Method for providing a temporal sequence of events representative of a meeting chronology, method for retrieving the information, devices and corresponding computer program

Abstract

The invention relates to a method for making available at least one temporal sequence of events representative of a chronology of a meeting between a plurality of individuals in a meeting space, and comprises: - obtaining (30) measurement signals collected by a plurality of sensors in said meeting space and connected to a communication network; - determining (31), from the measurement signals obtained, at least one event associated with at least one individual (I1, I2, I3), said at least one event comprising at least one descriptive piece of information relating to at least one time-stamped action, an identification piece of information for said individual, and a start time of the event; and - generating data representative of at least one temporal sequence of events for said at least one individual, from the determined at least one event. Figure 3

Description

Title of the invention: Method for providing a temporal sequence of events representative of a meeting chronology, method for retrieving the sequence, corresponding devices and computer program. Field of the invention

[0001] The field of the invention is that of a communication network, in particular of communication services provided by such a network.

[0002] The invention relates in particular to the creation of a temporal sequence of events representative of a chronology of a meeting of individuals using signals collected by sensors during this meeting. Previous art

[0003] Today, to know how a face-to-face meeting in a meeting room takes place, one must either be on site, or, by being at a distance, benefit from recordings of video and audio data signals from cameras and microphones distributed throughout the room, or even benefit from live observations from a third person who manually adds (in writing or by voice recording) information describing the presences and activities throughout the meeting.

[0004] In relation to [Fig.1a], the creation of a time sequence TL (in English, “timeline”) of events which occur during a meeting R, synchronized with the meeting, is done live via the intervention of a human OBS who plays the role of meeting observer, and adds description information or labels of LE1, LEi events as he detects them.

[0005] In relation to [Fig.lb], the addition of this descriptive information can also be done a posteriori from REC(V) audiovisual recordings of the meeting.

[0006] However, it is not always possible to find someone available to play this observer role. Furthermore, the tasks of annotating and describing meeting activities during the meeting are tedious and difficult to combine with active participation in the meeting.

[0007] There is therefore a need for an automatic solution to allow a terminal user to access information relating to the progress of a meeting, whether live or delayed. Description of the invention

[0008] The invention addresses this need by providing a method for making available at least one temporal sequence of events representative of a chronology of a meeting between a plurality of individuals in a meeting space, said process comprising: - obtaining measurement signals collected by a plurality of sensors in said meeting space and connected to a communication network; - the determination, from the measurement signals obtained of at least one event associated with at least one individual, said at least one event comprising at least one descriptive information relating to at least one time-stamped action, a descriptive information of said individual and at least one time of start of activity; and - the generation of data representative of at least one temporal sequence of events for said at least one individual, from the determined at least one event.

[0009] The invention proposes a completely new and inventive approach for the automatic creation of descriptive data for a meeting of individuals in a meeting space. It consists of relying on measurement data signals collected by sensors distributed in the meeting space, which are analyzed and interpreted into events associated with start and end times, to form one or more temporal sequences of these events, corresponding to the course of the actual meeting.

[0010] The method according to the invention can be implemented both during the meeting and after the meeting has ended.

[0011] The sequence(s) of events may be associated with one or more individuals participating in the meeting. They are then stored and made available to users of terminals connected to a communication network.

[0012] An event or activity comprises descriptive information for a sequence of time-stamped actions, such as an individual standing up, sitting down, going to the board, writing on the board, or speaking. It can be a single, instantaneous event or associated with a duration, defined by a start and end time. Of course, for on-the-fly implementation of the invention, it may happen that a given event is not completed or that its completion could not be established. In this case, it is envisaged to associate it with a provisional end time, for example, that of the most recent action it comprises, or to associate no end time at all to clearly indicate that it is not finished.

[0013] Descriptive information may be textual or indicate a location in the room or identify an individual or a given type of action. It may also include contextual information about the meeting space, such as temperature, humidity, and lighting measurements, or indicators deduced from measurements of various sensors, such as an atmosphere indicator (friendly, relaxed, lively, tense, etc.).

[0014] The identification information of the individual who performs the action may be intended simply to distinguish him from another individual ("individual A" as opposed to "individual B") or to identify him (for example by his family name or employee ID).

[0015] Since each event in a time sequence is associated with at least one start time, a user can quickly identify and focus on the key moments of the meeting. For example, during a meeting, a person might arrive late and want to review the topics already discussed before joining (whether via videoconference or in person). It could also be someone who was ultimately unable to attend the meeting and accesses the time sequence of activities to retrieve descriptive information relevant to them.

[0016] The invention applies to all types of meetings between individuals, whether work meetings, training sessions, family or association gatherings, etc., in any place, closed room, passageway, indoors, outdoors, provided that the meeting space is equipped with different types of sensors and that these sensors can be connected to a communication network.

[0017] According to another aspect, the process includes grouping events associated with several individuals, according to at least one grouping criterion and generating a temporal sequence of events associated with a group comprising said individuals, including the grouped events.

[0018] For example, grouping criteria include a location criterion, an activity criterion, etc. These are advantageously established from sensor measurements or information determined from sensor measurements. For example, position information can be deduced from signals captured by one or more cameras (2D, 3D, depth). The activity criterion, on the other hand, can be determined from measurements collected by motion sensors, a noise detector, etc.

[0019] According to yet another aspect of the invention, the plurality of sensors comprises at least one camera configured to record an audiovisual data signal of the meeting, the method comprises associating said at least one event with identifiers of the audiovisual data signal recordings and adding said identifiers as descriptive information of said event.

[0020] One advantage is to link an event in a time sequence with the camera or cameras that filmed it. In this way, the portions of this audiovisual content that correspond to the interval between the start time of the event and the end time of the event can be associated with the event as descriptive information.

[0021] The invention thus contributes to enriching a recording of representative audiovisual content of the meeting with descriptive information of events occurring during the meeting which are made accessible live or delayed.

[0022] The plurality of sensors includes at least one video camera (2D, 3D, depth, etc.) and a microphone. It may also include a door opening detector, motion detector, temperature detector, humidity detector, light sensor, etc.

[0023] A user can thus go directly to the start time of the event of interest without having to view the entire preceding portion of the video and audio recording of the meeting. The temporal sequence of events generated by the invention thus provides a kind of chaptering of the video and audio recordings of the meeting.

[0024] According to yet another aspect of the invention, the method comprises the transmission of at least a part of the data representing said at least a temporal sequence of events to a user terminal.

[0025] This transmission can be done in pull mode or in push mode.

[0026] According to another aspect of the invention, the method includes prior filtering of the temporal sequence of events, at least according to access rights associated with a user profile, and the part of the data to be transmitted results from said filtering.

[0027] User access rights depend, for example, on their role (meeting participant or non-participant, room manager, catering manager, etc.). These rights allow for filtering the data transmitted to the user's terminal. For example, the user may only have access to group activities and not individual activities, or only to a certain level of detail (i.e., information describing the activity), depending on their role within the organization.

[0028] According to yet another aspect of the invention, the method comprises receiving a request to access said data from the user terminal, said request comprising at least one user parameter for filtering events and the prior filtering further takes into account the at least one user filtering parameter received.

[0029] Advantageously, the terminal user selects the types of descriptive information that interest them. These are translated by the user terminal into values ​​for one or more filtering parameters. For example, the filtering parameter includes identification information for an individual participating in the meeting, a group identifier, or an activity identifier.

[0030] Correspondingly, the invention also relates to a device for making available at least one temporal sequence of activities representative of the course of a meeting between a plurality of individuals in a meeting space, said device being configured to implement at the level of a server equipment of the communication network: - obtaining measurement signals collected by a plurality of sensors in said meeting space and connected to a communication network; - the determination, from the measurement signals obtained, of at least one event associated with at least one individual, said at least one event comprising at least one descriptive piece of information relating to at least one time-stamped action, and descriptive information for said individual at the time the event began; and - the generation of data representative of at least one temporal sequence of events for said at least one individual, from the at least one determined event.

[0031] The aforementioned device implements the aforementioned provisioning process in its various embodiments.

[0032] Advantageously, said provisioning device is integrated into a server equipment connected to a communication network.

[0033] The invention also relates to a method for reconstructing at least one temporal sequence representative of the chronology of a meeting between a plurality of individuals in a meeting space. This method is implemented at the level of a user's terminal equipment connected to a communication network and comprises: - the reception from a server equipment of the communication network, of data representative of at least a part of said temporal sequence of events representative of a chronology of the meeting, said event having been determined from measurement signals collected by a plurality of sensors distributed in said meeting space and connected to the communication network, said event comprising at least one descriptive information relating to a time-stamped action, an identification information of an individual and a start time of the event; - the display of a graphical representation of said at least a part of the temporal sequence in a graphical interface of the terminal equipment, said graphical representation comprising at least one selectable graphical element corresponding to said at least one action of said event of said sequence; - upon detection of a selection of said graphical element by the user, the rendering, in the graphical interface, of descriptive information about said event.

[0034] With the invention, the user accesses, live or delayed, a graphical representation of the sequence of events corresponding to the progress of the meeting. They can click on an activity to obtain additional descriptive information about that activity.

[0035] Advantageously, it can also click on a participating individual or group of participating individuals to obtain descriptive information on the activity or activities in which they have participated or are participating.

[0036] According to one aspect of the invention, the method includes the prior issuance of a request to access said time sequence to a server equipment of the communication network.

[0037] This is therefore a pull-mode transmission.

[0038] According to another aspect of the invention, the access request includes at least one user parameter for filtering events and the portion of the received time sequence results from filtering the at least one time sequence of events associated with the meeting from at least one user parameter.

[0039] One advantage is that the user can specify the descriptive information and the level of precision he / she wants.

[0040] According to yet another aspect of the invention, an event of said sequence further comprises an identifier of an audiovisual data recording captured by at least one camera of the plurality of sensors during the meeting and the method comprises the playback of said recording from the start time.

[0041] One advantage is to directly link the temporal sequence of activities to the recordings produced by the different cameras distributed throughout the meeting space. When several cameras are available, the identifier of the one best positioned to film the activity is provided.

[0042] Correspondingly, the invention also relates to a device for displaying at least one temporal sequence of events representative of the chronology of a meeting between a plurality of individuals in a meeting space. This device is configured to implement, at the level of a user's terminal equipment connected to a communication network (CR): - the reception from a server equipment of the communication network, of data representative of at least a part of said temporal sequence of events, of the meeting determined from measurement signals collected by a plurality of sensors distributed in said meeting space and connected to the communication network, said event including at least one descriptive information relating to a time-stamped action and an event start time; - the display of a graphical representation of said at least a part of the time sequence in a graphical interface of the terminal equipment, said graphical representation comprising at least one selectable graphical element corresponding to said at least one action of said event of said sequence; - upon detection of a selection of said graphical element by the user, the rendering, in the graphical interface, of descriptive information of said event.

[0043] The aforementioned device implements the aforementioned restitution process in its various modes of embodiment.

[0044] Advantageously, said provisioning device is integrated into terminal equipment connected to a communication network.

[0045] The invention also relates to a system for managing a meeting between individuals, comprising the aforementioned server equipment and terminal equipment.

[0046] The system, server equipment, terminal equipment and provisioning and delivery devices according to the invention have at least the same advantages as those conferred by the aforementioned methods.

[0047] The invention finally relates to computer program products comprising program code instructions for the respective implementation of the aforementioned provisioning and restitution processes, when executed by a processor.

[0048] Such a program may use any programming language, and be in the form of source code, object code, or intermediate code between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0049] The invention also relates to at least one computer-readable recording medium on which computer programs are recorded, including program code instructions for executing the steps of the processes according to the invention as described above.

[0050] Such a recording medium can be any entity or device capable of storing the program. For example, the medium can include a storage means, such as a ROM, for example a CD-ROM or a microelectronic circuit ROM, or a magnetic recording means, for example a mobile medium (memory card) or a hard disk drive or an SSD.

[0051] On the other hand, such a recording medium can be a transmissible medium such as an electrical or optical signal, which can be transmitted via an electrical or optical cable, by radio, or by other means, so that the computer programs it contains can be executed remotely. The programs according to the invention can, in particular, be downloaded onto a network, for example, the Internet.

[0052] Alternatively, the recording medium or media may be one or more integrated circuits in which each program is incorporated, the circuit or circuits being adapted to execute or to be used in the execution of the aforementioned processes.

[0053] According to one embodiment, the present technique is implemented using software and / or hardware components. In this context, the term "module" in this document may refer to a software component, a hardware component, or a set of hardware and software components.

[0054] A software component corresponds to one or more computer programs, one or more subroutines of a program, or more generally to any element of a program or software capable of implementing a function or a set of functions, as described below for the module concerned. Such a software component is executed by a data processor of a physical entity (terminal, server, gateway, set-top box, router, etc.) and is capable of accessing the hardware resources of that physical entity (memory, storage media, communication buses, electronic input / output cards, user interfaces, etc.). Hereafter, the term "resources" refers to any set of hardware and / or software elements supporting a function or service, whether they are individual or combined.

[0055] Similarly, a hardware component corresponds to any element of a hardware assembly capable of implementing a function or a set of functions, as described below for the module concerned. It may be a programmable hardware component or one with an integrated processor for executing software, for example an integrated circuit, a smart card, a memory card, an electronic card for executing firmware, etc.

[0056] Each component of the system described above naturally implements its own software modules.

[0057] The different embodiments mentioned above can be combined with each other for the implementation of the present technique. Brief description of the drawings

[0058] Other features and advantages of the present invention will become apparent from the description below, with reference to the accompanying drawings which illustrate an example of an embodiment without being limiting in any way. In the figures:

[0059] [Fig. la] already described, schematically illustrates the manual creation of a temporal sequence of events representative of a chronology of a meeting between individuals, by an observer, according to the prior art;

[0060] [Fig.lb] already described, schematically illustrates the addition of descriptive information to an audiovisual recording of the meeting by an observer, according to the prior art;

[0061] [Fig.2] schematically illustrates an example of the architecture of a meeting management system, comprising a device for making available at least one temporal sequence of events representative of a chronology of the meeting and a device for returning the temporal sequence to a terminal equipment of a user according to the invention;

[0062] [Fig.3] presents in the form of a flowchart the steps of a method for making available at least one temporal sequence of events representative of a chronology of a meeting between individuals according to an embodiment of the invention;

[0063] [Fig.4] schematically illustrates examples of temporal sequences of meeting events associated respectively with individuals or groups of individuals according to the invention;

[0064] [Fig.5] schematically illustrates the formation of subgroups of individuals within a group of individuals associated with a given sequence of events;

[0065] [Fig.6] schematically illustrates a sequence of events filtered according to parameters of an individual according to an embodiment of the invention;

[0066] [Fig.7] presents in the form of a flowchart the steps of a method for reproducing at least one temporal sequence of events representative of a chronology of a meeting between individuals at a terminal equipment of a user, according to one embodiment of the invention;

[0067] [Fig.8] schematically illustrates the detection of a user interaction with a graphical representation of the temporal sequence of events and the triggering of a playback of an audiovisual recording of the meeting from a moment pointed out by the user, according to an embodiment of the invention;

[0068] [Fig.9] schematically illustrates an example of the material structure of a device for making available at least one temporal sequence of events representative of a chronology of a meeting between individuals, according to the invention; and

[0069] [Fig. 10] schematically illustrates an example of the material structure of a device for reproducing at least one temporal sequence of events representative of a chronology of a meeting between individuals, according to the invention. Description of the invention

[0070] The general principle of the invention consists of exploiting measurement signals collected by a plurality of sensors distributed in a meeting space during a meeting between individuals, to recognize events that occur during the meeting and automatically generate from the recognized temporal events, one or more temporal sequences representative of a chronology of the meeting.

[0071] The time sequence(s) of events are then stored in memory and made available to user terminal equipment.

[0072] The meeting can be a work meeting, a training session, a supply sale, a family celebration, etc.

[0073] The meeting space can be an enclosed room, a passageway, an outdoor space, etc.

[0074] The duration of the meeting can be a few minutes, a few hours, or even a few months.

[0075] The invention thus finds numerous applications, in a professional context, but also in a personal, associative, etc. context, more generally whenever several individuals gather in a space suitable for the installation of sensors connected to a communication network.

[0076] In relation to [Fig.2], an example of the architecture of a system S for making available one or more time sequences of TLR events representative of a chronology of a meeting R between individuals, according to the invention, is presented.

[0077] In this example, individuals Ul, U2,...UN, with N an integer greater than or equal to 1, here chosen to be equal to 3, are gathered around a table in a meeting space ER.

[0078] A plurality of sensors Cl, C2, ..., CM, with M an integer greater than or equal to 1, chosen here to be 4, are distributed throughout the meeting space ER so as to capture what happens during the meeting. These include, for example, one or more video cameras (2D, 3D, depth, etc.) and an associated microphone, a door opening detector, a motion detector, a temperature, humidity, or light sensor, etc. These sensors are objects connected to an RC communication network. They are therefore configured to connect, for example wirelessly, to a given access point and to retransmit the measurement signals they collect, for example via a wireless link, using any technology, for example radio, such as Wi-Fi® or Bluetooth, to equipment connected to the RC network.

[0079] In this example, the system S includes a server equipment ES configured to collect these signals measured by the sensors, for example via an E / R transmit / receive module according to a wired or wireless technology, for example ®.According to the invention, the server equipment further comprises a device 100 for making available at least one temporal sequence of STE events representative of a chronology of the meeting, configured to obtain measurement signals collected by the plurality of sensors of said meeting space and connected to the communication network RC, to obtain, from the measurement signals obtained, a determination of at least one temporal event associated with at least one individual, said at least one temporal event comprising at least one descriptive information relating to at least one time-stamped action, an identification information of said individual, at least one start time of the event, and to generate data representative of at least one temporal sequence of events for said at least one individual, from the at least one determined event.

[0080] Device 100 thus implements the method of making available at least one temporal sequence of events representative of a chronology of the meeting according to the invention which will be detailed below in relation to [Fig.3].

[0081] In [Fig. 2], the device 100 is integrated into the server equipment ES, but of course, the invention is not limited to this example. The device 100 can be independent of the server equipment ES, but connected to it by any type of link.

[0082] Advantageously, the ES server equipment further includes an AI artificial intelligence module, configured to determine time events from the measurement signals received from the sensors and an Ml memory configured to store in particular the measurement signals received from the sensors, the time events and the sequence or sequences of time events generated from the determined time events.

[0083] In this example, the system S also includes a user terminal equipment UE, such as a laptop or not, a smartphone, a tablet, etc., comprising a transmit / receive module configured to connect to the RC communication network by a wired or wireless link, a graphical interface, for example a DISP screen which may or may not be touch-sensitive, and an M2 memory.The terminal equipment UE further includes a device 200 for rendering at least one time sequence of TLR events representative of a chronology of the meeting R between individuals in the meeting space ER, configured to receive from the server equipment ES via the communication network RC, data representative of at least a part of said time sequence of events of the meeting, to display a graphical representation of said at least a part of the time sequence in a graphical interface of the terminal equipment, said graphical representation comprising at least one selectable graphical element corresponding to said at least one action of said event of said sequence, and, upon detection of a selection of said graphical element by the user, the rendering, in the graphical interface DISP, of descriptive information of said event.

[0084] Device 200 thus implements the method of restoring at least one temporal sequence of events representative of a chronology of the meeting according to the invention which will be detailed below in relation to [Fig.7].

[0085] In [Fig. 2], the device 200 is integrated into the terminal equipment UE, but of course the invention is not limited to this example. Alternatively, the device 200 can be independent of the terminal equipment UE, but be connected to it by any link, wired or wireless.

[0086] Advantageously, the terminal equipment UE includes a user interaction module (UI) through which the user selects a graphical element on the DISP graphical interface. This is, for example, a touch panel, a mouse, or a keyboard. Advantageously, the M2 memory is configured to store the or the time sequences of received TLR events and the graphical representation generated from this or these sequences.

[0087] An example of the implementation of a method for providing at least one temporal sequence of events representing a chronology of a meeting between individuals in a meeting space is now presented in relation to [Fig. 3], in the form of a flowchart, according to one embodiment of the invention. Advantageously, the method is implemented by device 100.

[0088] We are here considering the example configuration of [Fig.2]. We assume that the meeting R started at a time tO, for example equal to zero.

[0089] In step 30, a plurality of time-domain signals are received up to a time t by the server equipment ES from sensors C1, C2, ..., C1. It is assumed that at least one of these sensors is a camera configured to capture, for example, as a stream of encoded data, audiovisual content from at least one given viewpoint of the meeting space ER. The other sensors belong to a group comprising at least one door opening detector, a motion detector, etc. The received signals are stored in memory, for example, in memory ML. For example, the time-domain signals are received from the sensors continuously or discontinuously, depending on the type of sensor considered.In the discontinuous case, the time signals are received at regular intervals, with a duration parameterized according to the type of sensor and a capture frequency defined according to the needs of device 100, or irregularly according to events detected by the sensor itself (for example, a door opening). Alternatively, they are received continuously according to a capture frequency configured for each of the sensors.

[0090] In 31, the plurality of temporal signals received at time t is analyzed and interpreted so as to determine one or more temporal events that occur or have occurred during the meeting R. In other words, this analysis can be performed on the fly (live) or a posteriori, once the meeting has ended. For example, this determination is carried out by the artificial intelligence module AI of the ES equipment in [Fig. 2], configured to implement, in a manner known per se, a technique for predicting, recognizing, or classifying events or activities from among a plurality of predetermined event classes. Advantageously, these predetermined classes are associated with a given type of meeting. Advantageously, predetermined action classes are associated with a predetermined event class.For a work meeting, for example, event classes include, for example, a presentation, a table discussion, a round-table introduction, etc. For example, for a presentation type event, the possible actions are: "take the microphone", "speak", "start a slideshow", "point a laser at a target". For a demonstration-type meeting, possible events include: "a presentation projected on a screen," "giving the floor to another person," etc. For a demonstration-type meeting, possible events include: "gathering a crowd," "setting up a virtual reality headset," "manipulating one or more objects," etc. Finally, for a brainstorming session, possible events include: forming groups, presenting group work, a facilitator's intervention, etc. Corresponding actions include, for example, "writing on a whiteboard," "cutting a piece of paper," "moving around," "sticking sticky notes," etc.

[0091] By restricting the number of types / classes of events and / or the number of types / classes of actions to be searched for, the task of determining events is simplified and the risk of misclassifications is limited.

[0092] Advantageously, an event comprises at least one action and, more often, a sequence of actions. For example, actions include an individual entering or leaving the meeting space, an individual standing up, speaking, writing on a board, sitting down again, etc. An event may be limited to a single, one-off action associated with a given time point (start time), or it may comprise several actions that occur successively over a longer or shorter period. In this second case, the event is associated with a start date and an end date, and therefore with a duration. Of course, this end date will only be associated with the event once it has been established that it is over. Thus, in the case of on-the-fly implementation of the invention, an event may be determined without an end date or with a provisional end date, corresponding, for example, to that of the most recent detected action.Conversely, in the case of retroactive implementation, any non-one-off event will be associated with an end date.

[0093] For example, the artificial intelligence module in question implements a deep learning technique to build a classification model for multimodal data from sensors and to recognize the plurality of classes of previous events. The classification model can thus be specifically designed to recognize, from the measurement signals collected by the sensors, predetermined event classes associated with a given type of meeting, or, more generally, to recognize a wide range of event classes common to several types of meetings. It can also learn continuously and create new classes as it encounters new situations. It is understood that the resulting model is specific to the configuration and types of sensors installed in the meeting space.

[0094] In this regard, we know, for example, the document by Florea et al., entitled “Multimodal Deep Learning for Group Activity Recognition in Smart Office,” which is described here. Environments”, in August 2020, by the website www.mdpi.com in the section Future Internet, Future Internet 2020, 12, 133; doi: 10.3390 / fil2080133, which describes a multimodal deep learning approach that merges video and audio data signals captured in the room and uses them to recognize activities among given classes of typical activities.

[0095] A technique for recognizing human activities by fusing signals measured by a plurality of wearable sensors, using convolutional neural networks, is also known from the document by Ordônez, FJ; Roggen, entitled "Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition," published in Sensors in 2016, 16, 115. https: / / doi.org / 10.3390 / s 16010115. For example, the techniques presented in these documents can be used to perform step 31 of event determination according to the invention.

[0096] Advantageously, according to the invention, the activities or events determined in this first step 31 are associated with a given individual, such as, for example, an individual who stands up and points to a presentation projected onto a screen using a laser pointer, and / or with group activities or events involving several individuals, for example, several people around a table or whiteboard drawing together or taking turns on a sheet of paper. Such an event is described at least by the following descriptive data: an event or event class identifier, one or more action name identifiers composing the determined event, such as, for example, "stands up," "speaks," "writes," "sits back down," "opens the door," etc., and a start date.Optionally, this associated descriptive information includes, when the event is not a one-time occurrence, an end date and a field describing the individual(s) involved. The identification or description field for the individual in question may simply indicate that the action is performed by one or more individuals, or by individual A (to differentiate them from individual B, for example). Alternatively, it includes a field identifying this individual. In this case, precise identification of the participating individuals is achieved using sensor measurement signals (e.g., an audiovisual stream captured by a camera) by implementing a facial and / or voice recognition technique known per se, in conjunction with a list of people invited to the meeting or a more comprehensive list (such as a company's internal directory).

[0097] It is understood that the list of events or classes of events that can be determined in 31 is known to the device 100 and stored in memory.

[0098] Optionally, in 32, when several sensors are cameras configured to each capture an audiovisual sequence of the meeting from points of distinct views, we associate with the detected event a camera identifier ID_Ci corresponding to the audiovisual sequence that films the event.

[0099] Optionally, in 33, one or more group events are obtained by grouping the individual events. Such grouping is done by extrapolation, from the descriptive information listed above, for example by comparing the start and end times, and advantageously from other descriptive information, such as, for example, position information of the individuals.

[0100] It should be noted that this notion of grouping is general and that several grouping methods are envisaged within the framework of the invention. The notion of a group can indeed be linked to the grouping of several events of a given type or of similar types (communication, storage, etc.), or which occur over the same time period or in the same place. Another possible grouping method is by type of person, for example, employees of a company and external individuals, or people who speak English and those who speak French (following live detection by microphone-type sensors). Alternatively, several individual events can also be grouped into a single group event based on the fact that they are t

[0101] In 35, from the events obtained, one or more temporal sequences (in English, “timeline”) of the meeting R are generated, respectively associated with one or more individuals and / or one or more groups of individuals, as a temporal succession of events determined for that individual or group of individuals.

[0102] Thus, an individual time sequence associated with an individual Ui, with i an integer between 1 and N, can be written as the sum of the activities or events associated with this individual Ui in the time period considered, for example between a time tO of the start of the meeting and a current time t:

[0103] TL (Ui) = E (Aj (Ajdeb_Ui, Ajfin_Ui)

[0104] Where Ajdeb_Ui is the start time of activity and Ajfin_Ui is the end time of activity of activity Aj for user Ui.

[0105] The equality as written here simply means that a temporal sequence of events for an individual Ui consists of the sum of the events to which it has been associated. For simplicity, we do not specify here what other descriptive information is associated with each of these events, as previously stated.

[0106] For example, in relation to [Fig.4], the sequence of events associated with the individual UI includes, in chronological order, a single activity A1(U1) (he gets up), two persistent activities A2(U1) (he talks), A3(U1) (after a pause, he talks again) and a single activity A4(U1) (“he turns on the projector”). Immediately afterwards, individual U2 "takes the microphone", which corresponds to action / event A4(U2).

[0107] For a sequence of events concerning a group G of individuals, we have:

[0108] TL(Gk) = f (E TL(Ui))

[0109] We denote by f a function which determines, from the "individual" events associated with distinct individuals, at least one group event which includes these individual events.

[0110] In the example of [Fig.4], device 100 creates a group event G(U1, U2) entitled "Launch of presentation" involving individuals U1 and U2. For the group (U2, U3) the determined event is, for example, a group speech.

[0111] Still in relation to [Fig. 4], the TLR meeting sequence is defined as a temporal sequence of events comprising all the start and end times associated with events in the individual sequences TL(U1), TL(U2), and TL(U3) and the group sequences of the meeting TL(G1(U1,U2)) and TL(G2(U2,U3). It is understood that this TLR sequence summarizes the chronology of the activities or events detected during the period [t0, t] under consideration. According to a first option, the overall TLR temporal sequence includes all the descriptive information for the events of all the individual and group sequences. According to a second option, it includes only the start and end times and a pointer to the corresponding events of the individual and group sequences.

[0112] Optionally, in step 34, a previously detected group is split into L subgroups, where L is a non-zero integer greater than or equal to 2. For example, within a meeting space, such as a classroom, two groups of students may form in two separate locations to work. The activities of both groups are detected first. Then, within one of the groups, two subgroups are distinguished: a first subgroup comprising students standing and presenting ideas at the board, and a second subgroup comprising students sitting and listening. It is understood that it is sometimes necessary to wait a certain amount of time (t greater than or equal to tmin) to detect subgroups within a group whose activities were detected in the first few minutes of the meeting. The value of tmin naturally depends on the type of meeting considered and the types of group events associated with it.For example, for a business meeting, tmin can be set to 30 min.

[0113] If necessary, the sequence of subgroups Al, A2 detected within a group A is generated in 35 as illustrated by [Fig.5].

[0114] Advantageously, the method implements, in step 36, the detection of activities or events of supergroups consisting of at least two previously formed groups. This step is implemented after a certain time (i.e. (At a sufficiently large current time t, for example, greater than or equal to tmin) A time sequence of the supergroup (or higher-level group) events thus detected is added to the set of time sequences of events of the meeting. As an illustration, consider the example of a class with four groups of students seated in the four corners of the classroom to work in groups. Based on an analysis of the actions / events detected in each group, and for example, by considering a summation of these activities, we can deduce, after a given observation period, dependent on the type of meeting, two very active groups and two less active groups. At the level of the TLR (Time-Level List) event sequence of the meeting, descriptive information for a very active supergroup and a less active supergroup is added, and the events previously detected for the groups they respectively comprise are associated with each.For example, in a classroom, the actions / events determined for students in an initially defined group (by the 100-student system), who constantly get up, move around, and talk, will be grouped after 5 to 10 minutes into a subgroup of "active" students. Conversely, the other students in this initial group who do not speak at all, remain in their seats, and do not raise their hands will be assigned to a "passive" subgroup.

[0115] This higher-level grouping can also be performed retroactively, once the meeting is over or when a new event has been detected (for example, students return to their seats at the end of a group activity). For example, here, when all the students return to their seats, the system can analyze in detail all the activities detected in each group and deduce the presence of these supergroups or subgroups.

[0116] Thus, in the example just described, several time sequences of individual or group events and an overall time sequence of the TLR meeting have been generated which includes (or points to) all the events included in the individual and group sequences.

[0117] Beyond individual and group events, the temporal sequence of events can be enriched with information captured from the general context of the entire venue, such as heat, humidity, light, atmosphere, etc. Such information enriches the description of meeting events, allowing a user accessing the TLR sequence to more easily understand the conditions and context in which these events took place. For example, indicating a sound level can help the user perceive the atmosphere during a debate between several participants. Advantageously, these specific measurement signals can also be analyzed by the AI ​​artificial intelligence module and thus contribute to the identification of a given event. For example, a one-hour "presentation" event could thus appear on the TLR sequence as a chain of events of the type "quiet presentation" or "noisy presentation".

[0118] It is clear from the example just presented that the provisioning method according to the invention can be implemented on the fly, as the measurement signals from the sensors are received during the meeting (the current time t is less than the meeting's end time), and / or a posteriori after the meeting has ended. Of course, a combination of the two cases is envisaged, in the sense that at least the event determination, grouping, and generation steps can be implemented on the fly and then repeated after the meeting to refine the sequence(s) of events produced live, in order to determine group events and to perform possible higher-level groupings of events determined during the meeting.

[0119] We now consider that a time sequence of TLR events representative of a chronology of the meeting R has been generated for a period between 0 and t and we place ourselves at a time t', later than t. The meeting may still be in progress or finished.

[0120] In step 36, a request to access the TLR time sequence is received by device 100 from a terminal equipment (UE) of a user UT. In step 37, a check of access parameters for the sequence events is performed, and the TLR event sequence of the meeting is filtered based on these access parameters. In one embodiment of the invention, one or more of these access parameters are included in the request. For example, the user UT indicates in this request that they only wish to view activities associated with the individual Ul. In another embodiment, one or more other access parameters are obtained by the server equipment (ES), for example, from a local or remote data table that stores information about the access rights of users of this meeting information provision service.For example, in a professional context, access rights can easily be assigned to a user based on their position within the organization, including their hierarchical rank and the team they belong to, but also based on whether or not they participated in the meeting. Specifically, if the user (UT) was invited to the meeting but attends remotely by connecting after it has started, it is understandable that they would legitimately want information about what happened before their late arrival. Conversely, if the user (UT) in question was not invited to the meeting but requests access to the TLR (Time Log Replay), access can be denied or granted only partial access (only certain individuals, or only certain types of events) depending on their position within the organization and their connection to the meeting's topic. For example, if the user is an employee... For the employee in the company cafeteria, access rights can be limited to a minimum, allowing them to simply see if the meeting is about to end. For example, knowing the names of group events (based on a class tag, for instance) without access to more detailed descriptive information could be sufficient. In other words, the timeline of events would be filtered to show only the event names, their start dates, and, if applicable, their end dates, while hiding information such as the identity of participants, the link to the corresponding video recording, the details of the actions comprising each event, etc.

[0121] Furthermore, confidentiality aspects may be taken into consideration.

[0122] In the example in [Fig.6], a filtered time sequence TLRf(Ul) is sent to the user UT who had only requested the events A1(U1), A2(U1, A3(U1), A4(U1) associated with the user Ul. It therefore only indicates the start and end times of events involving the individual Ul, whether individually or within a group (in this case the group G(U1, U2)).

[0123] It should be noted that an access parameter can also indicate a desired or permitted level of information precision. For example, a first access level allows access to information of the type "person A", while a second access level provides the identity of person A. According to another example, the access parameter relating to a desired level of precision indicates that the sound level is not taken into account.

[0124] An example of the implementation of a method for reconstructing a temporal sequence of events representative of the chronology of a meeting between individuals in a meeting space, according to an embodiment of the invention, is now presented in relation to [Fig. 7] in the form of a flowchart. Advantageously, the method is implemented by the aforementioned device 200.

[0125] We are here considering the configuration example of [Fig.2], in which device 200 is integrated into the terminal equipment UE of user UT. We assume here that the meeting has started.

[0126] At time 40, the device 200 sends a request to obtain a temporal sequence of events representative of a chronology of the meeting R. It is assumed here that the meeting R has been underway for at least a duration equal to t. It may also already be finished. For example, the terminal equipment UE has a computer program, for example a software application loaded into memory, which, when executed on the terminal equipment UE, displays on the screen of the terminal equipment UE a graphical representation of a schedule of meetings planned within the organization to which the user UT belongs and allows the user to select a given meeting to request access to a time sequence of events representative of a chronology of that meeting.

[0127] In step 41, device 200 receives a response from the server equipment ES. This response may be negative if, after verification, device 100 of the server equipment ES has determined that user UT does not have the necessary rights to obtain meeting description information R. Here, it is assumed that the response is positive and includes at least a TLRf portion of a TLR time sequence of events representative of a chronology of the meeting R, generated by device 100.

[0128] The expression "at least a part" can here cover several aspects, including: - the case where the user UT does not have sufficient rights to access all the descriptive information of the TLR sequence; filtering is performed by device 100. For example, events involving certain individuals participating in the meeting are masked or deleted. According to another example, the events are retained, but the descriptive information concerning them is filtered so as to mask a certain level of detail; - the case where the user UT has specified their own filtering or search parameters in their request. For example, they have specified that they are only interested in events involving the individual Ul, or that they only wish to receive the sequence from a given time t'.It can also provide keywords, which will be searched in the descriptive information of the actions and / or events of the sequence(s) of the meeting in question.

[0129] The TLRF portion of the sequence to be transmitted to the client is therefore generated from the TLR sequence (and from individual or even group sequences, constructed by device 100 and on which the overall TLR sequence is based). It should be noted that if the user's request is received after the end of the meeting, then device 100 has been able to generate a finalized TLR sequence, in which the determined events have been grouped / divided as previously described, which is not necessarily the case when the request is received during the meeting.

[0130] The TLRf sequence is then converted into a file or data stream format suitable for transmission over the RC communication network. It should be noted that the file can be transmitted alone or with an encoded data stream representing the recording of the meeting by one or more cameras. Advantageously, the transmitted encoded data stream includes only extracts from the video(s) captured by the camera(s) identified in the events transmitted in the filtered TLRf sequence and corresponding to the associated start and end times. It is finally transmitted to the UE terminal equipment via the RC communication network. Upon receipt of the TLR, TLRf sequence, device 200 generates in 42 a graphic representation RG of the received TLR, TLRf sequence and displays it on its DISP screen.

[0131] For example, as illustrated in [Fig. 8], this graphical representation takes the form of a horizontal timeline progressing from left to right and comprising user-selectable elements (ES) accessible via the terminal equipment's (UE) user interface (see [Fig. 2]). These elements correspond to the times of isolated actions and the start and end times of events A1(U1), A1(U2), A1(U3), A1(G1), and A1(G2). A user (UT) wishing to access only certain parts of a meeting can then click on these location details to access additional descriptive information about those actions or events.

[0132] For example, upon detection at 43 of a user interaction INT(UT) on a selectable element ES relating to at least one event in the sequence, the device 200 triggers the rendering 44 of additional descriptive information relating to that event. For example, it displays descriptive information of the time-stamped actions that constitute the event.

[0133] Advantageously, when the event selected by the user includes an identifier of a REC(V) recording of audiovisual data captured by at least one camera during the meeting R, the recorded audiovisual data is played back to the user UT on their terminal equipment UE in 45 seconds, from the start time until the end time of the event (if applicable, otherwise, for example, until the end of the last action included in the event). For example, when the recording includes a file or stream of encoded data, this file or stream is transmitted to an audiovisual data player, which decodes and plays it from the start time chosen by the user UT.

[0134] We now present, in relation to [Fig.9], an example of the material structure of a device 100 for making available at least one temporal sequence of events, representative of a chronology of a meeting, according to the invention, comprising at least one module for obtaining measurement signals collected by a plurality of sensors of said meeting space and connected to a communication network, a module for obtaining a prediction, from the measurement signals obtained from at least one event associated with at least one individual, said at least one event comprising at least one descriptive information relating to at least one time-stamped action, an identification information of said individual, a start time of activity, and a module for generating data representative of at least one temporal sequence of events for said at least one individual, from the at least one determined event.

[0135] The term "module" can refer to a software component, a hardware component, or a set of hardware and software components, a software component corresponding itself to one or more computer programs or subprograms or more generally to any element of a program capable of implementing a function or a set of functions.

[0136] Advantageously, the device 100 also includes a module for grouping events associated with at least two individuals, based on at least one grouping criterion. In certain embodiments, it further includes a module for associating at least one event with an identifier of an audiovisual data recording of the meeting. Advantageously, it may also include a module for transmitting at least a portion of the data representing at least one temporal sequence of events to a user terminal. Finally, it may include a module for filtering at least one temporal sequence using filtering parameters.

[0137] The device 100 comprises a random access memory 103 (for example, RAM), a processing unit 102 equipped, for example, with a processor, and controlled by a computer program Pgl stored in a read-only memory 101 (for example, ROM or a hard drive). At initialization, the code instructions of the computer program are, for example, loaded into the random access memory 103 before being executed by the processor of the processing unit 102.

[0138] This [Fig. 9] illustrates only one particular way, among several possible ways, of implementing the device 100 so that it performs the steps of the aforementioned provisioning process (according to any one of the embodiments and / or variants described above in relation to [Fig. 3]). Indeed, these steps can be performed interchangeably on a reprogrammable computing machine (a PC, a DSP processor, or a microcontroller) executing a program comprising a sequence of instructions, or on a dedicated computing machine (for example, a set of logic gates such as an FPGA or an ASIC, or any other hardware module).

[0139] In the case where the device 100 is made with a reprogrammable computing machine, the corresponding program (i.e. the sequence of instructions) may be stored in a removable storage medium (such as, for example, a CD-ROM, a DVD-ROM, a USB key) or not, this storage medium being readable partially or totally by a computer or a processor.

[0140] In some embodiments, the device 100 is included in equipment connected to a communication network, such as, for example, the ES server equipment of [Fig.2].

[0141] An example of the material structure of a device 200 for reproducing at least one temporal sequence of events, representative of a chronology of a meeting, according to the invention, is now presented in relation to [Fig. 10], comprising at at least one receiving module from a server device on the communication network, receiving data representative of at least a part of a said temporal sequence of events from measurement signals collected by a plurality of sensors distributed in said meeting space and connected to the communication network, said event comprising at least one descriptive piece of information relating to a time-stamped action, an identification piece of information for said individual and a start time of the event, a display module for a graphical representation of said at least a part of the temporal sequence in a graphical interface of the terminal device, said graphical representation comprising at least one selectable graphical element corresponding to said at least one action of said event in said sequence, a module for detecting a selection of said graphical element by the user, and a rendering module, in the graphical interface,information describing the event.

[0142] The term "module" can refer to a software component as well as a hardware component or a set of hardware and software components, a software component itself corresponding to one or more computer programs or subprograms or more generally to any element of a program capable of implementing a function or a set of functions.

[0143] Advantageously, device 200 also includes a module for sending a request for access to said time sequence to a server equipment of the communication network and a module for reproducing a recording of audiovisual data whose identifier is associated with an event selected by the user, from the start time associated with the event.

[0144] The device 200 comprises a random access memory 203 (for example, RAM), a processing unit 202 equipped, for example, with a pP processor, and controlled by a computer program Pg2 stored in a read-only memory 201 (for example, ROM or a hard drive). At initialization, the code instructions of the computer program are, for example, loaded into the random access memory 203 before being executed by the processor of the processing unit 202.

[0145] This [Fig. 10] illustrates only one particular way, among several possible ways, of implementing the device 200 so that it performs the steps of the aforementioned recovery process (according to any one of the embodiments and / or variants described above in relation to [Fig. 7]). Indeed, these steps can be performed interchangeably on a reprogrammable computing machine (a PC, a DSP processor, or a microcontroller) executing a program comprising a sequence of instructions, or on a dedicated computing machine (for example, a set of logic gates such as an FPGA or an ASIC, or any other hardware module).

[0146] In the case where the device 200 is made with a reprogrammable computing machine, the corresponding program (i.e. the sequence of instructions) may be stored in a removable storage medium (such as, for example, a CD-ROM, a DVD-ROM, a USB key) or not, this storage medium being readable partially or totally by a computer or a processor.

[0147] In some embodiments, the device 200 is included in terminal equipment connected to the communication network, such as, for example, the UE terminal equipment of [Fig.2].

[0148] The invention just presented offers numerous advantages. It provides a user of terminal equipment with a temporal sequence of individual or group events that occurred during a meeting, whether ongoing or completed. The terminal equipment displays a graphical representation of this temporal sequence, including, for example, at least one timeline on which selectable elements corresponding to moments associated with these events are placed. At a glance, the user can see the highlights of the meeting. When the user wants more details about a particular event, a simple click gives them access to additional descriptive information, or even to a video recording excerpt corresponding to the start and end times of the event.The invention therefore provides a graphic and visual summary of the proceedings of the meeting in question, which is enriched with additional descriptive information when the user points to a particular event.

[0149] The invention thus enables: - to a person invited to the meeting but absent, to retrieve information of interest, - to easily access information exchanged during the meeting afterward and potentially replay a relevant section, to search the time sequences of several meetings, for example stored in memory, using metadata linked to descriptive information fields (event / action name, duration, location, number of individuals, noise level, etc.). For example, one can search for an event such as "applause" based on an action / event name and / or a noise level threshold.

[0150] Advantageously, the invention can be used in a meeting management service for professionals, associations, individuals, and more generally for any type of human activity. The benefits to the customer experience are numerous: - automatic generation of a chronological summary of the highlights of a meeting; - the possibility of obtaining more precise descriptive information in a targeted manner about a group, an individual participant, an event, etc., based on their interests and access rights, -access to the chronological summary during and after the meeting, which allows you to quickly find out what happened in case of a delayed arrival or early departure.

[0151] Finally, we consider three examples of users who might be interested in using a service based on the invention just presented:

[0152] According to a first example, Pierre is currently overwhelmed and summoned to several meetings at the same time. He prioritizes the one he will attend remotely, but displays the time slots of the other ongoing meetings on his terminal equipment. At a certain point, he notices in one of these time slots that the CEO is giving a presentation and decides to switch to that meeting to follow the presentation live.

[0153] According to a second example, Jeanne arrives late to a meeting she is physically attending. She takes her seat but quickly realizes that the meeting has already been underway for several minutes and she has no idea what has been said. She accesses the automatically generated timeline of events and discovers that, in fact, the main speaker at the meeting arrived only a minute before her and that no introductions were made. Therefore, she hasn't missed anything important.

[0154] According to a third example, Rose was ill last week and unable to attend several important meetings. To get a quick summary of everything that happened, she accesses the various time sequences of events from these meetings, specifying the main activities she is interested in using filter parameters. By simply clicking on the selectable elements corresponding to the start times of these activities, she can directly replay excerpts from the audiovisual recordings that correspond to those activities. Thus, in a very short time, she was able to catch up.

Claims

Demands

1. A method for making available at least one temporal sequence of events representative of a chronology of a meeting between a plurality of individuals in a meeting space, said method comprising: - obtaining (30) measurement signals collected by a plurality of sensors in said meeting space and connected to a communication network; - determining (31), from the measurement signals obtained, at least one event associated with at least one individual (II, 12, 13), said at least one event comprising at least one descriptive information relating to at least one time-stamped action, an identification information for said individual and at least one time of start of activity; and - generating (35) data representative of at least one temporal sequence of events for said at least one individual, from the determined at least one event;- the transmission (35) of at least a portion of the data representing said at least one temporal sequence of events to a user terminal, - the reception (36) of a request to access said data representing said at least one temporal sequence of events, from the user terminal, said request including at least one user parameter for filtering events obtained by said user terminal by translating at least one result of a selection made by the user of said user terminal, and the prior filtering (37) of the temporal sequence of events, at least according to access rights associated with a user profile, the portion of the data to be transmitted resulting from said filtering and said prior filtering further taking into account said at least one user parameter for filtering received.

2. A method according to claim 1, characterized in that it comprises grouping (33) events associated with several individuals, according to at least one grouping criterion, and generating a temporal sequence of events associated with a group including said individuals, said sequence including the grouped events.

3. A method according to any one of the preceding claims, characterized in that, the plurality of sensors comprising at least one camera configured to record an audiovisual data signal of the meeting, the method comprises associating (32) said at least one event with identifiers of the audiovisual data signal recordings and adding said identifiers as descriptive information of said event.

4. A method for reproducing at least one time sequence representative of a chronology of a meeting between a plurality of individuals (II, 12,..., IN), in a meeting space, characterized in that said method is implemented at the level of a terminal equipment (UE) of a user (UT) connected to a communication network (RC) and in that it comprises: - the reception (41) from a server equipment (ES) of the communication network, of at least a part of the data representative of said at least one time sequence of events (SQE, SQEf), of the meeting determined from measurement signals collected by a plurality of sensors distributed in said meeting space and connected to the communication network (RC), said part of the data to be received resulting from a prior filtering (37) of the time sequence of events, at least according to access rights associated with a user profile,said event comprising at least one descriptive piece of information relating to a time-stamped action, an identification piece of information for said individual and a start time of the activity; - the display (42) of a graphical representation of said at least a part of the time sequence in a graphical interface of the terminal equipment, said graphical representation comprising at least one selectable graphical element corresponding to said at least one action of said event of said sequence; - upon detection (43) of a selection of said graphical element by the user, the rendering (44), in the graphical interface, of descriptive information for said event, the method comprising the prior issuance (40) of a request to access said time sequence to a server equipment (ES) of the communication network (RC), the access request comprising at least one user parameter for event filtering and said prior filtering further taking into account said at least one user parameter for event filtering.

5. A restitution method according to claim 4, characterized in that an event of said sequence further comprises an identifier of an audiovisual data recording captured by at least one camera of the plurality of sensors during the meeting and in that the method comprises the restitution (45) of said recording from the start time.

6. Device (100) for making available at least one temporal sequence of activities representative of the course of a meeting between a plurality of individuals in a meeting space, said device being configured to implement at the level of a server equipment of the communication network: - the obtaining of measurement signals collected by a plurality of sensors of said meeting space and connected to a communication network; - the determination, from the measurement signals obtained of at least one event associated with at least one individual (II, 12,13), said at least one event comprising at least one descriptive information relating to at least one time-stamped action, an identification information of said individual and a start time of the event; and - the generation of data representative of at least one temporal sequence of events for said at least one individual, from the determined at least one event;- the transmission (35) of at least a part of the data representing said at least one temporal sequence of events to a user terminal, - the reception (36) of a request to access said data representing said at least one temporal sequence of events, from the user terminal, said request including at least one user parameter for filtering events obtained by said user terminal by translating at least one result of a selection made by the user of said user terminal,;

7. and the pre-filtering (37) of the temporal sequence of events, at least according to access rights associated with a user profile, the part of the data to be transmitted resulting from said filtering and said pre-filtering further taking into account said at least one received user filtering parameter. Device (200) for reproducing at least one temporal sequence of events representative of a chronology of a meeting between a plurality of individuals (II, 12,...IN), in a meeting space, characterized in that said device is configured to implement at the level of a terminal equipment (UE) of a user (UT) connected to a communication network (RC): - the reception from a server equipment (ES) of the communication network, of at least a part of the data representative of said at least one temporal sequence of events (SQE, SQEf), representative of a chronology of the meeting determined from measurement signals collected by a plurality of sensors distributed in said meeting space and connected to the communication network (RC), said part of the data to be received resulting from a prior filtering (37) of the temporal sequence of events, at least according to access rights associated with a user profile, said event comprising at least one descriptive information relating to a time-stamped action, an identification information of said individual and a start time of the event; - the display of a graphical representation of said at least a part of the temporal sequence in a graphical interface of the terminal equipment, said graphical representation comprising at least one selectable graphical element corresponding to said at least one action of said event of said sequence; and - upon detection of a selection of said graphical element by the user, the rendering, in the graphical interface, of descriptive information about said event, the device also implementing the prior issuance (40) of a request to access said time sequence to a server equipment (ES) of the communication network (RC), the access request including at least one user parameter for event filtering and said prior filtering further taking into account said at least one user parameter for event filtering.

8. Server equipment (SE) connected to a communication network, characterized in that it includes a device (100) for making available a time sequence of events in accordance with claim 6, and in that it includes an artificial intelligence (AI) module.

9. Terminal equipment (UE) of a user connected to a communication network (CR), characterized in that it comprises a device (200) for reproducing a temporal sequence of events representative of a chronology of a meeting between a plurality of individuals in accordance with claim 7, and in that it comprises a user interaction module (UI).

10. System (S) for managing a meeting between individuals, comprising a server equipment (ES) according to claim 8 and a terminal equipment (UE) according to claim 9.

11. Product computer program comprising program code instructions for implementing a method according to any one of claims 1 to 5, when executed by a processor.

Images