Method and device for managing a message intended for at least one terminal of a user.

The method and device adjust notification delivery based on user emotional state analysis, improving timing and content to match user emotional states, enhancing notification relevance and importance recognition.

FR3131159B1Active Publication Date: 2024-12-20ORANGE SA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
FR2021013778
Authority / Receiving Office
FR · FR
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-12-17
Publication Date
2024-12-20
Estimated Expiration
2041-12-17

AI Technical Summary

Technical Problem

Existing notification management systems fail to consider the user's emotional state, leading to inappropriate delivery times and potential negative perceptions or missed important notifications due to user emotional states.

Method used

A method and device that utilize physiological data, such as heart activity, to determine the user's emotional state through an AI algorithm, adjusting message delivery actions like timing, content, or form based on valence and arousal parameters, considering user preferences.

Benefits of technology

Enhances notification delivery to align with the user's emotional state, reducing negative perceptions and ensuring important notifications are not missed.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000020_0000
    Figure 00000020_0000
  • Figure 00000020_0001
    Figure 00000020_0001
  • Figure 00000021_0000
    Figure 00000021_0000
Patent Text Reader

Abstract

A method for managing a message intended for at least one terminal (2, 3) belonging to a user (1) comprises the following steps implemented by a management device (300): - obtaining physiological data (100) representative of an emotional state of the user (1), - determining at least one action related to the delivery of the message on at least said terminal, based on the physiological data obtained, and - implementing said at least one determined action. Figure for the abbreviation: Fig. 1
Need to check novelty before this filing date? Find Prior Art

Description

Title of the invention: Method and device for managing a message intended for at least one terminal of a user.

[0001] The present invention relates to a method for managing a message intended for at least one terminal of a user.

[0002] It also relates to a management device implementing the proposed management process.

[0003] The invention applies in particular to any equipment, terminal or object configured to receive messages and present them to a user.

[0004] User terminals, such as mobile phones, smartwatches or others, receive many notifications nowadays, whether they are text notifications such as emails, SMS (Short Message Service) type messages or notifications intended for applications (for example journalistic applications), or notifications of telephone calls.

[0005] The user's receipt of these notifications can alter their emotional state, both due to the content of the notification and the number of notifications received. Furthermore, the user's emotional state at the time of receiving a notification (current emotional state) can influence the perception of that notification.

[0006] Thus, sometimes, the user receiving a notification that affects his emotional state may not consider it and may even acquire a negative perception of the source of the notification or of a service offered by the notification.

[0007] On other occasions, due to a particular emotional state of the user, an important or urgent notification may go unnoticed by the user, or its importance or urgency may not be taken into account by the user.

[0008] Solutions exist for controlling message delivery to users based on user preferences, with these preferences being prefixed by the users. Very often, users define preferences to avoid being disturbed or interrupted at certain times, or at least to minimize interruptions. For example, a preference might stipulate that the delivery of a notification should be delayed if, when it is received by the terminal or the message management system, the user is busy, for example, in a meeting.

[0009] However, although the delivery of notifications takes into account the user's preferences, they may be delivered at times that are not convenient for the user or in contexts that are not conducive to taking the user's preferences into account. message from the user. For example, the user may feel stressed and unresponsive to notifications, even though there are no meetings scheduled in their calendar.

[0010] The present invention aims to improve this situation and proposes a method for managing notifications intended for a user's terminal, enabling the delivery of notifications at the most opportune time for the user.

[0011] To this end, the invention aims, according to a first aspect, at a method of managing a message intended for at least one terminal of a user.

[0012] According to the invention, the management process comprises the following steps implemented by a management device:

[0013] - to obtain physiological data representative of an emotional state of the user,

[0014] - determine at least one action relating to the delivery of said message on at least said terminal, based on the physiological data obtained, and

[0015] - to implement said at least one specific action.

[0016] Thus, thanks to the management process, the delivery of a message intended for at least one of the user's terminals is conditioned by the user's emotional state. In other words, the delivery of the message is modified so as to adapt it to the user's emotional state.

[0017] It should be noted that the purpose of delivering a message is to present the message to the terminal user. Thus, delivering a message to the terminal means presenting the message on the terminal via a user interface.

[0018] Determining an action related to message delivery may include, depending on the user's emotional state, determining whether the message will be presented (or determining that the message will be presented), refusing presentation (or determining that the message will not be presented), delaying the message presentation time, delivering the message at a specific time, modifying the content of the message to be presented, the form of message delivery, for example, whether the message is accompanied by a ringtone, a vibration, or neither, etc. In all cases, message delivery takes into account the user's emotional state, making it possible to deliver the message at the optimal time with respect to the user's emotional state.

[0019] For example, actions can be:

[0020] - deliver the message to at least one user terminal. The message may be delivered to several terminals that can be associated with at least one user terminal,

[0021] - to associate with the message a subsequent moment of delivery,

[0022] - modify at least part of the message content, for example the subject of a message, etc.

[0023] For example, thanks to the proposed method, if the user is nervous, it can be determined to delay the presentation of the message, thus preventing the message from being set aside by the user or the user from becoming even more nervous.

[0024] The message may be intended for one terminal (a first terminal) or several terminals of the user (including the first terminal). For example, the user may have several terminals receiving the message, and these terminals may be linked together. For example, a user may have a mobile terminal and an electronic watch or bracelet linked or paired with the mobile terminal. Thus, the mobile terminal and the electronic watch or bracelet can receive notifications or messages. In this case, the messages are intended for the user's mobile terminal and watch.

[0025] Physiological data representative of a user's emotional state can be obtained from a biometric module in the user's terminal to which the message is addressed, or from a biometric module in another electronic device, such as another associated user terminal. For example, in the case of a user with a mobile terminal and a smartwatch associated with the mobile terminal, physiological data can be obtained from a biometric module in the smartwatch. The biometric module is configured to measure the user's physiological data, this data being representative of the user's emotional state. Note that the message can be addressed to the mobile terminal and / or the smartwatch.

[0026] The management device implementing the management process can be integrated into a user terminal, which may be the terminal to which the messages are addressed or may be different from that terminal. Furthermore, the management device can be integrated into a server, for example, a mail server. In addition, the management device can be distributed among several of the aforementioned entities.

[0027] According to one feature, the physiological data obtained include data relating to the electrical activity of the user's heart.

[0028] A user's heart activity data gives a good indication of the user's emotional state.

[0029] According to one feature, the management process further includes determining the user's emotional state based on the physiological data obtained, the emotional state being represented by a set of parameters.

[0030] Thus, the method involves determining a set of parameters representative of the user's emotional state. This determined set of parameters represents the user's emotional state.

[0031] The value of the parameters of the assembly is determined according to the physiological data obtained.

[0032] For example, the parameters of the set may be valence, arousal (known in Anglo-Saxon terminology as arousal), and dominance. Valence defines the strength of attraction (positive valence) or repulsion (negative valence) that the user feels toward a situation or object. Arousal indicates a physiological activation order (e.g., low arousal or high arousal). Dominance indicates the degree of control the person has over the emotion felt. In the remainder of this document, we will use valence and arousal as examples, without being limiting. Furthermore, the parameter set may include other parameters representative of the user's emotional state.

[0033] Known methods exist for assigning values ​​to these parameters (valence, arousal, and / or dominance, for example) based on the user's physiological data, particularly data relating to the user's heart electrical activity. Thus, based on the parameter values, the user's emotional state can be determined.

[0034] According to one embodiment, the determination of the emotional state is implemented by an artificial intelligence algorithm.

[0035] Thus, the determination of the values ​​of the set of parameters such as valence and arousal is implemented by means of an artificial intelligence algorithm.

[0036] This artificial intelligence algorithm includes a neural network learning phase and a neural network use phase to determine the values ​​of parameters representative of the user's emotional state.

[0037] According to one feature, the determination of at least one action involves comparing the value of the parameters of the parameter set with threshold values ​​respectively, said at least one action being determined according to the result of said comparison.

[0038] Thus, by comparing the values ​​of parameters such as valence or arousal with predefined thresholds, an action related to message delivery is determined. For example, it can be estimated, based on the user's emotional state, whether or not to implement the delivery, or how the message delivery should be implemented.

[0039] In one embodiment, actions are associated respectively with the possible results of the comparison. For example, if the valence and arousal values ​​are greater than the respective thresholds, a first action is determined; if the valence value is greater than the valence threshold and the arousal value is less than the arousal threshold, a second action is determined, and so on.

[0040] It should be noted that several comparisons with several thresholds can be implemented for the same parameter. For example, the value of a parameter can be compared with a lower threshold and with an upper threshold, to determine whether the value of the parameter is inside or outside a range of values.

[0041] According to one characteristic, said at least one action is further determined according to a set of rules predefined by the user.

[0042] Thus, the determination of said at least one action takes into account, in addition to the emotional state of the user, preferences predefined by the user.

[0043] Message delivery rules are well-known and widely used nowadays, and correspond to any rule established by the user that impacts message delivery. For example, these rules may establish message delivery times or times when message delivery should be avoided, the delivery of all messages from a sender or, conversely, the non-delivery of messages from a sender, etc.

[0044] According to one embodiment, data retrieval is implemented upon receipt of said message by the terminal or by a server managing the reception of messages from said terminal.

[0045] Thus, obtaining data representing the user's emotional state is implemented each time a message intended for the user is received. The user's emotional state is therefore taken into account in real time for the delivery of a message.

[0046] According to embodiments, physiological data are obtained following the receipt of a message by the terminal to which the message is addressed or following the receipt of the message by the mail server associated with the terminal to which the message is addressed.

[0047] According to another embodiment, data acquisition is implemented periodically.

[0048] According to this embodiment, the user's emotional state is determined regularly and independently of message reception. Thus, upon receiving a message, the action to be taken on the message is determined more quickly. This embodiment is even more efficient when physiological data is obtained frequently, i.e., when the data acquisition period is short. This allows for consideration of changes in the user's emotional state.

[0049] The characteristics of the management process presented below can be taken individually or in combination with each other.

[0050] According to a second aspect, the present invention relates to a message management device intended for at least one user terminal, comprising:

[0051] - a data acquisition module configured to obtain physiological data representative of the user's emotional state,

[0052] - a determination module configured to determine at least one relative action to the delivery of said message on at least said terminal, based on said physiological data obtained, and

[0053] - an action module configured to implement said at least one action determined.

[0054] According to one feature, the acquisition module is configured to obtain said physiological data from at least one sensor associated with said user terminal.

[0055] For example, said at least one sensor may be located in the user terminal or in an electronic device associated with the user terminal. This electronic device may be a second user terminal.

[0056] The management device can be integrated into the terminal of the user to whom the message is addressed, into another terminal of the user associated with the terminal of the user to whom the message is addressed, or into a server receiving messages destined for at least the user's terminal.

[0057] The present invention relates, according to a third aspect, to a user terminal comprising a management device according to the invention, and a user interface for presenting messages.

[0058] The present invention relates, according to a fourth aspect, to a system comprising at least two user terminals associated with each other, at least one of the user terminals conforming to the invention.

[0059] The present invention relates, according to a fifth aspect, to a program for a management device, comprising program code instructions intended to control the execution of the steps of the management process according to the invention.

[0060] The present invention relates, according to a sixth aspect, to a processor-readable information carrier in a management device, on which the computer program according to the invention is recorded.

[0061] The management device, the user terminal, the system, the computer program and the information medium have characteristics and advantages similar to those described above in relation to the management process.

[0062] Other features and advantages of the invention will become apparent in the following description.

[0063] To the attached drawings, given by way of non-limiting examples:

[0064] - Fig. 1 represents an example of a context in which the management process can to be implemented,

[0065] - Figure 2 illustrates steps in the management process conforming to a method of realization of the invention,

[0066] - Figure 3 illustrates steps in a management process conforming to a second mode of the realization of the invention,

[0067] - [Fig. 4a] illustrates a hardware architecture capable of implementing the process management in accordance with the invention; and

[0068] - [Fig. 4b] is a functional representation of a conforming management device to an embodiment of the invention.

[0069] The invention applies to any user terminal receiving written and voice messages via a communications network.

[0070] Figure 1 illustrates an example of a context in which the management process can be implemented. In the illustrated context, a user 1 has several terminals 2, 3 capable of receiving messages or notifications. Note that the terms message and notification are used interchangeably in this document.

[0071] The term "user terminal" refers to an electronic device that enables the user to receive data via a communication network. In other words, the user terminal is an access point that connects to a wired or wireless communication network and allows the user to receive and decode messages received via that network. The user terminal is the recipient of a message, this message being addressed to the user. In this document, a message addressed to the user and a message addressed to the user terminal are equivalent.

[0072] In the illustrated example, the user terminals correspond to a smartwatch 2 and a mobile device 3 configured to receive messages intended for the user. For example, the smartwatch 2 can be associated with the mobile device 3. Thus, the smartwatch 2 can be configured to receive messages received by the mobile device 3. The terminals are considered to be associated with the user. Of course, this example is not limiting, as the invention applies to any type of terminal configured to receive messages. For example, the user terminal could be a tablet, a personal computer, a game console, a landline telephone, etc.

[0073] An embodiment of a user terminal capable of implementing the proposed management process will be described with reference to Figures 4a and 4b.

[0074] Messages received by a user's terminal can be of different types, for example, text messages, such as emails, short text messages or SMS messages, messages received via instant messaging, telephone call notifications, notifications relating to applications installed on the terminal, etc. Generally, the user's terminal is configured to receive different types of messages. via the communication network. For example, the terminal may contain several applications managing the sending and receiving of messages. For example, the terminal may include an instant messaging application, an application managing SMS messaging services, an application managing telephone calls, journalistic or other applications receiving notifications of information, alerts, advertising, etc.

[0075] The messages received in the terminals of user 2, 3 may come from another terminal 30 of a user 10 or from a notification server 5 configured to send notifications to user terminals, for example notifications from a log.

[0076] The method of managing (described with reference to Figures 2 and 3) a message intended for at least one user terminal 2, 3 is implemented by a management device 300. According to embodiments, the management device 300 can be integrated into a user terminal 2, 3, into a server 6 managing messages received by the user terminal such as a mail server, or distributed between one or more user terminals 2, 3, or between one or more user terminals 2, 3 and a server 6.

[0077] Fig. 2 illustrates steps in the process of managing a message destined for a user terminal according to one embodiment.

[0078] In one embodiment, the management process is implemented by one of the user's terminals, for example by the connected watch 2. The management device 300 is thus considered to be integrated into the connected watch 2. In this description, the management device 300 is considered to be the same as the connected watch 2. Thus, the connected watch 2 is considered to implement the steps of the management process.

[0079] According to other embodiments, the steps of the process can be carried out by another terminal such as the mobile terminal 3, or by a server 6 such as a mail server. According to another embodiment, steps of the process can be carried out by different terminals respectively and / or by the server.

[0080] As will be described below, thanks to the management method, the delivery of messages to a user terminal 2, 3 takes into account the emotional state of user 1. The management device in the smartwatch 2 is configured to manage messages to the smartwatch 2 itself and / or the mobile terminal 3. Of course, the messages can be intended for other terminals of the user.

[0081] According to some embodiments, messages intended for the connected watch 2 can be received by the connected watch 2 before the implementation of the method of management (for example, when the management process is implemented by the smartwatch, namely the described embodiment), or may remain in a server 6 of the email server type before the implementation of the management process (for example, when the management process is implemented by the server).

[0082] For the purposes of describing the management process below, it is assumed that the messages are intended for at least the connected watch 2 and that the messages are received by the connected watch 2 before the implementation of the management process. In one embodiment, the receipt of an email message triggers the implementation of the proposed management process.

[0083] When a message is received by a user terminal (the connected watch 2) during a reception step E0, the user terminal 2 obtains El physiological data (or biometric data) 100 representative of an emotional state of the user 1.

[0084] In one embodiment, the physiological data 100 includes data relating to the electrical activity of the user's heart 1.

[0085] Data from the electrical activity of the heart or cardiac activity of a user gives a good indication of the user's emotional state.

[0086] This data relating to the user's cardiac activity can be obtained from at least one electrocardiogram sensor or similar.

[0087] In the described embodiment, the connected watch 2 includes at least one ECG electrocardiogram sensor ([Fig.1]) configured to obtain data 100 relating to the electrical activity of the heart of user 1. Thus, in the described embodiment, the data 100 relating to the electrical activity of the heart of user 1 are obtained by said at least one ECG electrocardiogram sensor embedded in the connected watch 2.

[0088] In other embodiments, the physiological data 100 can be obtained from another electronic device. For example, if the management process is implemented by the mobile terminal 3, the physiological data 100 can be obtained from the connected watch 2 associated with the mobile terminal 3, this watch having at least one electrocardiogram (ECG) sensor configured to obtain, in turn, the data 100 relating to the electrical activity of the heart of the user 1.

[0089] It should be noted that when the user terminal does not have the means necessary to obtain physiological data 100 by itself, it is configured to obtain them from another electronic device associated with the user terminal.

[0090] According to some embodiments, the electronic device measuring the user's heart activity 1 can be a terminal, such as a smartwatch 3 or a connected bracelet, or any other electronic device with electrocardiogram sensors configured to measure and record the electrical activity of the user's heart, such as a Holter monitor.

[0091] As indicated above, in the described embodiment, the obtaining of data El is implemented upon receipt E0 of a message by the user terminal (the connected watch).

[0092] The physiological data 100 are thus obtained in real time and the determined emotional state is the current emotional state, i.e. at the time of receiving the message.

[0093] In the described embodiment, once the connected watch 2 has obtained the physiological data 100, it implements the determination E2 of the user's emotional state based on the physiological data 100 obtained.

[0094] In one embodiment, the emotional state is represented by a set of parameters representative of the emotional state. For example, the parameter set includes the user's valence and the user's arousal. It is known that these two parameters represent the user's emotional state. Valence (VAL) represents the strength of attraction or repulsion that the user feels toward a situation or object. Arousal (ARO) represents the physiological activation corresponding to an emotion.

[0095] Based on the physiological data obtained, a value is assigned to the parameters, this value numerically indicating the power of attraction or repulsion, in the case of valence, and the intensity of physiological activation in the case of arousal. By way of non-limiting example, a value from 1 to 10 can be assigned to each of the parameters. For example, in the case of valence, the value 0 indicates the maximum power of repulsion or minimum power of attraction, and the value 10 indicates the minimum power of repulsion or maximum power of attraction. Other, more or less precise, scales of values ​​can be used. According to another example, valence can be defined as positive or negative, and arousal as high or low.

[0096] In one embodiment, the determination E2 of the emotional state is implemented by an artificial intelligence algorithm. Thus, the valence values ​​VAL and arousal ARO are determined by an artificial intelligence algorithm. An artificial intelligence algorithm can be based on a learning model (deep learning model in Anglo-Saxon terminology) using a neural network, for example, of the Transformer type. This type of artificial intelligence algorithm is known and is not described here in detail. For example, the documents “Attention is All You Need. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, AN Gomez, L. Kaiser, I. Polosukhin. In Advances in neural information processing Systems, 2017 » and « BERT: pre-training of deep bidirectional transformers for language understanding. J. Devlin, M. Chang, K. Lee, K. Toutanova. In Conference of the North American chapter of the association for computational linguistics: human language technologies, 2019 » describe Transformer-type neural networks and uses of this type of neural network.

[0097] In one embodiment, the physiological data obtained El comprises data sequences. These data sequences are processed E21 by a processing module before being provided to the neural network for determining the emotional state of user 1. In one embodiment, the data sequences can be segmented to form data vectors vl. By way of non-limiting example, the data is segmented into 10 ms windows.

[0098] In one embodiment, the data vectors v1 can be provided E22 to a neural network, for example a convolutional neural network (CNN), to obtain second data vectors v2. These second data vectors v2 correspond to feature vectors describing the sequences of values ​​in the data vectors v1. A feature vector is understood to be a vector of numerical values ​​in a vector space whose dimensions are features allowing the discrimination of different situations, namely emotional states.

[0099] It should be noted that in the described embodiment, these feature vectors are automatically generated by learning with the convolutional neural network CNN.

[0100] Next, the second data vectors v2 are provided E23 to a second neural network to obtain values ​​for the VAL, ARO parameter set representative of the emotional state of user 1. In one embodiment, the neural network comprises a first Transformer-type section and a second section, attached to the first, of fully-connected neural layers.

[0101] According to one embodiment, this second neural network is first trained from data in a database DB_D containing numerous data sequences representative of the electrical activity of user 1's heart (ECG-type data) and associated VAL and ARO values. According to one embodiment, the neural network training comprises a first phase during which the Transformer-type neural network learns to reconstruct, from the feature vectors (second vectors v2), input sequence vectors (sequences containing ECG data) with missing data. A second phase uses, for each input sequence containing data ECG learning of VAL, ARO values ​​representative of the emotional state of user 1 to be provided as output.

[0102] Once the values ​​of the parameters of the set have been determined, each value of a parameter VAL, ARO is compared E31 with a threshold value respectively (threshold valence value and threshold wakefulness value).

[0103] In one embodiment, these comparisons allow E32 emotion to be classified into a category.

[0104] In one embodiment, emotions are classified into four categories based on the results of comparisons between the values ​​of the parameters VAL and ARO and the threshold values, respectively. These categories are as follows, determined based on the results of the comparisons:

[0105] - negative / weak when the valence is negative relative to the valence value of threshold and that the arousal value is less than the threshold arousal value,

[0106] - negative / strong when the valence is negative relative to the valence value of threshold and that the arousal value is greater than the threshold arousal value,

[0107] - positive / weak when the valence is positive with respect to the valence value of threshold and that the arousal value is less than the threshold arousal value,

[0108] - positive / strong when the valence is positive with respect to the valence value of threshold and that the arousal value is greater than the threshold arousal value.

[0109] In the example of a value scale shown below, the threshold value (for valence and arousal) can be 5.

[0110] Of course, other parameters can be used to represent the user's emotional state. Furthermore, the classification can include different emotion categories. In addition, several threshold values ​​can be used to determine the value of a parameter.

[0111] Next, in the described embodiment, an action relating to the delivery of said message on at least said terminal is determined E33 according to the category of emotion obtained.

[0112] In one embodiment, at least one action related to delivering a message is associated with each emotion category. A database, called the action database DB_E, lists the actions to be implemented for each emotion category. Thus, once the emotion category is obtained, the action can be determined by consulting this database. This database is updated over time.

[0113] In one embodiment, the determination of the action also takes into account a set of rules predefined by the user. These user rules or user preferences are stored in a database called the preference database DB_P. This preference database lists actions relating to the The user's desired delivery methods are independent of actions determined based on the user's emotional state. For example, and not limited to, actions such as delaying the delivery of received messages during a specific time period, only delivering messages from a particular sender, or not delivering a certain type of notification, etc.

[0114] In one embodiment, the emotions database DB_E is consulted first, and once the action to be implemented has been determined, the preferences database DB_P is consulted to check whether a rule should be taken into account. The definition and application of user rules and preferences are known and will not be described in detail here.

[0115] In one embodiment, the content of the message to the user is taken into account. An indicator of whether the message content is positive (if the message can positively influence the user's emotional state) or negative (if the message can negatively influence the user's emotional state) can be associated with the message. In some embodiments, this indicator can be sent with the message by the sender of the message or notification.

[0116] In one embodiment, the sender of the message or notification can associate a rating with the message, this rating being indicative of whether the message content is positive (if the message can positively influence the user's emotional state) or negative (if the message can negatively influence the user's emotional state). According to another embodiment, the terminal receiving the message is configured to perform semantic and / or syntactic analysis to recognize terms or expressions in the message and associate a positive rating with the message if the term or expression can positively influence the user's emotional state, or a negative rating if the term or expression can negatively influence the user's emotional state.

[0117] By way of non-limiting example, if the emotion category is negative / strong and / or if the cue associated with the message is negative (indicating that the message content may have a negative impact on the user's emotional state), an action related to message delivery may be to postpone the delivery of the message to a later time. As another example, if the emotion category is negative / strong and the cue associated with the message is positive (indicating that the message content may have a positive impact on the user's emotional state), the action related to message delivery may be to deliver the message to the user.

[0118] According to another example, if the emotion category is negative / strong, the information to be notified (message content) has a negative index, and the user's preference is to delay notifications, the message management device waits for a period of time to elapse, for example 5 minutes, before determining again The message management system assesses the user's emotional state and determines the appropriate action to take regarding message delivery. For example, if the user's preference specifies when notifications can be received, the message management system waits until that time to reassess the user's emotional state and determine the appropriate action to take regarding message delivery.

[0119] Of course, these examples are given for illustrative purposes only and are not exhaustive.

[0120] Once the action to be implemented on the message is determined, it is implemented E4.

[0121] Examples of actions relating to the delivery of the message may be the presentation of the message, the refusal to present the message, the delay in the presentation of the message, the delivery of the message at a specific time, the modification of the content of the message to be presented (for example, shortening it if it is very long or changing its subject or title), the form of delivery of the message, for example, whether the message is accompanied by a ring, by a vibration or by neither of the latter two, etc.

[0122] According to different embodiments, the steps can be implemented in different orders. Figure 3 illustrates steps in the message management process according to another embodiment. In this embodiment, the steps are similar but implemented in a different order than in the embodiment described with reference to Figure 2.

[0123] In this embodiment, data acquisition is performed periodically. The physiological data obtained E1' are stored in memory. When a message is received E0', the determination of the user's emotional state E2 is performed using the stored physiological data. Since the steps are similar to those described with reference to [Fig. 2], they will not be described again here.

[0124] According to this embodiment, since the user's emotional state is determined regularly, the action to be taken on the message is determined more quickly. It should be noted that the more frequently the physiological data is obtained, the closer the physiological data obtained is to the moment of message reception.

[0125] According to another embodiment not shown, obtaining and determining the user's emotional state is carried out regularly, and the data and / or emotional state is stored in memory. In this embodiment, when a message is received by the terminal (or the mail server), the stored emotional state is used to determine the action to be taken on the message. In this embodiment, message processing is faster.

[0126] Fig. 4a schematically illustrates a hardware architecture of a user terminal comprising a management device capable of implementing the proposed management process, and more particularly of a terminal comprising a management device capable of implementing the process.

[0127] The management device 200 or the user terminal 2, 3 includes a communication bus 200 to which the following are connected:

[0128] - a processing unit 201, named in the figure CPU (for "Central Processing") Unit") and may include one or more processors;

[0129] - a non-volatile memory 202, for example ROM (for "Read Only Memory"), EEPROM (for "Electrically Erasable Read Only Memory") or Flash memory;

[0130] - a 203 RAM (for "Random Access Memory");

[0131] - an input / output interface 204, labeled in the figure I / O (for "Input / Output") "), for example keys or buttons, a screen, a keyboard, a mouse, or another pointing device such as a touchscreen or remote control, enabling a user to interact with the user's terminal via a graphical user interface or human-machine interface; and

[0132] - a communication interface 205, named COM in the figure, adapted to exchanging data for example with other user terminals or other associated electronic devices, or with a server 5, 6, for example a mail server 6, via a communications network 4.

[0133] The random access memory 203 includes registers adapted for storing variables and parameters created and modified during the execution of a computer program comprising instructions for implementing the proposed management process. The instruction codes of the program stored in non-volatile memory 202 are loaded into RAM 203 for execution by the CPU 201.

[0134] The PG computer program can implement artificial intelligence to determine the user's emotional state based on physiological data. The implementation of the artificial intelligence can, for example, rely on data from a knowledge base listing emotional states previously determined based on prior physiological data.

[0135] The non-volatile memory 202 is, for example, a rewritable memory of the EEPROM or Flash type that can constitute a medium within the meaning of the invention, that is to say, that can include a computer program PG comprising instructions for implementing the proposed management method. The rewritable memory can include, for example, the database DB_D containing data sequences representative of the electrical activity of the user's heart used by the artificial intelligence algorithm, the database DB_E emotion database listing the actions to be implemented for each emotion category, DB_P preference database listing delivery-related actions desired by the user.

[0136] In another embodiment, the databases may be external to the user's terminal.

[0137] These databases can be updated as messages are received, physiological data are obtained, and emotional states and actions are determined.

[0138] In one embodiment, the user terminal includes at least one electrocardiogram (ECG) sensor configured to measure the electrical activity of the user's heart. In this embodiment, the user terminal may be a smartwatch or a smart bracelet.

[0139] In one embodiment, the ECG electrocardiogram sensor may be external to the management device 300.

[0140] The PG program defines, through its instructions, functional modules of the user terminal that implement and / or control the hardware elements described above. Figure 4b is a functional representation of a user terminal capable of implementing the process, and more particularly a terminal comprising a management device capable of implementing the process according to one embodiment.

[0141] These modules may include, in particular:

[0142] - a data acquisition module 21 configured to obtain physiological data representative of the user's emotional state,

[0143] - a determination module 22 configured to determine at least one action relating to the delivery of said message on at least said terminal, based on said physiological data obtained, and

[0144] - an action module 23 configured to implement the determined action.

[0145] In one embodiment, the data acquisition module 21 is configured to measure data relating to the electrical activity of the user's heart. In this embodiment, the data acquisition module is configured to obtain physiological data from at least one sensor associated with the user terminal. For example, the terminal could be a smartwatch or a fitness tracker. In another embodiment, the data acquisition module 21 is configured to obtain data relating to the electrical activity of the user's heart from another electronic device, the latter being configured to measure the data itself.

[0146] According to some embodiments, the management system may include:

[0147] - a determination module 24 configured to determine the emotional state of the user based on the physiological data obtained, the emotional state being represented by a set of parameters representative of the emotional state;

[0148] - a comparison module 25 configured to compare the value of the parameters of the set of parameters with respective threshold values.

[0149] In addition, the management device includes a processing module 26 configured to process the sequences of physiological data obtained.

[0150] The aforementioned modules and means are controlled by the processor of the processing unit 201. They can take the form of a program executable by a processor, or a hardware form, such as a specialized integrated circuit (known in Anglo-Saxon terminology as ASIC for "Application-Specific Integrated Circuit"), a system on chip (known in Anglo-Saxon terminology as SoC for "System On Chip"), or an electronic component of the type programmable logic circuit, such as a component of type FPGA (for "Field-Programmable Gate Array").

[0151] Thus, thanks to the invention, the delivery of a message on a user's terminal takes into account the emotional state of the user when receiving the message.

Claims

Claims

1. Method for managing a message intended for at least one terminal (2, 3), of a user (1), said management method comprising the following steps implemented by a management device (300): - obtaining (El') periodically and independently of the reception of said message, physiological data (100) representative of an emotional state of the user (1), - recording in memory said physiological data obtained, - determining (E2) periodically and independently of the reception of said message, a category of emotional state of the user as a function of the recorded physiological data, - recording in memory said determined category of emotional state, - when a message is received (E0'), determining (E3) at least one action relating to the delivery of said message on at least said terminal, said action being associated with the recorded category of emotional state, and - implementing (E4) said at least one determined action.

2. Management method according to claim 1, in which the physiological data (100) comprises data relating to the electrical activity of the heart of the user (1).

3. Management method according to one of claims 1 or 2, further comprising the determination (E2) of the emotional state of the user as a function of the physiological data obtained, the emotional state being represented by a set of parameters (VAL, ARO).

4. Management method according to claim 3, in which the determination (E2) of the emotional state is implemented by an artificial intelligence algorithm.

5. Management method according to one of claims 3 or 4, in which the determination (E3) of at least one action comprises the comparison (E31) of the value of the parameters of the set of parameters (VAL, ARO) with threshold values ​​respectively, said at least one action being determined (E33) as a function of the result of said comparison.

6. Management method according to one of claims 1 to 5, in which said at least one action is further determined (E3) according to a set of rules predefined by the user.

7. Device for managing a message intended for at least one terminal of a user, comprising: - an obtaining module (21) configured to obtain periodically and independently of the reception of said message, physiological data representative of an emotional state of the user, - a memory for recording said obtained physiological data, - a determination module configured to determine periodically and independently of the reception of said message, a category of emotional state of the user as a function of the recorded physiological data, - a memory for recording said determined category of emotional state, - a determination module (22) configured to determine at least one action relating to the delivery of said message on at least said terminal, the state action associated with the recorded category of emotional state, and - an action module (23) configured to implement the determined action.

8. Management device according to claim 7, wherein said obtaining module is configured to obtain said physiological data (100) from at least one sensor (ECG) associated with said user terminal.

9. User terminal comprising a management device according to one of claims 7 or 8 and a user interface for presenting messages.

10. A computer program for a management device, comprising program code instructions for controlling the execution of the steps of the management method according to one of claims 1 to 6, when executed on a processor.

11. Information carrier readable by a processor in a management device, on which the computer program according to claim 10 is recorded.