Method and system for adjusting data of output machine production line

Abstract

One embodiment of the present invention relates to a method and system for adjusting data for outputting a machine production line, in particular in a machine production line for filling and packaging food and / or beverages, where the machine production line comprises a plurality of machines. A large language model LLM is implemented on a server. A specific context is then set for the LLM. A particular context may set constraints for the output of the LLM. For example, the set constraints relate to at least one of the form, structure, source of information used, and degree of detail of the output of the LLM. And finally, inputting the state data of the machine production line into the LLM. Upon completion of the setting of the LLM, a user request may be received via a user interface to query the requested information about the machine line. The user request is entered into the LLM, and the LLM processes the user request based on the set particular context and the status data to determine the requested information from the status data. Finally, the LLM may provide these requested information.

Description

[0001] This invention relates to a method and system for adjusting output data of a machine production line, particularly in a machine production line for filling and packaging food and / or beverages, and a machine production line.

[0002] Today, filling and packaging equipment in the beverage and liquid food industry is highly optimized and can process up to 120,000 units per hour. Typical filling and packaging equipment usually consists of multiple different machines and modules connected by conveyor belts. Here, these units (such as bottles, cans, pallets, bundles, etc.) are transported from one machine to another, passing through the machines in the production line in a predetermined sequence.

[0003] During operation, such machine production lines generate a large amount of data. This data can contain important information about the performance and operating status of the machine production line, and effectively utilizing this data can help improve productivity, optimize maintenance, reduce downtime, and improve the quality of the products produced. For example, this data can be presented as historical production data in reports, allowing users to analyze downtime and malfunctions and draw conclusions for production optimization.

[0004] Other services offer users the possibility of visualizing sensor and machine data, as well as setting up monitoring to detect anomalies (such as continuously increasing motor current).

[0005] To date, the evaluation of machine data has been mostly performed either manually or automatically by specialized evaluation systems. Manual evaluation requires extensive knowledge and skills, and is often time-consuming and error-prone. Automated systems can improve efficiency, but their ability to perform complex analyses and output targeted information to the user is often limited.

[0006] Furthermore, the information provided is typically delivered to users via web portals. Users can thus navigate to the information they need, as well as processed statistics, graphs, tables, or other data, to obtain the information they require through the web portal. However, users are often forced to navigate through large amounts of general data to find information relevant to their specific needs.

[0007] Due to the high demand from clients for visualization and reporting, a significant amount of resources has been invested in the development of such dashboards and front-ends to ensure flexibility and variability.

[0008] Therefore, it is necessary to provide a more efficient way to offer users adjustment information. Users want information presented in an easy-to-understand format, wanting to know when and where malfunctions occur, the reasons, and what actions need to be taken to make the machine production line operate as optimally and without failures as possible. Existing reports and dashboards are merely means to an end.

[0009] Therefore, there is a need to improve the systems and methods used to adjust the data of the output machine production line.

[0010] According to the present invention, this objective is achieved by the method according to claim 1 and the system according to claim 8. Embodiments and improvements are included in the dependent claims.

[0011] One embodiment of the present invention relates to a method for adjusting data output from a machine production line, particularly in a machine production line for filling and packaging food and / or beverages, wherein the machine production line comprises multiple machines. The method includes the following steps: First, a Large Language Model (LLM) is implemented on a server. Here, the server may be designed as or include a server, industrial PC, or edge device. The specific design depends on, for example, the requirements of the LLM model used and / or the type of communication. For example, the LLM model may be hosted externally, i.e., at a service provider (e.g., a server farm operator). Communication with the machine production line can then be made via an API. However, the LLM model may also be hosted internally at the operator of the machine production line.

[0012] Next, a specific context is set for the LLM. This specific context sets constraints on the LLM's output. For example, the constraints may involve at least one of the following: the form, structure, information sources used, and level of detail of the LLM's output. Finally, the status data of the machine production line is input into the LLM. After this LLM setup is complete, a user request to create requested information about the machine production line can be received via a user interface. This user request is input into the LLM, and the LLM processes the request based on the set specific context and the status data to determine the requested information from the status data. Ultimately, the LLM can provide the requested information.

[0013] One embodiment of the present invention relates to a system having an LLM, a server, and a user interface.

[0014] Exemplary aspects of the invention are illustrated in the accompanying drawings. In the drawings: Figure 1 A schematic diagram is shown, illustrating an overview of the basic elements and structure of the invention. Figure 2 This diagram illustrates the phased adjustment of a large language model for application in a machine production line. Figure 3 An exemplary flowchart is shown for implementing a large language model and its operation in a machine production line; Figure 4 An exemplary device configuration for PET containers and adhesive strapping is shown; Figure 5An exemplary equipment configuration for PET containers and shrink packaging machines is shown; Figure 6 An exemplary device configuration for jars or glass bottles is shown; and Figure 7 An exemplary device configuration for a can is shown.

[0015] Figure 1 For illustrative purposes only, this diagram illustrates an overview of the basic elements and structure of the present invention. According to one embodiment, these basic elements may be a machine production line 100, a cloud or computer server 110, and a user interface 120 through which a user 130 can interact with the server 110 and, where appropriate, with the machine production line 100.

[0016] Machine production line 100 may be, for example, a machine production line for filling and packaging food and / or beverages, but is not specifically limited to such a production line. Different exemplary embodiments of such machine production line 100 are described in... Figures 4 to 7 The text is shown and explained.

[0017] Computer server 110 is not necessarily a single server, but may consist of one or more computer devices that are directly or indirectly connected to each other. As described in more detail below, server 110 may include a Large Language Model (LLM) and provide an interface between the LLM and user interface 120. Server 110 may be directly or indirectly connected to machine production line 100. For example, server 110 and machine production line 100 may be interconnected via an Internet connection, or they may have a direct communication connection.

[0018] User interface 120 allows user 130 to interact with server 110 or at least with specific services on server 110. Here, the user interface can take any form suitable for enabling the user to interact with the computer via input. The user interface is also known as a "human-machine interface" (MMS) or "human-machine interface" (HMI) and, in some cases, allows user 130 to observe equipment status and intervene in processes outside of operating machine production line 100.

[0019] Here, the user interface can be a simple computer, mobile phone, tablet, dedicated device of machine production line 100, voice assistant, computer application, computer terminal or other computer-aided device.

[0020] As previously mentioned, a so-called Large Language Model (LLM) can be implemented on server 110. These large language models, also known as 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 identifying patterns within it. This involves not only individual words and sentences but also the context in which they are used. A specialized language model called "Transformer" can recognize more complex contexts and learn to generate answers to questions, translate text, and even generate graphics (such as data graphs and diagrams). The known architecture of "Transformer" is based on a method called "Attention," which helps the language model understand the context of a word relative to all other words in a text paragraph.

[0021] These neural Transformers consist of multiple layers, each containing a large number of neurons. During training, each layer and each neuron is adjusted to better respond to the training data. The model's "depth" (number of layers) and "width" (number of neurons per layer) determine the complexity of the patterns the model can recognize.

[0022] The training process requires significant computational 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. These types of LLMs are offered pre-trained, fully-trained versions by various vendors, allowing end users to use "off-the-shelf" LLMs.

[0023] Embodiments of the present invention relate to integrating such an LLM into a user platform. According to an embodiment of the invention, the LLM is specifically tailored to provide user 130 with requested data from machine production line 100. When tailoring the LLM, security and data transparency are considered to ensure that erroneous information is not provided to the user.

[0024] The LLM adjustment plan is in Figure 2 This is shown in more detail below. Figure 2 The basic architecture in Figure 1 The architecture is the same, and it includes machine production line 100, server 110, and user interface 120. Additionally, Figure 2 An adaptation of the LLM 200, which is implemented exemplary on server 110, is also shown.

[0025] Here, LLM 200 can be a pre-trained general LLM that may not initially possess extended knowledge about machine production line 100 or the data generated by the machine production line. Therefore, context needs to be provided for the LLM first.

[0026] like Figure 2As shown, the "General LLM" 200 thus becomes a "Contextualized LLM" 200. The context can be specifically designed for a completely specific equipment configuration of the machine production line 100, or it can be specifically designed for a particular user group. The specific context sets constraints on the LLM output. Such constraints can relate to, for example, the form, structure, information sources used, or level of detail of the LLM output. Furthermore, the context may include specific instructions or descriptions for calculating specific metrics or information.

[0027] To precisely define the specific context of the LLM, appropriate specific text instructions can be set. These instructions can also be user-specific (e.g., what exactly customer plant managers and installation personnel can view). The expected form and structure of the LLM response are also defined here.

[0028] In order to find the cause when calculated indicators, such as abnormally low values, can be found, the LLM can also be provided with facts about the calculation of the indicators and the causal relationship.

[0029] Since a pre-trained LLM can "understand" and accept natural language as input, in one implementation, a specific context can also be expressed as such text input.

[0030] A simplified, exemplary specific context might look like this: "You are an intelligent assistant helping users answer questions about production data on their machine production line. Only answer using facts listed in the provided source list. If information is insufficient, say you don't know. Do not generate answers unrelated to the provided sources. Ask clarifying questions if it would be helpful. Your answers should be concise. Write the data in a human-readable format. Each source should have a name, followed by a colon and the actual information. Always include the source name for each piece of information used in your answer. Use square brackets to cite sources, e.g., [ " report_123 Do not merge sources; instead, list each source separately, for example, []. report_123 [<] link to report >]. This context is merely an example and may be more detailed and restrictive in actual implementation. This particular context, for example, is provided to LLM 200' by the manufacturer of machine production line 100. The context can be entered into LLM 200' in such a way that subsequent user 130 interacting with the LLM cannot modify the context, thus preventing the removal of constraints set by the context.

[0031] However, using the "contextualized LLM" 200' still cannot raise specific questions about the data of machine production line 100, because the data or status data of machine production line 100 must first be entered into the LLM as a source in a further step.

[0032] Data 230 can be loaded directly from machine production line 100 to cloud 110, for example, or it can be transferred to cloud 110 under the control of a third party. This data 230 constitutes a database for LLM to answer questions and can be directly collected or calculated metrics, sensor data from machine production line 100 or individual machines in machine production line 100, and / or machine data. For this purpose, an existing database can be used, which also serves as a source for existing services.

[0033] Depending on the implementation, it may be necessary to extract appropriate data from database 231, such as data from a specific production line during one or more time periods.

[0034] Depending on the implementation, it may also be necessary to convert the data 231 extracted from the database into a form suitable for use in an LLM so that the LLM can process it. This processing step is shown within a data frame 230, which illustrates the raw data 231, which is transformed into processed data 232 by extracting and processing appropriate content from the data 231. This may include converting numerical values ​​to appropriate units (e.g., timestamps, time differences, percentages), calculating ratios, and reconstructing larger cubes. The processing may also include adding data context to the data, such as labels about the data content and meaning, so that the LLM can correctly interpret the data.

[0035] As shown in data frame 230, this data preprocessing can be performed at fixed time intervals, with pre-computation and persistent storage periodically for specific time periods to minimize the latency of LLM processing user requests. In other words, processing data over longer periods (weeks, months, quarters) may take a long time. Therefore, for these cases, the data should be pre-computed and persistently stored to minimize the waiting time for user 130.

[0036] After completing the input of state data into the LLM with context, an "LLM with context and state data" 200'' is created, which is ready to be used in the cloud 110.

[0037] The LLM 200 can be invoked by user 130 via user interface 120 and can be used as a digital assistant to adjust the data and information output of the machine production line.

[0038] User 130 can now interact with LLM 200'' and send requests to LLM 200'' via user interface 120 to obtain the requested data from LLM 200''.

[0039] This improves the operability of the user platform for machine production line 100, as user 130 receives support via LLM in a question-and-answer format and navigates to the information they need more quickly. The increasing amount of data and metrics in machine production line 100 is difficult to manage and requires different interpretations due to varying customer needs. This flexibility cannot be achieved using static dashboards. LLM 200'' also provides functions such as creating data charts / graphs. Therefore, data charts can be generated by LLM 200'' without the need for time-consuming development by the user platform operator or separate configuration by user 130.

[0040] Figure 3 An exemplary flowchart is shown for implementing LLM and its operation in machine production line 100.

[0041] Method 300 begins with step S302, in which a large language model is implemented on server 110. This implementation process may include implementing a specific general language model optimized for a particular language (English, German, French, Spanish, Chinese, etc.) or mastering multiple languages.

[0042] In step S304, a specific context is set for the LLM. The specific context can set constraints on the LLM output. The set constraints can constrain at least one of the following: the form, structure, information sources used, and level of detail of the LLM output. This context can be set and input into the model by the manufacturer of machine production line 100, online service operator, or other organization. The specific context may also include user-specific context and / or instructions for calculating metrics.

[0043] In step S306, the status data of machine production line 100 is input into the LLM. The status data may include directly acquired or calculated metrics, sensor data, and / or machine data. The status data may originate from one or more specific time periods. In an optional sub-step of S306, the status data may also be preprocessed. Preprocessing of the status data of machine production line 100 must include at least one of the following operations: (i) converting one or more values ​​in the status data into one or more suitable units that can be processed by the LLM, (ii) calculating ratios, (iii) reconstructing the cube, (iv) aggregating the data, and / or (v) adding data context to the data.

[0044] In the next step S308, a user request to create requested information about machine production line 100 is received via user interface 120. For example, user 130's request could be to request the LLM to display and list all identified downtimes from the previous week, and further request an explanation for each downtime. This request is merely an example.

[0045] Then, in step S310, the user request is input into the LLM, and in step S312, the LLM processes the user request based on the set specific context and these state data to determine the requested information from these state data.

[0046] Finally, in step S314, the LLM provides the requested information. Providing this information may include forwarding the requested information to the user 130 who made the request, at which point method 300 ends. The process of the LLM providing the requested information may also include providing a description of one or more sources used by the LLM in determining the requested information. This description of one or more sources may be presented in text form and may be selected and associated with a corresponding source by the user 130. For example, the user may click on a source and, in addition to the LLM's response, access a database that forms the basis for the LLM's answer to the question.

[0047] In the following Figures 4 to 7 Various exemplary device configurations for various bottle filling devices are described herein, in which the invention or at least parts and aspects of the invention may be implemented. Figures 4 to 7 The description is intended only to provide a general overview of the machines for which state data can be collected, and on which the LLM can process user requests.

[0048] Figure 4 An exemplary device configuration 1000 for PET bottles or PET containers and adhesive strapping is shown. Figure 4 As shown, equipment configuration 1000 includes various modules that form a production line at the end of which filled PET containers are output on pallets in the form of bundles. Some of the modules and machines may be optional, and the invention is not limited to the specific form and arrangement of the equipment configuration.

[0049] Equipment configuration 1000 includes an oven 1002 for preforms, a preform sorter 1004 with a feeder, and a blow molding machine 1008. Modules 1002, 1004, and 1008 typically form a stretch blow molding machine in which PET containers are made and shaped from initial materials. The produced PET containers are then conveyed to a filler 1010, where bottles are filled. The filler may optionally include a rinsing device. During storage or transportation, various particles, such as dust, cardboard, or wooden pallet residue, may accumulate in the preforms. These particles can be removed using the rinsing device. A sealing machine may be arranged at the end of the filler to seal the PET containers after filling.

[0050] Optionally, the equipment configuration 1000 may include a rotating device after the filling machine 1010 for hot filling of PET containers. The filled PET containers are conveyed to a separator 1020 and then to a drying unit 1024 via one or more conveyor belts 1016 (which may also include a buffer 1018 for intermediate loading of filled containers), where the PET containers are dried.

[0051] After drying, the PET containers are conveyed to labeling machine 1026. Labeling machine 1026 can be designed for various labeling techniques, such as hot glue, cold glue, self-adhesive labels, or sleeve labels. After printing or labeling, the PET containers are conveyed to handle applicator via second drying unit 1028, production line distributor 1030, conveyor belt 1032, adhesive bundle production device 1034, and curing path. In adhesive bundle production device 1034, PET containers are grouped together in specific bundle sizes and packaged into bundles, such as "six-packs". In handle applicator, handles are attached to the containers, making it possible to comfortably carry the bundles. The finished bundles are then correspondingly arranged into layers by robot 1042 and packed on pallets by palletizer 1044.

[0052] In equipment configuration 1000, so-called format carriages or format racks can be arranged at various modules and machines to provide quickly changeable format kits for short changeover times and automated tool switching. Examples of format carriages are format carriage 1006 for blow molding machine 1008, format carriage 1012 for filling machine 1010, format carriage 1022 for labeling machine 1026, format carriage 1038 for adhesive bundling production device 1034, and format carriage 1046 for palletizer 1044.

[0053] Figure 5 Another exemplary device configuration 1100 for PET containers and shrink packaging machines is shown. Figure 5 Device 1100 includes from Figure 4 The equipment configuration includes 1000 modules and machines, but some differences exist. Therefore, for... Figure 5 The already combined part has been omitted. Figure 4 The description of the module.

[0054] A significant difference between the two exemplary device configurations 1000 and 1100 is that the labeling machine 1126, with labeling module 1127, can be installed after the blow molding machine 1008 and before the filling machine 1008. For this purpose, device configuration 1100 may include up to six transport tracks 1150 into which PET containers can be extruded. After the PET containers have been correspondingly extruded into one of the six tracks 1150, they are conveyed to a film wrapping module 1152 and then to a shrink tunnel 1154.

[0055] Figure 6 An exemplary device configuration 1200 for use with jars or glass bottles is shown. Figure 6 The exemplary device configuration 1200 is again with Figure 4 and Figure 5 The device configurations 1000 and 1100 have some similarities, therefore the description of the device configuration is limited to the differences in device configuration.

[0056] like Figure 6 As shown, an exemplary device configuration may include two separate feed sections. Figure 6 The first feed section on the left shows a branch for cans, or optionally a sub-branch for new reusable bottles. Here, the containers (i.e., cans or new bottles) are guided into the machine by the depalletizer 1302, where they are guided to the filler 1010 via a conveyor belt. Figure 6 The second feed section on the right shows a sub-branch for reusable bottles, which are introduced into the equipment from the reusable sorting device (not shown).

[0057] In cases where used reusable bottles are introduced into device 1200 via a sub-branch for reusable bottles, the reusable bottles first pass through a cleaning or washing machine 1304. Another possible difference in the exemplary device configuration 1200 is the addition of a transshipment packaging machine 1306 after the labeling machine 1026. The transshipment packaging machine can sort bottles or cans into cardboard clip application devices or boxes, or both.

[0058] Figure 7 An exemplary device configuration 1300 for cans is shown, wherein elements already described in other device configurations are not described again. In device configuration 1300, cans are introduced from a can magazine 1402 containing cans into a depalletizer 1302. After the cans have passed through a filling machine and been filled, the cans are sealed by means of a sealing magazine 1404, and the cans are further conveyed along device 1400 via a conveyor belt, as described above.

[0059] If not required, the optional pasteurizer 1408 can be bypassed via bypass 1412. In pasteurizer 1408, freshly filled products can be pasteurized for preservation.

[0060] Compared to device configurations 1000, 1100, and 1200, exemplary device configuration 1300 shows different tanks for corresponding consumables, such as tank 1410 having rinsing liquid and / or filling product, and tank 1406 having lubricant. These tanks may also be included in the exemplary device configurations already described above. For example, chemical product 106 conveyed from mixer 110 to the machine may be stored in tanks 1406 and 1410.

Claims

1. A method for adjusting data of an output 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 a server (110); setting (S304) a specific context for the LLM, wherein the specific context sets constraints for an output of the LLM, and wherein the set constraints constrain at least one of a form, structure, used information source, and a level of detail of the output of the LLM; inputting (S306) state data of the machine line into the LLM; receiving (S308) a user request for creating a requested information about the machine line via a user interface (120); inputting (S310) the user request into the LLM; processing (S312) the user request by the LLM based on the set specific context and the state data to determine the requested information from the state data; and providing (S314) the requested information by the LLM.

2. The method according to claim 1, further comprising: forwarding the requested information to a user (130) issuing the user request.

3. The method according to claim 1 or 2, wherein the state data comprises at least directly collected or calculated indicators, sensor data, and / or machine data, and wherein the state data is from one or more specific time periods.

4. The method according to any one of claims 1 to 3, further comprising: pre-processing the state data of the machine line, wherein the pre-processing of the state data comprises at least one of: converting one or more values in the state data into one or more suitable units processable by the LLM, calculating ratios, reconstructing multi-dimensional data sets, aggregating data, and adding a data context to the data.

5. The method according to claim 4, wherein the pre-processing of state data is pre-computed and persistently stored periodically for specific time periods to minimize a latency time for the LLM to process the user request.

6. The method according to any one of claims 1 to 5, wherein the specific context further comprises a user-specific context and / or an indication for calculating indicators.

7. The method according to any one of claims 1 to 6, wherein the LLM providing the requested information further comprises: providing an explanation about one or more sources used by the LLM in determining the requested information, wherein the explanation of the one or more sources is selectable by the user and associated with the respective source.

8. A system for adjusting data of an output 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: ​ a server on which a large language model, LLM, is implemented, wherein a specific context is set for the LLM, wherein the specific context sets a constraint for an output of the LLM, and wherein the set constraint constrains at least one of: a form, structure, used information source, and a level of detail of the output of the LLM; and a user interface for interacting with the LLM; wherein the LLM is adapted for: inputting state data of the machine production line; receiving a user request via the user interface to create a requested information about the machine production line; inputting the user request; processing the user request based on the set specific context and the state data to determine the requested information from the state data; and providing the requested information.

9. The system of claim 8, wherein the user interface is a web user interface, a voice assistant, or a computer application.

10. The system of claim 8 or 9, the LLM being further adapted for outputting the requested information in the form of one or more data graphs and / or graphics via the user interface. ​

Images