Method and system for using artificial intelligence with a language model for semantic analysis of text-based information relating to an industrial automation arrangement

Abstract

The invention relates to a method and a system for using artificial intelligence (AI) with a language model for semantic analysis of text-based information (IN) relating to an industrial automation arrangement, in particular text-based outputs, instructions or other information artefacts from an industrial program or automation object, wherein the artificial intelligence (AI) is confronted with a query containing the information (TE) and wherein the language model outputs a semantic analysis (SA) of the information (TE). The artificial intelligence (AI) is enriched with an ontology of the concepts of a domain of the industrial automation arrangement prior to the query. It is thus possible to identify information about the use of terms or other text elements and the correlations thereof and to use said information for operation or further development of the automation arrangement.

Description

[0001] Description

[0002] Method and system for using artificial intelligence with a language model for the semantic analysis of text-based information of an industrial automation system

[0003] The invention relates to a method for using artificial intelligence with a language model for the semantic analysis of text-based information of an industrial automation arrangement according to the preamble of patent claim 1, and to a system for using artificial intelligence with a language model for the semantic analysis of text-based information of an industrial automation arrangement according to the preamble of patent claim 8.

[0004] Artificial intelligence systems are increasingly being used to analyze program or text elements of industrial automation systems, such as program blocks, alarm messages, screen outputs, and the like. In particular, it is desirable to use common language models such as ChatGPT from OpenAI to support operating personnel, project engineers, and other specialists.

[0005] While it is possible to automate or transfer language constructs (so-called artifacts) of an industrial automation program or project such as tags (e.g. identifiers of variables or data points), data blocks, function blocks, alarms or screens into an ontology, the semantics of the application domain, i.e. the real automation arrangement to be controlled and its physical elements, is not accessible. The language constructs or artifacts mentioned are constructs of the automation programming language used; however, the term language construct is also intended to refer to other artifact types in an automation solution, such as e.g.

[0006] Screens (screen contents), alarms or alarm messages, devices and device descriptions (devices), etc. The purpose of a function block, the semantics of a tag, the content of a visualization element, etc. can only be understood through the respective name, comments, or other text elements. Therefore, semantic technology cannot be used to search for artifacts, describe relationships, understand the relationship between functions and operations and plant elements, or ensure consistency between automation artifacts and their external world. This would be necessary, in particular, to ensure that automation algorithms produce correct results, for example when generating automation code.

[0007] The publication US 11,397,762 B2 - Raval Contractor et al. "AUTOMATICALLY GENERATING NATURAL LANGUAGE RESPONSES TO USERS' QUESTIONS" discloses the generation of a textual answer to a textually formulated question in a domain using a pre-trained model.

[0008] Basic automation ontologies already exist that capture basic automation concepts such as FBs, DBs, tags, screens or alarms with relationships between them, but they lack the reference to real objects.

[0009] It is therefore an object of the present invention to propose a system and a method with which text elements from the industrial automation environment are semantically analyzed, wherein in particular the use of terms or text elements and their relationships are recognized.

[0010] The idea underlying the solution to this problem is to create an ontology that captures the main concepts of the area (domain) to which the automated projects relate. The application semantics are encoded, among other things, in a standardized naming convention, where the names typically refer to the visualized plant structure to which IO tags (i.e., input and output interfaces and their identifiers) are connected or which are controlled by a series of function blocks, each of which also has a structured name.

[0011] The object is achieved in particular by a method according to patent claim 1 and by a system according to patent claim 8.

[0012] A method is proposed for using artificial intelligence, in particular a language model, for the semantic analysis of text-based information of an industrial automation system, in particular text-based outputs, instructions or other information artifacts from an industrial program or automation object (e.g. screen output of an operating device), wherein the language model is confronted with a query with the information and wherein the language model outputs a semantic analysis of the information. The artificial intelligence is enriched with an ontology of the concepts of a domain of the industrial automation system, wherein in a first step naming conventions for text elements, in particular for structured identifiers, are derived from an automation system or from an automation standard common for the domain.extracted and converted into ontological concepts, in a second step, many or all text elements, in particular from program code, comments, alarms, messages or screen outputs, are extracted from at least one automation project of the domain or a related domain, in a third step, all irrelevant text components, in particular articles and prepositions, are removed from the text elements, in a fourth step, a probabilistic language model is generated from the text elements and all text elements, in particular nouns, that occur with a probability above a threshold value are added to the ontology, and in a fifth step, relations between text elements are determined and stored for or in the ontology,The language model then performs a semantic analysis of the input information based on the ontology and outputs semantic references to the input information. This makes it possible to determine information about the use of terms or other text elements and their relationships and to use this information for operating or further developing the automation system.

[0013] The object is achieved with the same advantages by a system for using artificial intelligence, in particular a language model, for the semantic analysis of text-based information of an industrial automation arrangement, in particular text-based outputs, instructions or other information artifacts from an industrial program or automation project, wherein it is provided that the language model is confronted with the information using a query and wherein the language model is set up to output a semantic analysis of the information. The system is set up to carry out the first to fifth method steps from the method according to patent claim 1.

[0014] Advantageous embodiments of the method according to the invention are specified in the dependent patent claims. The features described therein and their advantages also apply mutatis mutandis to the system according to the invention. The advantageous embodiments can be implemented both individually and in combination with one another.

[0015] A good solution is achieved if, in the fifth step, the relationships are determined based on conditions between the text elements and / or based on the probability of the text elements occurring together. Furthermore, when determining the probability of co-occurrence, a spatial distance between the text elements in a text block can be taken into account. An equally simple and reliable approach is to determine a relative or absolute frequency of occurrence of the text element in the analyzed automation project in the fourth step for generating the probabilistic language model and to use this to calculate the probability of occurrence of a text element or a coherent group of text elements.

[0016] Multiple entries, which particularly impair the statistical methods of the procedure, are avoided by reducing a word to its basic form in the third step and / or by determining and storing the role of a word (e.g. subject, predicate, object or verb).

[0017] According to the invention, artificial intelligence uses the ontology to convert the information into a graph, with each element of the graph being output with a function derived from the ontology and / or a relation to other elements. Graphs are a common form of notation in industrial environments that can also be easily processed by machines, particularly for analyses, decision trees, or software generators.

[0018] According to the invention, instructions for configuring, influencing, or maintaining the automation system are generated from the output of the artificial intelligence. For this purpose, it is also advantageously possible to generate program artifacts, control information, and / or configuration data for the automation system, in particular for generating program code for an industrial automation component of the automation system, from the output of the artificial intelligence.

[0019] An exemplary embodiment of the method according to the invention is explained below with reference to the drawing. It also serves to explain a system according to the invention. The figure shows that a number of automation projects PR and semantic conventions SK, also called semantic concepts, from a domain relevant to the respective application (e.g. production of body components, synthesis of hydrocarbon compounds or the like) of automation technology are evaluated in five steps S1, ..., S5 to form an ontology which is then incorporated into an artificial intelligence AI. Furthermore, existing (older) projects PR from the same industrial domain can optionally also be processed. The artificial intelligence AI is then confronted during operational use with queries which contain information IN, for example in the form of text components.The artificial intelligence AI then outputs a semantic analysis of the information IN, in this case the text modules or similar contained in the query.

[0020] To this end, we will demonstrate below that an ontology is created that captures the main concepts of the area (domain) to which the automated PR projects relate. The application semantics are encoded, among other things, in a standardized naming convention, where the names typically refer to the visualized plant structure to which I / O tags (i.e., identifiers of the input and output interfaces) are connected or which are controlled by a series of function blocks, each of which also has a structured name.

[0021] In the first step (S1), the naming conventions (SK) of the corresponding automation standard are analyzed. These can be customized; for example, an automobile manufacturer has its own identifiers and abbreviations for its common automation components, such as presses, robots, grippers, doors, etc. The naming rules are converted into ontological concepts.

[0022] An example:

[0023] A text element of a source code is: ++ST030+IR001 FB

[0024] In the naming convention, ST means station, IR means industrial robot, and FB can mean function module or function block. An ontology is then determined from the text element and incorporated into the artificial intelligence language model, which can look like this:

[0025] • Concept "Station" designated with ++STxxx ;

[0026] • "Industrial robot" concept, marked with +IRxxx ;

[0027] • The industrial robot can be part of a station.

[0028] In a second step S2, all texts (comments, alarm text, screen text, etc.) from a series of projects with a similar domain, e.g., all "white body" projects (body construction) of a manufacturer ("OEM") are extracted according to the above-mentioned standard. If the sources are different, these can also be translated into a common language if necessary.

[0029] In a third step (S3), which can also be combined with the second step (S2), all irrelevant words (articles, prepositions, etc.) are removed. To do this, the words are reduced or reduced to their root form (infinitive for verbs, nominative for nouns, etc.). In an advantageous variant, the type of word (noun, verb, adjective, adverb) and, if possible, the role of the word in the sentence (subject, predicate, object) are determined and stored as meta-information for the words.

[0030] In a fourth step S4, a probabilistic language model is created from the intermediate results determined above, which model analyzes in particular statistical properties of the occurrence of words or terms. This can cover the probability that a word occurs in a term or sentence, the probability that two words occur in the same sentence, or the conditional probability that a word occurs in a sentence or phrase if a certain other word occurs in the sentence or phrase. It can also differentiate between different roles of the word in its occurrence. Those words whose occurrence probability or frequency lies above a minimum probability limit are then added to the ontology. Different thresholds can be set depending on the word class or role.

[0031] In a fifth step (S5), the relationships between words are determined based on the conditional or joint probability and the role of the words. This means, for example, that a spatial relationship between words or conditions (e.g., from if-then constructs or from mathematical operations) reveals a relationship.

[0032] Now, for example, PLC and HMI artifacts (i.e., information based on text elements (TE) from programmable logic controller programs or from output texts from operator control and monitoring devices (HMI)) in a specific project can be semantically analyzed, searched, and annotated in a standardized way based on the derived ontology. For example, the automation artifacts (FBs, FCs, tags, networks, screens, alarms, etc.) can be integrated into a graph database, including their intended use (e.g., for networks), their relationship to the plant model (for functions, screens, or alarms), or their error types (for alarms). The technology used here is semantic technology such as SPARQL, SHACL, or OWL.

[0033] A first application example analyses the internal identifier of a display page for an operating and monitoring device (HMI - Human Machine Interface): • Screen with name

[0034] ++STO 10+ IRO 02_IDB_FG001_{ SYMB} ROBOT_APPL_GRIPPER { Register}

[0035] This text element is analyzed using a previously learned naming convention and the knowledge that terms such as "ROBOT", "APPL" and "GRIPPER" (gripper) are in direct spatial relationship in the text element TE to:

[0036] • Image of the "Station" 10 for an "Industrial Robot" in the functional group "001" and its "Gripper"-

[0037] " Application" .

[0038] A second application example analyses the comment on a program structure ("network comment") in an automation program

[0039] • “Invocation protective grid door Amgard”

[0040] (in German: "Call for the Amgard safety gate") .

[0041] This comment is analyzed using a previously learned naming convention and the previously trained ontology to produce a human-understandable commentary on the individual program structure (referred to as a "network" in industrial programming languages):

[0042] • The network purpose is to call the "protective gate" of the type "Amgard".

[0043] A third application example analyses an alarm text that is output by an operator panel (“HMI panel”) in an industrial environment:

[0044] Alarm text “close clamp

[0045] The German translation is "Klammer schließen" (close bracket). The user must "close" a bracket.

[0046] Initially, this is only a translation, but since the alarm is part of the automation ontology, its relationship to the affected function block (FB) and to the network (program structure) that triggers the alarm can be retrieved from an ontology manager (e.g., the GraphDB product), including the actuator or sensor that has failed in the plant.

[0047] Basic ontologies are well known in automation domains. These can be managed and displayed, for example, using the product "Simatic Project Insight." However, they do not refer to relationships with real objects; instead, they analyze relationships within a project or structure. The solution proposed here, based on the basic automation ontology, searches for automation artifacts and regular expressions that are processed using texts and comments. This makes it possible to determine real-world relationships. Questions such as "Which blocks in the program do this or that?" can be answered with reference to physical entities. For example, alarm messages can be analyzed without manually evaluating the underlying program code. The method therefore leads to a new type of "expert system."

Claims

Patent claims 1 . Method for using an artificial intelligence (AI) with a language model for the semantic analysis of text-based information (IN) of an industrial automation arrangement, in particular of text-based outputs, instructions or other information artifacts from an industrial program or automation object, wherein the artificial intelligence (AI) is confronted with a query with the information (TE) and wherein the language model outputs a semantic analysis (SA) of the information (TE), characterized in that the artificial intelligence (AI) is enriched with an ontology of the concepts of a domain of the industrial automation arrangement before the query, wherein in a first step (S l) naming conventions (SK) for text elements, in particular for structured identifiers, are derived from an automation arrangement or from an automation standard common for the domain.extracted and converted into ontological concepts, in a second step (S2) many or all text elements, in particular from program code, comments, alarms, messages or screen outputs, are extracted from at least one automation project (PR) of the domain or a related domain, that in a third step (S3) all irrelevant text components, in particular articles and prepositions, are removed from the text elements, that in a fourth step (S4) a probabilistic language model is generated from the text elements and all text elements occurring with a probability above a threshold value, in particular nouns, are added to the ontology, that in a fifth step (S5) relations between text elements are determined for or in the ontology, and stored, after which the language model carries out a semantic analysis (SA) of the input information (IN) on the basis of the ontology and outputs semantic references to the input information (TE), that the artificial intelligence (AI) uses the ontology to convert the information into a graph, whereby a function derived from the ontology and / or a relation to other elements is output for each of the elements of the graph, and that instructions for configuring, influencing or maintaining the automation arrangement are generated from the output of the artificial intelligence (AI).

2. Method according to claim 1, characterized in that in the fifth step (S5) the relations are determined on the basis of conditions between the text elements and / or on the basis of the probability of the text elements occurring together. 3 . Method according to claim 2 , characterized in that a spatial distance between the text elements in a text block is taken into account when determining the probability of joint occurrence.

4. Method according to one of the preceding claims, characterized in that in the first step (S1) at least one existing automation project (PR) is used to extend information about the naming conventions (SK).

5. Method according to one of the preceding claims, characterized in that in the third step (S3) a word is reduced to its basic form and / or the role of a word, in particular subject, predicate, object or verb, is determined and stored. 6 . Method according to one of the preceding claims, characterized in that in the fourth step ( S4 ) for generating the probabilistic language model, a relative or absolute frequency of occurrence of the text element in the analyzed automation project is determined and the probability of occurrence of a text element or a connected group of text elements is calculated therefrom.

7. Method according to one of the preceding claims, characterized in that program artifacts, control information and / or configuration data for the automation arrangement, in particular for the generation of program code for an industrial automation component of the automation arrangement, are generated from the output of the artificial intelligence (AI).

8. System for using artificial intelligence (AI) with a language model for the semantic analysis of text-based information of an industrial automation arrangement, in particular text-based outputs, instructions or other information artifacts from an industrial program or automation object, wherein it is provided to confront the language model with a query with the information (IN) and wherein the language model is set up to output a semantic analysis (SA) of the information (IN), characterized in that the system is set up to carry out the method steps from the method according to patent claim 1.

Images