DE102021129108A1 - Method, system and computer program product for outputting output values for analysis and/or evaluation and/or process control of an entity - Google Patents

Abstract

The invention relates to a method for outputting output values for analysis and/or evaluation and/or for process control of an entity (10), comprising the following method steps: - Generating at least one first data set (20), the data set (20) at least depicts a partial aspect of the entity (10);- generating at least one second data record (30), wherein the second data record (30) depicts at least a partial aspect of the entity (10), and wherein the second data record (30) is independent of the first data record ( 20) is generated;- processing the first data set (20) in the first encoder (25) to create a first representation (Z1);- processing the second data set (30) in the second encoder (35) to create a second representation ( Z2);- Creating a correlation function (55) between the first representation (Z1) and the second representation (Z2) from the correlation module (50);- Applying the correlation function (55) to at least a third data set (70) in order to Output module (80) to generate and output output values for analysis and/or for evaluation and/or for process control of the entity (10).

Description

The invention relates to a method, a system and a computer program product for outputting output values for analysis and/or evaluation and/or process control of an entity.

In mechanical engineering and in automotive engineering, a large number of components with mechanical, electrical, electronic, hydraulic, chemical, etc. components are required, which are subject to constant further development due to new model series, environmental specifications, etc., which is time-consuming and costly. For example, the choice or design of a bearing for a construction project is based on selected boundary conditions such as the relative speed of the two moving parts, the loads, the operating temperature, the service life, the material of the parts, etc. The elements of a bearing are constructed or designed in such a way that various parameters such as dimensions, shape and materials of the bearing are changed while maintaining the selected boundary conditions. Optimization algorithms can be used for this. Typically, however, a bearing is designed based on the expertise and experience of experts such as engineers. However, this is associated with a considerable expenditure of time and thus costs.

Access controls for people are an important issue in security technology, for example by means of passport control. Even if automated procedures are increasingly being used to identify and authenticate the authorized persons, the unambiguous assignment to a specific person is not always given.

The EP 3 382 630 A1 describes a method for providing production-related information for a product to be manufactured. Information about the product is checked against information from a database and the information retrieved is used to provide manufacturing related information.

The WO 2020/056041 A1 discloses a method of data acquisition and data processing to generate an output for use in an analysis of a physical object using machine learning algorithms to detect geometries, state or type of the physical objects.

The CN 111859048A discloses a method for retrieving vehicle part models, material parameters and manufacturing parameters of the vehicle parts being retrievable from a component model library by means of a query.

The U.S. 2021/0004719 A1 discloses a computer-implemented method for training a generative autoencoder. The generative autoencoder is configured to generate a data structure representing a mechanical assembly of rigid parts and containing a tree. Each leaf node represents a shape and positioning of a respective rigid part and a force applied to the respective rigid part.

The WO 2018/222285 A1 describes a method for designing a product using artificial intelligence algorithms.

The object on which the invention is based is now to create a method, a system and a computer program product for outputting output values for analysis and/or evaluation and/or process control of an entity, which is characterized by high reliability, security and accuracy and can be easily implemented.

According to the present invention, a method, a system and a computer program product are proposed which make it possible to improve an analysis and/or an assessment and/or a process control of an entity and to make it more sustainable and efficient.

This object is achieved according to the invention with regard to a method by the features of patent claim 1, with regard to a system by the features of patent claim 10, and with regard to a computer program product. The further claims relate to preferred embodiments of the invention.

• - Generieren zumindest eines ersten Datensatzes aus mittels zumindest eines Sensors ermittelten Daten und/oder aus in Datenbanken gespeicherten historischen Daten, wobei der Datensatz zumindest einen Teilaspekt der Entität abbildet;
• - Generieren zumindest eines zweiten Datensatzes aus mittels zumindest eines Sensors ermittelten Daten und/oder aus in Datenbanken gespeicherten historischen Daten, wobei der zweite Datensatz zumindest einen Teilaspekt der Entität abbildet, und wobei der zweite Datensatz unabhängig von dem ersten Datensatz generiert wird;
• - Weiterleiten des ersten Datensatzes an zumindest einen ersten Encoder;
• - Weiterleiten des zweiten Datensatze an zumindest einen zweiten Encoder;
• - Bearbeiten des ersten Datensatzes in dem ersten Encoder zur Erstellung einer ersten Repräsentation Z₁, wobei die erste Repräsentation Z₁ Parameter und Parameterwerte, Variablen und Variablenwerte umfasst;
• - Bearbeiten des zweiten Datensatzes in dem ersten Encoder zur Erstellung einer zweiten Repräsentation Z₂, wobei die zweite Repräsentation Z₂ Parameter und Parameterwerte, Variablen und Variablenwerte umfasst;
• - Zuführen der ersten Repräsentation Z₁ und der zweiten Repräsentation Z₂ zu einem Korrelationsmodul;
• - Erstellen einer Korrelationsfunktion zwischen der ersten Repräsentation Z₁ und der zweiten Repräsentation Z₂ von dem Korrelationsmodul;
• - Anwenden der Korrelationsfunktion auf zumindest einen dritten Datensatz, der aus mittels zumindest eines Sensors ermittelten Daten und/oder aus in Datenbanken gespeicherten historischen Daten generiert wird, wobei der Datensatz zumindest einen Teilaspekt der Entität abbildet, und wobei der dritte Datensatz unabhängig von dem ersten Datensatz und dem zweiten Datensatz generiert wird, um in einem Ausgabemodul Ausgabewerte zur Analyse und/oder zur Bewertung und/oder zur Prozesssteuerung der Entität zu erzeugen und auszugeben.

According to a first aspect, the invention provides a method for outputting output values for analysis and/or evaluation and/or process control of an entity. The procedure comprises the following procedural steps:

• - generating at least a first data set from data determined by means of at least one sensor and/or from historical data stored in databases, the data set depicting at least a partial aspect of the entity;
• - Generating at least one second data record from data determined by means of at least one sensor and/or from historical data stored in databases, the second data record depicting at least a partial aspect of the entity, and the second data set is generated independently of the first data set;
• - forwarding the first data set to at least a first encoder;
• - forwarding the second data set to at least one second encoder;
• - processing the first data set in the first encoder to create a first representation Z ₁ , the first representation Z ₁ comprising parameters and parameter values, variables and variable values;
• - processing the second data set in the first encoder to create a second representation Z ₂ , the second representation Z ₂ comprising parameters and parameter values, variables and variable values;
• - Feeding the first representation Z ₁ and the second representation Z ₂ to a correlation module;
• - creating a correlation function between the first representation Z ₁ and the second representation Z ₂ from the correlation module;
• - Application of the correlation function to at least a third data set, which is generated from data determined by means of at least one sensor and/or from historical data stored in databases, the data set depicting at least a partial aspect of the entity, and the third data set being independent of the first data set and the second data record is generated in order to generate and output output values for analysis and/or for evaluation and/or for process control of the entity in an output module.

In a further development it is provided that the first encoder and the second encoder each comprise a neural network.

In an advantageous embodiment it is provided that the first encoder is trained with the first data set and the second encoder is trained with the second data set.

In particular, the correlation engine uses artificial intelligence and machine learning algorithms.

A further embodiment provides for the use of canonical correlation analysis (CCA) algorithms.

Advantageously, at least one parameter or at least one variable represents a dimension or a material or a material composition or a shape or a characteristic value or a condition or a safety factor or an identification code or a location or a point in time or a thermal resistance or an electrical resistance or a conductivity or strength, or fracture behavior, or color, or density, or plastic deformation, or resistance to stress, compression, flexure, or material properties, or surface properties, or heat treatment.

A further development provides for the sensors to be used as clocks, counters, pressure sensors, piezo sensors, speed sensors, capacitive sensors, inductive sensors, temperature sensors, image-recording cameras in the visible range, UV cameras in the ultraviolet range, IR cameras in the infrared range, LIDAR ( Light detection and ranging) systems with optical distance and speed measurement, stereoscopic optical camera systems, ultrasound systems, radar systems and / or CAD systems are formed.

In an advantageous embodiment it is provided that the first data set is CAD data and the second data set is product data of a first product, and the third data set is CAD data of a second product.

In a further advantageous embodiment, it is provided that the first data set is physiological data determined by means of at least one sensor, such as the heart rate and/or biometric data such as the color of the iris of a person, and the second data set is image data recorded by at least one camera from the Person at a first point in time, and the third data set is image data of the person recorded by a camera at a different point in time.

According to a second aspect, the invention provides a system for issuing output values for analysis and/or evaluation and/or process control of an entity. The system comprises at least a first data module, at least a second data module, and at least a third data module, the first data module, the second data module and the third data module each having at least one sensor for determining data and/or at least one database with stored historical data are connected, a first encoder and a second encoder, a representation module for storing representations Z, a correlation module for creating correlations between data sets, and at least one output module for generation and outputting output values for analysis and/or for evaluation and/or for process control of the entity. The system is designed to carry out the method according to the first aspect.

In a further development, the first encoder and the second encoder each include a neural network.

A further embodiment provides that the first encoder is trained using the first data set and the second encoder is trained using the second data set.

In particular, the correlation engine uses artificial intelligence and machine learning algorithms.

In an advantageous embodiment, it is provided that algorithms of canonical correlation analysis (CCA) are used.

According to a third aspect, the invention provides a computer program product comprising executable program code configured, when executed, to carry out the method according to the first aspect.

The invention is explained in more detail below with reference to exemplary embodiments illustrated in the drawing.

• 1 ein Blockdiagramm zur Erläuterung eines Ausführungsbeispiels eines erfindungsgemäßen Systems;
• 2 ein Flussdiagramm zur Erläuterung der einzelnen Verfahrensschritte eines erfindungsgemäßen Verfahrens;
• 3 zeigt schematisch ein Computerprogrammprodukt gemäß einer Ausführungsform des dritten Aspekts der Erfindung.

It shows:

• 1 a block diagram to explain an embodiment of a system according to the invention;
• 2 a flowchart to explain the individual steps of a method according to the invention;
• 3 shows schematically a computer program product according to an embodiment of the third aspect of the invention.

Additional features, aspects and advantages of the invention or embodiments thereof will become apparent from the detailed description coupled with the claims.

1 shows a system 100 for outputting output values for analysis and/or evaluation and/or for process control of an entity 10. In particular, the entity 10 can be a product, for example an electric motor, a motor vehicle, a structural component such as a mechanical component such as a Bearings act as electrical and/or electronic and/or mechatronic and/or hydraulic and/or chemical and/or biological components. In addition, entity 10 can also be a production plant for manufacturing a product, such as a production plant for manufacturing a motor vehicle. The production facility can also be an interconnected network of production facilities that develops and manufactures a common product or a variety of different products.

However, entity 10 can also be model calculations for scientific studies, climate models, economic models such as stock trading, development projects such as drug development or product development, administrative tasks, route planning, software developments, for example for autonomous driving, etc. In addition to inanimate objects, the entity 10 can also be animate subjects such as people or animals.

The entity 10 is connected to sensors 23, 34, 73 which collect data from the entity 10. You sensors 23, 33, 73 can be used as clocks, counters, pressure sensors, piezo sensors, speed sensors, capacitive sensors, inductive sensors, temperature sensors, image-recording cameras in the visible range, UV cameras in the ultraviolet range, IR cameras in the infrared range, LIDAR (Light detection and ranging) systems with optical distance and speed measurement, stereoscopic optical camera systems, ultrasound systems, radar systems and / or CAD systems are formed.

The data determined by the sensors 23, 33, 73 can be images and/or data on physical, chemical, biometric and/or physiological processes and states.

The data from the sensors 23 are transmitted to a first data module 22 , the data from the sensors 33 to a second data module 32 and the data from the sensors 73 to a third data module 72 . The data modules 22, 32 and 72 are each provided with or connected to a processor and/or a memory module. In particular, the data modules 22, 32, 72 are each connected to a database 24, 34, 74. The database 24, 34, 74 contains in particular historical data about the entity 10.

In the context of the invention, a “processor” can be understood to mean, for example, a machine or an electronic circuit. A processor can in particular be a main processor (Central Processing Unit, CPU), a microprocessor or a microcontroller, for example an application-specific integrated circuit or a digital signal processor, possibly in combination with a memory unit for storing program instructions, etc. A processor can also be understood to mean a virtualized processor, a virtual machine or a soft CPU. It can also be a programmable processor, for example, which is equipped with configuration steps for executing the mentioned method according to the invention or is configured with configuration steps in such a way that the programmable processor has the inventive features of the method, the component, the modules, or other aspects and/or or realized partial aspects of the invention.

In the context of the invention, a “memory unit” or “memory module” and the like can mean, for example, a volatile memory in the form of a random-access memory (RAM) or a permanent memory such as a hard disk or a data carrier or e.g. B. be understood as a removable memory module. However, the storage module can also be a cloud-based storage solution.

In connection with the invention, a “module” can be understood to mean, for example, a processor and/or a memory unit for storing program instructions. For example, the processor is specially set up to execute the program instructions in such a way that the processor and/or the control unit executes functions in order to implement or realize the method according to the invention or a step of the method according to the invention.

In connection with the invention, “data” is understood to mean both raw data and already processed data from measurement results from sensors or from other sources.

"Database" means both a storage algorithm and the hardware in the form of a storage unit. In particular, the database is designed as a cloud computing infrastructure.

The sensors 22, 32, 72 send the ^determined data to the data modules 22, 32, 72 via a communication connection. Fi® trained.

The data modules 22, 32, 72 can represent separate units with regard to their hardware configuration, but they can also use identical hardware components and units to carry out their function.

The first data module 22 generates at least one first data set 20 from the data determined by means of at least one sensor 23 and/or from the historical data stored in the database 24 . This first data set 20 depicts at least a partial aspect of the entity 10 .

The second data module 32 generates at least one second data set 30 from the data determined by at least one sensor 33 and/or from the historical data stored in the database 34 . The second data set 30 depicts at least a partial aspect of the entity 10 and is generated independently of the first data set 20 .

The first data set 20 is forwarded to a first encoder 25 and the second data set 30 is forwarded to a second encoder 35 . In particular, the first encoder 25 and the second encoder 35 comprise artificial intelligence algorithms, in which case neural networks are used in particular.

A neural network consists of neurons that are arranged in several layers and connected to each other in different ways. A neuron is able to receive information from outside or from another neuron at its input, to evaluate the information in a certain way and to pass it on to another neuron in a changed form at the neuron output or to output it as the end result. Hidden neurons are located between the input neurons and output neurons. Depending on the network type, there can be several layers of hidden neurons. They ensure the forwarding and processing of the information. Finally, output neurons deliver a result and output it to the outside world. Different types of neural networks such as feedforward networks, recurrent networks or convolutional neural networks are created by the arrangement and linking of the neurons. The networks can be trained through unsupervised or supervised learning

The convolutional neural network (CNN) is a special form of an artificial neural network. It has multiple layers of convolution and is well suited for machine learning and artificial intelligence (AI) applications in the field of classification, such as image and speech recognition. The functioning of a CNN is to a certain extent based on biological processes and the structure is comparable to the visual cortex of the brain. The training of a CNN takes place usually monitored and can be trained very efficiently with the use of modern graphics processors. The CNN uses filters to detect and extract features from the input images. First of all, the CNN recognizes simple structures such as lines, color features or edges in the first levels. In the further levels, the CNN learns combinations of these structures such as simple shapes or curves. With each level, more complex structures can be identified. The data is repeatedly resampled and filtered in the layers.

The first data set 20 is processed in the first encoder 25 in order to create a first representation Z ₁ of the first data set 20 . A representation Z includes parameters and parameter values, variables and variable values. In particular, a representation is stored in the form of a vector or a matrix. The representation Z ₁ and further representations Z are stored in a representation module 40 . Provision can also be made for the representation module 40 to contain further algorithms, such as in particular classification algorithms, in order to further process and classify the representations Z.

The second data set 30 is processed in the second encoder 35 in order to create a second representation Z ₂ of the second data set 20 . The representation Z ₂ is also stored in the representation module 40 .

The first representation Z ₁ and the second representation Z ₂ are supplied to a correlation module 50 . The correlation module 50 contains algorithms for correlation analysis between different representations Z ₁ , Z ₂ , . . . , Z _n , in particular the representations Z ₁ and Z ₂ . In particular, Canonical Correlation Analysis (CCA) algorithms are used. Canonical Correlation Analysis is a way of deriving information from the relationship between two representations Z ₁ , Z _j of parameters and variables. In the case of the representations Z ₁ and Z ₂ can be, for example, the two vectors X = (X ₁ , ..., X _n ) and Y = (Y ₁ , ..., Y _m ) consisting of random variables calculated between the first representation Z ₁ and the second representation Z ₂ , which reflects the mutual dependencies and relationships between the two representations Z ₁ , Z ₂ .

This calculated correlation function 55 is applied to at least one third data set 70 in order to generate and output output values for analysis and/or for evaluation and/or for process control of entity 10 in an output module 80 . The data record 70 is generated from the data determined by means of at least one sensor 73 and/or from the historical data stored in databases 74 and depicts at least a partial aspect of the entity 10 . The third data set 70 is generated independently of the first data set 20 and the second data set 30 . However, the third dataset 70 can use the same sensors 23, 33 and the same databases 24, 34 with which the first dataset 20 or the second dataset 30 was generated.

In addition to the algorithms for canonical correlation analysis, other mathematical functions such as mean values, minimum and maximum values, models for expected values, linear regression methods or Gaussian processes, Fast Fourier transformations, integral and differential calculations, Markov methods, probability methods such as Monte Carlo can also be used Methods, temporal difference learning, extended Kalman filters, radial basis functions, data fields, convergent neural networks, deep neural networks, artificial neural networks and/or feedback neural networks in the correlation module 50 and/or the representation module 40 are used.

The output values are analysis results and assessments of properties of the entity 10 or suggestions for controlling processes of the entity 10. For example, it can be recommendations for a specific shape in a design process, a proposal for creating an electrical circuit or for the Choosing a specific parameter, such as a specific electrical resistance, act.

In particular, the first encoder 25 is trained with the first data set 20 and the second encoder 35 with the second data set 30 in order to generate stable and reliable results in the form of representations Z. The first data set 20 and the second data set 30 typically run through the first encoder 25 and the second encoder 35 10 to 20 times in order to ensure a satisfactory training result.

In one embodiment, the method and system according to the invention can be used for the construction of components. The first data set 20 can be CAD data (CAD—Computer Aided Design) and the second data set 30 can be product data for a first product, and the third data set 50 can be CAD data for a second product. The analysis of the first data set 20 and the second data set 30 can, for example, provide a recommendation for the choice of a material, a wall thickness, a dimensioning, etc. result.

In a further embodiment, the method and system according to the invention can be used for security systems for authentication and identification. In this case, the first data set 20 can be physiological data determined by a sensor 23, such as the heart rate and/or biometric data, such as the color of the iris of a person, and the second data set 30 can be image data recorded by a camera 33 from the person to a person act at the first point in time, and in the case of the third data set 70 to image data recorded by a camera 73 of the person at a different point in time. While two independent data sources are required for training the representations Z that are available to the correlation module 50, in practice only one image recording is required for identification and authentication. By training the two encoders 25, 35 with two data sources generated independently of one another, a meaningful correlation function 55 can be created which, when applied to the third data set 70, leads to secure and reliable statements regarding the identity and authentication of the respective person. If, for example, the first encoder 25 is trained with an image file of a person and the second encoder is trained with biometric data of the person, one image file is sufficient for an identity check in order to be able to establish the person's identity beyond doubt. Additional biometric or physiological data does not have to be requested. This significantly reduces the time required for a clear identification of a person.

In 2 the procedural steps for outputting output values for analysis and/or evaluation and/or process control of an entity 10 are shown.

In a step S10, at least a first data set 20 is generated from data determined by means of at least one sensor 23 and/or from historical data stored in databases 24, with the data set 20 depicting at least a partial aspect of the entity 10.

In a step S20, at least one second data set 30 is created from data determined by means of at least one sensor 33 and/or from historical data stored in databases 34, with the second data set 30 depicting at least a partial aspect of the entity 10, and with the second data set 30 being independent of the first data record 20 is generated.

In a step S30, the first data set is forwarded to at least one first encoder 40.

In a step S40, the second data set is forwarded to at least one second encoder 50.

In a step S50, the first data set 20 is processed in the first encoder 25 to create a first representation Z ₁ , the first representation Z ₁ including parameters and parameter values, variables and variable values.

In a step S60, the second data set 30 is processed in the second encoder 35 to create a second representation Z ₂ , the second representation Z ₂ including parameters and parameter values, variables and variable values.

In a step S70, the first representation Z ₁ and the second representation Z ₂ are fed to a correlation module 50 .

In a step S80, a correlation function 55 between the first representation Z ₁ and the second representation Z ₂ is created by the correlation module 50 .

In a step S90, the correlation function 55 is applied to at least one third data set 70 in order to generate and output output values for analysis and/or for evaluation and/or for process control of the entity 10 in an output module 80, with the data set 70 being made up by means of at least one Sensor 73 determined data and / or generated from historical data stored in databases 74, wherein the data set 70 depicts at least a partial aspect of the entity 10, and wherein the third data set 70 is generated independently of the first data set 20 and the second data set 30.

3 Figure 12 schematically illustrates a computer program product 200 comprising executable program code 250 configured to perform the method according to the first aspect of the present invention when executed.

With the method according to the present invention, output values for analysis and/or evaluation and/or for process control of an entity 10 can thus be reliably generated.

Reference List

10

entity

20

first record

22

first data module

23

sensor

24

Database

30

second record

32

second data module

33

sensor

34

Database

40

representation module

50

correlation module

55

correlation function

70

third record

72

third data module

73

sensor

74

Database

80

output module

100

system

200

computer program product

250

program code

QUOTES INCLUDED IN DESCRIPTION

This list of documents cited by the applicant was generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Patent Literature Cited

• EP 3382630 A1 [0004]
• WO 2020/056041 A1 [0005]
• CN 111859048A [0006]
• US 2021/0004719 A1 [0007]
• WO 2018/222285 A1 [0008]

Claims (15)

Method for outputting output values for the analysis and/or evaluation and/or process control of an entity (10), comprising the following method steps: - generating (S10) at least one first data set (20) from data determined by means of at least one sensor (23) and/or or from historical data stored in databases (24), the data record (20) depicting at least a partial aspect of the entity (10); - Generating (S20) at least one second data set (30) from data determined by means of at least one sensor (33) and/or from historical data stored in databases (34), the second data set (30) containing at least one partial aspect of the entity (10) maps, and wherein the second data set (30) is generated independently of the first data set (20); - Forwarding (S30) of the first data set (20) to at least one first encoder (40); - Forwarding (S40) of the second data set (30) to at least one second encoder (50); - Editing (S50) the first data set (20) in the first encoder (25) to create a first representation (Z ₁ ), the first representation (Z ₁ ) comprising parameters and parameter values, variables and variable values; - Editing (S60) the second data set (30) in the second encoder (35) to create a second representation (Z ₂ ), the second representation (Z ₂ ) comprising parameters and parameter values, variables and variable values; - Supplying (S70) the first representation (Z ₁ ) and the second representation (Z ₂ ) to a correlation module (50); - Creation (S80) of a correlation function (55) between the first representation (Z ₁ ) and the second representation (Z ₂ ) by the correlation module (50); - Applying (S90) the correlation function (55) to at least one third data set (70), which is generated from data determined by means of at least one sensor (73) and/or from historical data stored in databases (74), the data set (70 ) maps at least a partial aspect of the entity (10), and wherein the third data set (70) is generated independently of the first data set (20) and the second data set (30) in order to output values for analysis and/or in an output module (80). to generate and output for evaluating and/or for process control of the entity (10). procedure after claim 1 , wherein the first encoder (25) and the second encoder (35) each comprise a neural network. procedure after claim 1 or claim 2 , The first encoder (25) being trained with the first data set (20) and the second encoder (35) being trained with the second data set (30). Procedure according to one of Claims 1 until 3 , wherein the correlation module (50) uses artificial intelligence and machine learning algorithms. procedure after claim 4 , using Canonical Correlation Analysis (CCA) algorithms. Procedure according to one of Claims 1 until 5 , wherein at least one parameter or at least one variable is a dimension or a material or a material composition or a shape or a parameter or a safety factor or an identification code or a location or a point in time or a thermal resistance or an electrical resistance or a conductivity or a strength or fracture behavior, or color, or density, or plastic deformation, or resistance to stress, compression, flexure, or material properties, or surface properties, or heat treatment. Procedure according to one of Claims 1 until 6 , the sensors (23, 33, 73) being clocks, counters, pressure sensors, piezo sensors, speed sensors, capacitive sensors, inductive sensors, temperature sensors, image-recording cameras in the visible range, UV cameras in the ultraviolet range, IR cameras in the infrared range, LIDAR (light detection and ranging) systems with optical distance and speed measurement, stereoscopic optical camera systems, ultrasound systems, radar systems and/or CAD systems are designed. Procedure according to one of Claims 1 until 7 , wherein the first data set (20) is CAD data and the second data set (30) is product data of a first product, and the third data set (50) is CAD data of a second product. Procedure according to one of Claims 1 until 7 , the first data set (20) being physiological data such as the heart rate and/or biometric data such as the color of the iris of a person determined by means of a sensor (23) and the second data set (30) being recorded by means of a camera (33). Image data is from the person at a first point in time, and the third data set (70) is image data from the person recorded by a camera (73) at another point in time. System for outputting output values for analysis and/or evaluation and/or process control of an entity (10), comprising at least one first data module (22), at least one second data module (32), and at least one third data module (72), the first Data module (22), the second data module (32), and the third data module (72) are each connected to at least one sensor (23, 33, 73) and/or at least one database (24, 34, 74) with stored historical data , a first encoder (25) and a second encoder (35), a representation module (40) for storing representations (Z), a correlation module (50) for creating correlations between data sets (20, 30) and an output module (80) for generating and outputting output values for analysis and/or for evaluation and/or for process control of the entity (10), the system being designed in accordance with the method claim 1 to execute. system (100) after claim 10 , wherein the first encoder (25) and the second encoder (35) each comprise a neural network. system (100) after claim 10 or claim 11 , The first encoder (25) being trained with the first data set (20) and the second encoder (35) being trained with the second data set (30). System (100) according to one of Claims 10 until 12 , wherein the correlation module (40) uses artificial intelligence and machine learning algorithms. system (100) after Claim 13 , using Canonical Correlation Analysis (CCA) algorithms. Computer program product (200), comprising an executable program code (250), which is configured so that when it is executed it performs the method according to any one of Claims 1 until 9 executes

Images