A system and method for verifying data associated with supplied input materials.

Abstract

Disclosed are methods and apparatus, as well as related computer elements, for verifying input material data collected via a distributed network and associated with one or more input materials entering production, thereby avoiding the storage of defective data and ensuring the generation of reliable data when using the input material data in all data processing operations. Further disclosures are made regarding the use of the verified input material data to control the production of further products.

Description

Technical Field

[0002] , , , , , , , , , , ,

[0003] , , , , ,

[0004]

[0001] Technical Field A method, apparatus, and related computer elements are disclosed for verifying input material data associated with one or more input materials collected via a distributed network and entering production, avoiding storage of defective data, and ensuring generation of reliable data when using the input material data in all data processing operations. Further disclosure is made of the use of verified input material data for controlling the production of further products.

Background Art

[0002] Background Art In the production, reuse, repair, refurbishment, remanufacture, recycling and / or recovery of products, it is necessary to meet a plurality of different regulatory requirements depending on the product and the recycling chain. For example, product producers must provide product data to customers and recyclers to meet regulatory requirements. Such product data can be exchanged electronically and used to control the production of further products at the production site of product consumers to improve production efficiency, or to identify compounds present in end-of-life products to improve recycling efficiency. In order to enable such improved production and recycling efficiency, it must be ensured that the exchanged product data is not incorrect.

[0003] Therefore, it is necessary to avoid the storage and transfer of incorrect product data within the product ecosystem.

Summary of the Invention

Means for Solving the Problems

[0004] Summary In one aspect, the present disclosure relates to a computer-implemented method for verifying input material data associated with one or more input materials entering production, where production produces one or more products from one or more input materials, and the method comprises (a) Provide one or more distributed input material identifiers associated with one or more input materials, (b) Collect input material data associated with the provided distributed input material identifier via a distributed network from the distributed data provider network node associated with the input material data. (c) Validate at least a portion of the collected input data by using a rule-based engine that includes a validity threshold, or by using a data-driven model trained on a historical dataset that includes input data and validity scores. (d) Provide verified input data to process the verified input data based on the verified input data. Includes.

[0005] In a further embodiment, the Disclosure relates to an apparatus for verifying input data associated with one or more input materials entering into production, wherein production produces one or more products from one or more input materials, and the apparatus (a) A distributed input identifier provider configured to provide one or more distributed input identifiers associated with one or more input materials, (b) A distributed data consumption network node associated with production, configured to collect input data associated with the provided distributed input data identifier from the distributed data provision network node associated with each input data, (c) A rule-based engine or data-driven model trained on a historical dataset including validity thresholds or input material data and validity scores, configured to validate at least a portion of the collected input material data and to provide validated input material data based on the validated input material data, (d) Optionally, a data processor configured to process the provided verified input material data. Includes.

[0006] In a further aspect, this disclosure relates to the use of input material data verified by a computer implementation or apparatus disclosed herein to control the production of a product at least partially produced from the input material associated with the verified input material data.

[0007] In a further embodiment, the Disclosure relates to a computer element, such as a computer-readable storage medium containing instructions, a computer program, or a computer program product, which, when executed by a computing node or computing system, contains instructions that instruct the computing node or computing system to perform steps of a computer implementation method disclosed herein.

[0008] In a further aspect, the Disclosure relates to a computer element, such as a computer-readable storage medium, a computer program, or a computer program product, which, when executed by an apparatus or system disclosed herein, includes instructions that instruct the apparatus or system to perform steps configured to be performed by the apparatus or system disclosed herein.

[0009] Any disclosures, embodiments, and examples described herein relate to the methods, apparatus, systems, uses, and computer elements described above and below. Advantageously, any benefits derived from any one embodiment and example also apply to all other embodiments and examples.

[0010] Embodiment To avoid the erroneous storage and use of input material data collected from input material data owners via a decentralized network, a method and system are proposed for verifying collected input material data associated with supplied input materials before storing or further processing the collected input material data. By using a decentralized input material identifier associated with the input material data and controlling access to such input material data via decentralized data provision network nodes associated with the input material data owner, input material data can be securely and efficiently exchanged via a decentralized network under the control of each input material data owner. Thus, input material data owners can control access to said input material data via multiple decentralized data consumption services associated with input material consumers. This enables simplified and customizable data sharing or exchange from input material suppliers to product producers who use input materials to produce products. In this way, more reliable and efficient further processing of input materials supplied by upstream stakeholders in the supply chain can be achieved while keeping the data within the ownership of the chemical supplier supplying upstream stakeholders.

[0011] By using a rule-based engine or a trained data-driven model, the validity of individual data points, combinations of data points, or entire input material datasets can be validated. This makes it possible to determine whether the collected input material data contains incorrect data points and / or incorrect data types and / or combinations of data points and / or all the data required from a regulatory standpoint. Incorrect data points, data types and / or data combinations may include data points, data types and / or data combinations that are not valid for each input material. Validation of an input material dataset or a portion thereof can further enable validation of the input materials themselves. For example, the results of validation checks can be used to determine whether data included in the input material set that has not been validated using a rule-based engine or a trained data-driven model is invalid. For example, an invalid data point may lead to the determination that the input material cannot have the origin data included in the input material dataset. Rule-based engines can operate at the data point level, multiple data point levels, or the entire dataset level, and can use validity thresholds to determine whether individual data points, multiple data points, or the entire dataset are valid. The validity threshold may include rules defining the threshold for individual data points and / or rules defining acceptable combinations of data points and / or rules defining the content of the entire dataset. Rules defining the entire dataset may have associated locations to which each rule applies. By using rules associated with each location of production where input materials are used to produce a product, it becomes possible to ensure that all data required by applicable regulations at that location is included in the input material data.

[0012] By verifying collected input material data, high data quality can be ensured, and the absence of necessary input material data can be avoided. By verifying collected input material data, product production can be reliably controlled using such input material data, and production efficiency can be increased. By verifying collected input material data, it is ensured that no erroneous data is included in the digital twin of products in the product ecosystem, and therefore the use of erroneous data that could lead to decisions in inefficient production or recycling processes is avoided. Thus, by verifying collected input material data, high data quality of the digital twin used in the product ecosystem is ensured, and it is ensured that no erroneous data is entered into systems that manage product production or the recycling of used products. By verifying collected input material data, it is possible to ensure compliance with regulatory requirements that govern the necessary data provided when products are supplied to consumers and / or when input materials enter the system boundary of production by using those input materials to produce products.

[0013] The following outlines several embodiments of this disclosure as examples. It should be understood that this disclosure is not limited to the above embodiments and / or examples.

[0014] Input materials may include any non-individual materials, which may be continuous volumes of solid or liquid materials, or any individual materials, which may be components, parts, or component assemblies. Input materials may include starting materials used in any process carried out in production to produce a product. Input materials may be unused materials, which may not have experienced previous production and use cycles, in particular unused input materials. Input materials may be recycled materials that have undergone at least one recycling step. Input materials may include or may be any input materials that enter production and are provided at any entry point of production. Input materials may be any materials that enter the system boundary of production. Input materials may be used as raw materials to produce one or more products. Products may be produced through one or more intermediate products. Thus, input materials may be used directly or indirectly to produce one or more products.

[0015] Products may be non-individual products. Products may be chemical products. Products may be individual products. Products may be components or parts, component assemblies, or final products.

[0016] Production can be any production that produces a product. Production can consist of one or more production chains. A production chain can consist of one or more production steps. A production step can be performed by a machine or apparatus or a set of machines or apparatus. Production can be any facility or plant that performs at least one reuse, repair, refurbishment, remanufacturing, recycling, or recovery operation. Input materials can be used at any point in the production chain. Input materials can be used at any point in the production steps.

[0017] A product can be a chemical product. In this case, the input materials can be chemical materials. Similarly, a product produced by chemical production can be a chemical product. A chemical product may contain or contain any material produced by chemical production using at least one input material. A chemical product may contain or contain any chemical product produced by chemical production and offered at any exit point of chemical production. A chemical product or output material can be produced from input materials by chemical production. A chemical product can be produced from input materials through one or more chemical and / or physical processes. Therefore, a chemical intermediate product produced from input materials can be used to produce a chemical product or output material. A chemical process may include a chemical reaction. A chemical reaction may include any chemical reaction well known in the art in which reactants are converted into one or more different chemical products. A chemical reaction may include the use of catalysts, enzymes, bacteria, etc., to achieve the chemical reaction between reactants. A physical process may include mixing, separation, and / or extrusion. The input materials may be selected from petrochemical raw materials such as naphtha crude oil and natural gas, or intermediates from raw materials that require a certain amount of naphtha, crude oil, and natural gas. The input materials may be selected from natural raw materials such as vegetable oils, biologics such as enzymes, and / or naturally occurring inorganic or organic chemicals, or intermediates from raw materials that require a certain amount of vegetable oils, biologics, and / or naturally occurring inorganic or organic chemicals.

[0018] Chemical production can be a chemical production network. A chemical production network may include multiple types of production processes for producing different chemical products from input materials. A chemical production network may include a complex production network that produces multiple chemical products in multiple production chains or value chains. A production chain or value chain may include one or more processes configured to produce one chemical product or class of chemical products from one or more input materials. A chemical production network may include connected, interconnected, and / or disconnected production chains. The production chains included in a chemical production network may be defined by the physical system boundaries of the chemical production network. System boundaries may be defined by the location or control of the production processes. System boundaries may be defined by the locations of the chemical production network. System boundaries may be defined by production processes jointly controlled by one or more entities. System boundaries may be defined by value chains with time-staggered production processes to the final product, which may be controlled collectively or individually by multiple entities. A chemical production network may include steps such as waste collection and sorting, recycling steps such as pyrolysis, decomposition steps such as steam decomposition, production steps to produce chemical products or intermediates from provided inbound materials, separation steps to separate multiple intermediates from one process step, and further processing steps to convert such products into chemical products that exit the system boundary of the chemical production network. A chemical production network can produce multiple intermediates from input materials and one or more chemical products from intermediates. Input materials may enter the chemical production network at an inlet point. Chemical products may exit the production network at an outlet point (or discharge point).

[0019] A chemical production network may include one or more entry points where input materials are supplied to the chemical production network. These input materials may include raw materials or chemical intermediate products. The input materials may be supplied to a plant that performs the first production step in the production chain associated with a chemical product.

[0020] A distributed input material identifier may include any unique identifier uniquely associated with input material data, and optionally, the data owner of the input material data. A distributed input material identifier may link the physical entity of the input material to the input material data. A distributed input material identifier may include one or more universally unique identifiers (UUIDs) and / or one or more distributed identifiers (DIDs). One or more DIDs and / or UUIDs may be further associated with the input material. A distributed input material identifier may further include or be associated with input material identifiers associated with the input material. A distributed input material identifier may be issued by a central or distributed identity information issuer. A distributed input material identifier may be generated by or on behalf of the data owner of the input material data. A distributed input material identifier may include authentication information. Access to the input material data may be controlled by the data owner of the input material data through the distributed input material identifier and its unique association with the input material data associated with the input material and optionally, the data owner of the input material data. The data owner of the input material data may be the input material producer. This is in contrast to a centralized authority system, in which identifiers are provided by such centralized authority, and access to data is controlled by such centralized authority. In this context, decentralized refers to the use of decentralized input material identifiers in implementation, which are controlled by the data owner of the input material data. Decentralized input material identifiers can be digital or virtual identifiers and do not necessarily correspond to physical identifiers, for example, physically attached to the input material.

[0021] A decentralized input material identifier can include or be associated with one or more identifiers used in a decentralized network and enabling data exchange via the decentralized network. For example, the decentralized input material identifier can include or be associated with an identifier of a data set included in the input material data. The data exchange can include discovery of the decentralized identifier and optionally an identifier associated with the decentralized identifier of a participant node of the decentralized network, authentication of a participant node of the decentralized network, and / or authorization of data transfer via peer-to-peer communication between participant nodes of the decentralized network.

[0022] The decentralized input material identifier can be associated with one or more decentralized identifiers associated with materials used to produce the input material. Thereby, it becomes possible to determine the materials used to produce the input material based on the decentralized input material identifier.

[0023] The collected input material data may be part of a digital twin of the input material. A digital twin of an input material may be a digital representation of the physical entity of the input material, having a defined semantic description of the physical entity of the input material. Therefore, a digital twin of the physical entity of an input material is a digital version of the physical entity. Once created, a digital twin can be used to represent the physical entity of a product in a digital representation of a real-world system. A digital twin may be uniquely linked to the physical input material, at least via a distributed input material identifier. A digital twin may be created to be identical to the form and behavior of the corresponding input material. In addition, a digital twin may reflect the lifetime characteristics of the input material and / or events occurring with respect to the input material during its lifetime. For example, a sensor may capture real-time (or near-real-time) data, such as transport data or usage data, and / or event-driven data, such as data captured in response to a predetermined event of the physical input material, such as an accident, and relay the physical input material back to its remote digital twin. The digital twin may then be updated to maintain correspondence with the physical entity of the input material. Therefore, a digital twin may represent the current state of the physical entity of the input material at any time. A digital twin may include a distributed input material identifier. The distributed input material identifier may be associated with the physical entity of the input material to which the digital twin is linked. The distributed input material identifier may be associated with the physical entity of the input material from which the digital twin was generated. The distributed input material identifier may be associated with the distributed identifier of the material used to produce the input material. The distributed input material identifier may be associated with products, components, component assemblies, and / or final products produced using the input material (for example, an input material associated with a distributed input material identifier may be used in at least one production step of the production of a product, component, component assembly, and / or final product). This makes it possible to track input materials and their use within the product ecosystem.The distributed input material identifier can be or can be assigned to a physical identifier connected to the input material. The physical identifier can be any identifier of the produced input material, such as a batch number or a part number. The physical identifier can include, but is not limited to, passive or active elements, such as barcodes, QR codes (registered trademarks), RFID tags. The physical identifier can include a marker embedded in the input material or a similar physical arrangement that enables the digital identification of the input material. The digital twin can further include the input material identifier. The digital twin can include one or more data sets (e.g., digital twin data sets). Thus, the data set can represent a part of the digital twin.

[0024] The digital twin can be stored in dedicated storage associated with the data owner of the digital twin. Access to the dedicated storage can be controlled by the input material data or the data owner of the digital twin. Access to the dedicated storage, and thus access to the input material data or digital twin stored therein, can be controlled by the data owner via distributed data providing network nodes associated with the dedicated storage. The data owner can be the input material producer. The digital twin or input material data can be stored in dedicated storage for access by consumers of the input material, such as producers who use the input material to produce products.

[0025] The input material data can be associated with one or more representations for accessing the input material data or a part thereof. The representation can include a locator that refers to a distributed data providing network node associated with the dedicated storage storing each input material or a part thereof. The representation can be used by a distributed data consuming network node to request access to the input material data associated with such a representation.

[0026] The collected input material data may correspond to one or more datasets included in the digital twin. A dataset may be associated with or include a dataset identifier that uniquely identifies each dataset within the digital twin. The dataset identifier may be associated with a distributed input material identifier. This makes it possible to use the distributed input material identifier in combination with the dataset identifier to uniquely identify a given dataset. The datasets may contain different types of input material data. For example, the first dataset may contain production data, the second dataset may contain emissions data, the third dataset may contain composition data, and the fourth dataset may contain material safety data and technical data, etc.

[0027] A digital twin can be generated by a distributed participant node. A distributed participant node can communicate with a distributed data-providing network node that provides input material data. A distributed participant node can be associated with a distributed data-providing network node that provides input material data. A digital twin can be generated by the data owner of the input material data. The data owner of the input material data may be a production that produces the input material. The data owner of the input material data may be a legal entity that operates the production that produces the input material. The data owner of the input material data may be a natural person that operates the production that produces the input material. A digital twin can be generated on behalf of the data owner of the input material data. For example, a digital twin can be generated by a third party based on services provided to the data owner by the third party.

[0028] Collection may include receiving or retrieving data such as input material data. Producers who operate production facilities that produce products and input suppliers that supply input materials may be part of a product ecosystem. A product ecosystem may include different stages, including manufacturing, use, and reuse. In these stages, one or more ecosystem stakeholders may contribute to the manufacturing, use, or reuse of a product. For example, the manufacturing stage may include raw material manufacturers, intermediate material manufacturers, and / or final product manufacturers. Furthermore, for example, the use stage may include product users, product maintenance providers, and / or product distributors. Furthermore, for example, the reuse stage may include collectors, sorters, dismantlerers, recyclers, restorers, and / or refurbishers.

[0029] Participants in a product ecosystem may be connected via a decentralized network. The decentralized network may include computing nodes associated with the product ecosystem participants and may be configured to perform data transactions. Computing nodes associated with product ecosystem participants may be associated with producers, users, or reusers of physical products, such as chemical intermediate product producers, chemical product producers, intermediate product producers, final product producers, final product users, used product users, or product reusers. Data transactions may be based on transaction protocols that include authentication and / or authorization mechanisms. Peer-to-peer communication between computing nodes associated with product ecosystem participants may be established based on the authentication and / or authorization mechanisms. Each node in the decentralized network associated with a product ecosystem participant may be configured as a decentralized data consumption network node and / or a decentralized data provision network node.

[0030] One or more authentication mechanisms may be associated with or linked to a distributed identifier associated with the physical entity of each raw material, chemical product, intermediate product, finished product, or end-of-life product. The distributed identifier can uniquely identify each physical entity within the distributed network. The distributed identifier can link the physical entity of each raw material, chemical product, intermediate product, finished product, or end-of-life product data to the respective raw material data, chemical product data, intermediate product data, finished product data, and end-of-life product data. The distributed identifier may include one or more universally unique identifiers (UUIDs) and / or one or more distributed identifiers (DIDs). One or more authentication mechanisms associated with a distributed identifier may be provided to participant nodes. One or more authentication mechanisms associated with a distributed identifier may be accessible by data-providing network nodes and / or distributed data-consuming network nodes. The distributed configuration enables more efficient use of computing resources and enhances control by data owners in the distributed network.

[0031] One or more authorization mechanisms may include at least one authorization rule to control access to data under the control of the data owner. Computing nodes associated with stakeholders in the product ecosystem may be configured to provide data consumption network nodes and / or distributed data serving network nodes. Distributed data serving network nodes may be configured to serve or transmit data to other stakeholders nodes in the distributed network. Distributed data consumption network nodes may be configured to ingest or receive data from other stakeholders nodes in the distributed network. Providing data to a distributed data serving network node for access by a distributed data consumption network node may include indirect or direct access to the data by the distributed data consumption network node.

[0032] A distributed data serving network node may include computer executable instructions for serving and / or processing data within the distributed network, such as input material data, as requested by a distributed data consuming network node. A distributed data serving network node may be associated with or connected to one or more dedicated data storages that store input material data. A distributed data serving network node may be directly or indirectly connected to the data storages that store input material data. Thus, a distributed data serving network node may be associated with input material data. The dedicated data storage may be under the control of the data owner of the input material data. The data owner may have access to the dedicated data storage. In this way, the data owner of the input material data may control access to the input material data from various distributed data consuming network nodes.

[0033] In one embodiment, a distributed data consumption network node may include computer executable instructions for accessing and / or processing data within the distributed network, such as input material data, provided by a distributed data provision network node. The distributed data consumption network node may be controlled, owned, or associated with a consumer of input material data (e.g., a product producer). The consumer may be any entity that processes input material data. The consumer may be any entity that operates a production configured to process input materials. Processing may include producing a product using the input materials. Processing may include performing one or more recycling steps on the input materials. The consumer may be an upstream participant of an input material supplier in a product ecosystem to which the produced product is associated, e.g., in which the product is used.

[0034] A rule-based engine can be used to validate at least a portion of the collected input material data. A rule-based engine may be software or a software component that applies one or more rules to at least a portion of the collected input material data. A rule-based engine used to validate at least a portion of the collected input material data may include validity thresholds. Validity thresholds may be associated with individual data points, multiple data points, and / or entire datasets (e.g., complete data contained in collected input material data associated with a defined input material). A validity threshold associated with an individual data point may include one or more rules defining thresholds, such as minimum and / or maximum values, for the individual data point present with the collected input material data. Individual data points may correspond to values ​​associated with the chemical and / or physical properties of the input material. Individual data points may correspond to values ​​in key-value pairs that define the chemical and / or physical properties of the input material. The use of such validity thresholds makes it possible to identify invalid data points and thus avoid the storage and processing of invalid input material data points, which can result in inaccurate data, such as control data for controlling the production of products using the input material, when processing such input material data containing invalid data points.

[0035] A validity threshold associated with multiple data points may include one or more rules defining acceptable combinations of data points, and optionally, thresholds for the data points included in such combinations. The thresholds may define the minimum and / or maximum values ​​of data points present with a combination of data points. By using such validity thresholds, it becomes possible to identify invalid data point combinations and optionally invalid data points, thus avoiding the storage and processing of invalid input material data combinations that may result in inaccurate data, such as control data for controlling the production of products using the input materials, when processing such input material data containing invalid data combinations.

[0036] A validity threshold associated with the entire dataset may include one or more rules that define the data contained within the collected input data (e.g., collected input data associated with a specific input). The rules may further define one or more locations associated with the data contained within the collected input. This allows for the definition of data contained within the collected input, taking into account different regulations associated with different locations. Using such a validity threshold ensures the integrity of the collected input data and thus ensures compliance with regulatory requirements.

[0037] The rule-based engine may be further configured to compare data points, data types, and / or data combinations contained in multiple input material datasets associated with each input material. The comparison may be performed over a defined time span, which may be a predetermined time span. This may make it possible to detect deviations in data points and / or data types and / or data combinations. Such deviations may indicate that the production conditions of the input material may have changed without including any indication in the associated input material dataset. The determined deviations may be provided by the rule-based engine. The determined deviations may, for example, trigger a warning message if a persistent downward or upward trend in data points is determined.

[0038] A trained data-driven model can be trained on a historical dataset containing input data and one or more validity scores. The input data may include multiple input data points, such as individual input data points or combinations of input data points with the entire input dataset. A validity score can indicate the validity of each individual data point, combination of data points, or the entire dataset. For example, a validity score of 1 indicates that a data point, combination of data points, or the entire dataset is not valid, while a validity score of 5 indicates that a data point, combination of data points, or the entire dataset is valid. Scores between 1 and 5 can be used to indicate a finer degree of validity. Therefore, a validity score can be considered the likelihood of whether a data point, combination of data points, or entire set is considered valid.

[0039] A trained data-driven model can be a trained machine learning algorithm. Machine learning can refer to computer algorithms that improve through experience, and are built upon models based on sample data, often described as training data, using supervised, unsupervised, or semi-supervised machine learning techniques. Supervised learning may involve using training data with known labels or outcomes and preparing the model through a training process where it needs to make predictions, and the model is modified if those predictions are wrong. The training process may continue until the model achieves a desired level of accuracy on the training data. Semi-supervised learning may involve using a mixture of labeled and unlabeled input data and preparing the model through a training process where the model learns structure to organize the data and make predictions. Unsupervised learning may involve using unlabeled input data with no known outcomes and preparing the model by inferring structures such as general rules and similarities present in the input data.

[0040] A data-driven model can be trained by selecting inputs and outputs to define the internal structure of a machine learning algorithm, training the machine learning algorithm by applying a set of input and output data samples, validating the accuracy of the machine learning algorithm by applying material input data samples of known validity and comparing the produced output values ​​with expected output values, and modifying the parameters of the machine learning algorithm using an optimization algorithm if the received output values ​​do not correspond to the known validity. Inputs may include input material data points and / or combinations of input material data points, and / or entire input material datasets, each labeled with a validity score. Thus, each input material data, each combination of input material data points, and / or each entire input material dataset may be labeled with an appropriate validity score indicating the degree of validity (e.g., valid or invalid) associated with each data point, combination of data points, and / or entire dataset. Input data may be randomly selected, provided that the training data includes a full range of validity scores.

[0041] In one embodiment, the input material data includes one or more input material datasets. The input material dataset may include a dataset identifier, a distributed input material identifier, and a portion of the input material data.

[0042] In one embodiment, input material data includes at least one measured physical and / or chemical property of the input material and / or at least one physical and / or chemical property determined from collected data associated with the production and / or use of the input material. Chemical properties may be properties of the input material that become apparent during or after a chemical reaction. Therefore, chemical properties may be any quality that can only be established by altering the chemical identity of the input material. Examples of chemical properties include heat of combustion, enthalpy of formation, toxicity, chemical stability in a given environment, flammability, oxidation state, corrosiveness, combustibility, acidity and basicity, chemical composition, recyclate content used to produce or manufacture the input material, biobase content used to produce or manufacture the input material, renewable material content used to produce or manufacture the input material, and / or pH value. Properties may be any measurable properties. Therefore, the values ​​of physical properties describe the state of the input material. Examples of physical properties include absorption, brittleness, boiling point, capacitance, color, concentration, density, ductility, distribution, effectiveness, elasticity, charge, conductivity, electrical impedance, potential, flow rate, fluidity, hardness, heat capacity, inductance, intrinsic impedance, brightness, luminescence, gloss, mass, melting point, opacity, transmittance, dielectric constant, plasticity, pressure, radiance, resistivity, reflectivity, refractive index, solubility, specific heat, strength, stiffness, temperature, tension, thermal conductivity, thermal resistance, viscosity, volume, and wave impedance.

[0043] The measured at least one physical and / or chemical property may be acquired by a sensor configured to measure physical and / or chemical properties. The sensor may be included in a measuring device. The sensor may correspond to a measuring device. For example, the physical and / or chemical properties may include properties provided by a sensor in a mobile device such as a camera or by a measuring device configured to measure at least one physical and / or chemical property.

[0044] Data associated with the production of input materials may be collected before, during, and / or after the production of the input materials. The collected data may be used to determine at least one physical and / or chemical property of the produced input material. For example, input material discharge data may be determined based on data collected during the production of the input material. Data associated with the production of input materials may include production data from the production of the input material. Data associated with the production of input materials may include monitoring and / or control data associated with the production of the input material. Data associated with the use of input materials may be collected via at least one identifier associated with the input material. Data may be collected before, during, or after the use of the input material. The collected data may include at least one measured physical and / or chemical property of the used input material. The measured physical and / or chemical property may include the chemical and / or physical property described above. Data may be collected using appropriate sensors configured to measure chemical and / or physical properties. Sensor data may be correlated with identifiers associated with the product. Chemical and / or physical properties determined from sensor data may be correlated with identifiers associated with the product. The identifier may be an input material identifier. The identifier may be a distributed input material identifier. A distributed input material identifier may be linked to other distributed identifiers according to the physical relationship between the input material entity and other physical entities, such as products made using or from the input material. Linking a distributed digital twin identifier to other distributed product identifiers makes it possible to determine a distributed participant node that stores collected data associated with the use of the input material or determined physical and / or chemical properties. The collected data and / or determined chemical and / or physical properties may be provided by the distributed participant node and stored in the input material data. For example, a new dataset may be generated by applying a data model associated with the use of the input material to the collected data and / or determined properties, and the new dataset may be used to update the input material data.

[0045] In one embodiment, the input material data further includes data associated with the use of the input material, data associated with the production of the input material, one or more input material identifiers, input material name, chemical composition of the input material, input material emission data, input material recyclable content data, input material biobased content data, input material renewable content data, input material declaration data, input material safety data, certificate of analytical data associated with the input material, certificate data associated with the input material, or a combination thereof.

[0046] In one embodiment, the distributed input material identifier is provided by a sensor that reads an identifier element physically attached to the input material. The identifier element may be present on the packaging unit of each input material. The identifier element may be present on the input material. The identifier element may uniquely identify each input material. The identifier element may include any physical arrangement that associates the distributed input material identifier with each input material. The identifier element may include a marker embedded in the input material, a barcode, a QR code, a tag such as an RFID tag, or a similar physical configuration that enables digital identification of the input material. The identifier element may be a physical identifier physically attached to the input material, such as a packaging unit containing the input material. The packaging unit may be any housing suitable for storing the input material. The packaging unit may depend on the type of input material and the amount of input material produced or the intended use of the input material during production. Suitable packaging units for liquid input materials may include containers, bottles, tanks, etc. Suitable packaging units for solid input materials may include tanks, bags, bottles, containers, etc. The size of the packaging unit may depend on its intended use during production and the type of input material contained within the packaging unit.

[0047] In one embodiment, input material data is stored in dedicated storage associated with each distributed data-providing network node, and access to the input material data stored in the dedicated storage is controlled by the data owner of the input material data via the distributed data-providing network node. The dedicated storage may be associated with the data owner of the input material data. The dedicated storage may be the data owner's dedicated storage. The dedicated storage may be associated with production. The dedicated storage may be associated with a distributed data-providing network node. Therefore, the input material data may be accessible to the data owner. The data owner may be the owner of the input material data or the input material data owner. The data owner may be the owner of the input material associated with the input material data. The dedicated storage may be accessible by the data owner and the distributed data-providing network node. The data owner may be an entity that operates a production that produces the input material. The data owner may control access to the dedicated storage that stores the input material data. Access to the dedicated storage may be controlled by the data owner using the distributed data-providing network node associated with the dedicated storage.

[0048] In one embodiment, collecting input material data further includes determining a distributed identifier associated with the materials used to produce the input material, based on a provided distributed input material identifier, and collecting the material data from a distributed data-providing network node associated with the material data using at least a portion of the determined distributed identifiers. Each of the distributed data-providing network nodes may be associated with the data owner of the respective material data. The material data owner may be the producer of the material. The material data owner may be the owner of the material associated with the material data. The distributed data-providing network node may be associated with a participant in the product ecosystem. For example, the distributed data-providing network node may be associated with a provider of raw materials or intermediate products used to produce the input material, and the input material is used to produce the product. Identification-based access using distributed material identifiers may allow material data to be provided under the control of the data owner of the respective material data. In such embodiments, material data may be provided by a storage environment associated with the distributed data-providing network node, as described above. The use of the distributed data-providing network node allows the owner of the material data to control the use of the material data. In addition, it can enable secure data sharing or exchange across recycling or production chain participants.

[0049] The materials used to produce the input materials may include any materials used during the production of the input materials. This may include raw materials, chemical products, components, and component assemblies.

[0050] Material data may be collected by distributed network nodes. Distributed network nodes may be operational nodes of a distributed network. Distributed network nodes may be part of the infrastructure of a distributed network. Distributed network nodes do not necessarily have to be associated with stakeholders in the product ecosystem.

[0051] A distributed identifier can be determined by a distributed network node. The distributed identifier can also be determined by a further distributed network node communicating with a distributed network node that collects material data. For example, a further distributed network node may determine a distributed identifier and provide the determined distributed identifier to another distributed network node. The distributed network node may then collect material data based on the provided distributed identifier.

[0052] A distributed identifier is determined using a relational expression that specifies the relationship between an input material and the materials used to produce that input material. The relational expression can be directly or indirectly associated with the distributed input material identifier. This makes it possible to determine each relational expression using the distributed input material identifier. The relational expression may specify that a material can be used to produce an input material and / or that the input material is produced using a material. The relational expression can be associated with the relationship between an input material and each material used to produce it, for example, using the distributed input material identifier and material identifiers associated with all materials used to produce the input material. Thus, such a relational expression may also specify the raw materials, intermediate products, and components used in the production of the input material. The relational expression can be associated with the relationship between the input material and the output material of a single production step in an input material production chain. An input material production chain may include one or more production steps. An input material production chain may cover all production steps necessary to produce the input material. Relational expressions associated with a single production step may be linked to each other to reflect the entire input material production chain. Linking can be performed using distributed identifiers associated with input materials used in a production step and distributed identifiers associated with output materials resulting from that production step. Since the input materials of one production step correspond to the output materials of the previous production step, the relational representation of the previous production step is linked to the relational representation of the subsequent production step via their respective distributed material identifiers. Links in such relational representations can be used to obtain a bill of materials tree structure for input materials or parts thereof by recursively determining the links contained in such relational representations. Links in such relational representations can be used to recursively collect data associated with production inputs used to produce input materials or parts thereof at each production stage by recursively determining the links contained in such relational representations and collecting the respective data based on the distributed identifiers contained in the relational representations.

[0053] A relational representation can be accessed based on the data associated with the relational representation. The data associated with a relational representation can be stored in a distributed registry accessible by a distributed network node that determines a distributed material identifier. The distributed network node can use the distributed input material identifier to access the distributed registry and determine the data associated with the relational representation associated with the distributed input material identifier. The data associated with a relational representation may include a distributed relational representation identifier and a relational representation that points to each digital relationship. A digital representation pointing to a relational representation may include at least one interface to a distributed data consumption network node associated with the relational representation. It may further include at least one interface to a distributed data consumption network node associated with the digital relationship. It may include an endpoint for data exchange or sharing (resource endpoint) or an endpoint for service interaction (service endpoint) that is uniquely identified via a communication protocol. A digital representation pointing to a relational representation can therefore be uniquely associated with a distributed relational representation identifier and a distributed input material identifier. A relational representation pointing to a digital relationship can be considered a locator that points to the location or dedicated data storage where each digital relationship is stored.

[0054] The distributed network node may be configured to determine the data associated with each relational expression based on a distributed input identifier. For example, the distributed network node may be configured to retrieve data associated with a relational expression from a distributed registry that stores the data associated with the relational expression associated with the distributed input identifier, based on the distributed input identifier. The distributed network node may be configured to access the relational expression from the distributed data-providing network node associated with the relational expression. The distributed data-providing network node associated with the relational expression may be associated with the producer of the input material. The relational expression may be stored in a storage environment associated with the distributed data-providing network node. The relational expression may be part of the input material data associated with the distributed input identifier, and may be stored in a storage environment associated with the distributed data-providing network node. The distributed data-providing network node may be associated with the data owner of the input material data. The distributed network node may be configured to determine the distributed identifiers included in the accessed relational expression. If relational representations are linked, a distributed network node may be configured to determine at least some of the materials used to produce the input materials by recursively determining the data associated with the linked relational representations, access each relational representation using the determined data, and retrieve a distributed identifier associated with the materials used to produce the input materials based on the accessed relational representation.

[0055] In one embodiment, the rule-based engine operates on individual data points present in at least a portion of the collected input material data, on a group of data points present in at least a portion of the collected input material data, and / or on the entire collected input material data. The rule-based engine may be configured to determine the validity of individual data points, combinations of data points, and / or entire datasets. The rule-based engine may operate on individual data points, combinations of data points, and / or entire datasets using validity thresholds, as described above. For example, the rule-based engine may apply a validity threshold to individual data points, a group of data points, and / or the entire dataset to determine the validity of individual data points, a group of data points, and / or the entire dataset. If the rule-based engine determines that individual data points, a group of data points, and / or the entire dataset are valid, then the individual data points, a group of data points, and / or the entire dataset may be considered validated.

[0056] In one embodiment, the trained data-driven model is a classifier model. The classifier model can classify input data (e.g., at least a portion of the collected input data) into two classes, such as "valid" and "invalid". The classifier model can be selected from decision trees, Naive Bayes classifiers, K-nearest neighbors, support vector machines, and deep learning models. Deep learning can refer to methods based on artificial neural networks (ANNs) having an unlimited number of size-limited layers, which allow for practical applications and optimized implementations while maintaining theoretical universality under mild conditions. Deep learning architectures that implement deep learning algorithms may include deep neural networks, deep belief networks (DBNSs), recurrent neural networks (RNNs), convolutional neural networks (CNNs), and feedforward networks.

[0057] In one embodiment, providing verified input material data for processing includes storing at least a portion of the verified input material data in data storage. The data storage may be associated with production. The data storage may be associated with an entity operating production, such as a product manufacturer. The data storage may be associated with an operating system that controls and / or monitors production. The stored input material data may be used to generate control data for controlling the production of products using the input materials. The stored input material data may be used to generate a digital twin of a product produced using the input materials. Thus, the digital twin of a product may, for example, include a portion of the verified input material data.

[0058] In one embodiment, processing validated input material data includes performing one or more data processing operations on the validated input material data. Before performing such data processing operations, the operations can be validated, for example, to determine whether the operations are permitted to be performed on at least a portion of the validated input material data. Data processing operations may include data storage, generation of control data, etc. The data processing operations to be performed may be validated using a rule-based engine. The rule-based engine may be configured to determine a usage policy associated with the validated input material data. The rule-based engine may be configured to compare the usage conditions defined in the usage policy with the data processing operations to be performed to determine whether the intended data processing operations conform to the conditions defined in the usage policy.

[0059] A brief explanation of some of the figures in the drawing. The present disclosure will be further described below with reference to the attached drawings. The drawings and the same reference numerals in this disclosure are intended to refer to the same or similar elements, components and / or parts. [Brief explanation of the drawing]

[0060] [Figure 1]This document illustrates an exemplary embodiment of a decentralized network environment, including decentralized stakeholder network nodes associated with stakeholders in a product ecosystem involving various products. [Figure 2] This example shows a data structure for a digital twin of input materials that includes multiple digital twin datasets. [Figure 3] This schematic diagram illustrates how distributed data consumption network nodes associated with input material consumers provide access to input material data associated with those input materials via distributed data provision network nodes associated with data owners. [Figure 4] This shows an example of digital access elements, including DID owner data, DID document data, and a distributed identity infrastructure. [Figure 5] This example illustrates a production process that involves producing one or more products from one or more input materials, in relation to an operating system that includes an input material data verification system. [Figure 6] This example illustrates a production process that involves producing one or more products from one or more input materials, in relation to an operating system that includes an input material data verification system. [Figure 7A] The diagram shows an example of collecting input material data and using a rule-based engine to validate at least some of the collected input material data. [Figure 7B] The diagram shows an example of collecting input material data and using a trained data-driven model to validate at least some of the collected input material data. [Figure 8] This document provides an exemplary method for verifying input data associated with one or more input materials entering production. [Figure 9] This document provides an exemplary method for training a data-driven model to validate at least a portion of the collected input material data. [Modes for carrying out the invention]

[0061] Detailed explanation The following embodiments are merely examples of, and should not be considered as limiting, to the methods, systems, or application devices disclosed herein.

[0062] Figure 1 shows an exemplary embodiment of a distributed network environment. The distributed network environment may include a distributed participant network 134. The distributed participant network 134 may include one or more distributed network participants 102-112. Distributed network participants may be part of a product ecosystem that includes various products such as chemicals, components, parts assemblies, finished products and end-of-life products. The product ecosystem may include a production chain that produces the finished product. The product ecosystem may include a recycling chain for recycling at least a portion of the end-of-life products resulting from the use of the produced finished product. The product ecosystem may include input material suppliers 106, chemical product producers 102, chemical product consumers 108, OEMs 112, finished product users 114, EOL product collectors 116, and recyclers 118. The product ecosystem may enable the production of new finished products using materials obtained from the recycling of end-of-life products. The product ecosystem may be associated with the production of chemical products using one or more input materials and the use of the produced chemical products to produce further chemical products or distinct products.

[0063] Participants in the decentralized participant network 134 may be associated with the production of end products and / or the recycling of end products. Decentralized network participants 102-118 may refer to manufacturers of physical products such as chemical product producers 102, chemical product consumers 116, OEMs 112, end product users 114, EOL product collectors 108, and recyclers 118. Decentralized network participants may be associated with decentralized participant identifiers. Decentralized participant identifiers can uniquely identify decentralized network participants within the decentralized participant network 134.

[0064] Participants in the distributed participant network 134 may be connected via material flows 140. Material flows 140 may correspond to the flow of products from upstream participants in the distributed participant network 134 to their respective downstream participants. Material flows 140 may refer to continuous or discontinuous flows of products. Product flows may include any means of transport suitable for transporting products from upstream participants to their respective downstream participants. These means of transport may include pipes, containers, barrels, and packages. Material flows 140 may be associated with raw materials, chemical products, chemical intermediates, parts, part assemblies, finished products, used products, recycled materials, and the like.

[0065] The data flow 136 between distributed network participant nodes may be directly or indirectly associated with the material flow 140 between distributed network participants. For example, if input material data associated with the physical entities of input materials provided from input material supplier 106 to chemical product producer 102 is accessed by a distributed data consumption network node associated with the chemical product producer 102, the data flow 136 may be directly associated with the material flow 140. For example, if data associated with chemical products produced by chemical product producer 102 is accessed by a distributed data consumption network node associated with end product user 114 or recycler 118, the data flow 136 may be indirectly associated with the material flow 140.

[0066] At least some of the participants in the distributed participant network 134 may be associated with distributed participant network nodes 120, 122, 124, 126, 128, 130, and 132. Distributed participant nodes 120-132 may be under the control of each distributed participant associated with each distributed participant node. Distributed participant nodes 120-132 may form a distributed network 138. The distributed network 138 may be a peer-to-peer communication network. The distributed network 138 may be configured to execute data transactions 136. Data transactions 136 may be based on a transaction protocol that includes an authentication mechanism and / or an authorization mechanism. Based on the authentication and / or authorization mechanism, peer-to-peer communication may be established between distributed network nodes 120-132 associated with distributed network participants 102-118. One or more authentication mechanisms may be associated with or linked to a distributed identifier, as described in relation to Figure 3. One or more authentication mechanisms associated with a distributed identifier may be accessible by distributed data-providing network nodes and / or distributed data-consuming network nodes, as described in relation to Figure 3. The distributed configuration enables more efficient use of computing resources and enhances control by data owners of the distributed network.

[0067] Data transactions between participating nodes in a distributed network may be based on distributed identifiers associated with the data being accessed and / or distributed identifiers associated with the materials used to produce each input or output product. Distributed identifiers may be uniquely associated with the physical entity of the input material and associated input material data. Distributed identifiers may be uniquely associated with the physical entity of the output product and associated product data. Input materials may be any raw materials, chemical products, parts, parts assemblies, or used products. Output products may be any raw materials, chemical products, parts, parts assemblies, finished products, used products, or recycled materials. Distributed identifiers may uniquely identify each input or output product within the distributed network. Distributed identifiers may be associated with further distributed identifiers, such as distributed identifiers for the materials used to produce the input or output product. This may make it possible to track the materials used to produce the input or output product. Distributed identifiers may be included in digital access elements associated with input materials or output products, for example, as described with respect to Figures 3 and 4.

[0068] The distributed participant nodes 120-132 may be distributed computing nodes. A computing node may be any device or system that includes at least one physical, tangible processor and physical, tangible memory capable of having computer executable instructions executed by the processor. The memory may be in any form and depends on the nature and form of the computing node.

[0069] At least some of the distributed participant nodes 120-132 may be distributed data serving network nodes. At least some of the participant nodes 120-132 may be distributed data consumption network nodes. Participants in the distributed participant network 134 may be associated with distributed data serving network nodes and / or distributed data consumption network nodes, depending on whether data is provided to downstream participants and / or consumed by upstream participants. For example, input material supplier 106 may be associated with a distributed data serving network node configured to provide input material data associated with supplied input materials to a downstream participant (e.g., chemical product producer 102), as described, for example, in relation to Figure 3. In addition or alternatively, input material supplier 106 may be associated with a distributed data consumption network node configured to receive input material data associated with supplied input materials from an upstream participant (not shown) via a distributed data serving network node associated with the upstream participant.

[0070] The distributed network 138 may include further distributed network nodes. These further distributed network nodes may be distributed infrastructure service nodes (not shown in Figure 1). Distributed infrastructure service nodes may not be associated with any stakeholders in the product ecosystem. Distributed infrastructure service nodes may provide services to distributed stakeholder network nodes 120-132, such as verifying the identity of distributed stakeholder network nodes 120-132 before performing data exchange. Distributed network stakeholder nodes 120-132 may be associated with or include certificates, such as X.509 certificates. Certificates may be associated with distributed infrastructure service nodes that include, for example, certificate issuance services and / or dynamic provisioning services that provide dynamic attribute tokens (e.g., OAuth access tokens). Thus, distributed network stakeholder nodes 120-132 have a unique identifier embedded in the X.509 certificate that identifies each distributed network stakeholder node 120-132. Information required for certificate verification may be provided through an authentication registry associated with the certificate issuance service and / or dynamic provisioning service. For example, in the IDSA Reference Architecture Model, version 3.0 as of April 2019, prior to the execution of data exchange (not shown), distributed data serving network nodes associated with the data owner, certificate authorities (CAs), dynamic attribute provisioning services (DAPS), and distributed data consumption network nodes associated with the data consumer are used to verify the identity.

[0071] Figure 2 shows an exemplary data structure for a digital twin of input materials containing multiple digital twin datasets. The collected input material data may be part of such a digital twin. The exemplary data structure may be stored in dedicated storage associated with a distributed data-serving network node that provides access to the digital twin or a portion thereof.

[0072] An exemplary data structure may include a distributed input material identifier. The distributed input material identifier may include any unique identifier uniquely associated with the digital twin and / or digital twin dataset, and optionally, the data owner. The distributed input material identifier may link the physical entities of the input material to the digital twin. The distributed input material identifier may include one or more universally unique identifiers (UUIDs) or digital identifiers (DIDs). One or more DIDs and / or UUIDs may be associated with the digital twin and / or digital twin dataset. One or more DIDs and / or UUIDs may be further associated with the input material. The distributed input material identifier may be generated by the data owner or on behalf of the data owner of the digital twin data. The distributed input material identifier may include authentication information. Through the distributed input material identifier, the data owner may control access to the input material data or parts thereof, such as the input material dataset.

[0073] The exemplary data structure may include one or more datasets, such as dataset 1 206, dataset 2 208, and dataset 3 210. The number of datasets shown in Figure 2 is illustrative and should not be understood as limiting. Therefore, a digital twin may contain more or fewer datasets than those shown in Figure 2. Such datasets may be represented as digital twin assets or embodiments. Such datasets may be considered child nodes of the digital twin root node. Each dataset may include a distributed dataset identifier. The distributed dataset identifier may include one or more UUIDs and / or DIDs, as described above. The distributed dataset identifier can uniquely identify a dataset within the digital twin. The combination of the distributed input identifier and the distributed dataset identifier makes it possible to uniquely identify a dataset within a distributed network, such as the distributed network in Figure 1. The combination of the distributed input identifier and the distributed dataset identifier can be used to access input data, as described in relation to Figure 3.

[0074] Each dataset may further contain input material data. Input material data may contain individual data points or multiple data points. Input material data may contain one or more key-value pairs. Input material data may contain a tree structure that includes a root node and one or more leaf nodes (e.g., nodes that do not have child nodes). The tree structure may further contain intermediate nodes (e.g., nodes that are neither root nor leaf nodes). Each dataset may contain different input material data. For example, dataset 1 206 may contain production data, dataset 2 208 may contain emissions data, and dataset 3 210 may contain input material composition data.

[0075] An exemplary digital twin data structure can be generated by applying one or more data models with defined semantic descriptions to data associated with input materials, thereby generating one or more datasets. The generated datasets can then be associated with distributed input material identifiers to generate a digital twin data structure.

[0076] By using a digital twin data structure with a defined semantic description, it is guaranteed that input material data is provided in a uniform and harmonized data format. Therefore, it becomes possible to efficiently verify the received input material data without requiring data conversion to harmonize the received input material data into a uniform data format before verification.

[0077] Figure 3 shows a schematic diagram illustrating how distributed data consumption network nodes, associated with data users such as input material consumers, can be used to provide access to input material data associated with input materials via distributed data provision network nodes associated with data owners. The system shown in Figure 3 can be used within a distributed stakeholder network, such as the one described in relation to Figure 1, to exchange data such as input material data associated with input materials supplied to stakeholders in a product ecosystem to produce products, and / or data on products produced by stakeholders in a product ecosystem. Therefore, what is described in relation to input material data in relation to Figure 3 also applies to products produced from such input materials.

[0078] An input material 104 may be associated with a digital twin. The digital twin of an input material may include a distributed input material identifier and input material data. The input material data may include at least one measured physical and / or chemical property of the input material and / or at least one physical and / or chemical property determined from collected data associated with the production and / or use of the input material. The digital twin may be generated by a data owner of the input material data, such as a chemical product producer 102. The digital twin may be generated on behalf of a data owner of chemical product data. The digital twin may be generated by collecting data associated with the input material and applying one or more data models to the collected data to generate a digital twin dataset. The generated digital twin dataset can then be associated with a distributed input material identifier to generate a digital twin. The digital twin may include a distributed input material identifier. Access to the digital twin generated from the data, or to parts of the digital twin, such as a digital twin dataset included in the digital twin, may be controlled by the data owner through the distributed input material identifier and the digital twin (and therefore the input material) and optionally its unique association with the data owner. This is in contrast to a centralized authority system, where identifiers are provided by such centralized authority, and access to data is controlled by such centralized authority. In this context, decentralized refers to the use of decentralized identifiers in implementation, controlled by the data owner of the input material data. A decentralized input material identifier may include or be associated with one or more identifiers used in a decentralized network, enabling data exchange over the decentralized network. For example, a decentralized identifier may include or be associated with a digital twin dataset identifier, such as a UUID for a digital twin dataset (see, for example, Figure 2). Any combination of UUIDs and DIDs is possible. For example, a decentralized input material identifier may be a DID, while a digital twin dataset identifier may be a UUID.In another example, the distributed input material identifier and the digital twin set data identifier may be UUIDs. Data exchange may include the discovery of the distributed input material identifier and, optionally, identifiers associated with the distributed input material identifier of the participant nodes of the distributed network, authentication of the participant nodes of the distributed network, and / or authorization of data transfer via peer-to-peer communication between the participant nodes of the distributed network. The digital twin may be stored in dedicated storage (DT storage 320) associated with the distributed data providing network node 120. The digital twin may be stored in such dedicated storage 320 for access by consumers of the input material associated with the input material data stored in the dedicated storage 320. Consumers of the input material data may be product producers who use the input material to produce one or more products. The dedicated storage may be accessible to the data owner of the digital twin. The dedicated storage may be associated with the data owner of the digital twin. Access to the dedicated storage 320 may be controlled by the data owner of the digital twin, for example, via the distributed data providing network node 120. The data owner of the digital twin may be an input material producer.

[0079] A distributed input material identifier may be linked to other distributed identifiers according to the physical relationship between an input material entity and other physical entities, such as those used to produce using the input material or those produced from the input material. In this way, a distributed participant node in a distributed network may be able to interpret the relationship between a distributed input material identifier and a physical input material entity that corresponds to the physical relationship between the physical input material entity and other physical entities. By linking a distributed input material identifier to other distributed product identifiers, it becomes possible to determine which distributed participant node stores collected data associated with the use of the input material or the determined physical and / or chemical properties. The collected data and / or determined chemical and / or physical properties may be provided by the distributed participant node and stored in a digital twin. For example, a new dataset may be generated by applying a model associated with the use of the input material, and the new dataset may be used to update the digital twin. A distributed input material identifier may be a digital or virtual identifier and does not necessarily correspond to a physical identifier, for example, physically attached to the input material.

[0080] A distributed input material identifier may be or may be assigned to a physical identifier connected to the input material 104. The association of the physical identifier with the input material may be provided by a physical connection to the physical input material or physical entity. For example, the physical identifier may be connected to the physical entity of the input material. The physical identifier may have a one-to-one correspondence with virtual or physical identification information through a physical connection to the physical entity. The physical identifier may be physically attached to the input material via an identifier element. A physical identifier or physical identifier element may refer to any virtual or physical configuration that associates the distributed identifier with the input material. The physical identifier may be any identifier of the produced input material, such as a batch number or part number. The physical identifier element may include, but is not limited to, passive or active elements, such as QR codes or RFID tags. The physical identifier element may be a physical identifier physically connected to the input material. The identifier element may include a marker embedded in the input material, a barcode, a QR code, a tag such as an RFID tag, or a similar physical configuration that enables digital identification of the input material.

[0081] A digital access element may be generated for the produced input material 104. The digital access element may include a distributed access element identifier and access data. The distributed access element identifier may be associated with a distributed input material identifier. The distributed access element identifier may correspond to a distributed input material identifier. The access data may include a digital representation pointing to a distributed data-serving network node associated with the digital twin of the input material. The access data may include a representation for accessing the input material data. The distributed input material identifier may be associated with the representation for accessing the input material data. An example of such a digital access element is shown in Figure 4. The digital access element may further include or be associated with authentication and / or authorization information linked to the distributed access element identifier. The authentication and / or authorization information may be provided for authentication and / or authorization of distributed network nodes / distributed data-consuming network nodes and distributed data-serving network nodes. The digital access element may be provided to a distributed registry node, for example, as described with respect to Figure 3. The distributed registry node may store the distributed access element identifier and associated access data.

[0082] The physical entities of the input material 104 produced by the input material supplier 106 may be physically provided from the input material supplier 106 to the chemical product producer 102. The input material may be provided to the chemical product producer 102 in relation to a digital access element. The chemical product producer 102 may use the supplied input material to produce a product (e.g., an output product). The output product may be a chemical product or an individual product. The input material 104 may be associated with a code such as a barcode or QR code that encodes a distributed access element identifier. The chemical product producer 102, upon receiving the input material 104, can read the code through a code reader 302. The code reader 302 may be a smartphone running a code reading application such as a QR code reader app. The data obtained by the code reading application may be used to determine the distributed access element identifier. The data obtained by the code reading application may be used to determine the distributed input material identifier. The data obtained by the code reading application may be used to determine the input material identifier. Data obtained by the code reading application may be used to determine access data. The distributed passport identifier, distributed input material identifier, input material identifier, and access data may be determined by the code reader 302. For example, the distributed passport identifier determined by the code reader 302 may be a DID, and the code reader 302 may be configured to retrieve the associated DID document containing the distributed input material identifier and access data, for example, using a DID resolver (see also Figure 4). In another example, the input material identifier is determined by the code reader 302 and used to retrieve the distributed access element identifier and associated access data from a database, for example, a distributed registry node 308. Therefore, the code reader 302 may be configured to retrieve the digital access element containing the distributed access element identifier and access data from the distributed registry node 308.The code reader 302 may be configured to provide distributed access element identifiers and / or distributed input material identifiers to a database 306 associated with the chemical product producer 102. The code reader 302 may also be configured to provide the determined distributed access element identifiers, distributed input material identifiers, and access data to a distributed data consumption network node 122.

[0083] The code reader 302 may be configured to display identified / retrieved data on a user interface, as indicated by reference numeral 304. The user interface may display a determined distributed access element identifier (PP identifier), a determined distributed input material identifier (DT identifier), and determined access data (DT location). In this embodiment, the distributed access element identifier and the distributed input material identifier are different from each other. In another embodiment, the distributed access element identifier is equal to the distributed digital twin identifier. The user interface may further display identified input material identifiers (not shown). The user interface may also enable the initiation of a search for the digital twin or a portion thereof based on the distributed access element identifier and access data, as described below. This process may be initiated by a button labeled "Access DT". When the button is pressed, the code reader 302 may send a request to access the digital twin or a portion thereof to the distributed data consumption network node 120.

[0084] The distributed data consumption network node 122 may generate requests to access a digital twin or a portion thereof. The distributed data consumption network node 122 may generate requests based on data received from the code reader 302. For example, the distributed data consumption network node 122 may generate requests based on a distributed digital twin identifier received from the code reader 302. The distributed data consumption network node 122 may generate requests based on a distributed access element identifier and / or a distributed input material identifier provided to the database 306. For example, the distributed data consumption network node 122 may be configured to retrieve a distributed input material identifier from the distributed registry node 308 and access the data based on a distributed access element identifier or an input material identifier associated with an input material stored in the database 306. Requests generated by the distributed data consumption network node 122 may include a distributed input material identifier and a distributed stakeholder identifier of a chemical producer 102 associated with the distributed data consumption network node 122. The request may include a digital twin dataset identifier of the digital twin dataset to be accessed (e.g., input material data). The distributed data consumption network node 122 may be configured to determine the distributed data provision network node 120 associated with the digital twin of the input material 104 based on access data provided by the code reader 302 or retrieved from the distributed registry node 308, or based on the input material identifier.

[0085] The distributed data consumption network node 122 may send a request to access a digital twin or a portion thereof to an identified distributed data providing network node 120, as indicated by arrow 310. The distributed data providing network node 120 may be associated with an input supplier 106 that supplies input material 104 to a chemical producer 102. The distributed data providing network node 120 may be associated with a production that produces the input material. The distributed data providing network node 120 may be associated with the data owner of the input material 104. The distributed data providing network node 120 may be associated with an entity that operates the production that produces the input material 104. In addition to the request, authentication and / or authorization information may be provided by the distributed data consumption network node 122.

[0086] Requests can be authenticated. Access to a digital twin or part thereof can be authorized based on access policy data associated with the digital twin or part thereof. The access policy data may define distributed participant identifiers that are permitted to access input material data. The access policy data may define one or more authorization rules associated with the use of input material data. The access policy data may define one or more actions that distributed data consumption network nodes are permitted to perform on the input material data. This makes it possible to filter distributed data consuming network nodes requesting access based on the distributed participant identifiers associated with the network node and the requested actions to be performed on the accessed input material data. If a request is invalid, for example, if distributed data consumption network node 122 is not authorized to access the input material data, the peer-to-peer communication channel is terminated by distributed data providing network node 120 and the input material data is not provided.

[0087] If the request is approved, the distributed data providing network node 120 may initiate contract negotiations with the distributed data consuming network node 122 before providing input materials. The distributed data providing network node 120 may provide the distributed data consuming network node 122 with an electronic contract. The electronic contract may include one or more authorization rules associated with the distributed identifier. This allows the data consumer to determine the terms of use associated with the provided input data. The distributed data providing network node 120 and the distributed data consuming network node 122 may be configured to negotiate and sign the electronic contract. The use of the electronic contract ensures that the distributed data consuming network node 122 and any further systems handling the input data comply with at least one authorization rule associated with the input data. When the electronic contract is signed, the input data may be collected based on the provided distributed input identifier, and optionally, dataset identifiers and access policy data may be applied to the collected data, as indicated by arrows 312 and 314. The input material data obtained by applying access policy data to the collected input material data can be provided to the distributed data consumption network node 122 by the distributed data provision network node 120, as indicated by arrow 316.

[0088] The input material data provided by the distributed data provision network node 120 may be stored in the database storage 306 associated with the distributed data consumption network node 122, according to the access policy data, as indicated by arrow 318.

[0089] Through a decentralized input material identifier, input material data can be uniquely associated with the input material. Through a decentralized network, input material data can be transferred between input material producers and consumers in a standardized and secure manner, enabling input material producers to control access to input material data by multiple decentralized data consumption network nodes within the decentralized network. In this way, input material data can be shared reliably and securely among stakeholders in the product ecosystem, directly and without central mediation, using a unique association with the input material.

[0090] Figure 4 shows an example of a digital access element, including DID owner data, DID document data, and a distributed identity infrastructure. A digital access element may be associated with input materials. A digital access element may be associated with output materials. A digital access element may be associated with any input and / or output materials produced and transported within the product ecosystem, as shown in Figure 1. Output products may also include output products resulting from recycling operations.

[0091] A distributed identifier may be a distributed identifier (DID). In this case, a distributed identifier-based digital access element may be a DID document 404 associated with the DID. In addition to the DID document 404 acting as a digital access element, Figure 4 shows a DID owner data element 402 that includes distributed identifier-based owner data. Generally, distributed identifier-based owner data may include a distributed identifier associated with an object such as input material data and may include one or more authentication mechanisms. Distributed identifier-based owner data 402 may include owner data that is electronically owned and controlled by the DID owner. In this regard, electronically owned may mean data stored in an owner repository or wallet. Such data may be securely stored and / or managed on an organized server or client device. Distributed identifier-based owner data 402 may include a DID, a private key, and a public key. A DID owner may own and control a DID representing the identification information associated with the DID object, and a private key and public key pair associated with the DID. A DID may be understood as an identifier and authentication information associated with or uniquely linked to the identifier.

[0092] The DID object may be an input material. The DID object may be an output product. The DID object may be a machine, system, or device used for the production of an input material, or a collection of such machines, devices, and / or systems. The DID object may be a machine, system, or device used for the production of an output product, or a collection of such machines, devices, and / or systems. The DID owner may be a supply chain participant or a manufacturer such as an input material producer or an output product producer.

[0093] DID can be any identifier associated with the DID subject and / or DID owner. Preferably, the identifier is unique to the DID subject and / or DID owner. The identifier can be unique to the extent that the DID is expected to be unique when used. The identifier can be a local or global unique identifier of any participant in the product ecosystem, including input materials or output products, machines, systems or devices used to produce input materials or output products or sets of such machines, devices and / or systems, input material producers or output product producers, raw material chemical product suppliers, intermediate chemical product manufacturers, intermediate component manufacturers, component manufacturer, component assembly manufacturers, final product manufacturers, final product users, EOL collectors, recyclers or sets of such.

[0094] A DID can be any identifier associated with a DID object and / or DID owner. Preferably, a DID is unique to the DID object and / or DID owner. A DID can be unique to at least the extent to which it is expected to be unique when used. A DID can be a locally or globally unique identifier for any of the possible DID objects described above. A DID can also be a Unified Resource Identifier (URI), such as a Unified Resource Location Specifier (URL). Furthermore, a DID can be an Internationalized Resource Identifier (IRI). A DID can be a Unified Resource Identifier (URI), such as a Unified Resource Location Specifier (URL). A DID can be an Internationalized Resource Identifier (IRI). A DID can be a random string of numbers and letters for enhanced security. In one embodiment, a DID can be a sequence of 128 letters and numbers following the format did:method name:method-specific did, such as "did:example:ebfeb1f712ebc6f1c276e12ec21". DID can be a decentralized identity that is independent of a centralized third-party management system and is under the control of the DID owner.

[0095] A digital access element as a DID document 404 may be associated with a DID, i.e., a DID contained in the distributed identifier-based owner data 402. Thus, a digital access element may include a reference to a DID associated with a DID subject described by the DID document 404. The DID document 404 may also include authentication information, such as a public key. The public key may be used by a third-party entity that has been granted permission by the DID owner / subject to access information and data owned by the DID owner / subject. The public key may also be used to verify that the DID owner actually owns or controls the DID. The DID document may include authentication and authorization information, for example, to authorize a third-party entity to read the DID document or a portion of the DID document, without, for example, granting the third party the right to prove ownership of the DID.

[0096] The digital access element 404 may include, for example, one or more representations that digitally link to the digital twin or a portion thereof to which the digital access element is associated, via a service endpoint. The service endpoint may include a network address on which the service operates on behalf of the DID owner. In particular, the service endpoint may refer to a service such as a data-providing network node of the DID owner that provides access to input material data.

[0097] The digital access element 404 may include a digital twin dataset identifier and further identifiers such as input material or output product identifiers.

[0098] The digital access element 404 may contain various other information, such as metadata specifying when the digital access element was created, when it was last modified, and / or when it expires.

[0099] The DID and digital access element 404 may be associated with a distributed data service system or a distributed data service system 406, such as a data registry node, such as a distributed ledger or blockchain or a distributed file system. The distributed ledger or blockchain may be used to store a representation of the DID that points to the digital access element 404. The representation of the DID may be stored in the distributed computing nodes of the distributed ledger or blockchain 1906. For example, a DID hash may be stored in multiple computing nodes of the distributed ledger and point to the location of the digital access element 404. In some embodiments, the digital access element 404 may be stored in the distributed ledger 406. Each computing node may store a copy of the distributed ledger 406. In this way, each DID hash can be stored redundantly, thereby increasing data security. DIDs associated with multiple different digital access elements 404 may be included in the distributed ledger 406.

[0100] In some embodiments, the digital access element 404 may be stored in a distributed ledger 406, i.e., in addition to or alternative to the associated DID representation stored in the distributed ledger 406. In other embodiments, the digital access element 404 may be stored in data storage (not shown) associated with a distributed ledger, blockchain, or distributed file system.

[0101] A distributed ledger or blockchain 406 can be any distributed network containing various computing nodes that communicate with one another. For example, a distributed ledger 406 may include a first distributed computing node, a second distributed computing node, a third distributed computing node, and any number of additional distributed computing nodes (not shown). A distributed ledger or blockchain 1806 may include known technology stacks such as Bitcoin (see, for example, the Bitcoin documentation published on November 11, 2022 at https: / / en.bitcoin.it / wiki / Protocol_documentation), Ethereum (see, for example, the Ethereum documentation published on August 15, 2022 at https: / / ethereum.org / en / developers / docs / ), Solana (see, for example, the Solana documentation published on November 11, 2022 at https: / / spl.solana.com / ), Polygon (see, for example, the Polygon documentation published on November 11, 2022 at https: / / wiki.polygon.technology / ), or other implementations with varying degrees of data transactions performed on a distributed ledger. The description of the exemplary framework is for illustrative purposes only and should not be considered limiting.

[0102] Figure 5 shows an example of production in which one or more products are produced from one or more input materials, in relation to an operating system that includes an input material data verification system. The production may be chemical production 502. The products may be chemical products 142.

[0103] To produce one or more chemical products 142, different input materials (raw materials) 104 may be provided as physical inputs from a material provider or supplier 106 (see also Figure 1). The chemical products 142 produced from the input materials 104 may be supplied to a chemical product consumer 108, for example, as described in relation to Figure 1. Chemical production 502 may be a chemical production network. A chemical production network may include multiple interconnected processing steps. A chemical production network may be an integrated chemical production network with connected or interconnected manufacturing chains. A chemical production network may include multiple different manufacturing chains sharing at least one intermediate product. A chemical production network may include multiple stages of a chemical value chain. A chemical production network may include the production, refining, processing and / or purification of chemical products. A chemical production network may include multiple production chains producing chemical products that exit the chemical production network 4 from one or more input materials. A chemical production network may include multiple layers of a chemical value chain. A chemical production network may include physically connected or interconnected supply chains and / or production sites. Production sites may be located in the same place or in different places. In the latter case, production sites may be connected or interconnected by dedicated transportation systems such as supply chain vehicles, including pipelines, trucks, ships, or other means of freight transport.

[0104] Chemical production 502 can chemically convert input materials 104 into one or more chemical products 142 that exit chemical production 502 via chemical intermediates. Chemical production 502 can convert input materials 104 into one or more chemical products through chemical conversion.

[0105] The input material 142 can be supplied to the chemical production 502 at any inlet point. The input material 142 can be supplied to the chemical production 502 at the start of the chemical production 502. The input material may constitute, for example, the raw materials of a plant that performs the first production step of a production chain associated with a chemical product.

[0106] Chemical production 502 may produce chemical products 142 through a number of production steps. The production steps may be defined by the system boundary of chemical production 502. The system boundary may be defined by the location or control of the production process. The system boundary may be defined by the site of chemical production 502. The system boundary may be defined by a production process jointly controlled by one or more entities. The system boundary may be defined by a value chain having a time-staggered production process to the final product, which may be individually controlled by multiple entities. Chemical production 502 may include at least one of a waste recovery and sorting step, a recycling step such as pyrolysis, a cracking step such as steam cracking, a separation step for separating multiple outputs of one process step, and a further process step for converting such outputs into chemical products exiting the system boundary of chemical production 502.

[0107] The operating system 504 of the chemical production 502 may monitor and / or control the chemical production network 504 based on the operating parameters of different processes. One process step to be monitored and / or controlled may be the supply of input materials or the discharge of chemical products. Another process step to be monitored and / or controlled may be the collection of input material data associated with input materials entering the system boundary of the chemical production 502. Yet another process step to be monitored and / or controlled may be the verification of the collected input material data. Yet another process step to be monitored and / or controlled may be the processing of the verified input material data.

[0108] The operating system 504 may be configured to perform at least some of the steps described in relation to Figures 8 and 9. The operating system may include a data validation system, as described in relation to Figures 6 to 7B. The data validation system may be configured to validate the collected input material data, as described in relation to Figures 6 to 8. The data validation system may be configured to process the validated input material data, as described in relation to Figures 6 to 8.

[0109] Figure 6 shows an example of production in which one or more products are produced from one or more input materials, in relation to an operating system that includes an input material data verification system. Production could be a chemical production 502 that produces one or more chemical products from the input materials. Chemical production 502 is described above with reference to Figure 5.

[0110] The operating system 504 may be a digital operating system configured to collect, store, manage, and interpret a wide range of production and / or business data of the chemical production 502. The operating system 504 may be part of an enterprise resource planning (ERP) system. Alternatively, the operating system 504 may be partially implemented in an ERP system and partially implemented in one or more additional systems that are integrated with the ERP system. The operating system 504 may also be implemented in one or more systems outside of the ERP system.

[0111] The input material 104 may be supplied to the chemical production 502 at the supply point 602. The input material may include raw materials. The input material may include chemical intermediate products. The input material may include recycled materials. After being delivered to the chemical production 502, the input material 104 may be stored in an input material storage unit such as a tank once it enters the chemical production process.

[0112] The chemical product 142 produced by chemical production 502 may be stored in a chemical storage unit such as a tank before being supplied to the discharge point 604. At the discharge point 604, the produced chemical product 142 may be supplied to one or more chemical product consumers 108 (not shown; see, for example, Figure 1). The chemical product consumers 108 can use the supplied chemical product 142 to produce further chemical products or individual products.

[0113] The input material 104 may include a physical identifier element, as described in relation to Figure 3. The physical identifier element may be scanned by the code reader 302 to determine a distributed input material identifier (shown as ID1 and ID2 in Figure 6), for example, as described with respect to Figure 3. Referring to Figures 7A and 7B, the determined distributed input material identifier may be used by the data validation system 606 to initiate the collection of input material data via the distributed data consumption network node 122 associated with the operating system 504 (see operation 706 in Figures 7A and 7B). For example, as described in relation to Figure 3, the distributed data consumption network node may collect input material data from the distributed data provision network nodes 120a and 120b associated with the input material supplier 106. The input material data collected by the distributed data consumption network node 122 may be provided to the data validation system 606. Referring to Figure 2, the input material data collected by the distributed data consulting network node 122 may include one or more datasets. Each dataset may include one or more data points.

[0114] In one embodiment, referring to Figure 7A, the data validation system 606 may include a rule-based engine 704. The rule-based engine 704 may operate on individual data points, multiple data points, and / or entire datasets. The rule-based engine 704 may operate independently on each collected dataset. This allows each dataset to be validated individually, enabling more detailed validation of the input material data. The rule-based engine 704 may receive requests to validate acquired input material data. The rule-based engine 704 may be configured to determine a dataset identifier associated with the received input material data. For example, the rule-based engine 704 may analyze the received input material data to determine the data present in each dataset. The rule-based engine 704 may then determine the respective dataset identifier. The rule-based engine 704 may create rule requests to retrieve one or more rules from the rule DB 708. The requests may include a dataset identifier and optionally location data. The location data may be associated with the location of the chemical production 502. The rule DB 708 may store one or more rules. One or more rules associated with the dataset to be validated may be provided to the rule-based engine 704. These rules may define individual data points, acceptable combinations of data points, and / or optional thresholds for required data points associated with location data. A dataset identifier may be associated with one or more rules.

[0115] The rule-based engine 704 may be configured to apply received rules to input material data to be validated in order to validate the input material data (see operation 712). Validating input material data may include determining the validity of the input material data. Input material data may be considered valid if one or more rules applied by the rule-based engine 704 are satisfied. Applying rules to input material data may include comparing individual data points present in the input material data being validated with thresholds to determine whether individual data points in the input material data are above or below the thresholds defined by such rules. Applying rules to input material data may include comparing combinations of data points present in the input material data being validated with combinations of data points defined by rules to determine whether the input material data contains unacceptable combinations of data points. Applying rules to input material data may include comparing the entire input material dataset being validated with the data defined by rules to determine whether the input material dataset contains all the necessary data. The actions performed by the rule-based engine 704 may be determined by the rules collected from the rule DB 708. For example, rules collected from rule DB 708 can determine whether the rule-based engine 704 operates on individual data points and / or multiple data points and / or the entire dataset.

[0116] The rule-based engine 704 may be configured to determine whether the input material data being validated satisfies one or more applied rules (see operation 702). The rule-based engine 704 may provide at least a portion of the input material data to the database 610 in accordance with the validation of that portion of the input material data. The rule-based engine 704 may provide at least a portion of the input material data to the data processor 612 in accordance with the validation of that portion of the input material data. The data processor 612 may be configured to process at least a portion of the validated input material data received. The data processor 612 may be configured to collect the validated input material data from the database 610. Processing may include generating control data based on the validated input material data to control the production of chemical products using the input materials associated with the validated input material data. Processing may include performing one or more data processing operations on at least a portion of the validated input material data. Data processing operations may include generating further data using the validated input material data, such as cumulative data emission data, cumulative recyclable rate data, cumulative biobase content data, and certificate data.

[0117] If at least a portion of the received input material data cannot be validated, the rule-based engine 704 may proceed to operation 714. In operation 714, the rule-based engine 704 may generate message data indicating that it was unable to validate at least a portion of the input material data. The message data may include indications of data points for which the input material data could not be validated. The message data may be provided to a display device configured to display data received from the rule-based engine 704. The display device may include a graphical user interface 716. The display device may display the message in response to receiving the message data from the rule-based engine 704. This may trigger the correction of data points identified as invalid or inaccurate, or allow the acquisition of missing input material data from the input material data owner. Correction of data points may include generating message data indicating invalid or missing input material data and providing the message data to the input material data owner. The message data may be provided to the input material data owner via the distributed network 138. The message data may be provided to the input material data owner via a common data transfer protocol.

[0118] In another embodiment, referring to Figure 7B, the data validation system 606 may validate at least a portion of the collected input material data using at least one trained data-driven model 722. The data-driven model may be trained as described with respect to Figure 9. The data-driven model may be stored in data storage (not shown) associated with the data validation system 606 and may be collected by the data validation system 606 when at least a portion of the input material data is validated in operation 720.

[0119] Input material data may be obtained in operation 706 as described above with respect to Figure 7A, using a distributed input material identifier associated with the received input material. At least a portion of the input material data obtained in operation 706 may be validated in operation 720 using at least one trained data-driven model 722. For this purpose, the input material data to be validated may be provided as input to at least one trained data-driven model 722. At least one trained data-driven model 722 is a classifier model that classifies inputs into "valid" and "invalid". The classification may be used in operation 702 to determine whether the input material data to be validated is valid or not. The data validation system 606 may provide at least a portion of the input material data to the database 610 in accordance with the validation of that portion of the input material data. The data validation system 606 may provide at least a portion of the input material data to the data processor 612 in accordance with the validation of that portion of the input material data. The data processor 612 may process at least a portion of the validated material data as described above with respect to Figure 7A.

[0120] If at least a portion of the received input material data is not validated, the data validation system 606 may proceed to operation 714 as described in relation to Figure 7A.

[0121] Figure 8 shows an example of a method for verifying input data associated with one or more input materials entering production. Production may be a chemical production 502 that produces one or more chemical products from the input materials. Chemical production 502 is described above with reference to Figure 5. At least part of the method may be carried out by an operating system 504 described in reference to Figures 5 and 6.

[0122] In block 802, a distributed input material identifier may be provided, associated with the input materials entering the system boundary 608 of chemical production 502. The distributed input material identifier may be provided as described in relation to Figures 3 and 6.

[0123] In block 804, input material data associated with the provided distributed input material identifier can be collected from one or more distributed data provision network nodes 120 associated with the input material supplier 106 by a distributed data consumption network node 122 associated with the chemical production 502. The input material data can be collected as described in relation to Figures 3 and 6.

[0124] In block 806, at least a portion of the collected input material data may be validated using a rule-based engine or at least one trained data-driven model. Block 806 may be executed by the rule-based engine 704 described in relation to Figures 6 and 7A or by at least one trained data-driven model 722 described in relation to Figures 6 and 7B.

[0125] In block 808, it may be determined whether the input material data is validated, for example, as explained in relation to Figure 6. If all the input material data to be validated is validated, the method may proceed to block 820. If only some of the input material data to be validated is validated, the method may proceed to block 810. If the input material data to be validated is not validated, the method may proceed to block 816.

[0126] In block 810, at least a portion of the verified input material data may be provided for processing, for example, as described in relation to Figure 6. The method may then proceed to block 812, where message data regarding the unverified input material data is generated, for example, as described in relation to Figure 6 and Figure 7A / 7B (see operation 714). The generated message data may be provided, for example, as described in relation to Figure 6.

[0127] In block 816, message data may be generated as described above. The method can then proceed to block 818, where the generated message data can be provided, as described in relation to Figure 6. The message data may be provided to the data owner of the input material data. In this way, it is possible to trigger an update of the digital twin of the input material (e.g., input material data) by the data owner of the digital twin. By updating the digital twin in response to message data received from the data consumer, the data owner of the digital twin can eliminate errors in the digital twin data, thus improving data reliability within the distributed network. The message data may be provided to the data owner via the distributed network.

[0128] In block 820, at least a portion of the verified input material data may be provided for processing. Providing the verified input material data for processing may include storing the input material data in a database. The provided verified input material data may be processed, for example, as described in relation to Figures 6 and 7A (see optional block 822).

[0129] Figure 9 shows an exemplary method for training a data-driven model to validate at least a portion of the collected input material data. The method may be used to obtain a trained data-driven model 722, as described in relation to Figures 6 and 7B. The data-driven model may be a classifier model, as described in relation to Figures 6 and 7B.

[0130] In block 902, inputs and outputs are selected. If an artificial neural network (ANN) is used, inputs and outputs can refer to the number of data points in the input and output layers, respectively, separated by one or more layers of neurons in the ANN model. Any number of input and output data points can be used. There may be a large number of data inputs, such as a large number of input material data points, and two data outputs, such as whether the classifier is "valid" or "invalid".

[0131] In block 902, the training dataset is developed and / or collected. A generally accepted practice is to divide the model training dataset into three parts: the training set, the validation set, and the validation (or "test") set. When an ANN is used, the training set is used to tune the internal weighting algorithm and the functions of the neural network's hidden layers, thereby allowing the neural network to iteratively "learn" how to correctly recognize and classify patterns in the input data. The validation set, however, is primarily used to minimize overfitting. The validation set typically does not tune the neural network's internal weighting algorithm in the same way as the training set; rather, it verifies that the improvement in accuracy across the training dataset results in an improvement in accuracy over datasets that the neural network has not previously applied to, or at least datasets that the network has not yet trained on (i.e., the validation dataset). If the accuracy across the training dataset increases, but the accuracy across the validation dataset remains the same or decreases, the process is often called "overfitting" the neural network, and training should be stopped. Finally, the validation set is used to test the final solution to confirm the actual predictive ability of the neural network.

[0132] For example, approximately 70% of the developed or collected data model set is used for model training, 15% for model validation, and 15% for model verification. These rough divisions can be modified as needed to achieve the desired results.

[0133] Training data can be collected by gathering various input datasets (e.g., historical input data) from various inputs and annotating individual data points and / or combinations of data points and / or the entire dataset with validity scores. A validity score can indicate the validity of each individual data point, combination of data points, or entire dataset. For example, a validity score of 1 indicates that the data point, combination of data points, or entire dataset is not valid, while a validity score of 5 indicates that the data point, combination of data points, or entire dataset is valid. Scores between 1 and 5 can be used to indicate a finer degree of validity. Therefore, a validity score can be considered the likelihood of whether a data point, combination of data points, or entire set is considered valid. The training dataset may contain samples spanning the entire range of validity scores.

[0134] In block 906, a classifier model is selected. The classifier model can be selected from decision trees, Naive Bayesian classifiers, K-nearest neighbors, support vector machines, and deep learning models. Guidelines known to those skilled in the art and / or associated with specific algorithmic software may be helpful in the initial selection of model type and dimensions.

[0135] In block 908, the model selected in block 906 refers to the training and validation portions of the training dataset. Training, in the case of an ANN, is an iterative process of setting internal weights or weighting algorithms between ANN model neurons, where each neuron in each layer is connected to each neuron in each neighboring layer, and each connection is further represented by a weighting algorithm. With each iteration of the training data to adjust the weights, the validation data is run on the ANN model, and one or more measures of accuracy are determined by comparing the model output for the filling level with actual measurements of the filling level collected using the training data. For example, generally, the standard deviation and mean error of the output improve with each iteration of the validation data, and then begin to increase with subsequent iterations. The iteration in which the standard deviation and mean error are minimized is the most accurate set of weights for the ANN model on that training dataset.

[0136] In block 910, the algorithm points to a validation dataset and determines whether the algorithm's output is sufficiently accurate compared to the actual validity of each input material data. If the accuracy is insufficient, the method can return to block 906 or block 904 to improve the algorithm's accuracy. If the model has been trained to sufficient accuracy, the method proceeds to block 806.

[0137] A trained data-driven model can be improved over time using additional data, such as behavioral data.

[0138] This disclosure has been described in conjunction with preferred embodiments and examples. However, those skilled in the art who practice the claimed invention will be able to understand and practice other variations by examining the drawings, this disclosure, and the claims. In particular, any of the steps presented may be performed in any order, i.e., the invention is not limited to any particular order of these steps. Furthermore, it is not required that the different steps be performed in a specific location or on one node of a distributed system, i.e., each step may be performed on a different node using different equipment / data processing devices.

[0139] As used herein, “determine” also includes “initiate or cause to determine,” “generate” also includes “initiate and / or cause to generate,” and “provide” also includes “initiate or cause to determine, generate, select, transmit and / or receive.” “Initiate or cause to perform an action” includes any processing signal that triggers a computing node or device to perform the respective action.

[0140] In the claims and herein, the word “includes” does not exclude other elements or steps, and the indefinite article “a” or “an” does not exclude plural. A single element or other unit may perform the function of several entities or items described in the claims. The mere fact that certain means are described in different dependent claims does not indicate that a combination of these means cannot be used in a favorable implementation. In the claims and herein, the word “includes” or “inclusive” or similar expressions do not exclude other elements or steps and should not be construed as limiting the elements or steps described. The indefinite article “a” or “an” does not exclude plural. A single element or other unit may perform the function of multiple entities or items mentioned in the claims. The mere fact that certain means are described in different dependent claims does not indicate that a combination of these means cannot be used in a favorable implementation or that further elements cannot be included.

[0141] Providing information within the scope of this disclosure may include any interface configured to provide data. This may include application programming interfaces, human-machine interfaces such as displays, and / or software module interfaces. Providing information may include the communication of data or the transmission of data to an interface, in particular display to a user or use of the data by a receiving entity.

[0142] All terms and definitions used herein are to be understood in a broad sense and have their general meaning.

Claims

1. A computer implementation method for verifying input material data associated with one or more input materials entering into production, wherein the production produces one or more products from the one or more input materials, and the method is (a) To provide one or more distributed input material identifiers associated with one or more input materials, (b) Collecting input material data associated with the provided distributed input material identifier from a distributed data provider network node associated with the input material data via a distributed network, (c) Validate at least a portion of the collected input data by using a rule-based engine that includes a validity threshold, or by using a data-driven model trained on a historical dataset that includes input data and a validity score. (d) To provide the verified input material data in order to process the verified input material data based on the verified input material data. A computer implementation method, including

2. The computer implementation method according to claim 1, wherein the input material data includes one or more input material datasets.

3. The computer-aided method according to claim 1 or 2, wherein the input material data includes at least one measured physical and / or chemical property of the input material and / or at least one physical and / or chemical property determined from collected data associated with the production and / or use of the input material.

4. The computer implementation method according to any one of claims 1 to 3, wherein the production is chemical production and / or the product is a chemical product.

5. The computer implementation method according to any one of claims 1 to 4, wherein the distributed input material identifier is provided by a sensor that reads an identifier element physically connected to the input material.

6. The computer implementation method according to any one of claims 1 to 5, wherein the input material data is stored in dedicated storage associated with each of the distributed data provision network nodes, and access to the input material data stored in the dedicated storage is controlled by the data owner of the input material data via the distributed data provision network nodes.

7. A computer implementation according to any one of claims 1 to 6, further comprising: collecting input material data; determining a distributed identifier associated with the material used to produce the input material based on the provided distributed input material identifier; and collecting material data from a distributed data providing network node associated with the material data using at least a portion of the determined distributed identifier.

8. The computer implementation method according to claim 7, wherein the distributed identifier is determined using a relational expression that specifies the relationship between the input material and the material used to produce the input material.

9. The computer implementation method according to any one of claims 1 to 8, wherein the rule-based engine operates on individual data points present in at least a portion of the collected input material data, a plurality of data points present in at least a portion of the collected input material data, or the entire collected input material data.

10. The computer implementation method according to any one of claims 1 to 8, wherein the trained data-driven model is a classifier model.

11. The computer implementation method according to any one of claims 1 to 10, wherein providing the verified input material data for processing includes storing at least a portion of the verified input material data in data storage.

12. The computer implementation method according to any one of claims 1 to 11, wherein processing the verified input material data includes performing one or more data processing operations on at least a portion of the verified input material data.

13. An apparatus for verifying input material data associated with one or more input materials entering into production, wherein the production produces one or more products from the one or more input materials, and the apparatus (a) A distributed input material identifier provider configured to provide one or more distributed input material identifiers associated with one or more input materials, (b) A distributed data consumption network node associated with the production, configured to collect input material data associated with the provided distributed input material identifier from a distributed data provision network node associated with the input material data. (c) A rule-based engine including a validity threshold or a data-driven model trained on a historical dataset including input material data and a validity score, wherein the rule-based engine or data-driven model is configured to validate at least a portion of the collected input material data and to provide the validated input material data based on the validated input material data. (d) Optionally, a data processor configured to process the provided verified input material data. A device including a device.

14. Use of input material data verified by a computer implementation method according to any one of claims 1 to 12 or an apparatus according to claim 13 for controlling the production of a product at least partially produced from input materials associated with the verified input material data.

15. A computer element having instructions configured to be executed on one or more computing nodes to perform the steps of the method according to any one of claims 1 to 12, or to be performed by the apparatus according to claim 13.

Images