Method for data processing for an environmental impact assessment in a food protein value chain

Abstract

The invention refers to a method for data processing for an environmental impact assessment in a food protein value chain. At an environmental impact assessment system, a digital representation of product data associated with a food product in the food protein value chain is received from a participant of a food protein value chain. The digital representation includes both structured data and unstructured data. The information included in the digital representation of the product data is extracted a data normalisation function is deployed to the extracted information to generate structured product data. The data normalization function is configured to reorganize the extracted information to remove or reformat unstructured data to generate structured product data. An environmental impact assessment generation function is applied to the structured product data to generate assessment data indicative of an environmental impact assessment of the product and the assessment data is provided to the participant.

Description

[0001] Method for data processing for an environmental impact assessment in a food protein value chain

[0002] FIELD OF THE INVENTION

[0003] The invention refers to a computer implemented method, an apparatus and a computer program product for data processing for an environmental impact assessment in a food protein value chain. BACKGROUND OF THE INVENTION

[0004] The production of food protein can have a strong impact on the environment. Thus, improving the production of food protein with respect to its environmental impact is thus of high importance.

[0005] SUMMARY OF THE INVENTION The food protein value chain is a complex value chain with a plurality of participants that interact in a complex manner to produce respective food protein. For example, the value chain of a food product can comprise fertilized producers, plant production producers, crop farmers, livestock farmers, food packaging providers, regulators, certifiers, and consumers. In such a complex value chain it is nearly impossible for a participant to really assess an environmental impact of the production of the food protein due to the complex interactions of the participants and missing information. In particular, the data necessary for determining an environmental impact is not only spread through all participants of the food protein value chain but also exists in a plurality of formats and comes from a plurality of sources, for instance, structured data can be provided from sensors like humidity sensors, temperature sensors, etc. or from unstructured sources, for instance, an electrical bill, a transportation protocol, etc. Thus, in order to assess an environmental impact which then allows to improve the production such that the environmental impact is decreased, it is not only necessary to collect the respective data but also to make the information provided by the data available for further analysis.

[0006] Since the invention refers to a method, as described in more detail in the following, that comprises extracting information included in a digital representation of a product data from the digital representation and deploying a data normalization function to the extracted information to generate structured product data, wherein the data normalization function is configured to reorganize the extracted information to remove or reformat unstructured data to generate structured data, the information is made available for applying an environmental impact assessment generation function to the structured product data to generate assessment data indicative of an environmental impact assessment of the product. Thus, the environmental impact of each participant of a food protein value chain can be assessed in this way and based on the assessment the respective participants can identify actions that lead to an improvement of the environmental impact of the food production. The environmental impact of a food product can hence be improved throughout the complete food product value chain.

[0007] In an aspect of the invention, a computer implemented method is presented for data processing for an environmental impact assessment in a food protein value chain, wherein the method comprises a) receiving, at an environmental impact assessment system, a digital representation of product data associated with a food product in the food protein value chain from a participant of a food protein value chain, via a participant node, wherein the digital representation includes both structured data and unstructured data, b) extracting information included in the digital representation of the product data from the digital representation and deploying a data normalisation function to the extracted information to generate structured product data, wherein the data normalization function is configured to reorganize the extracted information to remove or reformat unstructured data to generate structured product data, c) applying an environmental impact assessment generation function to the structured product data to generate assessment data indicative of an environmental impact assessment of the product, d) providing the assessment data to the participant via a participant node..

[0008] The computer implemented method can be performed by any computer system comprising one or more data processors. For example, the computer implemented method can be performed by a standard general computer, dedicated hardware, or distributed computing in which a plurality of computing systems work together to perform the functions defined in the computer implemented method.

[0009] A food protein value chain can refer to a representation of the various processes and participants involved in producing a food product, starting, for instance, with respective raw materials and ending with the respective consumer product. However, also only parts of the food protein value chain can be utilized during the environmental impact assessment. The food protein can refer to any food product that provides protein for human or animal consumption. For example, the food protein can refer to plant based protein or to animal based protein or a combination thereof. In an embodiment, the food product is an animal protein product and the food protein value chain is an animal protein value chain. However, in another embodiment, the food product is a plant protein product and the food protein value chain is a plant protein value chain. Moreover, in an embodiment, the food product can also be a combination of an animal protein product and a food protein product and the value chain can be a respective combination of an animal protein value chain and a plant protein value chain.

[0010] The environmental impact that is assessed can be any environmental impact, for example, can be a carbon footprint, a general emission footprint, a land use, an energy consumption, water use, etc. In an embodiment, the environmental impact refers to a carbon footprint that can be defined as an amount of greenhouse gases emitted or removed in the production process of the food product through the complete food product value chain or only through parts of the food protein value chain, for instance, at one production facility participating in the food protein value chain.

[0011] Product data can refer to any data that is associated with the food product in the food protein value chain. In particular, the product data can comprise production data and / or environmental impact data. Production data refers to data that is collected from a food protein value chain process in order to monitor and / or optimize a production. For example, the production data can include data on fertilizers, plant protection, soil quality and type, crop yields, water usage, feed quality, feed quantity, additives, animal type, animal number, energy consumption, final product, and production rates. Production data is collected and used to track performance and identify areas for improvement to increase efficiency and reduce costs of a specific production step in the food protein value chain. Environmental impact data refers to data that is collected to assess the environmental impact of practices in the food protein value chain. The environmental impact data can include, for instance, data on greenhouse gas emissions, water usage, soil erosion, nutrient runoff, energy consumption, and waste production. Environmental impact data is used to identify the environmental impact of at least a part of the food protein value chain and to develop strategies for reducing negative impacts and promoting sustainability. In the food protein value chain, both production data and environmental impact data can be utilized for optimizing production processes and promoting sustainability. By collecting and analyzing this type of data, the participants of the food protein value chain can make informed decisions about how to manage their resources and reduce the environmental impact while maintaining or improving the yields.

[0012] A digital representation of the product data can refer to any kind of digital representation that comprises the information provided by the product data. In particular, the digital representation can refer to any digital format, type or structure. For example, a digital representation of energy consumption data can refer to an image of a scan of an electricity bill. In another example, a digital representation of temperature sensor measurements can refer to time series data containing the measurements of the sensor together with respective time stamps and sensor identifiers. Thus, a digital representation generally allows to represent the real-world information provided by the data in a digital environment such that it can be processed by digital processes.

[0013] Structured data comprises organized data, in particular, categorized data. Categorized data is associated with one or more predetermined categories. The data can be categorized based on the content with which the data is associated and / or based on the data itself. Structured data refers to data that is organized in a specific format that is easily searchable and can be processed by computers. Structured data is typically organized into tables, fields and records and is often stored in databases or spread sheets. Structured data has a defined and consistent format, making it easy to analyze and manipulate using respective software tools. Unstructured data comprises unorganized data, in particular, uncategorized data. Unstructured data refers to data that does not have a specific format and is not easily searchable or processed by computers. Unstructured data can take many forms, including physical documents, text files, images, audio and video files, social media posts and e- mails. Unstructured data is often stored in a variety of different locations and formats, making it difficult to analyze and manipulate without specialized tools. Thus, structured data comprises already categorized data and unstructured data comprises not yet categorized data. A participant of the food protein value chain can be any participant that performs a process or produces a product that is part of the food protein value chain. The participant has access to the respective product data produced during the process or production that the participant of the food protein value chain performs, wherein in most cases the product data in the digital domain will take a digital representation that includes both structured data and unstructured data. For example, the participant might receive structured data from a temperature sensor and at the same time receive a PDF containing an electricity bill as an unstructured data. In this example, both data contain information about energy consumption and environmental impact of the process or production performed by the participant and can thus be of interest for an environmental impact assessment.

[0014] The method comprises receiving, at a respective environmental impact assessment system, a digital representation of the product data from the participant via a participant node. The participant node can be any computational environment that allows a participant to access and upload the respective digital representation of the product data to the environmental impact assessment system. For example, the participant node can be realized in form of a smartphone, tablet, laptop, personal computer or any other computational hardware or computational interface. The receiving can then refer, for instance, to receiving an upload of the respective product data but also to accessing a respective storage unit on which the uploaded product data has been stored.

[0015] The environmental impact assessment system is then configured to perform the next step of the method of extracting the information included in the digital representation of the product data from the digital representation. Extracting the information included in the digital representation of the product data can include identifying the respective data content and making the identified data content available for further processing. In case of structured data, this process can simply refer to identifying the format of the structured data and, if necessary, converting the respective format to a format that allows to directly access the content for further processing by the environmental impact assessment system. In case of unstructured data, the extracting can comprise more complex processing steps. For example, the extracting can comprise identifying a respective data source and format, analyzing the respective digital representation with digital tools predefined for this data format and extracting the information provided such that the content of the unstructured data is directly accessible for the environmental impact assessment system. For example, if the unstructured data refers to an image or a PDF of a text document, the extracting of the information can refer to performing an optical character recognition and a natural language processing to make the text information provided by the PDF or image available for further processing. Moreover, this can be followed by utilizing a predefined content recognition that allows to identify predefined relevant content. For example, the content recognition can identify predefined keywords and respectively associated information.

[0016] Further, the method then comprises deploying a data normalization function to the extracted information to generate structured product data, wherein the data normalization function is configured to reorganize the extracted information to remove or reformat unstructured data to generate structured data. For example, the data normalization function can be configured to utilize the extracted information, for example, identified data content and categories, to transform the information into data in a standardized format. For instance, after the information provided by an electricity bill digitally represented as an image or a PDF, has been extracted by making the information accessible and categorizing the information into respective predetermined categories, the data normalization function can utilize the information and the categories to sort the data into a table format comprising for this example an electric energy consumption associated with a respective value. Moreover, the data normalization function can utilize a predetermined data format with predetermined data fields in order to sort the respective information into the different data fields generating a standardized format for the generated structured data.

[0017] The method then comprises applying an environmental impact assessment generation function to the structured product data to generate assessment data indicative of an environmental impact assessment of a product. The utilized impact assessment generation function can be configured to utilize known physical relationships, predetermined rules and other functional relationships to utilize the product data information provided in the structured product data to generate assessment data. In particular, a mass balance for predetermined substances can be utilized for determining the amount of a substance emission relevant for an environmental impact. Also functions determined by official regulations and laws can be utilized for specific aspects of an environmental impact assessment. Moreover, the environmental impact assessment generation function can also refer to a machine learning algorithms that is trained based on historical product data and respective environmental impacts. Utilizing a machine learning algorithm can for example decrease the number of parameters that have to be provided as input. The specific environmental impact assessment generation function utilized can depend on the respective information available. For example, if the participant is a farmer, other information is available than if the participant is a food product producer or a vendor of food products. Moreover, also for participants belonging to the same category, for instance, farmers, different information can be available. Thus, the environmental impact assessment generation function can comprise different parts and aspects that are only utilized for the environmental impact assessment if the respective information to which they refer is available. The structured product data allows in this case for a fast assessment which information is available and thus which environmental impact assessment generation function can be utilized based on the available information. The environmental impact assessment generation function then generates assessment data that is indicative of an environmental impact assessment of the product. For example, the assessment data can refer to one or more values of respective environmental impact metrics. In one example, the environmental impact assessment can refer to the value of a carbon footprint of the product. Moreover, the assessment data can also comprise more information than the simple environmental impact metric. For example, the assessment data can also comprise an analysis on the main sources of the respective environmental impact. Thus, the assessment data can be utilized for controlling and / or monitoring at least a part of a production process of the participant in the food protein value chain. The assessment data can then be provided by the environmental impact assessment system to the participant via the respective participant node. For example, a carbon footprint value can be provided to the participant via a connection to a smartphone of the participant.

[0018] In an embodiment, the method further comprises verifying the structured product data with the participant to generate verified structured product data and continuing the method with the verified structured product data. For example, the generated structured product data can be provided via the participant node to the participant, for instance, can be displayed on a respective display of a user interface provided by the participant node, and the participant can accept, correct or refuse the structured product data or parts of the structured product data for verifying the structured product data. Accordingly, it can be ensured that for the further processes only structured product data is utilized that has been verified by the participant and thus can be regarded as being correct.

[0019] In an embodiment, extracting the information from the digital representation includes classifying the extracted information into one or more predetermined product data types and the data normalisation function is configured to remove or reformate the extracted information based on the respective product data type to produce the structured product data. The product data types can, for instance, be based on the product data source, the product data content, a participant providing the product data, etc. The classification of the digital representation into the respective product data types then allows to provide the different data normalization functions for the different product data types. For example, if a digital representation of an electricity bill is classified in the product data type bills for energy consumption, the data normalization function can be configured specifically for the content of this kind of product data type. For instance, specific predetermined keywords, values, text format schemes, etc. are expected for this kind of product data type and can be utilized by the data normalization function to remove or reformat the extracted information.

[0020] In an embodiment, the generating of the structured product data further comprises processing the product data to remove duplicates, correct errors, and / or add missing information. This processing can be performed when extracting the information and / or when deploying the data normalization function. For example, if in the same document the same information is provided twice, the duplicate of the information can be removed at each stage of the processing of the product data into structured product data. Errors can be corrected, for instance, by utilizing a correction function that can detect obvious errors and, if possible, correct the respective obvious errors. An example of a detection of an obvious error could be the comparing of extracted values with predefined expected values stored on a database, wherein, if the values deviate from the expected value above a predetermined limit, a respective error can be detected. A correction of such an error can then, for instance, depend on respective rules that can, for instance, determine that instead of the erroneous value the respective expected value is utilized. However, error correction can also refer to making an operator aware of the error and requesting a respective correction action. Missing information can be added, for instance, by utilizing a respective information model depending on the respective expected information content. For example, databases can be accessed by the information model to find the missing information, for instance, in previous product data of the participant, in the product data of other similar participants or in a generated database. Moreover, the missing information can also be noted to the participant via the participant node and the participant can be requested to add the missing information. Also machine learning algorithms can be utilized, that are trained to provide missing information based on the present information. For example such machine learning model can be trained based on the product data of a plurality of participants to identify and determine respective missing data.

[0021] In an embodiment, the receiving of the digital representation comprises assisting the participant in providing the digital representation of the product data using a guided data entry process. The assisting of the participant can be realized, for instance, by providing a respective user interface that provides the participant with respective information on which and how to provide the digital representation of the product data. For example, the assisting can comprise requesting specific information and informing the participant how the information can be entered. To provide the information, the participant can then choose the respective suitable way to enter the information. For example, it can be requested from a user to provide information on an energy consumption and different possibilities of providing this information can be provided to a user. The user can then select to provide this information by scanning or photographing his / her electricity bill and additionally forwarding the measurement data of a temperature sensor, wherein in other cases the participant can select to directly enter the information from the electricity bill into respective data fields. Preferably, the assisting of the participant includes causing the participant to provide meta product data indicative of the type of product data to be entered by the user and selecting an entry module for guided data entry from a plurality of predefined entry modules based on the meta product data, wherein the entry module is configured to guide the entry of the product data for the specific product data type indicated by the meta product data. The meta product data is indicative of the type of product data to be entered by the user and can refer, for instance, to a selection provided to the user, from which the user can select the respective product data type to which the product data the participant is about to enter refers. For example, a selection point can refer to energy consumption data and the participant can select this selection point when wanting to provide product data that refers to an energy consumption, for instance, electricity bill data or temperature data. Meta product data can also refer to a format in which the participant is about to enter the respective product data. For example, the user can indicate as meta product data that the product data to be entered is provided in form of a PDF or JPEG image. A respective entry module can then be selected that allows to guide the user through the entry process of the selected product data type. Preferably, the entry module can comprise an entry template allowing for a structured entering of the product data. An entry template in this case refers to a data structure that can be represented such that a user can enter missing information into the data structure such that the missing information directly is associated with the respective content and thus allows for a direct structuring of the entered product data.

[0022] In an embodiment, the data normalisation function is part of an Application Program Interface (API), and the data normalisation function generates the structured product data according to a data model of the API. An application programming interface refers to a software interface that regulates and defines the communication and data utilization between different computer programs. Thus, an API can provide a regulated and defined access to functions and data of a computer program by another computer program. A data model of the API refers to a definition on how information and data is stored and retrieved in communication with and by the API. For example, the data model can define a data format, communication protocol, data structure, etc. that can be utilized in communication with the API. Preferably, the data model defines at least one of a structure, a format and a data type of the generated structured product data. In a preferred example, the data model defines at least one of a structure, a format and a data type of the generated structured product data. In a further aspect, an apparatus is presented for data processing for an environmental impact assessment in a food protein value chain, wherein the apparatus comprises an API configured for a) receiving, at an environmental impact assessment system, a digital representation of product data associated with a food product in the food protein value chain from a participant of a food protein value chain, wherein the digital representation includes both structured data and unstructured data, b) extracting the information included in the digital representation of the product data from the digital representation and deploying a data normalisation function to the extracted information to generate structured product data, wherein the data normalization function is configured to reorganize the extracted information to remove or reformat unstructured data to generate structured data, c) applying an environmental impact assessment generation function to the structured product data to generate assessment data indicative of an environmental impact assessment of the product, d) providing the assessment data to the participant.

[0023] In a further aspect, a computer program product is presented for data processing for an environmental impact assessment in a food protein value chain, wherein the computer program product causes an apparatus as described above to perform the method as described above when carried out on the apparatus.

[0024] It shall be understood that the method as described above, the apparatus as described above, and the computer program product as described above have similar and / or identical preferred embodiments, in particular, as defined in the dependent claims.

[0025] It shall be understood that a preferred embodiment of the present invention can also be any combination of the dependent claims or above embodiments with the respective independent claim.

[0026] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter.

[0027] BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Fig. 1 shows schematically and exemplarily application principles of a method utilized by a digital environmental impact assessment system,

[0029] Fig. 2 shows schematically and exemplarily a method for data processing for an environmental impact assessment in a food protein value chain, Fig. 3 shows schematically and exemplarily embodiments of a method for assisting a participant in providing a digital representation of product data,

[0030] Fig. 4 shows schematically and exemplarily functions of an API utilized by an environmental impact assessment system,

[0031] Fig. 5 shows schematically and exemplarily a data layer structure of an environmental impact assessment system, and

[0032] Fig. 6 shows schematically and exemplarily a decentralized database structure for a food protein value chain,

[0033] Figs. 7a, b show schematically and exemplarily product data utilized by the environmental impact assessment system.

[0034] DETAILED DESCRIPTION OF EMBODIMENTS

[0035] Fig. 1 shows schematically and exemplarily product data received by a digital environmental impact assessment system utilized for assessing an environmental impact of a food product in a food protein value chain. In the example shown in Fig. 1 , the food protein product refers to an animal protein product, for instance, based on the product produced by different animals, like meat, eggs, or milk. Thus, in this case, the participant of the food protein value chain is a farm utilizing the respective animals to produce the animal protein products. During the production of the animal protein products, a plurality of product data is generated by the farm. The product data can comprise production data and / or environmental impact data. Moreover, the product data can be acquired in form of structured but also in form of unstructured data. For example, sensor data from sensors provided in the environment of the animal protein product production can refer to structured data whereas data produced in the context, for instance, of the production management like bills, orders, animal monitoring data, etc. is often provided in an unstructured manner, for instance, as PDF, JPEG or a text document. The structured and unstructured product data can then be provided through a plurality of sensor hubs that can be managed, for instance, by a participant node to the digital environmental impact assessment system. For example, the points shown in Fig. 1 can refer to sensors in the production site of the animal protein product providing product data directly to the digital environmental impact assessment system or optionally via a participant node. The schematically shown smartphone and laptop represent sensor hubs that allow, for instance, to gather unstructured data like text documents, images or PDFs that can then be provided to the environmental impact assessment system also optionally via a participant node. An example of the process shown in Fig. 1 could be a farmer that can provide both structured and unstructured data for a digital environmental impact calculation. An example for the structured data can be data from a measurement with a near infrared spectroscope. Unstructured data can include images of documents like an electricity bill captured by a camera on a cell phone. The farmer can then use a personal computer to gather the structured and unstructured data and provide it to the digital environmental impact assessment system. For example, the farmer can provide the data via a file upload, an application programming interface, a batch processing, a streaming, or any other data transfer mechanism.

[0036] Fig. 2 shows schematically and exemplarily an embodiment of a method for data processing for an environmental impact assessment in a food protein value chain. The method 200 comprises in a step 205 receiving at a digital environmental impact assessment system product data from a participant in a food protein value chain. The product data can comprise both production data and environmental impact data and further can be provided in the form of structured data and unstructured data as exemplarily explained with respect to Fig. 1. In step 210, the method 200 comprises extracting the information included in the digital representation of the product data from the digital representation. Further, the step 210 comprises deploying a data normalization function to the extracted information to generate structured product data, wherein the data normalization function is configured to reorganize the extracted information to remove or reformat unstructured data. In optional step 215, the structured product data can be verified with the participant of the food protein value chain. Moreover, in optional step 220 it can also be determined if data updates have been received with respect to the structured product data. If respective data updates have been received, in step 225 the structured product data can be corrected. If no data updates have been received, the method can directly go to step 230. In particular, the steps 215, 220 and 225 can also be omitted and the method can directly go from step 210 to step 230. In step 230, the verified structured participant data or, if the step of verification has been omitted, the structured product data can be utilized in an environmental impact assessment calculation function to generate a digital participant environmental impact result as part of assessment data indicative of an environmental impact assessment for the product of the participant. In step 235, the assessment data can then be transmitted to the participant of the food protein value chain and the participant can utilize the assessment data to control and / or monitor a production process of the food product of the participant.

[0037] The method 200 can be performed by the digital environmental impact assessment system.

[0038] In particular, the digital environmental impact assessment system can extract the product data and apply the data normalization function to produce a structured participant data. The data extraction can include, for instance, identifying relevant data sources, selecting appropriate data fields and categories and using software tools to extract and transform the data into a standardized format. This can include cleaning and processing the data to remove duplicates, correct errors and / or fill in missing information. The data normalization function can be configured to organize unstructured or semi-structured data into a respective predefined standardized format that can be analyzed and manipulated more easily. For example, the data normalization function can identify the relevant data fields and categories and convert the information into a consistent data format that can be processed by other software tools. Also this process can involve cleaning and processing the data to remove duplicates, correct errors and fill in missing information.

[0039] Fig. 3 shows schematically and exemplarily different possibilities for a participant of the food protein value chain to provide product data to the environmental impact assessment system. In particular, the environmental impact assessment system can be configured to offer at least one or more preferably both methods to a participant who wants to provide the data to the environmental impact assessment system. In the example shown in Fig. 3, the participant is a farmer, however, the participant can also be any other participant of the food protein value chain. In the first embodiment shown in the upper part of Fig. 3, the environmental impact assessment system and the environmental impact assessment method are configured to enable the participant, here the farmer, to provide both structured and unstructured data, for instance, via a participant node, to the environmental impact assessment system. In this embodiment, for example, a participant requesting an environmental impact assessment for his food product can be prompted by utilizing a user interface of the environmental impact assessment system, like an app running on the participant node connected to the environmental impact assessment system, to input relevant data for the environmental impact assessment. In particular, in this example, the user interface can prompt the participant to input all available environmental impact relevant data regardless of its structural format, such that it can form a mix of structured and unstructured data. As described, for instance, in the exemplary method shown in Fig. 2, the environmental impact assessment system can be configured to then extract and structure the received mix of structured and unstructured data such that it can be utilized for the environmental impact assessment. Moreover, it can optionally also provide the generated structured data, for instance, via the participant node and user interface, again to the participant for verification or for receiving possible updates on the data. After having received the feedback to the generated structured data from the participant via the participant node, the respective optionally updated and verified generated structured data can then be provided as input for the environmental impact assessment function. The results of the respective environmental impact assessment can then be provided as assessment data to the participant again via the user interface and the participant node, wherein the participant can then utilize the assessment data, for instance, to improve the environmental impact on the food production.

[0040] In a second embodiment that can additionally or alternatively be provided by the environmental impact assessment system, the system is configured to provide assistance to the participant in the providing of the product data using a guided data entry. For example, again, a user interface can be provided on a participant node that can guide the user through the respective data entry steps. Also for this embodiment, the participant can enter structured and unstructured data. However, the part of the product data that is unstructured can be minimized by the guided data entry. In this embodiment, the user interface can be configured to provide the participant with an option to first enter meta product data indicative of the type of product data to be entered by the user. For example, the meta product data can referto the scope, the parameters to enter, the type of data to be entered, the role of the participant in the food protein value chain, etc. Based on the meta data, the environmental impact assessment system can be configured to select an entry module for the guided data entry, for instance, from a plurality of predefined entry modules, that is most suitable for the entry of the data indicated by the meta data. The respective entry module is then configured to get the entry of the product data for the specific product data type or types indicated by the meta product data. For example, the module can provide a respective template into which the data can be entered. Thus, the environmental impact assessment system allows to provide a customized data entry flow based on the data that the user wants to enter into the environmental impact assessment system.

[0041] In both embodiments, the environmental impact assessment system can be configured to recognize missing product data that is necessary for the environmental impact assessment as impact to the respective environmental impact assessment function. Recognizing missing data the environmental impact assessment system can be configured to prompt a user, for instance, via the participant node and the user interface, to insert the respective missing data. Additionally or alternatively, the environmental impact assessment system can be configured to utilize default data that can be predefined to replace missing data. Moreover, instead of default values also respective data values from third parties can be utilized for replacing the missing data. For example, respective product data from other participants that fulfil a predefined similarity criterion, for instance, have the same role in the food protein value chain, can be utilized. In another example, the product data can be based on scientific research or third party observations available for the respective missing product data. Fig. 4 shows schematically and exemplarily an embodiment of the environmental impact assessment system and / or method in which an API is utilized and the data normalization function is part of the API. In particular, the API of the environmental impact assessment system can be configured to provide a data model that defines a structure, format and data type not only for communication with the API but also for the generated structured product data. The API utilizing the data model is configured to enable the collection of product data but also of any other sustainability information from a plurality of different sources and participants in the food protein value chain. The data model can be defined for each source or can be generally defined and provides predetermined rules for the processing of the product data received from a respective data source. The definition with respect to each source and the respective rules can be set by a respective operator or can be set automatically, for instance based on a predetermined default. For example, the API and the utilized data model can be generalized for the food protein value chain such that it allows to receive GET / POST calls from different participants and provide respective requested data and response. Moreover, the API utilizing the data model can be configured to store, collect, manipulate and forward all received data, for instance, product data, such that it can be utilized by the environmental impact assessment function. For example, the API can utilize the data normalization function to structure received structured and unstructured data. Further, the API can be configured to unify and / or process received data, for instance, product data, in a predetermined way. For example, data that comes from different sources can be structured, unified and processed such that the data can be utilized in an environmental impact assessment utilizing the environmental impact assessment function. Another example is the conversion and unification of units, for instance, the conversion from a value in miles to a value in kilometres. Further, the API can be configured to perform the extraction of relevant data, for instance, can extract data that is relevant for the environmental impact assessment. An example would be that the API is configured to extract from an energy bill the exact amount of energy needed to produce the food product on the farm while ignoring all other energy consumers, for instance, the energy consumed by the private house of the farmer. Additional possible functions of the API shown, for instance, in Fig. 4, can also refer to retrieving of the environmental impact, for instance, a carbon footprint from the environmental impact assessment function or system performing the function to be provided to the respective participant node. Moreover, the API can be configured to provide a certification function that allows for a certification of data, either input data but also output data, for instance, the assessment data and the calculated environmental impact. Moreover, the API can provide a graphical representation function that allows to graphically represent the data in- and outputs. Further, the API can provide service functions forthe participant like providing a modelling for a carbon market or managing and monitoring transaction data. Fig. 5 shows schematically and exemplarily data levels of the environmental impact assessment system. In this figure, the environmental impact assessment system is schematically shown in the middle comprising, referred to as rule base, the environmental impact assessment function that can be utilized for the environmental impact assessment. However, additionally, the environmental impact assessment system can comprise data processing parts that can be configured for data receiving, aggregation and consolidation such that the data can then be utilized by the rule base, in particular, by the environmental impact assessment function. In particular, at least a part of data processing part refers to an API utilizing a data model, for example, as described above. On the left side, as first level, different possible data sources and formats are exemplarily shown that can be provided as input to the environmental impact assessment system. For example, the data represented on the left side can refer to manual input data, excel upload data, third party application data, literature data, etc. This data can referto product data which can comprise production data and also environmental impact data. The data utilized by the environmental impact assessment system can come from databases shown, for instance, forthe upperthree data sources but can also come from individual sources, for instance, a participant node, as shown for the lower four examples. The environmental impact assessment system then utilizes, for instance, an API, and a data model that allows to represent the received data that is exchanged between the API and the respective data sources. For example, the data model can define the structure, format and data type of the information that is exchanged utilizing the API. The API itself can be utilized as an interface that allows participants to access the environmental impact assessment system, for instance, its provided databases and functionalities that are provided on one or more respective servers. The API then defines the operations that the respective participants can perform and the data that they can access or modify. The relationship between the data model utilized by the API and the API can be regarded such that the data model defines the structure and format of the data that is exchanged through the API, while the API provides the interface for the participants to access that data and perform operations on it. Thus, the data model can be regarded as a component of the API that ensures that the data exchange between the participant, for instance, the participant node, and a server, is consistent and interoperable. In an example embodiment, the data model can be based on an XML file or a similar specification that defines for different data types the structure and format with which the data types can be exchanged with the environmental impact assessment system.

[0042] Fig. 6 shows schematically and exemplarily a decentralized data structure of the food protein value chain, wherein each of the respective databases 2200, 2202 and 2208 can be a source for product data or other information that can be usable forthe environmental impact assessment of s food product. Moreover, the environmental impact assessment system can be configured to store at least some of the environmental impact assessment data one or more of the respective databases 2200, 2202 and 2208 based on an ID of a food protein product or a chain of associated food protein product IDs. A food product or an intermediate ingredient 2720, e.g. a feed mix, arriving at a respective facility of a participant 220 can be identified. For example, a physical identifier, like a QR code can be scanned utilizing scanner 2206 and associated with a digital identifier. Based on the received intermediate ingredient or final food product 2720 utilizing the determined identifier 2222 a request to access product or environmental impact data associated with the intermediate ingredient or final food product can be triggered by a data consuming service 2210 of a participant. For example, the identifier may be provided 2212 to a data providing service 2205 associated with or of the producer of the intermediate ingredient or final food product. In addition, authentication and / or authorization information may be provided. The environmental impact data or assessment data associated with the intermediate ingredient or final food product can then be assessed via the identifier 2218 in the database 2202 of the producer. The database 2202 is a database associated with the producer and data owner of the intermediate ingredient or final food product. The one or more environmental impact data can refer to a product carbon footprint, N2, water consumption, recycled content or bio-based content and can be stored in database 2202 associated with the producer of the intermediate ingredient or final food product, e.g., feed mix, feed supplement, final food product e.g., a package of milk, eggs, meat, sausage, pizza, and the identifier. The associated data can then be provided via the data providing service 2205 to the data consuming service 2210 as signified by arrows 2220, 2216. The environmental impact data associated with the intermediate ingredient or final food product can then be stored in the data base 2208 associated with the user of the intermediate ingredient or final food product, e.g., a farm using the feed mix, as signified by arrow 2222.

[0043] Figs. 7a and 7b show schematically and exemplarily product data that can be utilized for an environmental impact assessment. In the first row of the tables the parameter name is provided. The following rows indicate a status of the parameter and typical or alternative sources. For example, a mandatory parameter is a parameter that in this example is necessary for the environmental assessment in this example case and thus has to be provided by the participant, if possible. Default values can be either set based as default, for instance, as an average from other data sources or from literature, or can be set to a specific value is available for the participant. Background values can be utilized, if available, but are only relevant for specific assessments or improvement goals. The data type and possible sources can, for instance, be defined in the data model. Generally, it is preferred that as many parameters as possible are provided by the participant to tune the assessment specifically to the production process of the participant. However, except of the mandatory parameters all other parameters utilized for the environmental impact assessment can be set to a default value. Generally, for other cases and environmental impact assessments also different parameter sets can be defined.

[0044] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.

[0045] For the processes and methods disclosed herein, the operations performed in the processes and methods may be implemented in differing order. Furthermore, the outlined operations are only provided as examples, and some of the operations may be optional, combined into fewer steps and operations, supplemented with further operations, or expanded into additional operations without detracting from the essence of the disclosed embodiments.

[0046] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0047] A single unit or device may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0048] Procedures like the receiving of product data, the extracting of information, the applying of an environmental impact assessment function, the providing of assessment data, etc. performed by one or several units or devices can be performed by any other number of units or devices. These procedures can be implemented as program code means of a computer program and / or as dedicated hardware.

[0049] A computer program product may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

[0050] Any units described herein may be processing units that are part of a classical computing system. Processing units may include a general-purpose processor and may also include a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or any other specialized circuit. Any memory may be a physical system memory, which may be volatile, non-volatile, or some combination of the two. The term “memory” may include any computer-readable storage media such as a non-volatile mass storage. If the computing system is distributed, the processing and / or memory capability may be distributed as well. The computing system may include multiple structures as “executable components”. The term “executable component” is a structure well understood in the field of computing as being a structure that can be software, hardware, or a combination thereof. For instance, when implemented in software, one of ordinary skill in the art would understand that the structure of an executable component may include software objects, routines, methods, and so forth, that may be executed on the computing system. This may include both an executable component in the heap of a computing system, or on computer- readable storage media. The structure of the executable component may exist on a computer-readable medium such that, when interpreted by one or more processors of a computing system, e.g., by a processor thread, the computing system is caused to perform a function. Such structure may be computer readable directly by the processors, for instance, as is the case if the executable component were binary, or it may be structured to be interpretable and / or compiled, for instance, whether in a single stage or in multiple stages, so as to generate such binary that is directly interpretable by the processors. In other instances, structures may be hard coded or hard wired logic gates, that are implemented exclusively or near-exclusively in hardware, such as within a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or any other specialized circuit. Accordingly, the term “executable component” is a term for a structure that is well understood by those of ordinary skill in the art of computing, whether implemented in software, hardware, or a combination. Any embodiments herein are described with reference to acts that are performed by one or more processing units of the computing system. If such acts are implemented in software, one or more processors direct the operation of the computing system in response to having executed computer-executable instructions that constitute an executable component. Computing system may also contain communication channels that allow the computing system to communicate with other computing systems over, for example, network. A “network” is defined as one or more data links that enable the transport of electronic data between computing systems and / or modules and / or other electronic devices. When information is transferred or provided over a network or another communications connection, for example, either hardwired, wireless, or a combination of hardwired or wireless, to a computing system, the computing system properly views the connection as a transmission medium. Transmission media can include a network and / or data links which can be used to carry desired program code means in the form of computer-executable instructions or data structures and which can be accessed by a general-purpose or specialpurpose computing system or combinations. While not all computing systems require a user interface, in some embodiments, the computing system includes a user interface system for use in interfacing with a user. User interfaces act as input or output mechanism to users for instance via displays.

[0051] Those skilled in the art will appreciate that at least parts of the invention may be practiced in network computing environments with many types of computing system configurations, including, personal computers, desktop computers, laptop computers, message processors, hand-held devices, multi-processor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, mobile telephones, PDAs, pagers, routers, switches, datacenters, wearables, such as glasses, and the like. The invention may also be practiced in distributed system environments where local and remote computing system, which are linked, for example, either by hardwired data links, wireless data links, or by a combination of hardwired and wireless data links, through a network, both perform tasks. In a distributed system environment, program modules may be located in both local and remote memory storage devices.

[0052] Those skilled in the art will also appreciate that at least parts of the invention may be practiced in a cloud computing environment. Cloud computing environments may be distributed, although this is not required. When distributed, cloud computing environments may be distributed internationally within an organization and / or have components possessed across multiple organizations. In this description and the following claims, “cloud computing” is defined as a model for enabling on-demand network access to a shared pool of configurable computing resources, e.g., networks, servers, storage, applications, and services. The definition of “cloud computing” is not limited to any of the other numerous advantages that can be obtained from such a model when deployed. The computing systems of the figures include various components or functional blocks that may implement the various embodiments disclosed herein as explained. The various components or functional blocks may be implemented on a local computing system or may be implemented on a distributed computing system that includes elements resident in the cloud or that implement aspects of cloud computing. The various components or functional blocks may be implemented as software, hardware, or a combination of software and hardware. The computing systems shown in the figures may include more or less than the components illustrated in the figures and some of the components may be combined as circumstances warrant.

[0053] Any reference signs in the claims should not be construed as limiting the scope. The invention refers to a method for data processing for an environmental impact assessment in a food protein value chain. At an environmental impact assessment system, a digital representation of product data associated with a food product in the food protein value chain is received from a participant of a food protein value chain. The digital representation includes both structured data and unstructured data. The information included in the digital representation of the product data is extracted a data normalisation function is deployed to the extracted information to generate structured product data. The data normalization function is configured to reorganize the extracted information to remove or reformat unstructured data to generate structured product data. An environmental impact assessment gen- eration function is applied to the structured product data to generate assessment data indicative of an environmental impact assessment of the product and the assessment data is provided to the participant.

Claims

Claims:1 . A computer implemented method for data processing for an environmental impact assessment in a food protein value chain, wherein the method comprises: receiving, at an environmental impact assessment system, a digital representation of product data associated with a food product in the food protein value chain from a participant of a food protein value chain, via a participant node, wherein the digital representation includes both structured data and unstructured data, extracting information included in the digital representation of the product data from the digital representation and deploying a data normalisation function to the extracted information to generate structured product data, wherein the data normalization function is configured to reorganize the extracted information to remove or reformat unstructured data to generate structured product data, applying an environmental impact assessment generation function to the structured product data to generate assessment data indicative of an environmental impact assessment of the product, providing the assessment data to the participant via a participant node.

2. The method according to claim 1 , wherein the method further comprises verifying the structured product data with the participant to generate verified structured product data and continuing the method with the verified structured product data.

3. The apparatus according to any of the preceding claims, wherein extracting the information from the digital representation includes classifying the extracted information into one or more predetermined product data types and the data normalisation function is configured to remove or reformate the extracted information based on the respective product data type to produce the structured product data.

4. The method according to any of the preceding claims, wherein the generating of the structured product data further comprises processing the product data to remove duplicates, correct errors, and / or add missing information.

5. The method according to any of the preceding claims, wherein the receiving of the digital representation comprises assisting the participant in providing the digital representation of the product data using a guided data entry.

6. The method according to claim 5, wherein the assisting of the participant includes causing the participant to provide meta product data indicative of the type of product data to be entered by the user and selecting an entry module for guided data entry from a plurality of predefined entry modules based on the meta product data, wherein the entry module is configured to guide the entry of the product data for the specific product data type indicated by the meta product data.

7. The method according to claim 6, wherein the entry module comprises an entry template allowing for a structured entering of the product data.

8. The method according to any of the preceding claims, wherein the data normalisation function is part of an Application Program Interface (API), and wherein the data normalisation function generates the structured product data according to a data model of the API.

9. The method according to claim 8, wherein the data model defines at least one of a structure, a format and a data type of the generated structured product data.

10. The method according to any of claims 8 and 9, wherein the data model defines at least one of a structure, a format and a data type of the generated structured product data.11 . The method according to any of the preceding claims, wherein the food product is an animal protein product and the food protein value chain is an animal protein value chain.

12. An apparatus for data processing for an environmental impact assessment in a food protein value chain, wherein the apparatus comprises an API configured for: receiving, at an environmental impact assessment system, a digital representation of product data associated with a food product in the food protein value chain from a participant of a food protein value chain, wherein the digital representation includes both structured data and unstructured data,extracting information included in the digital representation of the product data from the digital representation and deploying a data normalisation function to the extracted information to generate structured product data, wherein the data normalization function is configured to reorganize the extracted information to remove or reformat unstructured data to generate structured data, applying an environmental impact assessment generation function to the structured product data to generate assessment data indicative of an environmental impact assessment of the product, providing the assessment data to the participant.

13. A computer program product for data processing for an environmental impact assessment in a food protein value chain, wherein the computer program product causes an apparatus according to claim 12 to perform the method according to any of claims 1 to 10 when carried out on the apparatus.

Images