System and method for the adapted provision of control and status information

Abstract

The invention relates to a computer-implemented method, to a system and to a computer-readable storage medium for providing control and status information for operating a machine in a machine line, in particular a machine line for filling and packaging foodstuffs and / or beverages. The method begins with accessing a first control or information element intended for output to an operator of the machine via an HMI. An intermediate representation of the first control or information element is generated by means of artificial intelligence (AI). The AI then generates a second control or information element based on the intermediate representation and based on a detected operator context. The second control or information element is then output via the HMI.

Description

[0001] System and procedure for the customized provision of control and status information

[0002] The invention relates to methods, systems and computer-readable storage media for providing control and status information for operating a machine in a machine line, in particular a machine line for filling and packaging food and / or beverages.

[0003] In modern industrial manufacturing, production, filling, and packaging systems have significantly increased in complexity and performance. These machines often incorporate highly automated processes that are coordinated to ensure maximum efficiency, quality, and productivity. However, with the increasing level of automation and the integration of digital control systems, the demands on the operation and understanding of these systems have also risen. This poses a considerable challenge, especially for users and operators without extensive technical training.

[0004] A key aspect of operating modern machinery is the communication between the machine and the operator. Messages generated by the machine play a particularly important role in this communication. These messages can contain information, warnings, or troubleshooting instructions and serve as the interface between human and machine. However, it has become apparent that these messages are often formulated in highly technical language that is difficult for operators without technical expertise to understand. This is especially true for fault messages, documentation, error diagnoses, control elements, and other on-screen text and information elements provided by the machine.

[0005] One problem resulting from this language barrier is the high risk of misinterpreting the information provided. Incomprehensible or ambiguous messages can lead operators to make incorrect decisions, which in turn leads to machine malfunctions. Such malfunctions can have serious consequences, such as production downtime, machine damage, or even safety-critical situations.

[0006] Another disadvantage is the uncertainty many operators feel when using the technology. If the communication between humans and machines is perceived as too complicated, this not only leads to a rejection of the technology but can also impair confidence in the machine's reliability and ease of use. Operators may perceive the machines as "too difficult" or "too complex," which in turn reduces their willingness to utilize all the possibilities such technologies offer.

[0007] When a machine stops due to operator error or another problem, the situation is often exacerbated by difficult communication. Restarting the machine, in particular, proves time-consuming in such cases, as the identification and resolution of the fault are hampered by the difficult-to-understand messages. The resulting production losses can cause significant financial losses.

[0008] Therefore, there is a need for improved methods and systems for providing control and status information for operating a machine in a production line.

[0009] The problem is solved according to the invention by a computer-implemented method according to claim 1, a system according to claim 7, and a computer-readable storage medium according to claim 9. Embodiments and further developments are described in the dependent claims.

[0010] One embodiment relates to a computer-implemented method for providing control and status information for operating a machine in a production line, in particular a production line for filling and packaging food and / or beverages. The method begins by accessing a first control or information element intended for output to a machine operator via a human-machine interface (HMI). An intermediate representation of the first control or information element is generated by means of an artificial intelligence (AI). The AI ​​then generates a second control or information element based on the intermediate representation and on a captured operator context. The second control or information element is then output via the HMI.

[0011] Further embodiments relate to a corresponding system and a corresponding computer-readable storage medium.

[0012] Exemplary aspects of the invention are illustrated in the drawings. They show:

[0013] Figure 1: a diagram showing a system with a machine line in which embodiments of the invention are implemented; Figure 2: an exemplary computer device by means of which the embodiments of the invention can be carried out;

[0014] Figure 3: an exemplary plant configuration for PET containers and adhesive packaging;

[0015] Figure 4: an exemplary plant configuration for PET containers and shrink packers;

[0016] Figure 5: an exemplary plant configuration for cans or glass bottles; and

[0017] Figure 6: an example plant configuration for cans.

[0018] Figure 1 shows an exemplary architecture of a machine line 100 and various components for human-machine interaction according to embodiments of the invention.

[0019] One aim of the invention is to prepare the often complicated texts and outputs or information in general on a user interface, such as on an HM1 110 or screen or in other documentation, for an operator 120 of a machine and / or a machine line 100 in such a way that they are linguistically understandable to him.

[0020] Essentially, embodiments of the invention pursue three different concepts to convey such information to an operator 120 in an understandable way, which is important for the control of a machine line 100.

[0021] To address the challenges described above, embodiments of the invention provide systems and methods that perform the following functions. According to a first aspect, the system can translate or convert technical language into more easily understandable everyday language. The system is capable of translating complex technical texts and messages into everyday language using simple and easily understandable words. According to embodiments, the system also provides the possibility to ask follow-up questions to clarify ambiguities or request further details that assist the operator in solving a problem.

[0022] For example, it is common for manufacturers to describe certain terms, words, or explanations in a highly technical way, making the information understandable only to trained personnel. The methods described herein make it possible to translate these complex sentences into simpler language, enabling an untrained operator to understand the content and, if necessary, assess whether they can resolve the problem themselves or require expert assistance.

[0023] A second aspect of the system's capabilities is its ability to automatically identify poorly written or unclear sentences and transform them into unambiguous and clear formulations, thus enabling unambiguous interpretation. Many texts and technical documentation about machines are written by the technical developers. Often, these texts contain poor wording or grammar, which can lead to confusion during operation. Here, too, embodiments of the invention can help to automatically transform these texts into a more readable and understandable form.

[0024] According to a third aspect, the system can also translate texts into languages ​​that may not be supported by the machine manufacturer or that the customer has not explicitly requested. This enables operators worldwide to operate and understand machines in their preferred language without relying on the manufacturer's specific language options. In many cases, operators work on a machine even though they do not speak the language intended for machine control. In such cases, the embodiments of the invention can be used to automatically and selectively translate individual texts within the system into the operator's respective language.

[0025] Figure 1 shows an exemplary architecture in which the embodiments of the invention can be implemented. The essential steps of the embodiments generally take place in a computer device 105, which acts between the machine line 100 itself and the operator 120 and provides this operator 120 with a user interface 110, such as an HMI.

[0026] The computer device 105 can, for example, be a cloud system 105a, a local server 105b located near the machine line 100 and / or an edge device 105c, and can include the functionality as further described in Figure 2.

[0027] The exemplary computer device 105 comprises a plurality of functional components that interact to enable the implementation of the described invention. The computer device 105 includes, for example, a first memory 204 and possibly a second memory 206, which serve to store data and instructions required for carrying out the invention. The memories 204 and 206 can comprise volatile and / or non-volatile storage media, such as RAM, ROM, hard disk drives, or solid-state memory.

[0028] Data processing and instruction execution can be performed by a central processing unit, or CPU 208, which serves as the main processor of the computer device 105. The CPU 208 is capable of performing complex calculations and logical decisions that are essential for the function of the invention. It can be implemented as a single-core processor or as a multi-core processor to ensure higher processing efficiency. In addition to the CPU 208, one or more graphics processing units (GPUs) can also be provided (not shown), since many AI models typically run on such GPUs or, in the future, on dedicated neural processors. Therefore, in addition to a conventional CPU, other processors are also conceivable.

[0029] A user interface 214 enables a user to interact with the computer device 105 and, for example, to provide the HMI 110. It can consist of both hardware-based elements such as keyboards, touchscreens, or physical switches, and software-based interfaces provided via graphical user interfaces, such as the HMI 110. This interface serves to receive input from the operator 120 and to provide output in a form understandable to the operator 120.

[0030] For communication with external devices or networks, the device is equipped with a communication module 212. This module can support wired or wireless connections, for example via Ethernet, WLAN, Bluetooth, or cellular standards. The communication module 212 enables data exchange between the computer device and other systems, which is particularly important for networked applications or cloud-based services.

[0031] The various components of the computer device 105 are interconnected via a bus system 202. The bus system 202 serves as a communication medium that enables data transfer between the individual components. It ensures that data can be transferred efficiently and reliably between memory 204, CPU 208, communication module 212, and other connected modules.

[0032] Furthermore, the computer device 105 includes a control module 210, which is used for the customized output of control or information elements. According to embodiments, the control module can be software code representing the corresponding control and which can be executed by the technical means of the computer device 105. However, the control module 210 can also be a standalone hardware and software module that provides the control as a standalone solution for the computer device 105.

[0033] Various AI implementations are conceivable, such as deep learning implementations specifically trained to interpret languages ​​and texts about the technical documentation of machine line 100. Another AI technology that can be used for the embodiments of the invention is large language modeling technology.

[0034] A Large Language Model (LLM) is a machine learning-based system specifically trained to process and generate text data. It uses neural networks, particularly deep neural networks, to analyze the statistical and semantic relationships between words, sentences, and paragraphs. The foundation of an LLM typically consists of an architecture such as the Transformer model, which is capable of efficiently processing information across large sequences.

[0035] A key feature of a learning logic model (LLM) is its training phase, in which it is trained on a large amount of text data. This data comes from various sources, such as scientific articles, technical documentation, books, or online content. During the training process, the model optimizes its weights and parameters to make predictions about the next word in a text sequence based on the preceding words. This technique is called "autoregressive training." The Transformer architecture used by most LLMs consists of several layers of self-attention mechanisms and feedforward networks. The self-attention mechanism allows the model to identify relationships between words in a context, regardless of how far apart those words are.This is particularly important in order to correctly grasp semantic relationships and syntactic structures in a text.

[0036] After completing the training, the LLM can be used to solve various natural language processing (NLP) tasks. These include automatic text generation, answering questions, summarizing texts, machine translation, and analyzing text sentiment. The versatility of an LLM stems from its ability to recognize patterns and structures in text data and apply them to new contexts. To use an LLM in the specific application described herein, it can either be used directly or further fine-tuned on a smaller, domain-specific dataset. This fine-tuning allows the LLM to adapt to the requirements of a specific task or the documentation of machine line 100.The basic knowledge of the model is retained, while at the same time the ability to process content relating to machine line 100 is improved.

[0037] The LLM takes input in the form of text, which is converted into numerical vectors ("tokens") and processed through several layers of the neural network. The output also consists of numerical vectors, which are converted back into readable text. By using special optimization techniques and computing resources such as GPUs or TPLIs, the model is able to perform these calculations in a reasonable amount of time.

[0038] According to one embodiment, the control module 210 can access a first control or information element intended for output to the machine operator 120 via the HMI 110. The first control or information element can, for example, be stored in the first document memory 204. This could be textual information from digital controls of the HMI 110, files relating to technical documentation of the machine line 100, or current status information, etc.

[0039] The Kl module 210 can then create an intermediate representation of the first control or information element. This intermediate representation could, for example, be a numerical vector for the internal processing of the information by the Kl module. This intermediate representation of the control or information element is thus available in a generic form to the Kl module 210 and can be translated by the Kl module 210 into any desired output format.

[0040] According to embodiments, the Kl module 210 is based on an LLM in which a technical description of the machine or machine line 100 is embedded as a technical context. The embedded context of the machine can be used to create the intermediate representation and / or the second control or information element (as described below).

[0041] For further processing, an operator context can then be captured. The operator context can be entered by an operator and specify the type of control or information element to be output. For example, the operator context can specify a particular language for the output, such as a translation from German to Chinese, or output in a specific dialect, such as Bavarian or Low German. Furthermore, the operator context can also indicate the operator's membership in a specific operator group. An operator group can, for example, categorize an operator based on experience, access rights, language skills, training level, safety level, area of ​​responsibility, and / or certification. This can be done automatically by capturing the current operator (120) or entered manually by the operator (120).

[0042] Once the operator context has been captured, a second control or information element can be generated using the KL module 210, based on the intermediate representation and the operator context. This second control or information element supplements, replaces, and / or completes the first control or information element and can then be output via the HMI 110. The second control or information element can be stored, for example, in the second document memory 206, or it can be stored together with the first control or information element in the first document memory 204.

[0043] According to one embodiment, the first control or information element can be a text relating to technical documentation and the second control or information element can be a content-related reproduction of the technical documentation in improved and / or simplified language for the operator 120 of the machine.

[0044] According to another embodiment, the first control or information element can be a text relating to technical documentation in a first language, such as German, and the second control or information element can be the same text in a second language that differs from the first language.

[0045] According to embodiments, a text or speech input unit can also be provided to the operator 120 via the HMI 110. The operator 120 can receive text or speech input regarding the second control or information element via this unit. This text or speech input could, for example, be a question from the operator regarding the output, which can then be interpreted by the AI ​​module 210. The AI ​​module 210 can then generate a corresponding response and output it via the HMI 110. This allows the operator 120 to directly ask follow-up questions, which can be answered by the AI ​​module 210.

[0046] The embodiments described herein significantly improve the usability of the machines by using clear and understandable language, making operation easier even for less technically experienced users. This leads to noticeably higher user satisfaction, as the barrier to entry for dealing with complex technology is reduced. At the same time, it increases overall customer satisfaction, as users develop greater trust in the machines and feel more confident in operating them. The optimized communication between humans and machines thus contributes significantly to a positive user experience and simultaneously minimizes potential malfunctions and operating errors. This also has a particularly positive effect on the assessment of safety-relevant aspects in the operation of machine line 100.

[0047] Figures 3 to 6 below describe various exemplary system configurations for different bottle filling plants in which the invention, or at least parts and aspects of the invention, can be implemented. The description in Figures 3 to 6 is intended only to provide a general overview of machines for which the customized output of messages, control elements, or information elements can be performed.

[0048] Figure 3 shows an exemplary system configuration 1000 for PET bottles or PET containers and adhesive packaging. As can be seen in Figure 3, the system configuration 1000 comprises various modules that form a line at the end of which finished PET containers are dispensed as a bundle onto pallets. Some of the modules and machines may be optional, and the invention is not limited to the exact shape and arrangement of the system configurations.

[0049] The system configuration 1000 comprises an oven 1002 for preforms, a preform sorter with a feeding machine 1004, and a blow molding machine 1008. Modules 1002, 1004, and 1008 generally form a stretch blow molding machine in which PET containers are produced and formed from a raw material. The manufactured PET containers are then transferred 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 accumulate in the preforms during storage or transport. These are removed by the rinser. A capper can be installed at the end of the filler to seal the PET containers after filling.

[0050] Optionally, the system configuration 1000 can include a rotary device downstream of the filler 1010, which is used for hot filling of the PET containers. The filled PET containers are conveyed via one or more conveyor belts 1016, which can also include a buffer 1018 for intermediate loading of filled containers, to a singulator 1020 and then to a drying unit 1024, where the PET containers are dried. 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 hot melt adhesive, cold glue, self-adhesive labels, or sleeves. After printing or labeling the PET containers, the PET containers are guided through a second drying device 1028, a line distributor 1030, conveyor belts 1032, an adhesive packaging production unit 1034 and a curing section to a handle applicator.In the adhesive packaging production line 1034, the PET containers are grouped into specific sizes and packaged into a unit, such as a six-pack. A carrying handle is attached to the unit using a handle applicator, allowing for comfortable carrying. The finished units are then arranged by a robot 1042 for layering and packed onto pallets by a palletizer 1044.

[0051] In the 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 the format trolley 1006 for the blow molding machine 1008, the format trolley 1012 for the filler 1010, the format trolley 1022 for the labeling machine 1026, the format trolley 1038 for the adhesive packaging production 1034, and the format trolley 1046 for the palletizer 1044.

[0052] Figure 4 shows another exemplary plant configuration 1100 for PET containers and shrink wrappers. The plant 1100 in Figure 4 includes many of the modules and machines from the plant configuration 1000 in Figure 3; however, there are some differences. Therefore, the description of the modules already described in connection with Figure 3 is omitted for Figure 4.

[0053] A key difference between the two example system configurations 1000 and 1100 is that the labeling machine 1126 with the labeling modules 1127 can be installed after the blow molding machine 1008 and before the filler 1008. In contrast, system configuration 1100 can include six transport lanes 1150 into which the PET containers can be inserted. Once the PET containers have inserted themselves into one of the six lanes 1150, they are conveyed into the film wrapping module 1152 and then into the shrink tunnel 1154.

[0054] Figure 5 shows an exemplary plant configuration 1200 for cans or glass bottles. The exemplary plant configuration 1200 from Figure 5 again has some similarities to the plant configurations 1000 and 1100 from Figures 3 and 4, and the description of the plant configuration is therefore limited to the differences between the plant configurations.

[0055] As shown in Figure 5, the exemplary system configuration can include two separate infeeds. A first infeed, on the left in Figure 5, shows a branch for cans or, optionally, a partial branch for reusable new bottles. The containers, i.e., cans or new bottles, are fed into the machine from a depalletizer 1302, where they are conveyed via conveyor belts to the filler 1010. A second infeed, on the right in Figure 5, shows a partial branch for reusable bottles, which are fed into the system from a reusable bottle sorting system (not shown).

[0056] In the case that the already used reusable bottles are fed into system 1200 via the reusable bottle branch, the reusable bottles first pass through the cleaning machine or washing machine 1304. Another possible difference of 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, into crates, or both.

[0057] Figure 6 shows an exemplary system configuration 1300 for cans, in which the elements already described in the other system configurations are not described again. In system configuration 1300, the cans are fed from a magazine 1402 into the depalletizer 1302. After passing through the filler and being filled, the cans are sealed by means of a sealing magazine 1404 and conveyed further along the system 1400 via the conveyor belts, as described above.

[0058] The optional Pasteur 1408 can be bypassed via the Bypass 1412 if it is not needed. Freshly filled products can be pasteurized in the Pasteur 1408 for preservation.

[0059] In contrast to plant configurations 1000, 1100, and 1200, exemplary plant configuration 1300 shows various tanks for corresponding consumables, such as tanks 1410 containing rinsing fluid and / or the filling product, and tanks 1406 containing belt lubricant. These tanks can also be included in the exemplary plant configurations already described above. For example, chemical products 106, which are fed from mixer 110 to the machines, can be stored in tanks 1406 and 1410.

Claims

REQUIREMENTS 1. Computer-implemented method for providing control and status information for operating a machine in a production line, in particular a production line for filling and packaging food and / or beverages, wherein the method comprises: Accessing an initial control or information element intended for output to a machine operator via an HMI; Create, using artificial intelligence (AI), an intermediate representation of the first control or information element; Capturing an operator context; Create, using the KL, a second control or information element based on the intermediate representation and the operator context; and Output of the second control or information element via the HMI.

2. The method according to claim 1, wherein the first control or information element is a text relating to technical documentation and wherein the second control or information element is a content-related reproduction of the technical documentation in improved and / or simplified language for the operator of the machine.

3. The method of claim 1, wherein the first control or information element is a text relating to technical documentation in a first language and wherein the second control or information element is the same text in a second language that differs from the first language.

4. A method according to claim 1 or 2, further comprising: Providing a text or speech input unit via the HMI; Receiving text or voice input from the operator regarding the second control or information element, wherein the text or voice input is a question from the operator regarding the output; interpreting, using the computer, the received text or voice input and generating a corresponding response; and Output the generated response via the HMI.

5. Method according to any one of claims 1 to 4, wherein the operator context: is entered by an operator and specifies the type of control or information element to be output; and / or indicates the operator's affiliation with a specific operator group, where an operator group relates to a categorization regarding experience, access rights, language skills, level of training, security level, area of ​​responsibility, and / or certification.

6. Method according to any one of claims 1 to 5, wherein: the class is a Large Language Model (LLM); The LLM incorporates a technical description of the machine as a technical context; and The embedded context of the machine is used to create the intermediate representation and / or the second control or information element.

7. System for providing control and status information for operating a machine in a production line, in particular a production line for filling and packaging food and / or beverages, wherein the system comprises: at least one machine in a machine line; a human-machine interface (HMI); A computer device that is communicatively connected to the HMI and the machine in order to receive data from the machine and transmit control signals to the machine, wherein the computer device is further designed to: Accessing an initial control or information element intended for output to a machine operator via the HMI; creating, using artificial intelligence (AI), an intermediate representation of the initial control or information element; Capturing an operator context; Create, using the KL, a second control or information element based on the intermediate representation and the operator context; and Output of the second control or information element via the HMI.

8. System according to claim 7, wherein the first control or information element is a text relating to technical documentation and wherein the second control or information element is a content-related reproduction of the technical documentation in improved and / or simplified language for the operator of the machine; or wherein the first control or information element is a text relating to technical documentation in a first language and wherein the second control or information element is the same text in a second language that differs from the first language.

9. A computer-readable storage medium containing program instructions recorded on it, which, when executed by at least one computer device, configure at least one computer device to: Accessing an initial control or information element intended for output to a machine operator via an HMI; Create, using artificial intelligence (AI), an intermediate representation of the first control or information element; Capturing an operator context; Create, using the KL, a second control or information element based on the intermediate representation and the operator context; and Output of the second control or information element via the HMI.

10. Computer-readable storage medium according to claim 9, wherein the first control or information element is a text relating to technical documentation and wherein the second control or information element is a content-related reproduction of the technical documentation in improved and / or simplified language for the operator of the machine; or 14where the first control or information element is a text relating to technical documentation in a first language and where the second control or information element is the same text in a second language that is different from the first language. 15

Images