Method and system for analysing and outputting data of a machine line

Abstract

One embodiment of the invention relates to a method and a system for adapted output of data of a machine line, in particular in a machine line for bottling / boxing and packaging food and / or beverages. The machine line comprises a plurality of machines. A large language model, LLM, is implemented on an analysis module. A specific context for the LLM is defined that can define a restriction for an output from the LLM. A database for the LLM is defined that comprises state data and data of the machine line. In some embodiments, the database can also comprise data from similar machine lines and / or data of an external ecosystem. Following setup of the LLM, a user interface can be used to receive user queries for querying requested information relating to the machine line. The user query is input into the LLM and processed by the LLM on the basis of the defined specific context and on the basis of the database in order to determine the requested information.

Description

[0001] Method and system for analyzing and outputting data from a machine line

[0002] The invention relates to a method and a system for analyzing machine data and for outputting data from a machine line, in particular in a machine line for filling and packaging food and / or beverages, and to a machine line.

[0003] Today's filling and packaging systems in the beverage and liquid food industries are highly optimized and process up to 120,000 units per hour. A typical filling and packaging system typically comprises a multitude of different machines and modules connected by conveyor belts. The units, such as bottles, cans, pallets, containers, or similar, are transported from one machine to the next, passing through the individual machines on the line in a predetermined sequence.

[0004] During operation, such machine lines generate a significant amount of data. This data can contain important information about performance, availability, wear, maintenance, OEE, and the operating status of the machine line, among other things. Effective use of this data can help increase productivity, optimize maintenance, minimize downtime, minimize energy and media consumption, and improve the quality of the products produced. This data can, for example, present historical production data in a report, allowing users to analyze downtimes and errors and draw conclusions for production optimization.

[0005] Other services offer users the ability to visualize sensor and machine data and set up monitoring to detect anomalies (such as constantly increasing motor current).

[0006] Until now, this analysis of machine data was usually performed either manually or automated by specialized analysis systems. Manual analysis requires extensive knowledge and skills and is generally time-consuming and error-prone. Automated systems can improve efficiency, but their ability to perform complex analyses and deliver the information a user desires is often limited, requiring a high level of expert knowledge.

[0007] In addition, the information provided is often made available to users via a web portal. Users can navigate to the desired information and access prepared statistics, graphs, tables, or other data via the web portal. However, users are often forced to navigate through a large amount of generic data to find the information relevant to their specific needs.

[0008] Due to the multitude of customer requirements for visualizations and reports, many resources are invested in the development of such dashboards and front ends in order to ensure flexibility and variety.

[0009] It is therefore necessary to provide a more efficient way to deliver customized information to users. Users (even those with little expert knowledge) want information presented in an easily understandable way, want to know what went wrong and when, why it went wrong, and what measures need to be taken to ensure the machine line operates as optimally and smoothly as possible. Current reports and dashboards are merely a means to an end.

[0010] There is therefore a need for improved systems and methods for analyzing machine data and for the customized output of machine line data. Furthermore, there is a need for expanded data analysis that utilizes not only machine line data but also other data sources that do not primarily comprise machine line data.

[0011] The object is achieved according to the invention by a method according to claims 1, 5 and 8 and a system according to claim 9. Embodiments and further developments are covered in the subclaims.

[0012] One embodiment of the invention relates to methods for the customized output of data from a machine line, in particular in a machine line for filling and packaging food and / or beverages, as well as pharmaceutical products (primarily packaging). The machine line comprises a plurality of machines. A large language model (LLM) is implemented on an analysis module. A specific context is defined for the LLM, which can define a restriction for an LLM output. A database is defined for the LLM, which includes status data and data from the machine line. In embodiments, the database can also include data from similar machine lines and / or data from an external ecosystem. After the LLM has been set up, user requests for querying requested information regarding the machine line can be received via a user interface.The user request is entered into the LLM and processed by the LLM based on the specified specific context and based on the database to determine the requested information.

[0013] A further embodiment relates to a method in which status data, process data (e.g. containing performance, availability, wear, maintenance, OEE and the operating status of the machine line) and data from similar machine lines are used as an additional database for the LLM.

[0014] A further embodiment relates to a method in which machine line-independent data are used as an additional database for the LLM.

[0015] One embodiment of the invention relates to a system comprising an LLM, an analysis module and a user interface.

[0016] Exemplary aspects of the invention are illustrated in the drawings. They show:

[0017] Figure 1 : a diagram showing an overview of the essential elements and the basic structure of the invention;

[0018] Figure 2: a diagram showing a gradual adaptation of the large language

[0019] Model for use in a machine line;

[0020] Figure 3: an exemplary flow chart for a method for

[0021] Implementing a large language model and its operation in a machine line;

[0022] Figure 4: an exemplary system configuration for PET containers and

[0023] adhesive packaging;

[0024] Figure 5: an exemplary plant configuration for PET containers and

[0025] shrink packer;

[0026] Figure 6: an exemplary system configuration for cans or glass bottles; and

[0027] Figure 7: an example system configuration for cans.

[0028] Figure 1 is a diagram showing an overview of the essential elements and basic structure of the invention. These essential elements, according to one embodiment, comprise a machine line 100, an analysis module 110, and a user interface 120 in the analysis module 110, via which a user 130 can interact with the analysis module 110 and, if appropriate, also with the machine line 100. The machine line 100 can be, for example, a machine line for filling and packaging food and / or beverages, but is not specifically limited to such a line. Various exemplary embodiments of such a machine line 100 are shown and explained in Figures 4 to 7.

[0029] The analysis module 110 may be a single server, but may also consist of one or more computing devices that are communicatively connected directly or indirectly. As described in more detail below, the analysis module 110 may include a large language model (LLM) 200 and provide an interface between the LLM and a user interface 120. The analysis module 110 may be communicatively connected directly or indirectly to the machine line 100, such as via the data interface 125 of the analysis module 110. In some embodiments, an internet connection may exist between the analysis module 110 and the machine line 100, connecting them to each other, or there may also be a direct communication connection.

[0030] The user interface 120 allows a user 130 to interact with the analysis module 110. The user interface 120 can take any form suitable for a user to interact with a computer by means of inputs. The user interface is also referred to as a "human-machine interface" (HMI) and, in certain circumstances, allows the user 130 to observe the system status and intervene in the process beyond operating the machine line 100.

[0031] The user interface may be a simple computer, a mobile phone, a tablet, a special device of the machine line 100, a voice assistant, a computer application, a computer terminal or another computer-based device.

[0032] As already mentioned, a so-called large language model (LLM) can be implemented on the analysis module 110. Such large language models, or language models, are a type of artificial intelligence (AI) trained to understand and generate human language. They learn by analyzing large amounts of text data and recognizing patterns within it. This involves not only individual words and sentences, but also the context in which they are used. Special language models called "Transformers" can recognize more complex context and also learn to generate answers to questions, translate text, or even create graphics such as plots and diagrams. The well-known architecture called "Transformer," based on a method called "Attention," helps the language model understand the context of a word in relation to all other words in a text passage.

[0033] Such a neural transformer consists of several layers, each containing a set of neurons. Each layer and each neuron is adapted during the training process to better respond to the training data. The "depth" of the model (the number of layers) and the "width" (the number of neurons in each layer) determine the complexity of the patterns the model can recognize.

[0034] The training process requires a large amount of computing power and time, but once the model is trained, it can be used to generate or interpret text based on the patterns it has learned. Such LLMs are provided pre-trained by various vendors, allowing end users to use the "finished" LLMs.

[0035] Embodiments of the invention relate to the integration of such LLMs into a user platform. According to embodiments of the invention, the LLM 200 is adapted in a special way to provide the user 130 with requested data from the machine line 100. When adapting the LLM, security aspects and data transparency are taken into account to ensure that no false information is provided to the user.

[0036] This concept of adapting the LLM 200 is shown in more detail in Figure 2.

[0037] In addition to the essential elements mentioned above, Figure 1 shows further elements, such as one or more data stores 140a and 140b, an external database 150, and one or more additional machine lines 100b. The significance of these additional elements will be discussed later.

[0038] The architecture in Figure 2 is essentially the same as in Figure 1 and includes the machine line 100, the analysis module 110, and the user interface 120. The user interface 120 in Figure 2 is not shown as part of the analysis module 110 to emphasize that the user interface can also be accessed externally. Additionally, Figure 2 shows the adaptation of an LLM 200, which is implemented as an example on the analysis module 110.

[0039] The LLM 200 can be a general, fully trained LLM, which in its initial state may not have any advanced knowledge of the machine line 100 or the data produced by the machine line. It is therefore first necessary to give the LLM a context. The "general LLM" 200 thus becomes an "LLM with context" 200, as shown in Figure 2. The context can be specific to a very specific system configuration of the machine line 100 or specific to certain user groups. The specific context defines a restriction on the LLM output. Such restrictions can, for example, concern a form, a structure, a used information source, or a level of detail of the LLM output. Furthermore, the context can also include special instructions or guidance for calculating certain key figures or information.

[0040] To precisely define the context for the LLM, appropriate, specific textual instructions can be defined. These can also be user-specific (e.g., which content can be viewed by a customer, a plant manager, or a technician). This also defines the form and structure of the desired responses of the LLM.

[0041] In order to make it possible to find the cause of a particularly low value, for example, in the case of calculated key figures, the LLM can also be provided with facts about the calculation of the key figures and causal relationships.

[0042] Since the fully trained LLM "understands" and accepts human speech as input, the specific context can also be formulated as such a text input in one embodiment. Text input is also possible via voice input by user 130 speaking, as is voice output, preferably via user interface 120.

[0043] The context is supplied to the LLM 200, for example, by a manufacturer of the machine line 100. The context can be entered into the LLM 200 in such a way that it is not possible for a user 130 who later interacts with the LLM to change the context in such a way that restrictions defined by the context can be removed again.

[0044] However, with the "LLM with context" 200', specific questions about data from machine line 100 cannot yet be asked, since in a further step the data or status data from machine line 100 must first be entered into the LLM as sources.

[0045] The data 230 can, for example, be loaded directly from the machine line 100 into the analysis module 110 or can also be transferred to the analysis module 110 in a controlled manner by a third party. This data 230 can at least partially form the database for answering the questions by the LLM and can be directly collected or calculated key figures, sensor data, and / or machine data from the machine line 100 or individual machines in the machine line 100. An existing database can be used for this purpose, which also serves as a source for existing services. Specific examples of the database can be:

[0046] • Live production data in a machine line (incl. OEMs);

[0047] • Historical production data in a machine line (including OEMs);

[0048] • Condition monitoring data from machines and transporters;

[0049] • Performance data of the machine line and / or its machines and conveyors; and / or (e.g. OEE, machine availability, causes of production interruptions, OEE, unplanned downtimes and their top causes)

[0050] • Energy and media data of the machine line and / or its machines and conveyors; and / or

[0051] • Message data (e.g. current and historical faults, warnings, notices) -

[0052] • Existing SOPs (standard operating procedures) so that recommendations for action can be included in the response to a request, and / or

[0053] • Generated charts, diagrams, etc. to better understand answers in context.

[0054] Optionally, a PLM (Product Lifecycle Management) system can also be used as a database at the end user, for example, to incorporate maintenance plans into the response. An ERP (Enterprise Resource Planning) system can also be used by the end user, for example, to incorporate resource availability (personnel) into the response.

[0055] According to embodiments, the database can be further expanded to obtain a significantly deeper analysis of the machine line data. For example, data and operating data from similar machine lines can be used as an additional data source. This can enable benchmark analyses between multiple (similar) lines.

[0056] To enable this, the analysis module 110 can have access to a status database and machine data from a plurality of additional machine lines (e.g., machine line 100b in Figure 1) that match the machine line in at least one defined criterion. Thus, data and status data from similar machine lines can be used. Examples of such criteria can be a model series, a manufacturer, a packaging and / or filling technology, a specific type of machine, module or device, location data, and much more. The data of the at least one additional (i.e., similar) machine line can be retrieved by the analysis module 110, for example, directly from other machine lines, or the data is stored on one or more data storage devices 140 and stored centrally, for example.

[0057] The analysis module can analyze the data from similar machine lines 100b and compare it with the data from the user's machine line 130 to create conclusions and benchmark information.

[0058] The benchmark information is thus based on a comparison of data from the machine line with data from at least one similar machine line from the plurality of other machine lines. The benchmark information includes at least one condition monitoring, a cause of a production interruption, machine availability and / or unplanned downtimes and their causes, as well as energy and media consumption.

[0059] According to further embodiments, data / information from outside the machine system can also be used as a database. For this purpose, the analysis module 110 can have access to at least one database containing machine line-independent data. This combines an internal ecosystem (i.e., data from the machine line) with an external ecosystem to obtain significantly better analyses, forecasts, and action recommendations for the user 130. This makes it possible to provide a "global" context with important information. This overcomes the disadvantages of a limited context of data sources, which could lead to analyses / forecasts containing inaccuracies.

[0060] This external ecosystem of external data is shown in Figure 1 as external data 150. The machine-line-independent data 150 can include a variety of data originating from outside the machine line. For example, the machine-line-independent data 150 includes:

[0061] Data from material suppliers and / or manufacturers, in particular about containers, labels, syrup, and / or availability of materials, auxiliary and operating supplies, and / or spare parts;

[0062] Data from an energy supplier, in particular data on phases of time-dependent energy tariffs;

[0063] Data from a logistics company, in particular data from trucks for supply / disposal; data from a component supplier, in particular data on the availability of parts and / or machine components;

[0064] Data on operational information of the plant operator, in particular shift information, employee groups, employee qualifications and / or working time models in the individual areas;

[0065] Data on external intermediate storage facilities for beverages, in particular data on storage capacities;

[0066] Data from one or more distribution points, in particular data on forecasts and plans of supermarkets; and / or

[0067] Information from the Internet, in particular data on weather forecasts, disaster areas, traffic conditions, major events, and / or sales figures.

[0068] According to embodiments, it may be necessary to extract suitable data from the database 231, e.g., data for a specific production line for a specific time period or multiple time periods. Even though only the machine line 100 is shown as the origin of a database in Figure 2, it is understood that the additional data, as described above, can also be at least part of the database.

[0069] According to embodiments, it may further be necessary to suitably transform the data 231 extracted from the database for use in an LLM so that it can be processed by the latter. This processing step is shown within the data box 230, which shows raw data 231, which is converted into the processed data 232 by extracting and processing suitable contents of the data 231. This may include converting values ​​into suitable units (e.g., timestamps, time differences, percentages), calculating ratios, and restructuring larger, multidimensional data sets. The processing may also include adding data context to the data, such as labels about the content and meaning of the data, so that the LLM can correctly interpret the data.

[0070] This data preprocessing, as shown in data box 230, can be performed in regular intervals and regularly precalculated and persisted for specific periods of time to minimize the latency of the LLM's processing of the user request. In other words, processing data over longer periods of time (weeks, months, quarters) can take a long time. Therefore, in these cases, the data should already be precalculated and persisted to minimize the waiting time for the user 130. After completing the input of the state data into the LLM with context, an "LLM with context and with state data" 200 is created, which is ready for use in the analysis module 110.

[0071] The LLM 200 can be called up by a user 130 via the user interface 120 and can be used as a digital assistant for the customized output of data and information from the machine line.

[0072] The user 130 can now interact with the LLM 200 and send requests to the LLM 200 via the user interface 120 in order to receive requested data from the LLM 200.

[0073] The usability of the user platform of Machine Line 100 is thus improved, as the LLM supports the user 130 in a question-and-answer format, allowing them to navigate more quickly to the desired information. The increasing amount of data and key figures in a Machine Line 100 is difficult to grasp and can be interpreted differently depending on customer requirements. This flexibility is not possible with static dashboards. The LLM 200 also offers functions such as creating plots / graphs. This allows the LLM 200 to generate plots, which no longer require the operator of the user platform to develop them or to configure them individually.

[0074] Figure 3 shows an exemplary flowchart for a method for implementing an LLM and its operation in a machine line 100.

[0075] The method 300 begins with step S302, in which a large language model is implemented on the server 110. The implementation may include the implementation of a specific general language model that is optimized for a specific language (English, German, French, Spanish, Chinese, etc.) or that supports multiple languages.

[0076] In step S304, a specific context for the LLM is defined. The specific context can define a restriction on an output of the LLM. The defined restriction can restrict at least one of the following: a form, a structure, a used information source, and a level of detail of the output of the LLM. The context can be defined and entered into the model by a manufacturer of the machine line 100, an operator of the online service, or another entity. The specific context can further comprise a user-specific context and / or instructions for calculating key figures. In step S306, a database for the LLM is determined, which includes status data and data of the machine line 100. The status data can include directly collected or calculated key figures, sensor data, and / or machine data. As described above, the database can also include (e.g.In addition to the data and status data of the machine line 100, status data and data from similar machine lines 100b and / or external data 150 describing an external ecosystem are used. "Similar machine lines" can mean, for example, that data from machine lines (including lines distributed throughout the world) are used that match the machine line in at least one defined criterion, as described above.

[0077] The state data may be from one or more specific time periods. In an optional sub-step to S306, this state data may be preprocessed. The preprocessing of the state data (e.g., for the machine line 100, but also optionally for external data 150 and / or data of the similar machine lines 100b) may comprise at least one of the following operations: (i) converting one or more values ​​in the state data into one or more suitable units that can be processed by the LLM, (ii) calculating ratios, (iii) restructuring multidimensional data sets, (iv) aggregating data, and / or (v) adding data context to the data.

[0078] In the following step S308, a user request for creating requested information regarding machine line 100 is received via user interface 120. For example, the user request from user 130 may be a request that the LLM display and list all identified downtimes within the last week, with a further request that the reasons for each downtime be stated. This request is only an example.

[0079] The user request is then entered into the LLM in step S310 and processed by the LLM in step S312 based on the specified specific context and the status data to determine the requested information from the status data. The requested information may, for example, include benchmark information based on other (e.g., similar) machine lines and / or may include external data 150.

[0080] Finally, in step S314, the requested information is provided by the LLM. The provision may include forwarding the requested information to the user 130 from whom the user request originated, thereby concluding the method 300. The provision of the requested information by the LLM may further include providing information about one or more sources used by the LLM to determine the requested information. The information about the one or more sources may appear textually and be selectable by the user 130 and linked to the respective sources. For example, the user may click on the source and, in addition to the LLM's response, be taken to the database that serves as the basis for the LLM's answer to the question.

[0081] Providing may also include forwarding the requested information to another machine, whichever machine originates the user request, thus completing the process. Accordingly, it would also be possible for machines to interact with each other and exchange information (M2M).

[0082] The embodiments described herein offer a number of advantages compared to conventional information systems. For example, retrieving information no longer requires knowledge of a (complex) workflow or syntax. Thus, no (technical) expert knowledge is required to obtain the desired information.

[0083] The queries and responses are "human-friendly," as is usual with conventional internet search engines, for example. This means that several "free rules" can be incorporated into a search query, such as: "Show me all closure errors in system A over the last four months and the respective type with the respective speed and outside temperature."

[0084] This new "information collection and search" system can also be used to enhance or replace existing LDS / MES systems. Communication of information between multiple machines (M2M) is also conceivable.

[0085] The embodiments also serve the purpose of comparing similar lines and creating benchmarks between any machine lines, in particular filling and packaging lines (worldwide).

[0086] Furthermore, by combining data / information from the internal ecosystem and an external ecosystem, analyses, forecasts and recommendations for action can be significantly improved.

[0087] The following Figures 4 to 7 describe various exemplary system configurations for different bottling plants in which the invention, or at least parts and aspects of the invention, can be implemented. The description of Figures 4 to 7 is intended only to provide a general overview of machines for which status data can be collected, based on which the LLM can process user requests.

[0088] Figure 4 shows an exemplary system configuration 1000 for PET bottles or PET containers and adhesive packs. As shown in Figure 4, the system configuration 1000 comprises various modules that form a line, at the end of which the finished PET containers are dispensed in the form of a pack on pallets. Some of the modules and machines may be optional, and the invention is not limited to the exact form and arrangement of the system configurations.

[0089] The system configuration 1000 comprises an oven 1002 for preforms, a preform sorter with a feeding machine 1004, and a blow molding machine 1008. The modules 1002, 1004, and 1008 generally form a stretch blow molding machine in which PET containers are produced and formed from a starting material. The produced PET containers are forwarded to a filler 1010, where the bottles are filled. The filler can optionally include a rinser. Various particles such as dust, cardboard, or remnants of wooden pallets can settle in the preforms during storage or transport. These can be removed with the rinser. A closer can be arranged at the end of the filler, by means of which the PET containers are closed after filling.

[0090] Optionally, the system configuration 1000 can include a rotating device downstream of the filler 1010, which is used for hot filling of the PET containers. Via one or more conveyor belts 1016, which can also include a buffer 1018 for storing / buffering filled containers, the filled PET containers are conveyed to a separator 1020 and then to a drying device 1024, where the PET containers are dried.

[0091] After drying, the PET containers are conveyed to a labeling machine 1026. The labeling machine 1026 can be designed for various labeling techniques, such as labeling using hot melt, cold melt, self-adhesive labels, or sleeves. After the PET containers have been printed or labeled, they are conveyed through a second drying device 1028, a line distributor 1030, conveyor belts 1032, an adhesive pack production line 1034, and a curing section to a handle applicator. In the adhesive pack production line 1034, the PET containers are grouped into specific group sizes and packaged into a pack, such as a "six-pack." In the handle applicator, a carrying handle is attached to the pack, which allows for comfortable carrying of the pack.The finished containers are then arranged accordingly by a robot 1042 for layer production and packed on pallets by a palletizer 1044. In the system configuration 1000, so-called format carriages or format racks can be arranged on various modules and machines to provide quickly interchangeable format sets for short changeover times and automatic tool changes. Examples of format carriages are the format carriage 1006 for the blow molding machine 1008, the format carriage 1012 for the filler 1010, the format carriage 1022 for the labeling machine 1026, the format carriage 1038 for the adhesive container production 1034, and the format carriage 1046 for the palletizer 1044.

[0092] Figure 5 shows another example system configuration 1100 for PET containers and shrink packers. System 1100 from Figure 10 includes many of the modules and machines from system configuration 1000 from Figure 4, but there are some differences. Therefore, the description of the modules already described in connection with Figure 4 is omitted for Figure 10.

[0093] A key difference between the two exemplary system configurations 1000 and 1100 is that the labeling machine 1126 with the labeling modules 1127 can be installed downstream of the blow molding machine 1008 and upstream of the filler 1008. For this purpose, the system configuration 1100 can comprise six transport lanes 1150 into which the PET containers can be pushed. After the PET containers have pushed into one of the six lanes 1150, they are conveyed into the film wrapping module 1152 and then into the shrink tunnel 1154.

[0094] Figure 6 shows an example system configuration 1200 for cans or glass bottles. The example system configuration 1200 from Figure 6 again has some similarities to the system configurations 1000 and 1100 from Figures 4 and 5, and the description of the system configuration is therefore limited to the differences between the system configurations.

[0095] As shown in Figure 6, the exemplary system configuration can include two separate feeders. A first feeder, on the left in Figure 6, shows a branch for cans or, optionally, a partial branch for new, reusable bottles. The containers, i.e., cans or new bottles, are fed into the machine by a depalletizer 1302, where they are guided via conveyor belts to the filler 1010. A second feeder, on the right in Figure 6, shows a partial branch for reusable bottles, which are fed into the system by a reusable sorting system (not shown).

[0096] In the case that the already used reusable bottles are introduced into the system 1200 via the sub-branch for reusable bottles, the reusable bottles first pass through the cleaning machine or washing machine 1304. Another possible difference in the exemplary system configuration 1200 is the transfer packer 1306 after the labeling machine 1026. The transfer packer can sort the bottles or cans into a carton clip application or into crates, or both.

[0097] Figure 7 shows an exemplary system configuration 1300 for cans, in which the elements already described in the other system configurations are no longer described. The cans in system configuration 1300 are fed into the depalletizer 1302 from a magazine 1402 containing cans. After passing through the filler and being filled, the cans are closed by means of a closure magazine 1404 and transported further along the system 1400 via the conveyor belts, as described above. The optional pasteurizer 1408 can be bypassed via the bypass 1412 if it is not required. In the pasteurizer 1408, the freshly filled products can be pasteurized for preservation.

[0098] In contrast to plant configurations 1000, 1100, and 1200, the exemplary plant configuration 1300 shows various tanks for corresponding consumables, such as tanks 1410 with rinsing liquid and / or the filling product and tanks 1406 with belt lubricant. These tanks can also be included in the exemplary plant configurations described above. For example, the chemical products 106 that are fed from the mixer 110 to the machines can be stored in tanks 1406 and 1410.

Claims

CLAIMS 1. A method for the adapted output of data from a machine line (100), in particular in a machine line for filling and packaging food and / or beverages, wherein the machine line comprises a plurality of machines, and wherein the method comprises: Implementing (S302) a large language model, LLM, on an analysis module (110); Defining (S304) a specific context for the LLM, wherein the specific context defines a constraint on an output of the LLM, and wherein the defined constraint restricts at least one of the following: a form, a structure, a utilized information source, and a level of detail of the output of the LLM; Creating (S306) a database for the LLM, which includes status data and machine line data; Receiving (S308), via a user interface (120) of the analysis module, a user request to create requested information regarding the machine line; Entering (S310) the user request into the LLM; Processing (S312) the user request by the LLM based on the specified specific context and based on the state data and the machine line data to determine the requested information from the state data; and Provision (S314) of the requested information by the LLM.

2. Method according to claim 1, wherein the database is directly collected or calculated key figures, sensor data and / or machine data from a machine line or from individual machines of a machine line.

3. The method according to claim 1 or 2, wherein the database comprises at least: Live production data of the machine line; historical production data of the machine line; Condition monitoring data of the machine line and / or conveyors within the machine line; Performance data of the machine line and / or its machines and conveyors; and / or Energy and media data of the machine line and / or its machines and transporters; and / or Reporting data on current and / or historical incidents, warnings or notices; 4. The method according to any one of claims 1 to 3, further comprising: Preprocessing the condition data for the machine line, wherein the preprocessing of the condition data comprises at least one of: Converting one or more values in the state data into one or more suitable units that can be processed by the LLM, Calculating ratios, To structure multidimensional data sets, Aggregating data, and Adding data context to the data.

5. A method for the adapted output of data from a machine line (100) by an analysis module (110), in particular in a machine line for filling and packaging food and / or beverages, wherein the machine line comprises a plurality of machines, wherein the analysis module has access to a status database and machine data from a plurality of further machine lines that match the machine line in at least one defined criterion, and wherein the method comprises: Implementing (S302) a large language model, LLM, on the analysis module (110); Setting (S304) a specific context for the LLM, wherein the specific context specifies a restriction of an output of the LLM, and wherein the specified Restriction restricts at least one of the following: a form, a structure, a source of information used, and a level of detail of the output of the LLM; Creating a database for the LLM, which includes condition data and machine line data; Receiving (S308), via a user interface (120) of the analysis module, a user request to create requested information regarding the machine line, wherein the requested information comprises benchmark information comprising status data and machine data of the plurality of further machine lines; Entering (S310) the user request into the LLM; Processing (S312) the user request by the LLM based on the specified specific context and based on the status data, the data of the machine line, and the status data and machine data of the plurality of further machine lines to determine the requested information from the status data; and Provision (S314) of the requested information by the LLM.

6. The method according to claim 5, wherein the benchmark information is based on a comparison of data of the machine line with data from at least one similar machine line from the plurality of further machine lines, and wherein the benchmark information comprises information on at least one of condition monitoring, a cause of a production interruption, machine availabilities and unplanned downtimes and their causes.

7. A method for the adapted output of data from a machine line (100) by an analysis module (110), in particular in a machine line for filling and packaging food and / or beverages, wherein the machine line comprises a plurality of machines, wherein the analysis module has access to at least one database containing machine line-independent data, and wherein the method comprises: Implementing (S302) a large language model, LLM, on the analysis module (110); Defining (S304) a specific context for the LLM, wherein the specific context defines a constraint on an output of the LLM, and wherein the defined constraint restricts at least one of the following: a form, a structure, a utilized information source, and a level of detail of the output of the LLM; Creating (S306) a database for the LLM, which includes status data and machine line data; Receiving (S308), via a user interface (120) of the analysis module, a user request to create requested information regarding the machine line; Entering (S310) the user request into the LLM; Processing (S312) the user request by the LLM based on the specified specific context and based on the state data, the machine line data, and the machine line-independent data to determine the requested information from the state data; and Provision (S314) of the requested information by the LLM.

8. The method of claim 7, wherein the machine line-independent data comprises a plurality of data originating from outside the machine line and / or wherein the machine line-independent data comprises: Data from material suppliers and / or manufacturers, in particular about containers, labels, syrup, and / or availability of materials, auxiliary and operating supplies, and / or spare parts; Data from an energy supplier, in particular data on phases of time-dependent energy tariffs; Data from a logistics company, in particular data from trucks for supply / disposal; Data from a component supplier, in particular data on the availability of parts and / or machine components; Data on operational information of the plant operator, in particular shift information, employee groups, employee qualifications and / or working time models in the individual areas; Data on external intermediate storage facilities for beverages, in particular data on storage capacities; Data from one or more distribution points, in particular data on forecasts and plans of supermarkets; and / or Information from the Internet, in particular data on weather forecasts, disaster areas, traffic conditions, major events, and / or sales figures.

9. A system for the adapted output of data from a machine line, in particular in a machine line for filling and packaging food and / or beverages, wherein the machine line comprises a plurality of machines, and wherein the system comprises: an analysis module on which a large language model (LLM) is implemented, wherein a specific context is defined for the LLM, wherein the specific context defines a restriction of an output of the LLM, and wherein the defined restriction restricts at least one of the following: a form, a structure, a used information source, and a level of detail of the output of the LLM; and a user interface of the analysis module for interacting with the LLM; wherein the LLM is adapted to: Maintaining a database for the LLM, which includes condition data and machine line data; Receiving a user request via the user interface to create requested information regarding the machine line; Entering the user request; Processing the user request based on the specified specific context and based on the state data and the machine line data to determine the requested information from the state data; and Providing the requested information.

10. The system of claim 9, wherein: the analysis module further has access to: a status database and machine data from a plurality of further machine lines that match the machine line in at least one defined criterion; and / or at least one database containing machine line-independent data; and wherein the requested information comprises: Benchmark information, which includes condition data and machine data of the multitude of other machine lines, and / or Relationships between machine line data and machine line-independent data.

Images