Method and system for an adapted output of data of a machine line

Abstract

An embodiment of the invention relates to a method and a system for an adapted output of data of a machine line, in particular in a machine line for filling and packaging food and / or beverages, said machine line comprising a plurality of machines. A large-language model, LLM, is implemented on a server. A specific context is then defined for the LLM. The specific context can define a restriction of the output of the LLM, e.g. the defined restriction relates to at least one of the following: the shape, the structure, and used information source, and the degree of detail of the output of the LLM. Lastly, state data is entered into the LLM for the machine line. After the aforementioned set up of the LLM is complete, user queries for requesting required information relating to the machine line can be received via a user interface. The user query is entered into the LLM and is processed by the LLM on the basis of the defined specific context and on the basis of the state data in order to ascertain the required information from the state data. Finally, the required information can be provided by the LLM.

Description

[0001] Method and system for the customized output of data from a machine line

[0002] The invention relates to a method and a system for the adapted output of data of 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 the performance and operating status of the machine line, and effective use of this data can help increase productivity, optimize maintenance, minimize downtime, and improve the quality of the products produced. For example, this data can 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 a user's desired information is often limited.

[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 want information presented in an easily understandable manner, 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 the customized output of data from a machine line.

[0011] The object is achieved according to the invention by a method according to claim 1 and a system according to claim 8. 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, wherein the machine line comprises a plurality of machines. The method comprises the following steps. First, a large language model, LLM, is implemented on a server. A server can be designed as or comprise a server, an industrial PC or an edge device. The specific design depends, for example, on the requirements of the LLM model used and / or on the type of communication. For example, it is possible to host the LLM model externally, i.e. with a service provider such as the operator of a server farm. Communication with the machine line can then take place via an API. However, the LLM model can also be hosted internally by the operator of the machine line.

[0013] A specific context is then defined for the LLM. The specific context can specify a restriction on the output of the LLM. For example, the specified restriction concerns at least one of the following: a form, a structure, a used information source, and a level of detail of the LLM output. Finally, status data for the machine line is entered into the LLM. Once the LLM is fully configured, user requests for generating 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 defined specific context and the status data to determine the requested information from the status data. The requested information can then be provided by the LLM.

[0014] One embodiment of the invention relates to a system comprising an LLM, a server and a user interface.

[0015] Exemplary aspects of the invention are illustrated in the drawings. They show:

[0016] Figure 1 : a diagram showing an overview of the essential elements and the basic structure of the invention;

[0017] Figure 2: a diagram showing a gradual adaptation of the large language

[0018] Model for use in a machine line;

[0019] Figure 3: an exemplary flow chart for a method for

[0020] Implementing a large language model and its operation in a machine line;

[0021] Figure 4: an exemplary system configuration for PET containers and

[0022] adhesive packaging;

[0023] Figure 5: an exemplary plant configuration for PET containers and

[0024] Sch rumpf packer;

[0025] Figure 6: an exemplary system configuration for cans or glass bottles; and

[0026] Figure 7: an example system configuration for cans.

[0027] Figure 1 is a diagram showing an overview of the essential elements and basic structure of the invention. According to one embodiment, these essential elements may be a machine line 100, a cloud or computer server 110, and a user interface 120 via which a user 130 can interact with the server 110 and, if appropriate, also with the machine line 100.

[0028] The machine line 100 may, for example, be a machine line for filling and packaging food and / or beverages, but is not specifically limited to such. Various exemplary embodiments of such a machine line 100 are shown and explained in Figures 4 to 7. The computer server 110 is not necessarily a single server, but may consist of one or more computer devices that are communicatively connected directly or indirectly. As described in more detail below, the server 110 may include a large language model (LLM) and provide an interface between the LLM and a user interface 120. The server 110 may be communicatively connected directly or indirectly to the machine line 100.For example, there may be an Internet connection between the server 110 and the machine line 100, via which they are connected to each other, or there may also be a direct communication connection.

[0029] The user interface 120 allows a user 130 to interact with the server 110 or at least with certain services on the server 110. The user interface can take any form suitable for a user to interact with a computer by means of input. 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.

[0030] 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.

[0031] As already mentioned, a so-called large language model (LLM) can be implemented on server 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.

[0032] 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.

[0033] 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.

[0034] Embodiments of the invention relate to the integration of such LLMs into a user platform. According to embodiments of the invention, the LLM 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.

[0035] This concept of LLM customization is shown in more detail in Figure 2. The architecture in Figure 2 is essentially the same as in Figure 1 and includes the machine line 100, the server 110, and the user interface 120. Additionally, Figure 2 shows the customization of an LLM 200, which is implemented on the server 110 as an example.

[0036] 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. Therefore, it is first necessary to give the LLM a context.

[0037] 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.

[0038] To precisely define the context for the LLM, suitable, specific textual instructions can be defined. These can also be user-specific (e.g., which content can be viewed by a customer, such as a plant manager or a technician). This also defines the form and structure of the desired responses from the LLM. To enable the determination of the cause of a particularly low value in calculated key performance indicators, for example, the LLM can also be provided with facts about the calculation of the key performance indicators and causal relationships.

[0039] Since the fully trained LLM “understands” and accepts human language as input, the specific context can also be formulated as such a text input in one embodiment.

[0040] A simplified, exemplary specific context could be as follows:

[0041] "You are an intelligent assistant helping users with their questions about the data produced by their machine lines. Answer ONLY with the facts listed in the list of sources provided to you. If this information is insufficient, say you don't know. Do not generate answers that do not refer to the provided sources. If a clarifying question to the user would help, ask it. Keep your answers brief. Write the data in a human-readable format. Each source has a name, followed by a colon and the actual information. Always add the name of the source for each piece of information you use in your answer. Use square brackets to refer to the source, e.g., [report_123]. Do not combine sources; list each source separately, e.g., [report_123][<link_to_report> ].“

[0042] This context is only exemplary and may be even more detailed and restrictive in the actual implementation. For example, the context is supplied to the LLM 200' by a manufacturer of machine line 100. The context may be entered into the LLM 200' in such a way that a user 130 who later interacts with the LLM cannot change the context in such a way that restrictions defined by the context can be removed.

[0043] 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.

[0044] The data 230 can, for example, be loaded directly from the machine line 100 into the cloud 110 or can also be transferred to the cloud 110 in a controlled manner by a third party. This data 230 forms 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.

[0045] According to embodiments, it may be necessary to extract suitable data from the database 231, e.g., data for a particular production line for a particular time period or multiple time periods.

[0046] 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.

[0047] This data preprocessing, as shown in data box 230, can be performed in regular intervals and can be 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.

[0048] 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 cloud 110.

[0049] 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.

[0050] The user 130 can now interact with the LLM 200 and send requests to the LLM via the user interface 120 to receive requested data from the LLM 200.

[0051] 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 / graphics. This allows the LLM 200 to generate plots, which no longer require the operator of the user platform to develop them or the user 130 to individually configure them.

[0052] Figure 3 shows an exemplary flowchart for a method for implementing an LLM and its operation in a machine line 100.

[0053] 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.

[0054] In step S304, a specific context for the LLM is defined. The specific context may specify a restriction on an output of the LLM. The specified restriction may 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 may 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 may further include a user-specific context and / or instructions for calculating key figures.

[0055] In step S306, status data is entered into the LLM for the machine line 100. The status data may include directly collected or calculated key figures, sensor data, and / or machine data. The status data may be from one or more specific time periods. In an optional sub-step to S306, this status data may be preprocessed. Preprocessing the status data for the machine 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) restructuring multidimensional data sets, (iv) aggregating data, and / or (v) adding data context to the data.

[0056] 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.

[0057] The user request is then input into the LLM in step S310 and processed by the LLM in step S312 based on the specified specific context and based on the state data to determine the requested information from the state data.

[0058] 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.

[0059] 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.

[0060] 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.

[0061] The system configuration 1000 comprises an oven 1002 for preforms, a preform sorter with 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 passed on to a filler 1010, in which 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.

[0062] 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 intermediate loading of filled containers, the filled PET containers are conveyed to a separator 1020 and then to a drying device 1024, in which the PET containers are dried.

[0063] 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.

[0064] In system configuration 1000, so-called format trolleys 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 trolleys are format trolley 1006 for blow molding machine 1008, format trolley 1012 for filler 1010, format trolley 1022 for labeling machine 1026, format trolley 1038 for adhesive pack production 1034, and format trolley 1046 for palletizer 1044.

[0065] Figure 5 shows another exemplary system configuration 1100 for PET containers and shrink packers. The system 1100 from Figure 5 includes many of the modules and machines from the system configuration 1000 from Figure 4, but there are some differences. The description of the modules already described in connection with Figure 4 is therefore omitted for Figure 5. 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 include six transport lanes 1150 into which the PET containers can be pushed. After the PET containers have entered one of the six lanes 1150, they are transported to the film wrapping module 1152 and then to the shrink tunnel 1154.

[0066] 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.

[0067] 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).

[0068] 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.

[0069] 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.

[0070] The optional pasteurizer 1408 can be bypassed via bypass 1412 if not needed. In the pasteurizer 1408, the freshly filled products can be pasteurized for preservation. In contrast to the system configurations 1000, 1100, and 1200, the exemplary system 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 system configurations described above. For example, the chemical products 106, which 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 a server (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; Entering (S306) status data into the LLM for the machine line; Receiving (S308), via a user interface (120), 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 to determine the requested information from the state data; and Provision (S314) of the requested information by the LLM.

2. The method of claim 1, further comprising: Forwarding the requested information to a user (130) from whom the user request comes.

3. The method according to claim 1 or 2, wherein the status data comprise at least directly collected or calculated key figures, sensor data and / or machine data, and wherein the status data are from one or more specific time periods.

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, Restructuring multidimensional data sets, Aggregating data, and Adding data context to the data.

5. The method according to claim 4, wherein the preprocessing of state data is regularly precalculated and persisted for certain time periods in order to minimize a latency of the processing of the user request by the LLM.

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

7. The method according to any one of claims 1 to 6, wherein providing the requested information by the LLM further comprises: Providing an indication of one or more sources used by the LLM to determine the requested information, wherein the indication of the one or more sources is selectable by the user and is linked to the respective sources.

8. A system for the customized 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: a server 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 for interacting with the LLM; the LLM is adapted to: Entering status data for the machine line; 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 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 is further adapted to output the requested information in the form of one or more plots and / or graphics via the user interface.

Images