoint matrix arithmetic, specifically utilizing FP16 (half-precision) inputs to produce either full-precision (FP32) or halfprecision (FP16) outputs. In the case of FP16 output, a tensor core may provide a performance boost by storing the intermediate accumulation results in FP32 format, thereby maintaining the precision necessary for accurate results. For example, a processor may comprise several thousand tensor cores, each capable of performing 64 floating point FMA (Fused M ulti ply-Add) operations per clock cycle. With these capabilities, such a GPU may allow for hundreds of 231228

[0332] 66

[0333] TFLOPs (Tera Floating-Point Operations per Second) of performance in mixed-precision computations. Furthermore, a tensor core may support a variety of numerical formats, including IEEE standard half-precision, single-precision, and double-precision floating-point formats, as well as a range of integer formats.

[0334] A processor may be a processor of any suitable type, and is preferably a processor configured for parallel processing of at least a hundred or at least a thousand threads in parallel, e.g. a graphical processing unit (GPU). For instance, the processor comprises at least a hundred or a at least a thousand parallel processing cores. In particular, the processor may comprise at least one (preferably at least a thousand) compute unified device architecture (CUDA) core(s), which may allow for using a graphical processing unit as the processor, which may increase computational efficiency. For instance, the processor may comprise at least one (e.g. at least a hundred) streaming multiprocessor cores, which may allow for increasing the data throughput. As a further example, the processor may comprise one or more (e.g. at least a hundred) tensor core(s) and / or (e.g. at least a hundred) tensor processing units (TPUs) . A tensor core may be specifically adapted to perform matrix operations and may allow to accelerate large matrix operations. A tensor core may be configured to perform mixed-precision matrix multiply and accumulate calculations in a single operation. For instance, a tensor core may perform mixed-precision floating-point matrix arithmetic, specifically utilizing FP16 (half-precision) inputs to produce either full-precision (FP32) or half-precision (FP16) outputs. In the case of FP16 output, a tensor core may provide a performance boost by storing the intermediate accumulation results in FP32 format, thereby maintaining the precision necessary for accurate results. A tensor processing unit may be an application-specific integrated circuit (ASIC). It may comprise a matrix multiplication unit (MXU), which may be specifically adapted or configured for dense linear algebra operations. TPUs may be configured to handle large-scale matrix operations efficiently, which may provide high computational throughput for Al tasks. A TPU may be equipped with on-chip high-bandwidth memory (HBM), which may enhance the capability for the use of larger models and batch sizes. TPUs may be connected in groups called Pods, which may scale up workloads with minimal code changes. An MXU may be specifically configured for performing matrix multiplications. A TPU may comprise a tensor core.

[0335] For example, a processor may comprise several thousand tensor cores, each capable of performing 64 floating point FMA (Fused Multiply-Add) operations per clock cycle or (e.g. at least several hundred) tensor processing units (TPUs) being specifically configured for accelerating machine learning (ML) workloads, particularly for cloud-based applications. Additionally, Field-Programmable Gate Arrays (FPGAs) and Application-Specific Integrated Circuits (ASICs) may provide flexibility and performance benefits for specific Al tasks.. With these capabilities, such a GPU may allow for hundreds of TFLOPs (Tera Floating-Point Operations per Second) of performance in mixed-precision computations. Furthermore, a tensor core may support a variety of numerical formats, including IEEE standard halfprecision, single-precision, and double-precision floating-point formats, as well as a range of integer formats.

[0336] A processor may be a central processing units (CPU) configured with an advanced architecture. A CPU may be configured for sequential processing and general-purpose computing. These CPUs may incorporate vector instruction sets, such as AVX-512, to accelerate mathematical computations that may e.g. enhance Al model training and 231228

[0337] 67 inference. Furthermore, CPUs may integrate Al accelerators i.e. a CPU may be specifically configured for deep learning workloads.

[0338] The processor may be coupled to memory having a memory bandwidth of at least a hundred gigabytes per second, which may allow efficient handling of extensive data sets and may allow faster reading, processing, and writing compared to a general-purpose processor such as a computational processing unit.

[0339] The memory may be a high-capacity memory configured to manage the data-intensive nature of Al applications, providing necessary bandwidth and storage capacity for complex datasets. The memory may for instance be DDR4, DDR5, High Bandwidth Memory (HBM) and / or GDDR6X memory, which may improve data transfer rates and reduce latency. Such memory may enhance e.g. modeling and real-time sensor data for monitoring and control. Further, the memory may be operated with memory optimization techniques, such as caching and prefetching, which may enhance the execution speed of Al algorithms. Non-volatile Memory (NVM) technologies, including NAND Flash and 3D XPoint, may provide persistent storage solutions with high-speed access, which may enhance rapid data storage and retrieval for Al applications.

[0340] Any disclosure and embodiments described herein relate to the methods, the systems, apparatuses, devices, chemicals, materialsthe, computer program elements lined out above and vice versa. Advantageously, the benefits provided by any of the embodiments and examples equally apply to all other embodiments and examples and vice versa.

[0341] All terms and definitions used herein are understood broadly and have their general meaning

Claims

23122868Claims:1 . A method for generating a digital asset associated with at least one supply chain product, wherein the digital asset is configured to exchange product data associated with the at least one supply chain product, the method comprising: providing at least one user and / or system interaction relating to a request for providing the digital asset by generating the digital asset and / or by accessing the generated digital asset, generating at least one selection instruction for selecting at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product based on accessing a configuration data base and at least in part based on the at least one user and / or system interaction, wherein the configuration data base provides access to configuration data including at least decentral network protocols and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol, selecting at least one decentral network protocol and / or at least one data model based on the at least one selection instruction, generating the digital asset based on the selected at least one decentral network protocol and / or at least one data model, wherein generating the digital asset includes generating at least one product data set according to the selected at least one data model by generating at least one selection instruction for selecting at least one product data point from a product data base based on the selected at least one data model and / or at least in part based on the at least one user and / or system interaction, wherein the product data base provides product data associated with the at least one supply chain product, generating the digital asset by providing one or more decentral identifier(s) uniquely associated with the supply chain product based on the selected decentral network protocol and by providing a locator to the generated product data set, providing the digital asset for access by one or more data consuming node(s) according to the selected at least one decentral network protocol.

2. The method of claim 1 , wherein the user and / or system interaction relates to at least one decentral network protocol for exchanging product data associated with the supply chain product, at least one data model related to product data associated with the supply chain product and / or a product data set to be generated according to the provided or selected at least one data model.

3. The method of any of the preceding claims, wherein the user and / or system interaction relates to a request for providing the digital asset by generating the digital asset and / or by accessing the generated digital asset by one or more participant(s) of one or more decentral network(s) and / or for one or more supply chain product(s).231228694. The method of any of the preceding claims, wherein the selection instruction includes at least one instruction configured to search the product data base and / or the configuration data base, at least one instruction configured to retrieve configuration data from the configuration data base and / or product data from the product data base, at least one instruction configured to interact with a template data base storing template instructions for interaction with a Large Language Model (LLM), at least one instruction configured to interact with the Large Language Model (LLM), at least one instruction configured to retrieve a selection from the Large Language Model (LLM) or any combinations or subsets thereof.

5. The method of any of the preceding claims, wherein the selection instruction includes multiple sub-instructions to be executed for one or more stages, wherein the one or more stages include a retrieval stage, a semantic search stage and / or a LLM retrieval stage, wherein the multiple stages are staggered, wherein depending on successful or failed selection per stage the retrieval stage may be followed by the semantic search stage and / or the LLM retrieval stage.

6. The method of any of the preceding claims, wherein the configuration data base stores configuration data in key value pairs including decentral network protocols and per decentral network protocol one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol, wherein the at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product are selected based on the key-value pairs.

7. The method of any of the preceding claims, wherein the configuration data base stores configuration data including descriptions in natural language of configuration data points stored as configuration data, wherein the at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product are selected based on the descriptions in natural language of configuration data points stored as configuration data.

8. The method of any of the preceding claims, wherein the product data base stores product data in key value pairs including property data related to properties associated with the supply chain product and to be exchanged by the decentral network protocol, wherein the at least one at least one product data set according to the selected at least one data model is selected based on the key-value pairs.

9. The method of any of the preceding claims, wherein product data base stores product data including descriptions in natural language of product data points stored as product data, wherein the at least one at least one product data set according to the selected at least one data model is selected based may be selected based on the descriptions in natural language of product data points stored as product data.2312287010. The method of any of the preceding claims, wherein the configuration database is populated and / or updated based on web data related to the one or more decentral networks, wherein web data is retrieved by a web interface configured to access web repositories and / or scrape webpages, wherein web data is mapped to configuration data for populating and / or updating the configuration data base.11 . The method of any of the preceding claims, wherein the product database is related to the decentral network node associated with a decentral network participant producing the at least one supply chain product, wherein the product database is directly or indirectly communicatively connected to a target data base for storing generated digital assets, wherein the target data base for storing generated digital assets is directly or indirectly communicatively connected to the decentral network node associated with a decentral network participant producing the at least one supply chain product.

12. The method of any of the preceding claims, wherein the configuration database is related to at least one operating system orchestrating decentral network data exchange in multiple decentral networks and / or digital asset generation for orchestrating decentral network data exchange in multiple decentral networks and / or the configuration database is related to the decentral network node associated with a decentral network participant producing the at least one supply chain product.

13. An apparatus for generating a digital asset associated with at least one supply chain product, wherein the digital asset is configured to exchange product data associated with the at least one supply chain product, the method comprising: an input interface configured to provide at least one user and / or system interaction relating to a request to provide the digital asset by generating the digital asset and / or by accessing the generated digital asset, a selection component configured to generate at least one selection instruction for selecting at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product based on accessing a configuration data base and at least in part based on the at least one user and / or system interaction, wherein the selection component is configured to select at least one decentral network protocol and / or at least one data model based on the at least one selection instruction, a configuration data base configured to provide access to configuration data including at least decentral network protocols and / or respective one or more data model(s) related to product data associated with the supply chain product to be exchanged by the decentral network protocol, an asset generation component configured to generate the digital asset based on the selected at least one decentral network protocol and / or at least one data model, wherein asset generation component is configured to execute the steps of generating at least one product data set according to the selected at least one data model by generating at least one selection instruction for selecting at least one product data point from a23122871 product data base based on the selected at least one data model and / or at least in part based on the at least one user and / or system interaction, wherein the product data base provides product data associated with the at least one supply chain product, generating the digital asset by providing one or more decentral identifier(s) uniquely associated with the supply chain product based on the selected decentral network protocol and by providing a locator to the generated product data set, an output interface configured to provide the digital asset for access by one or more data consuming node(s) according to the selected at least one decentral network protocol.

14. Use of the configuration data base storing configuration data including at least one decentral network protocol for exchanging product data associated with the supply chain product and / or at least one data model related to product data associated with the supply chain product and / or the product data base storing product data associated with the at least one supply chain product for generating a digital asset associated with at least one supply chain product according to the methods of claims 1 to 12 or by the apparatus of claim 13.

15. Use of the digital asset associated with at least one supply chain product generated according to the methods of claims 1 to 12 or by the apparatus of claim 13 for providing the product data set generated according to the selected or provided at least one data model for access by a peer-to-peer communication according to the selected or provided at least one decentral network protocol for exchanging product data associated with the supply chain product and / or use of the digital asset associated with at least one supply chain product generated according to the methods of claims 1 to 12 or by the apparatus of claim 13 for accessing the product data set generated according to the selected or provided at least one data model by a peer-to-peer communication according to the selected or provided at least one decentral network protocol for exchanging product data associated with the supply chain product.

Images