Method for generating a virtual person for an interaction with a real person by means of a system, computer program product, computer-readable storage medium, and system

Abstract

The invention relates to a method for generating a virtual person (12) for an interaction (24) with a real person (14) by means of a system (10) for outputting the virtual person (12), having the steps of: - providing a digital model (26) for virtual persons (12) by means of an electronic computing device (16) of the system (10); - detecting an adaptation input (28) from a user of the electronic computing device (16), said adaptation input (28) corresponding to at least one virtual personality parameter for the virtual person (12); - adapting a personality profile (30) of the digital model (26) on the basis of the adaptation input (28) for the virtual person (12) by means of the electronic computing device (16); - transmitting the virtual person (12) with the adapted personality profile (30) to an output device (18) of the system (10); and - outputting the virtual person (12) in order to interact (24) with the real person (14) by means of the output device (18). The invention additionally relates to a computer program product, to a computer-readable storage medium, and to a system (10).

Description

[0001] 202312739 Foreign Version 1 Description Method for generating a virtual person for interaction with a real person by means of a system, computer program product, computer-readable storage medium and system The invention relates to a method for generating a virtual person for interaction with a real person by means of a system for outputting the virtual person. Furthermore, the invention relates to a computer program product, a computer-readable storage medium and a system. The user experience during communication with a digital assistant, in particular a virtual person, suffers from a lack of empathy and provided context. Conversation is not possible because a digital assistant only has a number of properties and otherwise relies on knowledge from, for example, the Internet, such as Wikipedia.The conversation is reduced to a pure knowledge query and, accordingly, difficult for real people to enjoy. This leads to no recurrence and no unique and therefore memorable exchange. The appearance, or the so-called user interface (UI), of a digital assistant is designed independently of a personality. The knowledge base is filled without empathy. Especially with the introduction of generative artificial intelligence dialogue frameworks, such as ChatGPT, it is arbitrary whether a question is answered humorously or sarcastically, in detail or concisely. These frameworks have no embodiment and no empathy. However, empathy is fundamental for the persistent transfer of knowledge to the human brain. Furthermore, effective human-machine communication is only possible—especially in the area of ​​complex issues—ifwhen empathy is evident on both sides. Effectiveness, on the other hand, is the key to energy-saving, sustainable, and economically successful use of machines. For digitalization technology to penetrate all areas, it is essential that the barriers between real and virtual people—especially on the real people side—are reduced as much as possible, for example, so that the real people no longer react to their virtual counterparts in a stressed manner, but rather in a completely normal and / or relaxed manner. This task can be accomplished through psychological training of real people, but also through further development of the virtual people, particularly their personality, which empowers the virtual person to show empathy. The object of the present invention is to create a method, a computer program product, a computer-readable storage medium, and a system,by means of which improved communication between a real person and a virtual person can be realized. This task is achieved by a method, a computer program product,a computer-readable storage medium and a system according to the independent patent claims. Advantageous embodiments are specified in the subclaims. One aspect of the invention relates to a method for generating a virtual person for interaction with a real person by means of a system for outputting the virtual person. A digital model for an individual personality or personality profile of the virtual person is provided by means of an electronic computing device of the system. The digital model is individually generated and / or compiled and / or extracted from a library of individually generated digital models. Optionally, an adaptation input from a user of the electronic computing device is also recorded.wherein the adaptation input corresponds to at least one virtual personality parameter for the virtual person. The personality profile of the digital model is adapted to the virtual person by means of the electronic computing device 202312739 Foreign Version 3 depending on the adaptation input. The virtual person with the adapted personality profile is transmitted from the backend of the system to an output device of the system, and the virtual person is output for interaction with the real person by means of the output device located in the frontend of the system. This enables improved communication between the virtual person and the real person. In particular, it is proposed that an initial digital model for the personality of the virtual person be provided. A user, for example a programmer for the personality of the virtual person,can then make a corresponding adjustment input to provide the digital model with personality parameters, such as character traits of the virtual person. The digital model is then adjusted accordingly depending on this adjustment input and provided with an individual personality profile. The digital model with the adjusted personality profile is then made available to an output device so that a person, in particular an end user,can communicate with the virtual person in a relaxed and open manner – and thus in a time- and energy-efficient manner. In particular, during communication, the predefined digital model changes depending on the adaptation input, and based on this, communication between the real person and the digital person can be carried out in a realistic manner. A correspondingly modeled personality profile is particularly intended to ensure that communication takes place in the same way as can be carried out with a real person. The virtual person thus interacts not only with pure knowledge, for example, through an internet query, but can also display personality traits such as smiling, blinking, politeness, commenting, joy, optimism, but also sarcasm.Anger or the like can be incorporated into the communication. Thus, the virtual person is assigned a digital personality, as a real person is used to when communicating with other real people, which positively influences the virtual person's output and thus the communication in terms of realism. This allows for improved communication with the real person, as the real person can develop empathy for the virtual person – and vice versa – thereby realizing improved persistent knowledge transfer. In particular, the difference according to the state of the art is the extension to a virtual person in a dialogue system with a modeled digital personality profile and / or digitized character traits or, for example, an individual history, a life background,and the resulting personality and emotional, human-like reaction of the virtual person to inputs from the real person, based on the personality profile. In particular, the invention thus provides that, for example, character traits, or even a past personality profile, give the virtual person a personality. This personality is reflected in corresponding answers, reactions, and the appearance of the virtual person. Past personality profiles can be retrieved, for example, in special storage units of the system and / or in the IoT within a library. The focus of the invention is particularly on fictional personalities. According to an exemplary embodiment, these fictional personalities should neither resemble the real person with whom they are currently communicating in terms of personality structure, cultural background, and / or individual history.202312739 Foreign Version 5 imitate and / or even mirror them. This is especially to avoid the "uncanny valley" effect. Rather, the virtual person, for example the avatar, has its very own fictional story. This is generated using sources with comprehensive biographies and / or parameters such as the zodiac sign: Pisces. In this way, I immediately endow the personality of the virtual person with character traits such as "sociable, amiable, sensitive, daydreamer, etc...". For example, one of the Myers-Briggs types "MBTI" is used to determine a psychological type for the personality of a virtual person. The MBTI is an instrument with which the psychological types developed by Carl Gustav Jung can be captured. Of course, there are personalities,which combine several of these MBTI types and / or several types contribute to the development of personality to varying degrees. This is already known for real people and can be implemented in virtual people using the present invention. For example, as an alternative or in addition to the MBTI type, the Holland Code is used to generate the personality of a virtual person. According to the Holland Code, there are six personality types – specifically job-related – although several personality types of varying degrees are also often used to digitally form the personality of a virtual person according to one embodiment of the invention. The personality of a virtual person is modeled in this way by the programmer, preferably at least also via text input, e.g., continuous text or XML. This creates a unique blend and individual personality of the virtual person.just like real people are. 202312739 Foreign Version 6 For implementation, a prompted LLM and / or a prompted NLP serves as a source for generating a personality in the backend of the system. These personality(ies) are collected, for example, in the form of a library and / or can be applied to various visual images of the virtual persons. Inputs in text format, written and / or verbal, are preferably used as a source for developing the personality structure of a virtual person. Video inputs are optionally used as support, but due to their visual manifestation, they are not as suitable as text inputs.that create a personality independent of the virtual person's appearance. As already mentioned, the personality / personality profile of the virtual person is located in the backend of the system and not in the frontend. This allows the personality / personality profile to be stored and used independently of the image. The image, the representation of the virtual person, is created in the frontend of the system. The personality of the virtual person is determined by their appearance,Image decoupled. The optics are in the frontend and the personality / personality profile in the backend of an exemplary system according to an embodiment of the invention. For example, such a system also supports the exchange of the personality / personality profile from a virtual person to a virtual person with a completely different image and / or appearance. According to an advantageous embodiment, the output device is provided as a display device. For example, the display device can be provided in the form of a display. The virtual person can then be provided as a type of avatar, in particular in the form of a human. The virtual person can have personalized or individualized clothing as well as facial features, hair color, or the like. The display device is, for example, life-size.202312739 Foreign Version 7 so that the virtual person is also displayed life-size on the display device. This allows for improved interaction between the real person and the virtual person. It is also advantageous if the virtual person is displayed as an avatar. An avatar is, in particular, a virtual or artificial person in the form of a graphic figure in the front end of the system, which in particular represents the embodiment of a person. In other words, the virtual person can be displayed as a digital person, in particular with corresponding body extremities.Facial features and the like can be displayed. In particular, the avatar can also perform facial and body movements depending on the output signal for the avatar's output. For example, when the avatar speaks, corresponding mouth movements can be output. Thus, extremely realistic communication between the real person and the virtual person, in particular the avatar, can be realized. It is also advantageous if an input from the real person is recorded by means of a recording device of the system, and a reaction from the virtual person is output depending on the input and depending on the adapted personality profile. For example, the recording device can be designed in the form of a camera or in the form of a microphone device. A corresponding voice input or optical input, for example a movement of the real person,can thus be captured by the virtual person. A corresponding movement or speech can then be evaluated by the electronic computing device, and a reaction, particularly depending on the personality profile, can be initiated by the virtual person. Thus, corresponding inputs from the real person can be responded to, enabling extremely realistic communication, particularly depending on the situation. 202312739 Foreign Version 8 It has also proven advantageous if a speech input from the real person and / or a gesture from the real person and / or facial expressions from the real person are captured as input. In particular, the corresponding human emotions of the real person can thus be captured by the virtual person and evaluated accordingly. For this purpose, a corresponding database can be available, in particular.which, for example, carries out corresponding evaluations and stores corresponding reactions based on the personality profile. In particular, the electronic computing device evaluates the recorded input and links it with reactions for the virtual person. This allows the real person to be addressed in a situation-dependent and highly individual manner, enabling realistic communication between the real person and the virtual person. A further advantageous embodiment provides for the virtual person's voice output and / or gestures and / or facial expressions to be adapted depending on the input. In particular, the corresponding gestures, facial expressions, or voice output can also be adapted depending on the input. This allows a human reaction to be simulated by the virtual person.whereby the communication between the virtual person and the real person can be generated in an extremely realistic manner. It has also proven advantageous if the digital model of the personality profile is adapted using artificial intelligence in the electronic computing device. In particular, the electronic computing device can, for example, have a neural network, which in turn can adapt the personality profile accordingly – even during ongoing communication in real time. For example, during the ongoing operation of the virtual person, the personality profile is, in particular, continuously,adapted. This allows, for example, an adaptation of the personality to be carried out even after the start of operation. In particular, the virtual person can, for example, react to corresponding inputs by the person and / or build a corresponding reaction to current events - which, for example, flow into the communication from the IoT. These events are continuously retrieved using keywords, for example, and / or incorporated into the ongoing communication. Depending on the topic, this can create a new turn and / or mood in the communication. The data on the event and the adaptation of the communication are also saved, for example, and, if necessary, used as training data for adapting the personality profile. This allows communication to be carried out in a highly up-to-date manner. It is also advantageouswhen the behavior of the real person is recorded and stored, and the personality profile of the virtual person is adjusted depending on the recorded behavior. If, for example, the real person is consistently late for appointments, this can be stored accordingly and, for example, adjusted in the personality profile of the virtual person. For example, the virtual person can then output appropriate reactions to the consistent lateness, such as reacting angrily. In particular, it can thus be provided that real persons can be identified using the virtual person. For this purpose, the electronic computing device can, for example, implement a corresponding recognition algorithm,For example, they may have an object recognition algorithm. Thus, the virtual person or the personality profile of the virtual person can be adapted to the real person's behavior. It has also proven advantageous if a virtual background story for the virtual person is entered as an adaptation input. In particular, a type of past life can be suggested to the virtual person, for example, a marital status, character traits, and experiences, which in turn can influence the personality of the virtual person. Based on these background stories, the virtual person can, for example, incorporate appropriate answers or reactions into communication with the real person.whereby communication with the real person can be provided in a realistic manner. Furthermore, it has proven advantageous if a location of the virtual person is recorded and the personality profile is adapted depending on the location. For example, if the virtual person is to be deployed within an industrial environment, the personality profile can be adapted accordingly so that the virtual person in the industrial environment has a personality profile for the industrial environment. For example, the relevant terminology used and the clothing displayed can be adapted depending on the location. Another advantageous embodiment providesthat a plurality of output devices are provided at a location where the virtual person is deployed, and the virtual person is output using the plurality of output devices. For example, the virtual person can then be displayed accordingly at different locations. In particular, different display devices can be provided at different locations to show the virtual person. Thus, the virtual person is not only addressable at one location, but different locations within the location are possible where the virtual person can be deployed, and thus communication with the virtual person can be carried out at different locations. It has also proven advantageouswhen interacting with different people at different output devices. Thus, interaction with different people can take place at different locations, so that, for example, parallel interaction with different people is also possible. Thus, the virtual person can be flexibly deployed within a location. The presented method is, in particular, a computer-implemented method. Therefore, a further aspect of the invention relates to a computer program product with program code means which cause an electronic computing device, when the program code means are processed by the electronic computing device,to carry out a method according to the preceding aspect. Furthermore, the invention therefore also relates to a computer-readable storage medium with the computer program product. Yet another aspect of the invention relates to a system for generating a virtual person for interaction with a real person, comprising at least one electronic computing device and an output device, wherein the system is designed to carry out a method according to the preceding aspect. In particular, the method is carried out by means of the system. Advantageous embodiments of the method are to be regarded as advantageous embodiments of the computer program product, the computer-readable storage medium, and the system. For this purpose, the system has, in particular, material features in order to be able to carry out corresponding method steps. Here and in the following, an artificial neural network can be understood as software code,which is stored on a computer-readable storage medium and represents one or more networked artificial neurons or can simulate their function. The software code can also contain several software code components, which can, for example, have different functions. In particular, an artificial neural network can implement a non-linear model or a non-linear algorithm that maps an input to an output, wherein the input is given by an input feature vector or an input sequence, and the output can, for example, contain an output category for a classification task, one or more predicted values, or a predicted sequence. Within the scope of the present disclosure, an object recognition algorithm, for example for recognizing / identifying a real person,can be understood as a computer algorithm that is capable of identifying and locating one or more objects within a provided input data set, for example, an input image, for example by defining corresponding bounding boxes or regions of interest (ROIs) and, in particular, by assigning a corresponding object class to each of the bounding boxes, wherein the object classes can be selected from a predefined set of object classes. The assignment of an object class to a bounding box can be understood in such a way that a corresponding confidence value or probability that the object identified within the bounding box belongs to the corresponding object class is determined.is provided. For example, the algorithm may provide such a confidence value or probability for each of the object classes for a given bounding box. Assigning the object class may, for example, involve selecting or providing the object class with the highest confidence value or probability. Alternatively, the algorithm may simply specify the bounding boxes without assigning a corresponding object class. Algorithms for automatic visual perception, which may also be referred to as computer vision algorithms, machine vision algorithms, or machine vision algorithms, can be considered computer algorithms for automatically performing a visual perception task. A visual perception task, also referred to as a computer vision task,can, for example, be understood as a task for extracting visual information from image data. In particular, the visual perception task can, in principle, be performed by a human who is able to visually perceive an image corresponding to the image data. In the present context, however, visual perception tasks are also performed automatically, without the need for human assistance. A computer vision algorithm, for example for recognizing / identifying a real person or for evaluating a gesture or facial expression of the real person, can, for example, contain an image processing algorithm or an image analysis algorithm that is or has been trained by machine learning and is based, for example, on an artificial neural network, in particular a convolutional neural network.The computer vision algorithm can, for example, include an object detection algorithm, an obstacle detection algorithm, an object tracking algorithm, a classification algorithm, a semantic segmentation algorithm, and / or a depth estimation algorithm. Corresponding algorithms can also be implemented analogously based on input data other than images visually perceivable by humans. For example, point clouds or images from infrared cameras, lidar systems, etc., can also be evaluated using appropriately adapted computer algorithms. Strictly speaking, the corresponding algorithms are not algorithms for visual perception, since the corresponding sensors can operate in areas that are visually imperceptible to the human eye.for example, in the infrared range. Therefore, such algorithms are referred to as algorithms for automatic perception in the context of the present invention. Algorithms for automatic perception therefore include algorithms for automatic visual perception, but are not limited to these with regard to human perception. Consequently, an algorithm for automatic perception according to this understanding can contain a computer algorithm for automatically performing a perception task, which is or has been trained, for example, by machine learning and can in particular be based on an artificial neural network. Such generalized algorithms for automatic perception can also include object detection algorithms, object tracking algorithms, classification algorithms, and / or segmentation algorithms, for example semantic segmentation algorithms.If an artificial neural network is used to implement an algorithm for automatic visual perception, a frequently used architecture is that of a convolutional neural network, CNN. In particular, a 2D CNN can be applied to corresponding 2D camera images. CNNs can also be used for other automatic perception algorithms. For example, 3D CNNs, 2D CNNs, or 1D CNNs can be applied to point clouds, depending on the spatial dimensions of the point cloud and the details of the processing. The result or output of an automatic perception algorithm depends on the specific underlying perception task. For example, the output of an object detection algorithm may contain one or more bounding boxes.which define a spatial position and optionally an orientation of one or more corresponding objects in the environment and / or corresponding object classes for the one or more objects. An output of a semantic segmentation algorithm applied to a camera image can contain a pixel-level class for each pixel of the camera image. Analogously, an output of a semantic segmentation algorithm applied to a point cloud can contain a corresponding point-level class for each of the 202312739 foreign version 15 points. The pixel-level or point-level classes can, for example, define an object type to which the respective pixel or point belongs. A computing unit / electronic computing device can be understood to mean, in particular, a data processing device,which contains a processing circuit. The computing unit can therefore, in particular, process data to perform computing operations. This may also include operations to perform indexed accesses to a data structure, for example a look-up table (LUT). The computing unit can, in particular, contain one or more computers, one or more microcontrollers, and / or one or more integrated circuits, for example one or more application-specific integrated circuits (ASICs), one or more field-programmable gate arrays (FPGAs), and / or one or more single-chip systems (SoCs). The computing unit can also contain one or more processors, for example one or more microprocessors, one or more central processing units (CPUs).one or more graphics processing units (GPUs) and / or one or more signal processors, in particular one or more digital signal processors (DSPs). The computing unit can also include a physical or virtual network of computers or other of the aforementioned units. In various embodiments, the computing unit includes one or more hardware and / or software interfaces and / or one or more memory units. A memory unit can be implemented as a volatile data memory, for example as a dynamic random access memory (DRAM) or a static random access memory (SRAM), or as a non-volatile data memory, for example as a read-only memory (ROM), as a programmable read-only memory,PROM (programmable read-only memory), EPROM (erasable programmable read-only memory), EEPROM (electrically erasable programmable read-only memory), Flash memory or Flash EEPROM, FRAM (ferroelectric random access memory), MRAM (magnetoresistive random access memory), or PCRAM (phase-change random access memory). For applications or application situations that may arise during the process and are not explicitly described here,that according to the method, an error message and / or a request for user feedback is output and / or a default setting and / or a predetermined initial state is set. Regardless of the grammatical gender of a particular term, persons with male, female, or other gender identities are included. Further features and combinations of features of the invention emerge from the figures and their description, as well as from the claims. In particular, further embodiments of the invention do not necessarily have to contain all features of one of the claims. Further embodiments of the invention may have features or combinations of features,which are not mentioned in the claims. The sole figure shows: FIG. 1 shows a schematic block diagram according to an embodiment of a system. 202312739 Foreign version 17 In the FIG. 1, identical or functionally equivalent elements are provided with the same reference numerals. The FIG. 1 shows a schematic block diagram according to an embodiment of a system 10. The system 10 is designed to generate a virtual person 12 for an interaction 24 with a real person 14. For this purpose, the system 10 has at least one electronic computing device 16 and at least one output device 18. In the present exemplary embodiment, the output device 18 is designed, for example, as an optical display device 20.and for this purpose, for example, further comprises a microphone device 22 for outputting a voice output. In particular, the FIG shows a method for generating the virtual person 12 for an interaction 24 with the real person 14. A digital model 26 for virtual persons 12 is provided by the electronic computing device 16. An adaptation input 28 is acquired from a user of the electronic computing device 16,wherein the adaptation input 28 corresponds to a virtual personality profile for the virtual person. A personality profile 30 of the digital model 26 is adapted to the virtual person 12 as a function of the adaptation input 28 by means of the electronic computing device 16. The virtual person 12 with the adapted personality profile is then transmitted to the output device 18 of the system 10. The virtual person 12 is then output for interaction 24 with the real person 14 by means of the output device 18. In particular, the FIG shows that the virtual person 12 can be displayed as an avatar. Furthermore, it can be providedthat an input 32 of the real person 14 is recorded by means of a recording device 34 of the system 10, and a reaction 36 of the virtual person 12 is output depending on the input 32 and depending on the adapted personality profile 30. For this purpose, it can be provided, for example, that a voice input of the real person 14 and / or a gesture of the real person 14 and / or a facial expression of the real person 14 is recorded as input 32. Furthermore, a voice output of the virtual person 12 and / or a gesture of the virtual person 12 and / or facial expression of the virtual person 12 can be adapted depending on the input 32. Furthermore, it can be provided that the personality profile 30 is adapted by means of an artificial intelligence 38 of the electronic computing device 16. Furthermore, it can be providedthat a behavior of the real person 14 is recorded and stored, and the personality profile 30 of the virtual person 12 is adapted depending on the recorded behavior. In particular, it can be provided that a virtual background story for the virtual person 12 is entered as adaptation input 28. Furthermore, it can be provided that a deployment location 40 of the virtual person 12 is recorded, and the personality profile 30 is adapted depending on the deployment location 40. Furthermore, a plurality of output devices 18 can be provided in a deployment location 40 of the virtual person 12, and the virtual person 12 can be output using the plurality of output devices 18. It is also possiblethat different people 14 are then interacted with at the different output devices 18. In particular, the FIG describes the introduction of a past and a characteristic for the virtual person 12, thereby generating a personality profile 30 for the virtual person 12 202312739 Foreign Version 19. The personality is reflected in the answers, the reaction 36, and the appearance of the virtual person 12. For example, if an avatar as a virtual person 12, particularly as a user interface, is given a corresponding background story or past, such as that it is a patient, hardworking mother of two children and works full-time, but misses this very much, and comes from a small village in Ukraine and has worked her way up in a company on her own with hard work and intellect and is now very proud to have been employed as a guide at an innovation center,This makes the necessary appearance of the virtual person 12 clear, and also enriches the answers to questions with emotions. The real person 14 thus converses with the virtual person 12 and does not interact with a purely digital assistant. For each person, the background story and / or the modeled personality are "promptly" supplemented to the generative artificial intelligence 38, and when asked a question, it is instructed to enrich this modeled personality with the appropriate emotion, which is then reproduced by the virtual person 12. For example, if the real person 14 asks when the appropriate opening hours of an innovation center are, the virtual person 12 can answer that the innovation center will be closed in an hour. The virtual person 12 smiles and adds,This allows the children of the virtual person 12 to be picked up at the same time. Compared to the prior art, the difference lies in the fact that, according to the SdT, a response from the virtual person only includes, for example, that the innovation center will be closed in one hour. In a conversation with real people, the virtual system's response could therefore be met with rejection because the real person would perceive this uncommented information as impolite. However, a virtual person according to embodiments of the present invention 202312739 Foreign Version 20 could, thanks to their "own" modeled personality and individual background, empathize and immediately incorporate the link to concern for the children into the response, which would certainly increase the real person's openness and / or willingness to talk, as well as the efficiency of the information exchange in the machine-human interaction.

[0002] 202312739 Foreign version 21 List of reference symbols 10 system 12 virtual person 14 real person 16 electronic computing device 18 output device 20 display device 22 microphone device 24 interaction 26 digital model 28 adaptation input 30 personality profile 32 input 34 recording device 36 reaction 38 artificial intelligence 40 place of use

Claims

202312739 Foreign version 22 patent claims 1. Method for generating a virtual person (12) for an interaction (24) with a real person (14) by means of a system (10) for outputting the virtual person (12), comprising the steps of: - providing a digital model (26) for a personality of the virtual person (12) by means of an electronic computing device (16) of the system (10); - detecting an adaptation input (28) from a user of the electronic computing device (16), wherein the adaptation input (28) corresponds to at least one virtual personality parameter for the virtual person (12); - adapting a personality profile (30) of the digital model (26) as a function of the adaptation input (28) to the virtual person (12) by means of the electronic computing device (16); - transmitting the virtual person (12) with the adapted personality profile (30) to an output device (18) of the system (10);and - outputting the virtual person (12) for interaction (24) with the real person (14) by means of the output device (18).

2. Method according to claim 1, characterized in that the output device (18) is provided as a display device (20).

3. Method according to claim 2, characterized in that the virtual person (12) is displayed as an avatar.

4. Method according to one of the preceding claims, characterized in that an input (32) of the real person (14) is detected by means of a detection device (34) of the system (10) and a reaction (36) of the virtual person (12) is output depending on the input (32) and depending on the adapted personality profile (30).; 202312739 Foreign Version 23 5. The method according to claim 4, characterized in that a voice input of the real person (14) and / or a gesture of the real person (14) and / or a facial expression of the real person (14) is recorded as input (32).

6. The method according to claim 4 or 5, characterized in that a voice output of the virtual person (12) and / or a gesture of the virtual person (12) and / or a facial expression of the virtual person (12) is adapted as a reaction (36) depending on the input (32).

7. The method according to one of the preceding claims, characterized in that the personality profile (30) is adapted, in particular continuously, by means of artificial intelligence (38) of the electronic computing device (16). 8.Method according to one of the preceding claims, characterized in that a behavior of the real person (14) is recorded and stored and the personality profile (30) of the virtual person (12) is adapted depending on the recorded behavior.

9. Method according to one of the preceding claims, characterized in that a virtual background story for the virtual person (12) is entered as the adaptation input (28).

10. Method according to one of the preceding claims, characterized in that a location (40) of the virtual person (12) is recorded and the personality profile (30) is adapted depending on the location (40).

11. Method according to one of the preceding claims, characterized in that. 202312739 Foreign Version 24 In a deployment location (40) of the virtual person (12), a plurality of output devices (18) are provided, and the virtual person (12) is output by means of the plurality of output devices (18).

12. The method according to claim 11, characterized in that interaction takes place with different real persons (14) at the different output devices (18).

13. A computer program product with program code means which, when the program code means are processed by the electronic computing device (16), cause an electronic computing device (16) to carry out a method according to one of claims 1 to 12.

14. A computer-readable storage medium with at least one computer program product according to claim 13. 15.System (10) for generating a virtual person (12) for an interaction (24) with a real person (14), with at least one electronic computing device (16) and an output device (18), wherein the system (10) is designed to carry out a method according to one of claims 1 to 12.

Images