Assessment of the statement in respect to a personal characteristic represented by a virtual person

Abstract

An automated method of assessment of the statement in respect to a personal characteristic represented by a virtual person comprising the steps: Configuring (S1) a digital model for a virtual person (V) based on a configuration parameter (CP) by a first large language model (LLM1), wherein the configuration parameter (CP) defines a personal characteristic (C) of the virtual person (V), generating (S3) a representation (P) of the virtual person (V) based on the digital model, wherein the virtual person (V) represents the personal characteristic (C), receiving (S4) a user (U) input comprising a statement (Q), and generating (S8) a report (A) based on a result of the assessment, and - outputting (S9) the report (A).

Description

[0001] DESCRIPTION

[0002] Assessment of the statement in respect to a personal characteristic represented by a virtual person

[0003] Independent of the grammatical term usage, individuals with male, female or other gender identities are included within the term.

[0004] Field of the Invention

[0005] The embodiments disclosed herein relate to an automated method for assessing a user input in respect to a personal characteristic represented by a virtual person. A corresponding system, computer program product, and computer-readable storage medium are disclosed as well.

[0006] Background of the Invention

[0007] Training materials for soft skill assessment and assessment of personal characteristic are of limited availability. In the area of talent acquisition the focus lies on the interviews with candidates applying for jobs or certain tasks. The skill that needs training is the conversation or interview itself, e.g. to gain useful information on the candidate during the conversation and to learn if a certain candidate fulfils requirements for a task or a job.

[0008] Accordingly, there is a need for a training and a quantitative assessment of a conversation (or communication) skill and / or interpersonal interaction skill.

[0009] Summary

[0010] Embodiments herein generally relate to a method for assessing a user input in respect to a personal characteristic represented by a virtual person.

[0011] The method comprises the step of configuring a digital model for a virtual person based on a configuration parameter by a first large language model. The configuration parameter defines a personal characteristic of the virtual person. The configuration parameter can be seen as a parameter used to prompt the first large language model (LLM). The configuration parameter defines a personal characteristic of the virtual person and thereby a personality of the virtual person. The personal characteristic results out of a backstory of the virtual person. Therefore, the prompt used by the first large language model to configure the digital model includes the backstory (life story and personality) of the virtual person.

[0012] The configuration parameter defines personal characteristic of the virtual person comprising a personal age, and / or an accent, and / or a life habit, and / or a location of living, and / or a gender, and / or an ethnicity, each of the virtual person. Different variables for a configuration parameter allow to configure the virtual person according to different personalities and according to different training needs and certain user skills to train. A user profile with previous assessed user skills serves optionally to select the configuration parameter.

[0013] The method comprises the further step of outputting a briefing information (to the user), the briefing information comprising a requirement (to be fulfilled) for executing a task, especially an imaginary task. The task being especially a job task or a job profile comprising several tasks. Wherein the requirement comprises a skill, and / or a competence, and / or an ability, and / or an experience, and / or a proficiency, and / or an education.

[0014] The method comprises the further step of generating a representation (e.g. a visualization and a sound, e.g. a voice output) of the virtual person based on the digital model. The virtual person represents the personal characteristic defined by the configuration parameter.

[0015] In a further embodiment the generation of the virtual person for interaction with the real person (e.g. the user) based on the digital model is done by a 3D computer graphics engine (for example by “unreal engine”, a series of 3D computer graphics game engines developed by Epic Games) and a displaying unit, e.g. an output device, especially a monitor, and / or glasses (e.g. virtual reality glasses).

[0016] Generating the representation (or “visualization”) (e.g. displaying, presenting, outputting the visualisation) of the virtual person is of advantage as it makes the interaction between real person and the virtual person easier to execute. The virtual person is especially generated (displayed) in life-sized. This enables an improved and more realistic interaction between the real person and the virtual person.

[0017] The method comprises the further step of receiving a user input comprising a statement, especially more than one statements. The user input is received via a user interface, especially via a microphone supported by a camera. Option for input devices comprises motion controller, and / or a VR controller, and / or a gesture recognition system, and / or a motion capture system, and / or a microphone, and / or a keyboard and / or a mouse, and / or a touchscreen, and / or a biometric sensor.

[0018] The statement comprises an assertion (the virtual person may disagree on), and / or an assumption (the virtual person may disagree on), and / or a question, and / or an open question, and / or a closed question.

[0019] The user input comprising the statement is received as a voice input and / or a written text and / or a mimic and / or a gestic.

[0020] The method comprises the further step of performing an assessment (e.g. an evaluation) of the statement (especially of more than one statements and / or especially of a further statement after a reply of the virtual person has been put out (see further embodiments)) in respect to the configuration parameter and in respect to the briefing information, e.g. in respect to the requirement for executing the task and thereby in respect to the personal characteristic represented by the virtual person and defined by the configuration parameter.

[0021] Especially, it is assessed if the statement is coherent with the briefing information and / or the requirement. Further, if more than one statements are received, it is especially assessed if the more than one statements are coherent within themselves.

[0022] The method comprises the further step of generating a report comprising user assessment (on the user’s performance) and optionally advice (e.g. a recommendation) on how to improve framing of a statement and / or framing a question and / or questioning technique based on a result of the assessment.

[0023] The method comprises the further step of outputting the report. The report is outputted via the user interface which is also used for displaying the virtual person. “Outputting the report” is to be understood as making the report available, e.g. readable and / or hearable and / or visually capturable (e.g. showing a “thumbs up) to the real person (the user).

[0024] The method supports the user with a simulation of a personal interaction, e.g. a role play, meaning that a real person meets a virtual person, and the virtual person represents a personal characteristic. The user has to phrase a statement. The statement is assessed with respect to the requirement for executing the task of the briefing information and with respect to the represented personal characteristic, e.g. if the statement is useful to learn more about the personal characteristic represented so far by the virtual person, and / or if the statement is useful to estimate if the personal characteristic suits to fulfil the requirement for executing the task. The report and the comprised assessment (and optionally the advice and / or recommendation) serve the user to improve their statement in repetition, e.g. a restart, of the training, e.g. a repetition of the whole method.

[0025] Further, the training results can be stored in a user profile and reused in case of the training repetition.

[0026] In a further embodiment the virtual person is configured as an avatar. An avatar is a virtual person or an artificial person in the form of a 3D high-poly asset with the integrated skeleton, which represents the embodiment of a person, especially a photorealistic representation with a digital personality. The skeleton of a 3D asset, often referred to as a "rig," is a hierarchical structure composed of interconnected bones or joints that allows for the animation and manipulation of a 3D model. This skeleton serves as an internal framework to which the 3D mesh is attached, enabling realistic movements and deformations. In other words, the virtual person can be represented as a digital person, especially with corresponding attributes. The attributes can be classified into two groups: Physical attributes and behavioural attributes. The physical attributes and behavioural attributes serve as configuration parameters for the virtual person.

[0027] Physical attributes comprise:

[0028] • Height: The height of the character, which affects interactions with the environment and other characters.

[0029] • Build: Body proportions, such as muscular, slim, athletic, etc.

[0030] • Facial Features: Shape of the face, eyes, nose, mouth, and ears.

[0031] • Hair Style and Colour: Type (straight, curly, etc.) and colour of hair.

[0032] • Skin Tone: Colour and texture of the skin.

[0033] • Age: Young adult, middle-aged, elderly, etc.

[0034] • Gender: Male, female, or other.

[0035] • Clothing: Style and type of clothing worn.

[0036] Behavioural attributes comprise:

[0037] Personality Traits: Extroverted, introverted, adventurous, cautious, etc. • Skills and Abilities: Proficiency in various activities or fields (e.g., combat skills, technical skills).

[0038] • Interests and Hobbies: Activities the character enjoys or pursues.

[0039] • Behavioural Patterns: Typical reactions to situations, habits, mannerisms.

[0040] In particular, the avatar can also perform movements of the face and body depending on the output signal for the output of the avatar. For example, when the avatar speaks, corresponding mouth movements can be issued. Thus, an extremely realistic communication between the real person and the virtual person, especially the avatar, can be realized.

[0041] The prompting of a large language model combined with a photorealistic avatar and preceding brief for the user to follow enable a natural, unique, and memorable user experience that will ensure, seeing as the situation was “lived” (as opposed to consumed), resulting in that the learnings are manifested in the user’s long-term memory.

[0042] According to a further embodiment the configuration parameter comprises a professional configuration parameter defining a professional characteristic, e.g. a professional background, of the virtual person, wherein the virtual person further represents the professional characteristic defined by the professional configuration parameter, wherein the assessment is further performed in respect to the professional configuration parameter (and thereby in respect to the professional characteristic represented by the virtual person and defined by the professional parameter).

[0043] The professional configuration parameter defines professional characteristic of the virtual person comprising a profession, and / or a professional skill, and / or a communication skill, and / or a management skill, and / or an organization skill, and / or a social skill, and / or an interaction skill, and / or a mindset parameter, and / or a motivational parameter. Different variables for a professional configuration parameter allow to configure the virtual person according to different personalities and according to different training needs.

[0044] Further the (general) configuration parameter (compared to the professional configuration parameter, which is a species of the configuration parameter) may influence the professional characteristic.

[0045] According to a further embodiment the briefing information further comprises an information about the virtual person according to the configuration parameter and / or an information about the virtual person according to the professional configuration parameter and / or a professional information about the virtual person, e.g. a resume and / or a CV, and / or an instruction on how to pose a job interview question and / or an instruction on questioning technique and / or an instruction on how to pose a behavioural question.

[0046] Behavioural interview questions are questions or statements that ask job candidates, here the virtual person, to share examples of specific situations they've been in. Behavioural interview questions are questions based on how you acted in a specific situation.

[0047] According to a further embodiment the statement comprises a question to be answered by the virtual person by a reply.

[0048] According to this embodiment, the statement does not only comprise an assertion (the virtual person may disagree on), and / or an assumption (the virtual person may disagree on), but also a question, e.g. an open question, and / or a closed question. The question is assessed with respect to the requirement for executing the task of the briefing information and with respect to the represented personal characteristic, e.g. if the question is useful to learn more about the personal characteristic represented so far by the virtual person, and / or if the question is useful to estimate if the personal characteristic suits to fulfil the requirement for executing the task.

[0049] According to a further embodiment the method comprises the further step of forwarding the statement to a second large language model. The second large language model is arranged to perform an analysis (arrange to analyse) of the statement in respect to the configuration parameter (and thereby in respect to the personal characteristic represented by the virtual person and defined by the configuration parameter). The second large language model is further arranged to configure (e.g. to generate) a reply based on a result of the analysis.

[0050] Therefore, the reply is based on the received statement from the user and the configuration parameter of the virtual person. The reply is to be seen as a reply to the statement according to the personal characteristics of the virtual person.

[0051] According to a further embodiment, the second large language model is further arranged to perform the analysis (further arrange to analyse) of the statement in respect to the professional configuration parameter (and thereby in respect to the professional characteristic represented by the virtual person and defined by the professional configuration parameter). As an embodiment, for the second large language model, instead of using a different large language (LLM) model, the first large language model and / or the third large language model are used again. This means that using only one large language model for the disclosed method and all its embodiments is possible (but not necessary). In this embodiment the first large language model, the second large language model, and the third large language model are identical and only on entity. The second large language model is also to be understand as a progression (ongoing development) of the first large language model, e.g. the first large language model is trained and amended during the simulation (execution of the disclosed method) and the second large language model is created. E.g. there is a change in the first large language model over, this is described by using the term “second large language model”. The same applies for the third language model in relation to the first and / or the second large language model, respectively.

[0052] In this embodiment the same (identical) LLM is used during the whole training, so there is one LLM and the prompt several times inject.

[0053] The prompt injection is having the following sequence:

[0054] 1. Inject the first prompt with the virtual personality description and instructions to execute the role (this info is static and stored in the backend).

[0055] 2. LLM interacts with the user (this info is dynamic and is accessible via Ul - user can enter input and get output).

[0056] 3. Inject evaluation prompt to perform conversation analysis (this info is static and stored in the backend).

[0057] 4. LLM generates output and sends it to the user (this info is dynamic and comes in form of a textual summary).

[0058] At any point of time, the same LLM is used and given instructions.

[0059] According to a further embodiment the method comprises the further step of outputting the reply via the virtual person (e.g. a voice output by the virtual person).

[0060] The reply is especially outputted by a voice output (plus corresponding visual speaking animation, especially plus mimics, gestic) of the virtual person. This step is carried out especially by a 3D computer graphics engine and a displaying unit, e.g. an output device, especially a monitor, and / or glasses (e.g. virtual reality glasses). The generated representation of the virtual person can be seen as a user interface and / or a user interface showing the representation.

[0061] According to this embodiment, the virtual person, e.g. an avatar welcomes statements and / or questions and answers, e.g. replies, according to the configuration parameter, e.g. the prompted backstory and motivation.

[0062] According to an embodiment, the second LLM receives the statement, e.g. a question, and configures (generates) answer in text form based on the pre-defined prompt (the configuration parameter. An option for a pre-defined prompt is: “Pretend to be Jack Peshwari. Avoid answering the questions, change topic, reply with a question”; or “evaluate Jack's answers during conversation and compare them with expected competencies”. Text answer (reply) configured by the second LLM is transcribed into audio file in .wav format with pre-configured voice accent (according to the configuration parameter). The .wav file is downloaded on the local visualization machine and played together with a lip-sync animation of the representation of the virtual person.

[0063] According to a further embodiment the steps of receiving the user input comprising the statement, forwarding the statement to the second large language model, and outputting the reply via the virtual person are repeated for a user input comprising a further statement and a further reply, respectively.

[0064] According to this embodiment, the method suggests a dialogue with several statements, especially questions, from the user and several reactions, e.g. replies, from the virtual person. According to this embodiment an interaction and / or conversation and / or an interview between the virtual person and a real person, e.g. a user, is provided, e.g. simulated. The method provides a training possibility to practice interpersonal interaction and / or conversation and / or an interview. In the assessment the statement and the further statement are assessed in respect to the configuration parameter and in respect to the requirement for executing the task of the briefing information and with respect to the represented personal characteristic, e.g. if the statement and the further statements are useful to learn more about the personal characteristic represented so far by the virtual person, and / or if the statement and the further statements are useful to estimate if the personal characteristic suits to fulfil the requirement for executing the task. According to a further embodiment the assessment is performed by a third large language model, wherein the third large language model is arranged to assess (doing an assessment) the statement in respect to configuration parameter (e.g. in relation to the represented personal characteristic) and in respect to the briefing information (e.g. in respect to the requirement), and wherein the third large language model is arranged to generate the report based on a result of the assessment.

[0065] According to this embodiment, a third LLM generates an overall conversation summary, the result of the assessment and the report, based on a pre-defined evaluation prompt. Especially, it is assessed by the third large language model if the statement is coherent with the briefing information and / or the requirement. Further, if more than one statements are received, it is especially assessed if the more than one statements are coherent within themselves.

[0066] As an embodiment, for the third large language model, instead of using a different large language model, the first large language model and / or the second large language model are used again. This means that, as described in detail above, using only one large language model for the disclosed method and all its embodiments is possible (but not necessary).

[0067] According to a further embodiment the method comprises the further step of receiving a further user input comprising an estimation on a fit of the personal characteristic), and optionally the professional characteristics, represented by the virtual person to the requirement. Wherein the following assessment is further performed of the estimation (e.g. both user inputs, the statement and the estimation are assessed), again in respect to the configuration parameter (and thereby in respect to the personal characteristic represented by the virtual person and defined by the configuration parameter) and in respect to the briefing information (e.g. in respect to the requirement).

[0068] The further user input is received via a user interface, especially via typing (textual input), speaking (sound input using a microphone), and additional via streaming (video input using a camera).

[0069] The method supports the user with a simulation of a personal interaction, e.g. a real person meets a virtual person, and the virtual person represents a personal characteristic. The user has to phrase a statement and according to this embodiment has to give an estimation on a fit of the personal characteristic represented by the virtual person to the requirement for executing the task. The statement and the estimation are assessed with respect to the requirement for executing the task of the briefing information and with respect to the represented personal characteristic, e.g. how close the estimation on the fit of the personal characteristic to the requirement for executing the task are to an estimate of the third large language model.

[0070] According to a further embodiment the configuration parameter is received and / or loaded from a data base, especially with a corresponding user profile.

[0071] According to this embodiment the configuration parameter, especially several configuration parameters, is / are received / loaded from the data base and have been pre-defined by a developer of the method, e.g. a software solution.

[0072] With the corresponding user profile, a previous report of a previous training (e.g. the execution of the described method) is storable. A configuration parameter is selectable according to the corresponding user profile, e.g. a virtual person according to certain user skills is configurable.

[0073] According to a further embodiment the configuration parameter is further received via a user interface (e.g. there are more than one configuration parameters, and the configuration parameters are partly defined by a user).

[0074] According to this embodiment the configuration parameter, especially several configuration parameters, is / are not only received / loaded from the data base and have not only been predefined by a developer of the method, e.g. a software solution. A part of the configuration parameters has been defined by a user.

[0075] According to a further embodiment the personal characteristic is represented by the virtual person in a voice output, and / or a spoken sentence, (especially with a corresponding speaking animation (e.g. an animation of mouth and lips of the virtual person), and / or a description of a skill, and / or a mimic, and / or a gestic, and / or a movement. This means that the representation of the virtual person includes a voice output, and / or a spoken sentence, and / or a mimic, and / or a gestic, and / or a movement each of the virtual person.

[0076] Further representation, e.g. visual output, options for personal characteristics of the virtual person include a facial animation, interactive animations, lip-syncing, and interactive eye contact. With “facial animation” the virtual person, also a “character” is arranged to be able to display a wide range of facial expressions, enabling realistic emotion portrayal. With “interactive animations”, the virtual person, especially an avatar, is arranged to be animated to interact with a user (real person) and to provide a more immersive and interactive experience. “Lip syncing” synchronizes a character's lip movement with spoken dialogue, enhancing the realism and immersion of the character's speech. With “interactive eye contact” the virtual person, especially an avatar, is arranged to be able to dynamically react to the user's gaze, creating a more engaging and interactive environment.

[0077] According to a further embodiment the reply and / or the report is / are outputted by a voice output (plus corresponding speaking animation, especially plus mimics, gestic) of the virtual person, especially advantageous for the reply, and / or as text on a displaying unit, e.g. a screen, especially advantageous for the report.

[0078] According to a further embodiment a system for assessing a user input in respect to a personal characteristic represented by a virtual person is disclosed. The system comprises a computational device and an output device, wherein the system is arranged to execute a method according to this disclosure.

[0079] The system comprising a computational device (electronic computation unit (e.g. a processor)) and an output device (e.g. a displaying unit, e.g. a monitor, and / or a display, and / or a holographic display, and / or virtual reality (VR) headset, and / or glasses (e.g. virtual or augmented reality glasses, and / or a projector, and / or speakers), wherein the system is arranged to execute a method according to this disclosure.

[0080] According to a further embodiment a computer program product comprising instructions which, when the program is executed by a computational device, cause the computational device to carry out the steps of the method according to this disclosure.

[0081] According to a further embodiment a computer-readable storage medium comprising instructions which, when executed by a computational device, cause the computational device to carry out the steps of the method according to this disclosure.

[0082] It is to be understood that the elements and features recited in the appended claims may be combined in different ways to produce new claims that likewise fall within the scope of the present invention. Thus, whereby the dependent claims appended below depend from only a single independent or dependent claim, it is to be understood that these dependent claims can, alternatively, be made to depend in the alternative from any preceding or following claim, whether independent or dependent, and that such new combinations are to be understood as forming a part of the present specification.

[0083] While the present invention has been described above by reference to various embodiments, it should be understood that many changes and modifications can be made to the described embodiments. It is therefore intended that the foregoing description be regarded as illustrative rather than limiting, and that it be understood that all equivalents and / or combinations of embodiments are intended to be included in this description.

[0084] Brief Description of the Drawing

[0085] Fig. 1 shows a system according to the disclosure.

[0086] Detailed Description of the Drawing

[0087] Fig. 1 shows a system for assessing a user II input in respect to a personal characteristic C represented by a virtual person V. The system comprises a computational device CU and an output device, e.g. a displaying unit DU, wherein the system is arranged to execute a method as follows.

[0088] The method comprising the step of configuring (step S1) a digital model for a virtual person V based on several configuration parameters CP by a first large language model LLM1 , wherein the configuration parameters CP define a personal characteristic C of the virtual person V.

[0089] Wherein the configuration parameters CP comprise several professional configuration parameters PCP defining a professional characteristic PC, e.g. a professional background of the virtual person V, wherein the virtual person V further represents the professional characteristic PC defined by the professional configuration parameter PCP, wherein the assessment in step S8 (described below) is further performed in respect to the professional configuration parameter PCP.

[0090] Wherein the configuration parameter CP is received and / or loaded from a data base DB, especially with a corresponding user U profile.

[0091] The method comprising the further step of outputting (step S2) a briefing information, the briefing information comprising a requirement RQ. The briefing information further comprises an information about the virtual person V according to the configuration parameter CP and / or an information about the virtual person V according to the professional configuration parameter PCP and / or a professional information about the virtual person V, and / or an instruction on how to pose a job interview question and / or an instruction on questioning technique and / or an instruction on how to pose a behavioural question.

[0092] The method comprising the further step of generating (step S3) a representation P of the virtual person V based on the digital model, wherein the virtual person V represents the personal characteristic C defined by the configuration parameter CP.

[0093] Wherein the personal characteristic C is represented (step S3) by the virtual person V in a voice output, and / or a spoken sentence, and / or a mimic, and / or a gestic, and / or a movement.

[0094] The method comprising the further step of receiving (step S4) a user II input comprising a statement Q, wherein the statement Q comprises a question Q.

[0095] The method comprising the further step of forwarding S5 the statement Q to a second large language model LLM2, wherein the second large language model LLM2 is arranged to perform an analysis of the statement Q in respect to the configuration parameter CP, and wherein the second large language model LLM2 is arranged to configure a reply R based on a result of the analysis.

[0096] The method comprising the further step of outputting (step S6) the reply R via the virtual person V, wherein the reply R is outputted by a voice output of the virtual person V.

[0097] Wherein the steps of receiving S4 the user II input comprising the statement Q, forwarding S5 the statement Q to the second large language model LLM2, and outputting S6 the reply R via the virtual person V are repeated (shown by the arrows pointing in circle shape) for a user II input comprising a further statement Q2 and for a further reply R2, respectively.

[0098] The method comprising the further step of receiving (step S7) a further user II input comprising an estimation E on a fit of the personal characteristic C and the professional characteristics represented by the virtual person to the requirement RQ, wherein the following assessment in step S8 (described below) is further performed of the estimation E, again in respect to the configuration parameter CP and in respect to the briefing information. The method comprising the further step of performing an assessment S8 of the statement Q in respect to the configuration parameter CP and in respect to the briefing information, and generating S8 a report A based on a result of the assessment, and wherein the assessment S8 is performed by a third large language model LLM3, wherein the third large language model LLM3 is arranged to assess the statement Q in respect to configuration parameter CP and in respect to the briefing information, and wherein the third large language model LLM3 is arranged to generate the report A based on a result of the assessment. The method comprising the further step of outputting S9 the report A, wherein the report A is outputted as text on a displaying unit DU.

[0099] Although the invention has been explained in relation to its advantageous embodiment(s) as mentioned above, it is to be understood that many other possible modifications and variations can be made without departing from the scope of the present invention. It is, therefore, contemplated that the appended claim or claims will cover such modifications and variations that fall within the true scope of the invention.

Claims

CLAIMS1. An automated method for assessing a user (U) input in respect to a personal characteristic (C) represented by a virtual person (V), the method comprising the steps:- Configuring (S1) a digital model for a virtual person (V) based on a configuration parameter (CP) by a first large language model (LLM1), wherein the configuration parameter (CP) defines a personal characteristic (C) of the virtual person (V),- outputting (S2) a briefing information, the briefing information comprising a requirement (RQ),- generating (S3) a representation (P) of the virtual person (V) based on the digital model, wherein the virtual person (V) represents the personal characteristic (C) defined by the configuration parameter (CP),- receiving (S4) a user (U) input comprising a statement (Q),- performing an assessment (S8) of the statement (Q) in respect to the configuration parameter (CP) and in respect to the briefing information, and generating (S8) a report (A) based on a result of the assessment, and- outputting (S9) the report (A).

2. Method according to claim 1 , wherein the configuration parameter (CP) comprises a professional configuration parameter (PCP) defining a professional characteristic (PC) of the virtual person (V), wherein the virtual person (V) further represents the professional characteristic (PC) defined by the professional configuration parameter (PCP), wherein the assessment is further performed in respect to the professional configuration parameter (PCP).

3. Method according to one of the previous claims, wherein the briefing information further comprises:- Information about the virtual person (V) according to the configuration parameter (CP) and / or- information about the virtual person (V) according to the professional configuration parameter (PCP) according to claim 2 and / or- a professional information about the virtual person (V), and / or- an instruction on how to pose a job interview question and / or- an instruction on questioning technique and / or- an instruction on how to pose a behavioural question.

4. Method according to one of the previous claims, wherein the statement (Q) comprises a question (Q).

5. Method according to one of the previous claims, with the further steps of:- forwarding (S5) the statement (Q) to a second large language model (LLM2), wherein the second large language model (LLM2) is arranged to perform an analysis of the statement (Q) in respect to the configuration parameter (CP), and wherein the second large language model (LLM2) is arranged to configure a reply (R) based on a result of the analysis, and- outputting (S6) the reply (R) via the virtual person (V).

6. Method according to claim 5, wherein the steps of:- receiving (S4) the user (II) input comprising the statement (Q),- forwarding (S5) the statement (Q) to the second large language model (LLM2), and- outputting (S6) the reply (R) via the virtual person (V) are repeated for a user (II) input comprising a further statement (Q2) and for a further reply (R2), respectively.

7. Method according to one of the previous claims, wherein the assessment (S8) is performed by a third large language model (LLM3), wherein the third large language model (LLM3) is arranged to assess the statement (Q) in respect to configuration parameter (CP) and in respect to the briefing information, and wherein the third large language model (LLM3) is arranged to generate the report (A) based on a result of the assessment.

8. Method according to one of the previous claims, with the further step of:- receiving (S7) a further user (II) input comprising an estimation (E) on a fit of the personal characteristic (C), and optionally the professional characteristics according to claim 2, represented by the virtual person (V) to the requirement (RQ), wherein the assessment is further performed of the estimation (E), again in respect to the configuration parameter (CP) and in respect to the briefing information.

9. Method according to one of the previous claims, wherein the configuration parameter (CP) is received and / or loaded from a data base (DB), especially with a corresponding user (II) profile.

10. Method according to claim 9, wherein the configuration parameter (CP) is further received via a user (II) interface.

11. Method according to one of the previous claims, wherein the personal characteristic (C) is represented (S3) by the virtual person (V) in: o a voice output, and / or o a spoken sentence, and / or o a description of a skill, and / or o a mimic, and / or o a gestic, and / or o a movement.

12. Method according to one of the previous claims, wherein the reply (R) according to claim 5 and / or the report (A) is outputted (S6, S9):- by a voice output of the virtual person (V), and / or- as text on a displaying unit (DU).

13. System for assessing a user (U) input in respect to a personal characteristic (C) represented by a virtual person (V), comprising a computational device (CU) and an output device (DU), wherein the system is arranged to execute a method according to one of the claims 1 to 12.

14. A computer program product comprising instructions which, when the program is executed by a computational device (CU), cause the computational device (CU) to carry out the steps of the method according to one of the claims 1 to 12.

15. A computer-readable storage medium comprising instructions which, when executed by a computational device (CU), cause the computational device (CU) to carry out the steps of the method according to one of the claims 1 to 12.

Images