A method for the automatic recognition of the psycho-aptitude skills of a user and a computer program implementing such method

Abstract

A method for the automatic recognition of the psycho-aptitude skills associated with a user, comprising the steps a) provision of means for image and / or video acquisition (1); b) provision of means for audio acquisition (2); c) provision of processing means (3); d) activation of the means for image and audio acquisition (2) to acquire a sequence of video frames and / or audio frames of predetermined duration; e) and f) generation of first and second digital data (d1) associated with the information in the video frames and in the audio frames acquired during the execution of said step d); g) processing of first digital data (d1) to obtain third digital data (d3) associated with the movements and position of the parts of the body assumed by the user; h) processing of second digital data to obtain fourth digital data (d4) associated with the semantics of the words pronounced by the user; i) provision of fifth digital data (d5) associated with the user's profile; j) provision of sixth digital data (d6) associated with the user's educational career and / or professional experience; k) processing of the third data (d3), of the fourth data (d4), of the fifth data (d5) and of sixth data (d6) to obtain output digital data (dout) containing information associated with psycho-aptitude skills of the user. A computer product suited configured to execute such method.

Description

A METHOD FOR THE AUTOMATIC RECOGNITION OF THE PSYCHO-APTITUDE SKILLS OF A USER AND A COMPUTER PROGRAM IMPLEMENTING SUCH METHODDESCRIPTIONField of application of the invention

[0001] The present invention is in the technical field of human resources management and the subject of the object of the invention is a method for the automatic recognition of the psycho-aptitude skills associated with a user.

[0002] Moreover, the invention also provides a computer product suited to implement such method, this computer product is suited to be installed and executed on a device equipped with processor means.State of the art

[0003] As is known, in the human resources field, as in other related fields, there is a need to determine a plurality of parameters and characteristics associated with one or more users.

[0004] In particular, in these fields, it is important to provide a representation of users that is truthful and accurate to their actual physical, psychic, mental, behavioural and aptitude characteristics.

[0005] Currently, the recognition of parameters associated with the psycho-aptitude characteristics of a user is performed manually by specialised operators (or personnel).

[0006] These operators have specific training that enables them to define a user by means of a plurality of unique characteristics that determine their profile.

[0007] In order to obtain a complete profile of a user, the specialised operator makes use of both in person interviews with the user and a variety of data provided by the user (curriculum, etc.).

[0008] These operator may be recruiters, i.e. personnel who deal with personnel selection and recruitment processes, or different figures who nevertheless carry out a task in the area of human resources administration and management (e.g. within organisations, institutions, companies, etc.).

[0009] The manual definition of a user profile requires a not inconsiderable number of steps that make the execution of this task rather complex.

[0010] Firstly, the operator must organise an in-person meeting with the user to assess(through direct observation) a plurality of parameters that are fundamental to the definition of a profile.

[0011] Through an interview, in fact, the operator can estimate the user's behaviour by analysing the verbal and non-verbal language that such user uses during the interview.

[0012] The interview thus makes it possible to determine the most important characteristics of the user, i.e. all those parameters that relate to the relational and emotional sphere of the person.

[0013] In addition to this, during the execution of the interview, the operator can learn about the user's curriculum vitae and in particular the type of educational and academic training associated with them, as well as their work and professional experience.

[0014] At the end of the interview, the operator will be able to define a plurality of parameters associated with the user that mainly describe the user's physical- characterial, attitudinal and experiential characteristics.

[0015] These characteristics will be further weighed with any additional information provided by the user in oral and / or written form or through references by third parties (e.g. previous employers, colleagues, professionals in general) intended to highlight particular skills associated with the user.

[0016] The operator's task, therefore, is to interpolate all this information and define a complete and accurate profile of the user on the basis of the theories dealing with the management and selection processes of people (generally the job-oriented selection theory and the person-oriented selection theory).

[0017] This methodology has the drawback of maintaining a high degree of subjectivity in the identification of psycho-aptitude skills associated with a user.

[0018] The figure of the operator (or recruiter) is, in fact, central to the process of selecting and defining a user profile since it is the operator themselves who collects and processes all the sensitive data to define that profile.

[0019] The assessment of a user, therefore, can change considerably as the operator assigned to carry out the survey varies, and this can lead to considerable uncertainty with respect to a user's actual aptitude or ability to perform a task requiring specific skills.

[0020] The problem of the subjectivity of judgement is also transferred to the area of personnel search, as the association of a given user profile (offer) with a job application (demand) is strictly dependent on the recruiter.

[0021] As a result, the methods currently in use have a rather uncertain outcome withrespect to the determination of a user's psycho-aptitude skills and do not allow an objective profile of the user to be drawn up that is free of interpretations related to and intrinsic to the selection method.Documents US 2021 / 279668 and US2002 / 106617 describe methods for the automatic, and computerised recognition of the characteristics of one or more users. These documents, however, are also affected by the drawbacks described above. Presentation of the invention

[0022] The present invention intends to overcome the aforementioned technical drawbacks by providing a method for the automatic recognition of psycho-aptitude skills associated with a user that is particularly efficient and high-performance.

[0023] In particular, the main purpose of the present invention is to provide a method suited to allow the recognition of psycho-aptitude skills associated with a user in a fully automatic manner.

[0024] A further purpose of the present invention is to provide a method for the automatic recognition of psycho-aptitude skills associated with a user that can minimise the intervention of an external operator.

[0025] Another purpose of the present invention is to provide a method capable of automatically recognising the psycho-aptitude skills associated with a user in a particularly objective manner based on a plurality of data provided by the user themselves.

[0026] A further purpose of the present invention is to provide a method for automatically recognising the psycho-aptitude skills associated with a user that allows for a multitude of factors to be taken into account, some of which are not strictly related to the analytical information provided by the user themselves.

[0027] A further purpose of the present invention is to provide a method for the automatic recognition of psycho-aptitude skills associated with a user that can also take into account the non-verbal language attributable to the user themselves.

[0028] Still, not the least purpose of the present invention is to provide a method for automatically recognising the psycho-aptitude skills associated with a user that can be easily used in many contexts in which in-depth knowledge of the skills and aptitudes associated with the user is required.

[0029] These purposes, together with others that will be better clarified below, are achieved by a method for the automatic recognition of psycho-aptitude skills associatedwith a user of the type according to claim 1 .

[0030] Other purposes that will be better described below are achieved by a method for the automatic recognition of psycho-aptitude skills associated with a user in accordance with dependent claims.

[0031] According to a further aspect of the present invention, a computer product is provided in accordance with claim 11.Brief description of the drawings

[0032] The advantages and features of the present invention will become clear from the following detailed description of some preferred but not limiting configurations of a method for the automatic computer product of psycho-aptitude skills associated with a user with particular reference to the following drawings:-Figure 1 is a block diagram of a preferred embodiment of the method according to the invention;Detailed description of the invention

[0033] The present invention has as its object a method for the automatic recognition of psycho-aptitude skills associated with a user.

[0034] In particular, this method can be used in all those contexts wherein it is necessary to know the psychological and aptitude characteristics associated with a user.

[0035] In the context of the present description this method is specifically applied in the context of personnel selection processes to promote the matching between a job demand and a job offer.

[0036] However, this particular field of application is to be regarded as purely illustrative, since the method which is the subject matter of the present invention can be applied in all those contexts wherein it is useful to recognise a user's psycho-aptitude skills.

[0037] As will be better explained below in this description, the main advantage of this method is that it promotes the recognition of a user's psycho-aptitude skills in a fully automatic manner so as to minimise the contribution of an external operator.

[0038] For example, the present method can also be applied in a social-health context or in an educational / academic context to estimate the cognitive / behavioural skills of a subject or student and / or to assess what skills they may be particularly gifted at.

[0039] It is therefore possible to highlight how the method which is the subject of this invention is particularly suited for recognising a user's soft skills.

[0040] The expression “soft skills" is intended to refer to all those transversal skills of auser formed by cognitive skills, personality traits, attitudes, beliefs and values in general.

[0041] These transversal skills make it possible to outline a precise psycho-aptitude profile of the user, which makes it possible to assess their ability to adapt to a specific social or work context, regardless of what are thier main skills at a cognitive / experiential / operational level (generally referred to as hard skills).

[0042] The method first comprises a step a) of provision of means 1 for image and / or video acquisition and a stap b) of providing means 2 for audio acquisition.

[0043] Conveniently, the means 1 for image and / or video acquisition and the means 2 for audio acquisition may be defined by an electronic device capable of acquiring audio and video frames in digital format.

[0044] For example, these means 1, 2 can be made by means of a digital camera and a microphone selectively operable by the user.

[0045] In general, these means 1, 2 can be incorporated into a commonly used electronic device such as, for example, a smartphone, a laptop, a digital camera, and other similar electronic devices.

[0046] However, it is important that these means 1, 2 are configured to transduce the images and the audio acquired by the physical devices into digital numerical data with characteristics suited to be processed and stored by the known processor systems.

[0047] The method also comprises a step c) of arranging processing means 3.

[0048] Also in this case, the expression “processing means” is intended to refer to all those electronic devices equipped with a processor capable of processing digital data.

[0049] Accordingly, the processing means 3 may be integrated within the same electronic device comprising the means for image and / or video acquisition 1 and the means for audio acquisition 2.

[0050] Alternatively, the processor means 3 used in the present method can be installed in devices other than the devices integrating means for image and / or video acquisition 2 and means for audio acquisition 3.

[0051] Thus, in this case, one or more electronic devices are provided able to comprise means for image and / or video acquisition 1 and means for audio acquisition 2 and an electronic apparatus or system separate from that device and comprising processing means 3.

[0052] The processing means 3 may be operatively connected to the electronic devices comprising means for image acquisition 1 and means for audio acquisition 2 throughappropriate cabling or through network connections.

[0053] As will be further clarified below, means for image and / or video acquisition 1 and means for audio acquisition 2 are generally installed in a device owned by (or closely associated with) the user - e.g. the personal smartphone.

[0054] Thanks to this device, the user will then be able to generate video frames and audio frames that will then be processed by the processing means 3 provided in step c) of the method.

[0055] Processing means 3 are generally not accessible by the user.

[0056] In general, therefore, these processing means 3 are distinct and different from those contained in the device associated with the user and can be defined by the CPUs of servers or computers located in physical environments remote from the user and not accessible by the latter.

[0057] This will become clearer during the description of the next steps of the method.

[0058] Conveniently, the method also comprises a step d) of activation of the means for image and / or video acquisition 1 and the means for audio acquisition 2.

[0059] The purpose of the step d) is to acquire a sequence of video and / or audio frames having a predetermined duration.

[0060] The execution of the step d) is promoted directly by the user since the video and audio frames generated during this step have the user themselves as their object.

[0061] In fact, during the execution of step d) the user promotes the activation of means for image acquisition 1 and means for audio acquisition 2 in order to record a video (provided with audio) during which he describes general or specific topics.

[0062] During the acquisition of step d), the means for images acquisition 1 are suited to general frames wherein at least the face of the user is visible.

[0063] In general, in fact, during the execution of step d) it is provided the recording of a video (including the audio) of at least one part of the user's body wherein it is comprised the head and face.

[0064] The duration of the video / audio acquisition executed during step d) is relatively brief and generally between 30 seconds and 2 minutes.

[0065] During the execution of step d), the user can record a single video or, alternatively, can record a plurality of videos all having a relatively limited duration.

[0066] It is clear from the context that the expression "recording a video" and the expression "acquiring a sequence of video / audio frames" are to be intended assynonymous, since during the execution of step d) the user records a video (including audio) during the execution of which the means for images acquisition 1 and the means for audio acquisition 2 are suited to generate relative video / audio frame sequences associated with that recording.

[0067] For the purposes of the correct execution of this method, during the execution of step d) the user must generate both a video and an audio sequence, generally associated with a topic chosen by the user themselves and having as its subject matter a topic relevant to the purposes for which an assessment of psycho-aptitude skills is required.

[0068] For example, in the case where the method aims to recognise a user's psychoaptitude skills for work purposes (job search or similar), the audio frames acquired during step d) generally refer to topics related to the user's education and / or physical-aptitude description and / or work experience and / or character description.

[0069] As described above, the means for image and / or video acquisition 1 and the means for audio acquisition 2 are suited to generate respective digital data suited to be processed by processing means 3.

[0070] For this reason, the method comprises a step e) of generating the first digital data di associated with the information in the video frames acquired during the execution of step d).

[0071] In addition to this, it is provided a step f) of generating second digital data da associated with the information contained in the audio frames acquired during the execution of step d).

[0072] The first di and second da digital data are sent to the processing means 3 so that they can processed them.

[0073] In general, therefore, the user makes a video by means of his electronic device (comprising means for image acquisition 1 and means for audio acquisition 2) through which it is possible to obtain subsequently the first di and the second da digital data that are subsequently sent to the processing means 3 (generally located remotely from the user).

[0074] Alternatively, the user can record a video with his electronic device and send an audio-video file directly to the processing means 3 through the use of the Internet or a computer platform dedicated for such purpose.

[0075] Consequently, the file received by the processing means can be of the standardtype (i.e. in a format used for video files - for example MP4, MOV, AVI, etc.) and the processing means 3 can be configured to extract from that file the first di and the second da digital data.

[0076] The method also comprises a step g) of processing of the first digital data di by the processing means 3.

[0077] During the execution of step g), first of all, a processing of the images composing the video frames is provided in order to obtain third digital data ds associated with the movements and the position of the part of the body assumed by the user during the activation of the means for image and / or video acquisition 1 executed in step d).

[0078] The purpose of step g) is to extract from the video fame peculiar information with respect to the attitude and posture assumed by the user during the activation of the means for image and / or video acquisition 1 and the means for audio acquisition 2 executed during step d).

[0079] To this end, during step g) it is provided the processing of the images associated with the video frames in order to determine the body position and the recognition of expressive parameters associated with the user.

[0080] In other words, step g) makes it possible the extraction of all information related to the user's body language by means of an automatic selection of the information contained in the video mainframe.

[0081] In particular, the step g) can comprise the following sub-steps: sub-step g1): processing by the processing means 3 of the first digital data di in order to extract from the latter further digital data di A associated with specific parts of the user's body (e.g. limbs, torso, head, joints, etc.); sub-step g"): processing by processing means 3 of digital data di A in order to determine further digital data d2_A associated with the position assumed over time by the user's body parts (e.g. limbs, torso, head, joints, etc.); sub-step g'"): processing by the processing means of digital data digital data d2_A in order to determine the third digital data dice ds containing information on the trajectory followed over time by the user's body parts (e.g. limbs, torso, head, joints, etc.) in the time interval during which the means for image and / or video acquisition were activated [step d)].

[0082] During the execution of step g), the video frames are then processed by processing means 3 in such a way as to define the user's body (or the parts of the user'sbody) as the main element on which processing is performed, thus causing all other elements contained within those frames to go into the background.

[0083] Following this data decomposition, an analysis of the user's body can be obtained by modelling an object in two-dimensional (2D) or three-dimensional object (3D).

[0084] As a result of this modelling, it will be possible to obtain third digital data ds containing information on the elements that make up the user's face and on any movements that have as object the user's torso, head, or limbs.

[0085] In order to execute steps g1) - g1"), it is possible to involve the provision of an artificial intelligence (better described below) instructed to execute the automatic processing of the digital data di associated with the video frames so as to promote the tracking of the user's body parts (e.g. limbs, torso, head, joints, etc.) and the tracing of the trajectory followed over time by these body parts.

[0086] Conveniently, during the execution of step g) of processing, it will be possible to generate third data ds containing information associated at least with the position of a plurality of predetermined points contained in the user's face and / or associated with the position of the head and / or associated with the position of the upper limbs.

[0087] Conveniently, the above-described sub-step g1) may possibly be configured to promote the processing of the first digital data di in order to extract from the latter further digital data di A associated with predetermined points contained in the user's face or exclusively referred to the contour of the user's head or, even, to the position of one or more of the user's upper limbs.

[0088] In this case, therefore, prior to executing the processing step, the sub-step g1) requires the execution of a pre-processing of the first data di in order to extract from such data one or more predetermined points (or area) contained in the user's face, or a continuous set of points suited to delimit the contours of the user's head alone and / or of one or more upper limbs of the user themselves.

[0089] The third data ds, therefore, are associated with information relating to the body language that the user has maintained during the execution of the activation step of the means for images and / or videos acquisition 1 and the means for audio acquisition 2.

[0090] The information contained in the third digital data ds is therefore very significant as it provides direct elements of with respect of the behaviour assumed by the user during the recording of the video.

[0091] As previously mentioned, this information is gathered during the acquisition of avideo during which the user had the opportunity to express themselves on a topic related to the purpose of determining his psycho-aptitude skills.

[0092] For example, in the case that the video acquired in said step d) is intended to introduce a user with the intention of looking for a new job, the execution of step g) makes it possible to obtain information associated with the body language assumed by the user during the recording, such information being indicative for the assessment of the user in the context of a personnel search or selection.

[0093] The present method comprises a step h) of processing of the second digital data d2.

[0094] This step h) is also executed by the processing means to generate fourth digital data d4 associated with the semantics of the words pronounced by the user during the activation of the audio acquisition means 2 executed in step d).

[0095] In particular, during the execution of step h) it is possible to generate fourth digital data d4 containing information associated with the meaning of the words pronounced by the user during the activation of the means for audio acquisition 2 that takes place in step d).

[0096] The term “semantics” used in this context identifies the meaning associated with the words / expressions / periods used by the user (in the language used by the user themselves) recognized by the means for audio acquisition 2 during their activation.

[0097] In the context of the present invention, therefore, the words "semantics" and "meaning", when declined to the words pronounced by the user during the execution of step d) can be used as synonyms, since these terms are intended to refer to the correct and common interpretation that these words present in the language chosen by the user in accordance with the linguistic dictionaries of reference.

[0098] The fourth digital data d4, therefore, contain information about the speech pronounced by the user while recording the video that took place during the execution of step d).

[0099] The information contained in the fourth digital data d4 relate and content expressed by the user through the verbal language.

[0100] This content also concerns important information that can be used to delineate certain peculiar aspects of the user such as, for example, their expressive skill, degree of confidence in a verbal conversation, grammatical competence and complexity of the vocabulary used, etc.

[0101] Step h) can also comprise the following sub-steps: sub-step h1): provision of a database containing the meaning of words in one or more languages (e.g. according to the meaning in the main nationally / internationally recognised dictionaries); sub-step h"): processing by processing means 3 of the second data da so as to obtain further digital data d4_A; such digital data d4_A are associated with the division into single words or tokens of the text corresponding to the audio pronounced by the user during the execution of the steps d) and f) [the sub-step h") is thus a tokeralisation step); sub-step h1"): processing by processing means 3 of the digital d4_A in order to obtain further digital data d4_B; such digital data d4_B correspond to a subset of the single words or tokens object of the sub-step h") with the exception of stopwords (i.e. words with purely grammatical and not semantic meaning - e.g. conjunctions); (the sub-step h1") thus promotes the removal of words without semantics); sub-step hlv): processing by processing means 3 of the data d4_B in order to determine further digital data d4_c containing information on the root (or lemma) of each single word associated with the data d4_B. sub-step hv): digital comparison d4_c with the database provided during sub-step h1) in order to obtain digital data d4_D containing information relating to the meaning of each word that makes up the data d4_c; this comparison being executed by the processing means 3; sub-step hvl): further digital comparison d4_o with the database arranged during sub-step h1) in order to determine fourth data d4 associated with the semantics (i.e. the meaning) of each word evaluated in the context of the entire speech pronounced by the user during step d) .[from the digital point of view such speech is contained in the second data da ]. Sub-step hvl) is also executed by processing means 3.

[0102] In addition to this, the information contained in the fourth digital data d4 also contains important indications regarding emotional aspects associated with the user.

[0103] In particular, during the processing executed in step h), it is possible to obtain fourth digital data d4 that, in addition to the semantic information associated with the user's audio, also contain information associated with the tone of voice used by the user,the presence or absence of errors in their speech, the evaluation of pronunciation, etc.

[0104] These characteristics can be of help in defining the emotional state of the user when the user places themselves in front of means for video acquisition 1 and audio means for acquisition 2 to record a personal video already knowing that this video will later be used to determine their psycho-aptitude profile.

[0105] Conveniently, the method also comprises a step i) of providing fifth digital d5associated with the user's profile.

[0106] In particular, the fifth digital data d5obtained as a result of the execution of step i) can be obtained as a result of the processing, by the processing means 3, of the second data da and / or the third data ds generated in steps e) and associated with the step d) of activation of the means for the acquisition of image 1 and / or video 2.

[0107] Furthermore, during the execution of step i), can be involved the processing, by the processing means 3, of the fourth digital data d4 generated in said step f) and associated with the activation step of the means for audio acquisition means 2.

[0108] In other words, the information associated with the fifth digital data d5obtained during the execution of step i) can be obtained automatically from the video and audio (i.e. the semantic information associated with the words pronounced by the user) recorded by the user themselves during the execution of step d).

[0109] The fifth data dscan contain the typical information associated with a person's profile, i.e. the assignment of an age range, some parameters derived from somatic traits, any indications of the presence of disabilities, etc.

[0110] Following step i), the method comprises a step j) of providing sixth digital data de associated with the user's educational career and professional experience.

[0111] In the execution of this method, the sixth digital data de provided in said step j) can be provided by the user themselves according to alternative manner with respect to the video recorded during the activation step of the means for image acquisition 1 and the means for audio acquisition 2.

[0112] For example, this digital data de could be obtained by sending information associated with the user's educational career and professional experience provided through digital means other than video.

[0113] In particular, the sixth data de could be obtained through textual (or meta- textual) files containing all information relating to the user's education and professional experience; these files, for example, could be the digital version of the user's curriculumvitae drawn up in digital format according to the file types per se known (Word, PDF, etc.).

[0114] Conveniently, the sixth digital data de) arranged during the execution of step j) can be formed by the following additional digital data: data de_A: associated with the user's personal information (name, surname, date of birth, etc.); data de_B: associated with the user's education (degree, universities / schools / institution / associations attended, length of the study cycle for each university / school / institution / association / attended, marks associated with the degree, etc.); data de_c: associated with the user's professional experience (place and organisation where the user found employment, duration of the collaboration, type of collaboration, etc.).

[0115] The sixth digital data de can be defined as the set of the additional data indicated above, i.e.: de = d6_A + d6_B + d6_c + etc.

[0116] Subsequently, this method comprises a processing step, by the processing means 3, of the third data ds, the fourth data d4, the fifth data d5and the sixth data de in order to obtain output digital data.

[0117] In particular, the following digital data are processed during the step k): digital data containing non-verbal information about the user and associated with the video frames acquired during the execution of step d) [third data ds]; digital data containing verbal information relating the audio generated by the user and accompanying the video of the user acquired during the execution of step d) [fourth digital data d<i]; digital data associated with the user profile; generally, this digital data is obtained from the video and audio frames acquired during the execution of step d) [fifth data d5]; digital data associated with the user's educational career and professional experience [sixth data de].

[0118] With reference to the above list, it is possible to highlight how the third data ds, the fourth data d4 and the fifth data d5are obtained fully automatically, according to the methods describe above, starting from the audio-video recording carried out by the user during the execution of step d).

[0119] The information contained in this data allows the processing means 3 to derive output data douT whose information is associated with a plurality of parameters suited to delineate the user's psychological and emotional state, as well as their potential skills in the operational field.

[0120] For this reason, the output data douT, processed by processing means 3 following the generation of the digital data listed above, contains information relating the psycho-aptitude skills of the user.

[0121] Conveniently, step k) can comprise a sub-step k1) wherein a set of parameters pi x, P2_x, P3_x associated with particular psycho-aptitude characteristics linked to human behaviour can be defined.

[0122] A non-exhaustive set of these psycho-aptitude characteristics (or soft skills) is reported below:Psycho-aptitude characteristics associated with communication: oral and written communication, active listening, body language, negotiation, persuasion, clarity; Psycho- aptitude characteristics associated with leadership: integrity, empathy, trust, influence, responsibility, ability to delegate;Psycho-aptitude characteristics associated with teamwork: collaboration, conflict resolution, feedback, coordination, focus, reliability;Psycho-aptitude characteristics associated with adaptability: flexibility, critical thinking, open-mindedness, creativity, continuous learning, motivation.

[0123] For each characteristic belonging to the above-mentioned groups, it is possible to define a parameter pi_x, P2_x, ps_x each of which can assume a value comprised between a predefined minimum and maximum value.

[0124] For example, for the first group (psycho-aptitude characteristics associated with communication), a number of parameters pi_i - pi_6 equal to the number of characteristics (oral and written communication, active listening, body language, negotiation, persuasion, clarity) may be provided; each parameter may have a value selectable from a predetermined range delimited by a minimum and a maximum value.

[0125] For example, the parameter pi_i associated with oral and written communication may have a value between 1 and 5, while the parameter pi 3 associated with body language may vary between 1 and 8.

[0126] The above example highlights how the minimum and maximum extremes of each parameter pi_x can be the identical or different.

[0127] What was stated above for the parameters pi_x of the first group (psychoaptitude characteristics associated with communication) can also be repeated for the parameters p2_x and ps_x of the second and third group (associated, respectively, with the psycho-aptitude characteristics associated with leadership and the psycho-aptitude characteristics associated with adaptability).

[0128] Step k) also includes a sub-step k") executed by processing means 3 during which the processing of the third data ds, the fourth data d4, the fifth data d5and the sixth data de is promoted in order to define a value for each of the parameters pi_x, P2_x, ps_x defined in sub-step k1).

[0129] In other words, the value of the parameters pi_x, P2_x, ps_x can vary depending on the digital data (ds , d4 , ds , de ), and the execution of step k") allows a predetermined value to be set for each parameter that takes into account the information contained in this data (ds , d4 , ds , de ).

[0130] Following the sub-step k") there is a further sub-step k'") promoted by processing means 3 during which these means process the value associated with all parameters pi_x, P2_x, ps_x in order to determine the output data douT.

[0131] Therefore, the information associated with the output data douT is obtained by interpolating the values associated with the parameters pi_x, P2_x, ps_x.

[0132] Consequently, the information associated with output data douT depends on the set of values associated with all parameters pi_x, P2_x, ps_x previously assigned during the execution of step k").

[0133] Conveniently, during the execution of step k'"), the parameters pi_x, P2_x, ps_x can be processed by the processing means 3 through the use of one or more weights (i.e. scalar mathematical entities), suited to define a correct interpolation of the parameters themselves pi_x, P2_x, p 3_x in order to obtain output data douT consistent and adherent to the candidate's characteristics.

[0134] The value of these weights can be set by the processing means 3 prior to the execution of step k'") according to a criterion that aims to maintain a certain relationship between the user's psycho-aptitude skills.

[0135] Conveniently, the value of the weights can be set automatically by the processing means 3 before the execution of sub-step k'").

[0136] In this case, therefore, the value of the weights associated with the parameters Pi_x, P2_x, P3_x may be dynamically variable as a function of the information contained inone or more of the third data ds, fourth data d4, fifth data d5or sixth data de.

[0137] Conveniently, the method may include a further step I) of providing an artificial intelligence system 4 operatively linked to the processing means 3.

[0138] As is well known, the term “Artificial Intelligence” refers to a complex system consisting of hardware equipment and algorithms intended to implement a system of neural networks (machine learning), i.e. a computer system capable of learning and refining skills over time through large-scale repetition of assigned tasks and access to vast databases.

[0139] Artificial intelligence, therefore, makes it possible to obtain results that are increasingly reliable and grounded in reality, since the algorithms underlying it and the access to large databases allow increasingly complex and refined calculations and processing.

[0140] For the purposes of this method, artificial intelligence systems 4 provided in step I) belong to the broad set of Al systems suited to process images and / or sounds containing or produced one or more persons in order to obtain sets of information relating to verbal communication, non-verbal communication, facial recognition, the association of emotions and moods, and the prediction of professional / operational skills and attitudes.

[0141] Conveniently, most or all of the processing steps executed in this method and executed by the processing means can involve the artificial intelligence system 4 provided in step I).

[0142] In particular, the processing steps g) and h) can be executed by the processing means by querying the artificial intelligence system 4 provided in step I).

[0143] In addition, the processing performed during step i) can also be performed by the processing means 3 through the interrogation of the artificial intelligence system 4 provided in step I).

[0144] For instance, the interrogation of artificial intelligence can be particularly useful in determining the information relating the verbal and non-verbal behaviour of the user, and in determining a particularly precise profile associated with the latter.

[0145] Conveniently, the method may include a step m) of determining seventh digital data d?.

[0146] The seventh digital data d? can be associated with metadata related to the user, i.e. information representing the activities performed by the user during theexecution of step d) of activation of the means for image and / or video acquisition 1 and audio acquisition means 2.

[0147] This metadata may be associated with particular physical activities (i.e. activities performed by the user with body parts) during the recording of the video, alternatively, such metadata can be associated with activities / information performed in the past by the user that are not part of normal professional experience.

[0148] The information contained in the metadata is also useful in outlining a psychoaptitude profile of the user.

[0149] For this reason, during the execution of step k), the processing means 3 may be configured to promote not only the processing of third d3and fourth d4 data, fifth d5, and sixth de data, but also the processing of seventh d? data [e.g. during the execution of step k'")].

[0150] In this way, the output data douT associated with the psycho-aptitude skills of a user, will also take into account the information contained in the metadata and transferred to the seventh digital data d7provided during the execution of step m).

[0151] The method described above can be applied, for example, in the context of personnel search suitable for a specific job offer.

[0152] As is well known, each job offer can be broken down into a set of aptitude and operational requests to which a score (comprised between a lower and an upper limit) can be applied.

[0153] The method above described can be applied to a potential user potentially suitable for performing the role sought in the job offer.

[0154] For the application of steps a) to k) of this method (or steps a) to m)) makes it possible to determine the psycho-aptitude framework of the user; in general, this framework is composed of a plurality of factors that can represent a fixed mask that can be associated with each person and thus also with the user themselves.

[0155] However, the application of this method allows a score to be estimated for any factor contained in this fixed mask.

[0156] As described above, it is possible to score each factor in an essentially automatic manner based solely on a video of a brief duration recorded by the user and the data contained in their curriculum, if any, or other professional / educational experience.

[0157] It is, therefore, possible to compare the score associated with the parametersdefining the job offer (which are considered important by those offering the employment) with the score associated with the psycho-aptitude factors of the user derived automatically following the execution of the present method.

[0158] As a result of this comparison, therefore, it will be possible to understand whether the user under scrutiny presents an overall profile that is substantially suitable for the role outlined in the job offer.

[0159] The same result can be achieved when the user promotes the execution of the method comprising the steps described above of their own free will, in order to be included in a database of possible candidates who are looking for employment.

[0160] In this case, jobseekers can provide data on their curriculum and upload one or more short videos in which they describe a specific activity or their main aptitudes in the context of the world of work.

[0161] Such videos and the user's curricular information will subsequently be processed by processing means 3 in accordance with the method described above in order to generate output data douT that define the user's psycho-aptitude skills.

[0162] All parameters defining the user's psycho-aptitude skills can be stored in a database in order to make a possible comparison with job positions still open or with future job positions that will be uploaded to the applicant management system.

[0163] According to a further aspect of the present invention, a computer-executable computer product is provided.

[0164] In particular, the calculating has at least one CPU and storage means operatively connected to the CPU itself.

[0165] Conveniently, the computer product comprises a plurality of instructions that can be stored in the storage means and executed by the CPU in order to generate and process digital data.

[0166] A computer-executable computer product is suited to allow information associated with the user to be displayed on a screen (or another similar interface).

[0167] Specifically, the instructions are suited to reproduce the previously described method in such a way as to recognise the user's psycho-aptitude skills fully automatically.

[0168] This computer product can be implemented on an IT platform that can be set up to function in various ways. For example, the user can upload video / audio frames of short duration previously made with their personal device (e.g. a smartphone) onto the platform.

[0169] Alternatively, the platform may be configured to allow direct access by the user to allow the latter to record video and audio sequences directly on the platform itself.

[0170] In addition, it is possible to store all the data associated with the video / audio recorded by the user (or uploaded on the platform) together with any other data relating to the user (e.g. information contained in a curriculum or other documents) in a database associated with the platform so as to obtain datasets relating to the user's psychoaptitude skills and relating to their professional / educational experiences.

[0171] Digital data associated with requests for personnel (job advertisements, etc.) can also be stored in the databases; such data contains information on the indication of the ideal profile which is the subject of these requests.

[0172] The digital data associated with the psycho-aptitude skills of a user obtained with the computer programme suited to reproduce the above described method can subsequently be compared with the digital data associated with the personnel request in order to determine the degree of affinity between the characteristics of each user stored in the database and the ideal profile associated with the request.

[0173] This comparison can be performed fully automatically without the intervention of an operator as the platform is able to perform this task autonomously starting from only the videos / audios recorded by the user or provided by the user to the platform.

[0174] The present invention can be realised in other variants all falling within the scope of the inventive features claimed and described; these technical features can be replaced by different technically equivalent elements and the materials used; the shapes and dimensions of the invention can be any as long as they are compatible with its use.

[0175] The numbers and reference marks inserted in the claims and description are only intended to increase the clarity of the text and must not be considered as limiting the technical interpretation of the objects or processes identified by them.

Claims

CLAIMS1. A method for the automatic recognition of the psycho-aptitude skills associated with a user, comprising the following steps: a) provision of means for image and / or video acquisition (1); b) provision of means for audio acquisition (2); c) provision of processing means (3); d) activation of said means for image and / or video acquisition (1) and of said means for audio acquisition (2), said activation being carried out by the user in order to acquire a sequence of video frames and / or audio frames of predetermined duration; e) generation of first digital data (di) associated with the information in said video frames acquired during the execution of said step d); f) generation of second digital data (da) associated with the information in said audio frames acquired during the execution of said step d); g) processing, by said processing means (3), of said first digital data (di) in order to obtain third digital data (ds) associated with the movements and position of the parts of the body assumed by the user during the activation of the means for image and / or video acquisition (1) executed in said step d); h) processing, by said processing means (3), of said second digital data in order to obtain fourth digital data (d4) associated with the semantics of the words pronounced by the user during the activation of the means for audio acquisition (2) executed in said step d); i) provision of fifth digital data (ds) associated with the user's profile; j) provision of sixth digital data (de) associated with the user's educational career and / or professional experience; k) processing, by said processing means (3), of said third data (ds) of said fourth data (d<i), of said fifth data (ds) and of said sixth data (de) to obtain output digital data (douT); wherein said output data has information associated with the user's psychoaptitude skills.

2. Method according to claim 1 , characterised in that said step g) of processing is suited to generate third data (ds) associated with at least the position of a plurality of predetermined points contained in the user's face and / or the position of the head and / or the position of the upper limbs.

3. Method according to claim 1 or 2, characterised in that said step h) of processing is suited to generate fourth data (d<i) containing information associated with the meaning of the words pronounced by the user during the activation of said means for audio acquisition (2).

4. Method according to one or more of the preceding claims, characterised in that said step i) involves the processing, by said processing means (2), of said second data (da) and / or of said third data (ds) so as to generate said fifth data (d5) associated with the user's profile.

5. Method according to claim 4, characterised in that said step i) further involves the processing of said fourth data (d4) to selectively recognise information exclusively associated with user characteristics from among the semantic information associated with the words pronounced by the user during the activation of the means for audio acquisition (2).

6. Method according to one or more of the preceding claims, characterised in that it comprises a step I) of providing an artificial intelligence system (4) operationally linked to said processing means (3).

7. Method according to claim 6, characterised in that the processing by said processing means (3) in said steps g) and h) is executed by interrogating said artificial intelligence system (4) provided in said step I).

8. Method according to claim 6, characterised in that the processing by said processing means (3) in said step i) is executed by interrogating said artificial intelligence system (4).

9. Method according to one or more of the dependent claims, characterised in that it comprises a step m) of determining seventh digital data (d?) associated with information related to the activities performed by the user during the execution of step d) of activating said means for image and / or video acquisition (1) and said means for audio acquisition (2).

10. Method according to claim 9, characterised in that, during the execution of said step k), said processing means (3) are suited to promote the processing of said third data (ds), of said fourth data (d<i), of said fifth data (ds), of said sixth data (de) and of said seventh data (d7) to obtain said output digital data (dou-r).

11. A computer product executable by a computer, wherein the computer has at least one CPU and storage means operatively connected to the CPU, wherein saidcomputer product comprises a plurality of instructions storable in the storage means and executable by the CPU, characterised in that said plurality of instructions are suited to reproduce the method for the automatic recognition of the psycho-aptitude skills associated with a user of the type according to one or more of the preceding claims.

Images