Method for creating a multimedia element, and corresponding electronic device and computer program product

Abstract

The invention relates to an at least partially automatic method for creating a multimedia element, the method comprising: - obtaining a first sequence via a user interface of a first communication device; - generating at least one multimedia element suitable for sending, via at least one first communication tool to at least one first recipient, the multimedia element being automatically generated and comprising a second textual sequence derived from the first sequence and at least one visual element, wherein the visual element depends on the first sequence; - sending the multimedia element via the first communication tool to the at least one first recipient. The invention also relates to the electronic device and to the corresponding computer program product and medium.

Description

[0001] DESCRIPTION

[0002] Title of the invention: Method for creating a multimedia element, electronic device and corresponding computer program product

[0003] 1. Technical field

[0004] This application relates to the field of information exchange between electronic devices of at least one communication network. This may in particular be information intended for users of such devices. It relates in particular to a method for the at least partially automatic creation of a multimedia element, implemented by an electronic device, as well as a corresponding electronic device, server, computer program product and medium.

[0005] 2. State of the art

[0006] Due to the convenience they offer (in terms of traceability as well as ease of editing, sharing, or transferring information), electronic communications have become essential in exchanges between individuals. This is particularly the case in situations of teleworking or "multi-site" teamwork.

[0007] These communications are often asynchronous, so as not to require joint availability of the communication partners.

[0008] An individual therefore often needs to generate electronic communications (e.g., electronic messages), whether in their personal life or at work. The content of an electronic message can sometimes be dense, particularly in the professional world, for example due to the complexity of the real-life situation to which it relates, or because the message is intended for different stakeholders, from whom the sender of the message expects different reactions.

[0009] However, the proliferation and sometimes complexity of remote communications increasingly confronts individuals with information overload (sometimes referred to as "infobesity"). Also, individuals receiving messages may sometimes be slow to process a message, or even forget to process it, or process it only partially. They may also not see that a response from them to a message received is expected (particularly when the message is addressed to several people).

[0010] There is therefore a need for a sender of an electronic message for a solution helping him to improve the effectiveness of his communication, for example to help him obtain the treatment (reading or response) expected from his interlocutors.

[0011] 3. Statement of the invention

[0012] The present application aims to improve the situation by using a method for at least partially automatic creation of multimedia elements.

[0013] According to the application, said method comprises: obtaining a first sequence via a user interface of a first communication device, generating at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second text sequence obtained from the first sequence and at least one visual element; sending said multimedia element via said first communication tool to said at least one first recipient.

[0014] In some embodiments, at least one said visual element depends on said first sequence.

[0015] In some embodiments, said first sequence is a text or audio sequence.

[0016] Thus, in certain embodiments, said method comprises: obtaining a first sequence via a user interface of a first communication device, generating at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second text sequence obtained from the first sequence and at least one visual element, said visual element depending on said first sequence; sending said multimedia element via said first communication tool to said at least one first recipient. In certain embodiments, at least one said visual element is a visual background of said multimedia element.

[0017] In some embodiments, the method may comprise proposing on a user interface of said device said generated multimedia element, said sending being carried out upon receipt of a confirmation (for example from the user interface of said device).

[0018] In at least some embodiments, the method comprises an automatic (or at least partially automatic) selection of at least a first visual element of said multimedia element from among visual contents of a library of visual contents based on a semantic similarity between descriptors of said visual contents of the library and the second textual sequence.

[0019] These descriptors may be metadata (also called "tags" or "keywords") describing the visual content and embedded in the visual content they describe or stored in association with identifiers of this content in a storage space separate from the content library.

[0020] In at least some embodiments, said first recipient is a function of said first sequence.

[0021] In at least some embodiments, the method comprises associating said multimedia element with a generation context for said multimedia element.

[0022] In at least some embodiments, the method comprises storing said multimedia element and said associated generation context during said sending.

[0023] In at least some embodiments, said multimedia element further comprises at least one actuator dependent on said second text sequence. In at least some embodiments, said actuator initiates communication with a second recipient designated in said second text sequence.

[0024] In at least some embodiments, said actuator initiates a communication to a communication device of a user of said first communication device.

[0025] In at least some embodiments, said initiated communication is a communication via said first communication tool.

[0026] In at least some embodiments, said initiated communication is a communication via a second communication tool used for obtaining said first sequence.

[0027] In at least some embodiments, said second sequence is positioned in juxtaposition relative to at least one of said visual element of said multimedia element.

[0028] In at least some embodiments, said method comprises proposing a plurality of multimedia elements obtained from said first sequence.

[0029] The features presented in isolation in the present application in connection with certain embodiments of the method of the present application can be combined with each other according to other embodiments of the present method.

[0030] According to another aspect, the present application also relates to an electronic device adapted to implement the method of the present application in any of its embodiments.

[0031] For example, the present application thus relates to an electronic device comprising at least one processor configured for at least partially automatic creation of a multimedia element, said creation comprising: obtaining a first sequence via a user interface of a first communication device, generating at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second text sequence obtained from the first sequence and at least one visual element; sending said multimedia element via said first communication tool to said at least one first recipient.

[0032] For example, the present application thus relates to an electronic device comprising at least one processor configured for at least partially automatic creation of a multimedia element, said creation comprising: obtaining a first sequence via a user interface of a first communication device, generating at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second text sequence obtained from the first sequence and at least one visual element, said visual element depending on said first sequence; sending said multimedia element via said first communication tool to said at least one first recipient.

[0033] For example, the present application thus relates to a server of a communications network comprising at least one microprocessor adapted to:

[0034] - a reception, via a first communication tool, of at least one multimedia element comprising at least one textual sequence and at least one visual element; and of at least one creation context associated with said at least one multimedia element, said creation context comprising at least:

[0035] • a designation of a device transmitting said multimedia element,

[0036] • a designation of at least one device receiving said multimedia element,

[0037] • at least one so-called original textual or audio sequence which reformulates at least in part said textual sequence and

[0038] • a designation of at least one second communication tool used to obtain said original sequence; a transmission to said at least one recipient device of said multimedia element; upon receipt of feedback relating to consumption of content by said recipient, transmission of said feedback to a device of a user of said transmitting device using said second communication tool.

[0039] For example, the present application thus relates to a server of a communications network comprising at least one microprocessor adapted to:

[0040] - a reception, via a first communication tool, of at least one multimedia element comprising at least one textual sequence and at least one visual element; and of at least one creation context associated with said at least one multimedia element, said creation context comprising at least:

[0041] • a designation of a device transmitting said multimedia element,

[0042] • a designation of at least one device receiving said multimedia element,

[0043] • at least one so-called original textual sequence which at least partly reformulates said textual sequence and

[0044] • a designation of at least one second communication tool used to obtain said original sequence; a transmission to said at least one recipient device of said multimedia element; upon receipt of feedback relating to consumption of content by said recipient, transmission of said feedback to a device of a user of said transmitting device using said second communication tool.

[0045] The present application also relates to a computer program comprising instructions for implementing the various embodiments of the above method, when the program is executed by a processor, and a recording medium readable by an electronic device and on which the computer program is recorded.

[0046] For example, the present application thus relates to a computer program comprising instructions for implementing, when the program is executed by a processor of an electronic device, a method for at least partially automatic creation of a multimedia element, said method comprising: obtaining a first sequence via a user interface of a first communication device, generating at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second text sequence obtained from the first sequence and at least one visual element, sending said multimedia element via said first communication tool to said at least one first recipient.

[0047] For example, the present application thus relates to a computer program comprising instructions for implementing, when the program is executed by a processor of an electronic device, a method for at least partially automatically creating a multimedia element, said method comprising: obtaining a first sequence via a user interface of a first communication device, generating at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second text sequence obtained from the first sequence and at least one visual element, said visual element depending on said first sequence; sending said multimedia element via said first communication tool to said at least one first recipient.

[0048] For example, the present application thus relates to a computer program comprising instructions for the implementation, when the program is executed by a processor of a server of a communications network, of a method comprising:

[0049] - a reception, via a first communication tool, of at least one multimedia element comprising at least one textual sequence and at least one visual element; and of at least one creation context associated with said at least one multimedia element, said creation context comprising at least:

[0050] • a designation of a device transmitting said multimedia element,

[0051] • a designation of at least one device receiving said multimedia element,

[0052] • at least one so-called original textual or audio sequence which reformulates at least in part said textual sequence and

[0053] • a designation of at least one second communication tool used to obtain said original sequence; a transmission to said at least one recipient device of said multimedia element; upon receipt of feedback relating to consumption of content by said recipient, transmission of said feedback to a device of a user of said transmitting device using said second communication tool.For example, the present application also relates to a recording medium readable by a processor of an electronic device and on which is recorded a computer program comprising instructions for implementing, when the program is executed by the processor, a method for at least partially automatic creation of a multimedia element, said method comprising: obtaining a first sequence via a user interface of a first communication device, generating at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second text sequence obtained from the first sequence and at least one visual element; sending said multimedia element via said first communication tool to said at least one first recipient.

[0054] For example, the present application also relates to a recording medium readable by a processor of an electronic device and on which is recorded a computer program comprising instructions for implementing, when the program is executed by the processor, a method for at least partially automatic creation of a multimedia element, said method comprising: obtaining a first sequence via a user interface of a first communication device, generating at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second text sequence obtained from the first sequence and at least one visual element, said visual element depending on said first sequence; sending said multimedia element via said first communication tool to said at least one first recipient.

[0055] The present application also relates to a recording medium readable by a processor of a server of a communications network and on which is recorded a computer program comprising instructions for the implementation, when the program is executed by the processor, of a method comprising:

[0056] - a reception, via a first communication tool, of at least one multimedia element comprising at least one textual sequence and at least one visual element; and of at least one creation context associated with said at least one multimedia element, said creation context comprising at least:

[0057] • a designation of a device transmitting said multimedia element,

[0058] • a designation of at least one device receiving said multimedia element,

[0059] • at least one so-called original textual or audio sequence which reformulates at least in part said textual sequence and

[0060] • a designation of at least one second communication tool used to obtain said original sequence; a transmission to said at least one recipient device of said multimedia element; upon receipt of feedback relating to consumption of content by said recipient, transmission of said feedback to a device of a user of said transmitting device using said second communication tool.

[0061] The above-mentioned programs may use any programming language, and may 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.

[0062] The recording (or information) media referred to in this application may be any entity or device capable of storing the program. For example, a medium may include a storage medium, such as a ROM, for example a CD ROM or a microelectronic circuit ROM, or a magnetic recording medium.

[0063] Such a storage medium may, for example, be a hard disk, a flash memory, etc. On the other hand, an information carrier may be a transmissible medium such as an electrical or optical signal, which may be conveyed via an electrical or optical cable, by radio or by other means. A program according to the invention may in particular be downloaded from a network such as the Internet.

[0064] Alternatively, an information (or recording) medium may be an integrated circuit in which a program is incorporated, the circuit being adapted to execute or to be used in the execution of any of the embodiments of the method which is the subject of the present patent application.

[0065] Generally speaking, by obtaining an element, we mean in the present application for example a reception of this element from a communication network, an acquisition of this element (via for example user interface elements or sensors), a creation of this element by various processing means such as by copying, encoding, decoding, transformation etc. and / or an access of this element from a local or remote storage medium accessible to at least one device implementing, at least partially, this obtaining.

[0066] 4. Brief description of the drawings

[0067] Other characteristics and advantages of the invention will appear more clearly on reading the following description of particular embodiments, given as simple illustrative and non-limiting examples, and the appended drawings, among which:

[0068] [Fig 1] shows a simplified view of an exemplary system in which at least some embodiments of the method of the present application may be implemented,

[0069] [Fig 2] shows a simplified view of a device suitable for implementing at least certain embodiments of the method of the present application,

[0070] [Fig 3] presents an overview of the method of the present application, in some of its embodiments. [Fig 4] presents an example user interface of an electronic device implementing at least some embodiments of the method of the present application.

[0071] [Fig 5] presents an example of a timing diagram of exchanges between a transmitting terminal, a server and a receiving terminal for the implementation of at least certain embodiments of the method of the present application.

[0072] 5. Description of embodiments

[0073] The present application proposes to create, at least partially automatically, from a first sequence (textual or audio), one or more multimedia elements intended to be shared via an electronic communication tool. The first sequence can be obtained from a user. It can be, for example, a textual sequence obtained via keyboard input or an audio sequence acquired via a microphone, for example.

[0074] A multimedia element is understood herein to mean a content element having at least one textual and / or audio component and / or one visual component (such as an image or image sequences or a video). The multimedia element comprises at least one second sequence (textual or audio) obtained from the first sequence. By "from" is meant a second sequence extracted from the first sequence or a second sequence reformulating (for example in a shorter, simpler or clearer manner) at least a portion of the first sequence.

[0075] By "automatic" is meant an implementation that allows the creation of at least one multimedia element from the electronic device without involving any voluntary intervention by its user in this regard, except for the installation of an application implementing the method and the invocation of this application, once certain prerequisites (similar to an initial configuration) have possibly been carried out (such as an assignment of default values ​​to certain parameters of the application, such as a messaging tool to be used for sending the multimedia element, a maximum size of a visual element in a multimedia element or a maximum size of a created multimedia element, etc., and a definition of possible configuration rules for said application).

[0076] The communication tool may in particular correspond to an application implementing at least partially the method. For example, it may be an application of an application platform deployed on a server and client terminals, to allow exchanges of multimedia elements between these client terminals, via “client” applications running on these terminals and at least one central application running on the server.

[0077] The method of the present application can therefore help to simplify the creation of multimedia elements for a user. More specifically, such a method can, on the one hand, help to accelerate the average time for sharing information (via the automation of the creation of the multimedia element) and, on the other hand, help to generate a more complete or more “professional” multimedia element than that which the user would be able to generate by himself, if he is not an expert in computer graphics.

[0078] Thus, in certain embodiments, the multimedia element may comprise at least one visual element. Indeed, the presence of a visual element in a multimedia element may help to improve the understanding of a textual sequence (by illustrating its context). The presence of a visual element in a multimedia element may also have a positive impact on the quality of the multimedia element as perceived by its consumers (i.e. by the people who will consult it). A visual element may also help to make the generated multimedia element more attractive and therefore promote the reading of a textual sequence present in this multimedia element, thus helping the user (sender of the multimedia element) in his search for consumption by third parties of this textual sequence.

[0079] The attractiveness of a multimedia element, intended to be shared with other people, can also be important for a user, in terms of brand image or reputation, as well as for the company to which he belongs.

[0080] The visual element can be chosen automatically, for example via a library of visual content such as an image library, based for example on a similarity or complementarity between the visual element and the “second” textual sequence present in the multimedia element. For example, a visual element intended to accompany, in a multimedia element, the “second” textual sequence “Have you reread the CSR document?” could be an image representing nature (forest, ocean, animal, etc., .. ). Such embodiments can help to make the understanding of the second sequence present in the multimedia element (or the theme of this second sequence) more immediate. They can also contribute to the attractiveness of a multimedia element as highlighted above and therefore to the speed of its consumption.

[0081] The present application is now described in more detail in connection with Figure 1. Figure 1 represents a telecommunications system 100 in which certain embodiments of the invention can be implemented. The system 100 comprises one or more electronic devices, at least some of which can communicate with each other via one or more communication networks 120, possibly interconnected, such as a local area network or LAN (Local Area Network) and / or a wide area network, or WAN (Wide Area Network). For example, the network may comprise a corporate or home LAN network and / or a WAN network of the internet type, or cellular, GSM - Global System for Mobile Communications, UMTS - Universal Mobile Telecommunications System, Wifi - Wireless, etc.).

[0082] As illustrated in Figure 1, the system 100 may also comprise several electronic devices, such as a terminal (such as a laptop 110, a smartphone 130, 132, 134, a tablet 136), and / or a server 140, for example an application server, a storage device 150. The system may also comprise management and / or network interconnection elements (not shown). These electronic devices may be associated with at least one user 160, 162, 164, 166 (for example via a user account accessible by login), some of the electronic devices 110, 130 being able to be associated with the same user 160.

[0083] At least one of the electronic devices of the system 100 can transmit at least one multimedia element generated according to the method of the present application (as described below) to at least one other device of the system 100, recipient of this multimedia element. In the example illustrated, a “client” application 170, 172, 174, 176, 178 implementing at least partially the method of the present application (for example dedicated to the method) can execute on each of these devices. These client applications can exchange multimedia elements (or messages, for example messages following the consumption of these multimedia elements by their recipient(s)) directly or via a central application 180, also implementing at least partially the method of the present application (for example dedicated to the method) and executing remotely, for example on the server 140 of the system 100.According to the embodiments, the multimedia elements can be generated locally by a client application 170, 172, 174, 176 or remotely by the application 180 executing on a server 140.

[0084] The client applications 170, 172, 174, 176, 178 running on the devices may, for example, use the server for storing multimedia elements generated according to the method of the present application and, for example, sent and / or received by these devices. Such centralized storage may help secure access to the multimedia elements or to the elements intended to be incorporated therein (text sequence, image library, actuator library, etc.) and, by centralizing the storage, help to save on memory usage for the deployment of the application platform (in particular for the client applications 170, 172, 174, 176, 178). Centralized storage may help to obtain simpler and therefore easier to maintain client applications.

[0085] In some embodiments, the server may have hub capabilities and interconnection capabilities, enabling interconnections between the central application 180 and other applications (such as communication tools (or channels) running on at least some of the devices). Such capabilities may enable the server to direct a return from a recipient of a multimedia element generated via the method of the present application to a particular communication tool, for example a tool used to create a sequence at the origin of the multimedia element generated via the method of the present application. In such embodiments, a link may be created at the server level between plugins, to the application platform implementing the method, integrated with other tools (such as Teams ©, Slack ©, Google Workplace ©, etc.).

[0086] Client application versions can be synchronized with the 180 application versions running on the server for cross-device compatibility.

[0087] In certain embodiments, the central part of the application platform (i.e. the “central” application 180 running on the server) may comprise several modules, such as a module for managing users of the application platform (i.e. the users of one of the client applications), a module for managing notifications, modules for managing multimedia elements emitted (published) by / via a client application at least partially implementing the method and running on one of the devices.The module for managing the multimedia elements sent via the application platform can, for example, store contextual elements relating to this multimedia element, such as information relating to the original sequence, to the “user” context, to the communication tool (channel) from which the original sequence originates, to the components of the multimedia element (“second” textual sequence obtained by reformulating at least a portion of the original sequence, visual element(s), actuators, etc.), such as these components, their presentation (size, color, etc.) or and / or their positioning, the recipients of the multimedia element, any feedback received, etc.). The module for managing the multimedia elements can also comprise an extraction module 181, a conversion module 182 and a module 183 for managing the consumption of multimedia elements as illustrated further on in connection with FIG. 5.

[0088] Figure 2 illustrates a simplified structure of an electronic device 200 of the system 100, for example the device 110, 130 or 140 of Figure 1, adapted to implement the principles of the present application. Depending on the embodiments, it may be a server, and / or a terminal.

[0089] The device 200 comprises in particular at least one memory M 210. The device 200 may in particular comprise a buffer memory, a volatile memory, for example of the RAM type (for “Random Access Memory” according to English terminology), and / or a non-volatile memory, for example of the ROM type (for “Read Only Memory” according to English terminology). The device 200 may also comprise a processing unit UT 220, equipped for example with at least one processor P 222, and controlled by a computer program PG 212 stored in memory M 210. At initialization, the code instructions of the computer program PG are for example loaded into a RAM memory before being executed by the processor P.Said at least one processor P 222 of the processing unit UT 220 can in particular implement, individually or collectively, any one of the embodiments of the method of the present application (described in particular in relation to figure 3), according to the instructions of the computer program PG.

[0090] The device may also comprise, or be coupled to, at least one I / O input / output module 230, such as a communication module, allowing for example the device 200 to communicate with other devices of the system 100, via wired or wireless communication interfaces, and / or such as a module for interfacing with a user of the device (also called more simply in this application “user interface”).

[0091] By user interface of the device, we mean for example an interface integrated into the device 200, or a part of a third-party device coupled to this device by wired or wireless communication means. For example, it may be a secondary screen of the device or a set of speakers connected by wireless technology to the device 200.

[0092] A user interface may in particular be a user interface, called an “output” interface, adapted to rendering (or controlling rendering) of an output element of a computer application used by the device 200, for example an application running at least partially on the device 200 or an “online” application running at least partially remotely, for example on the server 140 of the system 100. Examples of output user interfaces of the device include one or more screens, in particular at least one graphic screen (touch screen for example), one or more speakers, a connected headset.

[0093] Such an output user interface may in particular be adapted to the rendering of a multimedia element as generated (created) by the method of the present application.

[0094] By rendering, we mean here a restitution (or “output” according to English terminology) on at least one user interface, in any form, for example comprising textual, audio and / or video components, or a combination of such components. Furthermore, a user interface may be a user interface, called “input”, adapted to an acquisition of a command from a user of the device 200. This may in particular be an action to be carried out in connection with a rendered item, and / or a command to be transmitted to a computer application used by the device 200 (for example an invocation of an application 170, 172, 174, 176, 178 implementing the method of the present application).Depending on the embodiments, this may be an application 170, 172, 174, 176, 178 running at least partially on the device 200 or an “online” application 180 running at least partially remotely, for example on the server 140 of the system 100. Examples of user input interface of the device 200 include a sensor, an audio and / or video acquisition means (microphone, camera (webcam) for example), a keyboard, a mouse.

[0095] Said at least one microprocessor of the device 200 may in particular be adapted for at least partially automatic creation of a multimedia element, said creation comprising: obtaining a first sequence via a user interface of a first communication device, generating at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second text sequence obtained from the first sequence and at least one visual element, said visual element depending on said first sequence; sending said multimedia element via said first communication tool to said at least one first recipient.

[0096] Some of the above input / output modules are optional and therefore may be absent from the device 200 in certain embodiments.

[0097] The present application is sometimes detailed in connection with a device 200 (such as the device 110, 130 of the system 100) communicating with at least one second device (such as the devices 132, 134, 136 of the system 100). The method can for example be implemented locally by the device 200 for the generation of a multimedia element before sending this multimedia element to the second device.

[0098] On the contrary, in some of its embodiments, the generation of a multimedia element can be implemented in a distributed manner between at least two devices (such as the devices 110, 130, 140 and / or 150 of the system 100). An example of distributed implementation is discussed further below in connection with FIG. 5. By the term “module” or the term “component” or “element” of the device, is meant here a hardware element, in particular wired, or a software element, or a combination of at least one hardware element and at least one software element. The method according to the invention can therefore be implemented in various ways, in particular in wired form and / or in software form.

[0099] Figure 3 illustrates certain embodiments of the method 300 of the present application. The method 300 can for example be implemented by the electronic device 200 illustrated in Figure 2.

[0100] In the illustrated example, the method 300 can be implemented during the execution of a software application running at least partially on the device 200. This can be an application dedicated at least partially to the method or an existing application on which an extension (or "plug-in" in English) has been installed (as detailed later). The existing application can be diverse depending on the embodiments and in particular depending on the activities of a user of the device 200. For example, it can be an electronic messaging application, such as "email" or instant messaging for example, or a software collaborative platform allowing various exchanges between users (such as Slack, Teams, etc.), etc.

[0101] As illustrated in Figure 3, the method 300 may comprise obtaining 310 at least one textual or audio sequence to be processed. This sequence may for example be acquired via an input user interface of the device 200. For example, in the case of an application dedicated at least partially to the method of the present application, the application may be invokable via the operating system of the device 200. The invocation of the application may for example be proposed in a menu accessible to a user (by mouse click for example), the text selected during the click being considered as the sequence to be processed.

[0102] In other embodiments, it may also involve an application (dedicated at least partially to the method) that can be invoked via a user interface of another application (for example via a choice additional to the choices conventionally offered by the other application and added by “plug-in”), such as a “reformulate and share” choice inserted in a menu. Such an embodiment may allow a user to select a communication tool to be used for sending at least one multimedia element generated from a sequence to be processed (or an element to be included in the multimedia element, as detailed below). Alternatively, in certain embodiments, the method may be implemented automatically. For example, the use of the method may be proposed via a user interface of a third-party application and implemented in the absence of explicit refusal by the user (for example at the end of a timeout).

[0103] In some embodiments, the sequence may be obtained by reception on a communication interface of the device 200, for example when the sequence is entered via another device of the user, coupled to the device 200 (such as the devices 110, 130 of FIG. 1). Optionally, the method may comprise obtaining 320 (optional in some embodiments) at least one additional information, such as a designation of a recipient of the sequence via the communication tool used to generate the original sequence (email address, designation of an Instagram account, Twitter, etc.).

[0104] In the case where the sequence obtained is an audio sequence, the method 300 may comprise a transcription 330 of the audio sequence obtained into a text sequence via a speech recognition tool (or STT for Speech To Text according to the English terminology). This transcription 330 may of course be optional in certain embodiments. In the present application, the sequence to be processed will be referred to as “first sequence” or “original sequence”, when it is a text sequence, or the text sequence transcribed from an audio sequence to be processed.

[0105] As illustrated in Figure 3, the method 300 may comprise obtaining at least one second sequence. This obtaining may for example comprise an analysis 341 of the first sequence obtained 310, 330. The analysis may comprise a transposition 342 of the first sequence obtained 310, 330 into at least one second textual sequence. The number of sequences resulting from the transposition may vary depending on the first sequence obtained 310, 330, in particular depending on its length and complexity.

[0106] In certain embodiments, the method may comprise a search for at least one theme in the first sequence obtained 310, 330 and a division, according to the themes identified during this search, of the first sequence obtained 310, 330 into portions.

[0107] The themes sought may have been defined beforehand, by configuration for example, possibly after a learning phase on a set of annotated text sequences (i.e. already associated with the themes sought).

[0108] For example, "generic" themes can be defined by default during the initial configuration of the process. These can be, for example, general themes, likely to apply to different areas of business activity (telecoms, finance, etc.), or relating to a user's professional or personal context. The themes can then be adapted over time, during learning with text sequences labeled by specific themes.

[0109] In some embodiments, the method may comprise searching for questions in the first sequence obtained 310, 330 and dividing, based on the questions identified during this search, the first sequence obtained 310, 330 into portions, each comprising at least one of the identified questions or, alternatively, each portion comprising at most one question.

[0110] The method may also comprise a reformulation of the first sequence obtained 310, 330, or of at least a portion resulting from the cutting of the first sequence obtained 310, 330. The reformulation may vary according to the embodiments and according to the first sequence obtained 310, 330. According to a first example, a reformulation may correspond to a summary of the sequence or portion of sequence considered (therefore to a shorter text). According to a second example, a reformulation may correspond to a more explicit formulation of the sequence or portion of sequence considered (the abbreviations present in the sequence or portion of sequence being for example replaced by the words that they represent). It may also involve reformulation to obtain simpler sentences, or more correct sentences from the point of view of their spelling and / or their grammar.

[0111] When an obtained sequence 310 is transposed 312 into several second sequences, the method may comprise associating each of its second sequences with a level of importance and ranking (ordering) these second sequences according to their relative importance. For example, the second sequences may be ranked from most important to least important.

[0112] The level of importance associated with a sequence may take into account, in certain embodiments, a theme identified in the sequence. It may also take into account a possible layout of the sequence obtained 310 (for example, passages highlighted in the sequence by highlighting, underlining, use of the "bold" style, etc. to mark the importance given to these passages by the author of the sequence) or the identification in the sequence of keywords (such as "absolutely", "imperatively", "last deadline", etc., marking this importance). The level of importance associated with a sequence may also take into account the presence of named entities (dates, for example). A reformulation of a portion of a sequence may also take into account a context relating to this portion in the sequence but absent from this portion (such as a context given by a portion preceding this portion in the reading order of the sequence).For example, the "isn't it too early?" part of the sequence "There's a train leaving Rennes at 7:15. That would be fine for me, because I'm an early riser, but isn't it too early for you? If you like, I'll buy some croissants on the way to the station" can be reformulated as "Isn't the 7:15 train too early for you?"

[0113] Transposition can be implemented using language modeling algorithms, for example algorithms such as those implemented in LLM (Large Language Model) solutions, NER (Named Entity Recognition) or algorithms provided by automatic language processing software libraries such as the Spacy © software library. These various solutions can help extract key passages from a sequence to be processed.

[0114] The transposition can also use solutions known as “generative AI (for Artificial Intelligence)”, by providing as input a sequence or portion of a sequence to be reformulated as well as possible reformulation instructions (for example “Shorter reformulation of “XXXX”, or “Reformulation of “XXXX”, taking into account the “YYYY” context of “XXXX”).

[0115] For example, at least one portion considered important may be extracted from the sequence obtained from the user, a reformulation (for example a synthesis) then being applied to this portion. In the example of Figure 3, the transposition of the first sequence obtained 310, 330 results in a list of second sequences, shorter than the initial sequence, each of which may correspond to a “key message”, linked to a given theme, a particular task to be carried out, or a question asked. Simply put, the potentially complex original sequence obtained 310 has been transposed into n (“second”) sequences adapted to faster processing than the original sequence by their recipient (for example sequences each adapted to be processed independently of each other).

[0116] The transposition 342 can be carried out iteratively, a sequence resulting from a transposition being itself then able to be transposed into one or more sequences (with again a search for a theme in the sequence already resulting from the transposition). When no theme is identified in a candidate sequence resulting from a transposition of a portion of an original sequence, the method can comprise a search for a theme from theme(s) associated with the original sequence, or from other sequences obtained by transposition (possibly iterative) of the original sequence, for example sequences relating to portions of text of the original sequence located before a portion of text to which the candidate sequence is relative in the reading direction of the original sequence.

[0117] As illustrated in Figure 3, the method 300 may also comprise obtaining 350 at least one additional element (audio and / or visual), intended to enrich at least one of the “second” sequences resulting from the transposition.

[0118] This additional element may depend on the implementation methods and in particular on the communication tool which will be used to send the multimedia element to be generated from the “second” sequence considered, once it has been finalized.

[0119] Several additional elements may be associated with the same “second” sequence (and therefore with the multimedia element to be generated from this sequence) in certain embodiments.

[0120] The method may for example comprise obtaining 351 at least one additional element which corresponds to a visual element, such as an image or a video. Such a visual element may be intended to be used as a visual background for a multimedia element to be generated from a “second” sequence, or more generally to enhance this multimedia element.

[0121] In some embodiments, the visual element may be identical for all the multimedia elements generated via the method. It may for example be a default wallpaper for all the multimedia elements generated by the method of the present application. Such an embodiment may allow a simpler implementation of the method (for example on a device not having access to an image bank). It may also help to ensure the association with each multimedia element of a background specific to the method (for the purposes of identifying the multimedia elements resulting from the method, for a search for software errors (or "bugs" according to English terminology) for example). In some embodiments, the visual element may be identical for all the multimedia elements relating to "second" sequences obtained by transposition of the same original sequence.Such embodiments may help to create a "visual commonality", and thus a unity, between the multimedia elements comprising these "second" sequences, both for the user of the method (who provided the original sequence) and for the receivers of these multimedia elements, and therefore facilitate the traceability of the method of the present application between an original sequence and the corresponding multimedia elements. It may also facilitate the identification of the multimedia elements corresponding to an original sequence, among other multimedia elements, and help to group them, or to group their responses (if these use the same visual element).Such embodiments can also help to limit the cost, in terms of processing time and memory occupation of the method of the present application, since the processing to obtain the visual element can only be carried out once for all the sequences taken from an original sequence.

[0122] In some embodiments, on the contrary, the visual element may differ between sequences obtained by transposition of the same sequence. Such embodiments can help to differentiate between the different sequences obtained by transposition. In addition, they can make it possible to associate with a sequence considered a visual element more specific to the sequence considered (since it is specific to it) and therefore potentially more suited to this sequence.

[0123] Obtaining an additional element can, for example, be based on an artificial intelligence algorithm generating images corresponding to a provided label (or "prompt" according to the terminology used for this type of tool). Examples of such tools are, for example, DALL-E © or DALL-E2, developed by the company Open Al, or the Stable Diffusion © tool or a tool from the company MidJourney ©.

[0124] Such an image generation tool may, for example, have been trained to generate images from annotated images from image banks. In embodiments where an identical visual element is sought for all the sequences obtained by transposition of the same original sequence, the original sequence may be provided as a "prompt." In embodiments where a visual element specific to a "second" sequence resulting from a transposition is sought, the "second" sequence resulting from the transposition or a theme of this second sequence may be provided as a "prompt."

[0125] The visual element may, for example, be obtained by selecting an image from among those offered as output by such a tool. For example, the selected visual element may be the image considered by the image generation tool as most likely to respond to the prompt.

[0126] Optionally, the method may use an image generation tool that has been previously trained with respect to the user's context. For example, the tool may have been previously trained to generate images from images in one or more image libraries relating to the user, such as an image library specific to the user or to the company to which the user belongs or to the user's industry.

[0127] Alternatively, a visual element can be obtained by searching in at least one library of images and / or videos specific to the user's context (as set out above), taking into account the similarities between at least one theme identified in a sequence or and themes associated with the images in the library (in the form of meta-data for example).

[0128] Obtaining 350 at least one additional element may comprise obtaining 352 at least one interfacing element with at least one application, represented by an icon for example, the selection of which causes an innovation of the application (with possibly the provision of input parameters depending on the context of the interfacing element). Such an element is called in the remainder of the description “actuator” or “action button” or even “action gadget” or “action widget” according to English terminology.

[0129] For example, the obtaining 350 may comprise an association of an intent ("call", "message"), identified in a textual sequence, with one or more "actuator(s)". An actuator may further be associated with a third-party application (other than the client applications 170, 172, 174, 176 and 180 relating to the method of the present application), such as a "base" application installed in the factory on the device 200 or installed (by a user for example) after the device 200 leaves the factory.

[0130] Depending on the embodiments, the third-party application may or may not accept input parameters (e.g., a telephone number for the "telephone" application).

[0131] The relationship between an intention (e.g. "call") and one or more actuators, as between an actuator and one or more applications, can be configured in a local or remote configuration file accessible to the device 200 (for example a file stored on the server 140 of the system 100). The actuator to be inserted into the multimedia element may in certain embodiments be represented by an icon linked to the identified intention and / or linked to the application to which it gives access.

[0132] For example, it may be an actuator (illustrated by a telephone) initiating a voice or video call between the terminal from which the actuator is used (i.e. the terminal of the receiver of the multimedia element) and a terminal of a particular individual (such as the user of the process and provider of the original sequence from which the multimedia element originates), or even an individual (designated for example in the text sequence), whose addressing information (such as an email or telephone number) is accessible to the device (for example via a user's contacts file or via a process configuration file).For example: a "call" intention can be associated, via an actuator, with the "Teams" © application, the actuator to be inserted into the multimedia element can for example be represented by the Teams © icon, and a Teams © call link (URI in English) can be dynamically associated (when creating the actuator) as an input parameter to this actuator.

[0133] According to another example, it may be an actuator (illustrated for example by an envelope or the logo of an electronic messaging application) initiating a composition of an electronic message between the receiver of the multimedia element which comprises the actuator and a particular individual (such as the user of the method and provider of the original sequence from which the multimedia element originates, or even an individual (designated for example in the textual sequence of the multimedia element) whose addressing information is accessible to the device (for example via a contact file of the user or via a configuration file of the process).Obtaining an actuator to be included in the multimedia element to be generated may comprise an analysis of intent in the sequence considered, i.e. a detection of at least one keyword in the sequence, representative of a potential intention of the recipient of the multimedia element in discovering this multimedia element, and with which at least one particular actuator may be associated. These may in particular be keywords such as “call” (associated with a call-type actuator), “contact” (associated with a call-type actuator and an electronic message-type actuator), “send an email” (associated with an electronic message-type actuator), “confirm” (with an automatic sending of binary response (yes / no) type actuator, etc.). The analysis of intent may also comprise an analysis of the content of the sequence (for example words located near these keywords).The method may also include access to information relating to contacts of the user of the method (for example an electronic address book accessible to the device 200) to extract addressing information (to be used for the actuator) relating to contacts whose names are cited in the sequence (for example in proximity to intent(s) detected in the sequence).

[0134] A context may be associated with an actuator included in a multimedia element generated according to the method of the present application. In some embodiments, the context of an actuator may be included in the generated multimedia element (for example in the relevant actuator of this multimedia element or in a more general context of the multimedia element) and therefore transmitted in this multimedia element to the recipient device. In other embodiments, it may be stored separately from the multimedia element (and possibly transmitted separately to the multimedia element) and be accessible to the relevant actuator of the multimedia element from the recipient device).The context of an actuator may include elements relating to the original sequence of the multimedia element to which it belongs, a designation of a communication tool used to generate the original sequence, elements relating to the author of the original sequence (name, telephone number, email, etc.), as well as elements relating to an action to be triggered by the actuator (type of message (for example, response) to be generated (ok / not ok, calls, SMS, etc.), communication tool to be used, an identifier of a recipient of the response (name, telephone number, email, etc.). Some of these elements may have been determined by an intention analysis as explained above).

[0135] For example, if in a text sequence it is suggested to call a contact C, an actuator to be included in the multimedia element can be an actuator allowing to quickly call this contact C mentioned in the sequence. The call action is transposable to mail, instant message, etc. It should be noted that obtaining an actuator can take into account the tool via which the method was invoked. For example, obtaining an actuator can include an identification of a tool via which the original sequence was obtained, and a proposal for action related to the identified tool.For example, if the sequence was obtained via an electronic messaging tool, an actuator included in a media element from the original sequence that allows contacting the user (and provider of the original sequence from which the media element originated) will initiate an electronic message composition via that messaging tool (or an automatic response via that tool) rather than a voice call.

[0136] For example, if the original sequence was obtained via an electronic messaging tool, an actuator included in a multimedia element from the original sequence may comprise a solution for automatically generating a response based on the context associated with the actuator. Thus, two “like / dislike” actuators of different multimedia elements may trigger different detailed responses based on the contexts respectively associated with these two actuators in these multimedia elements.

[0137] In some embodiments, the method 300 may also comprise obtaining at least one other visual element, such as an emoticon, to be inserted into the multimedia element. Such a visual element may for example be selected after a semantic analysis of the “second sequence” considered and be inserted to replace a portion of the sequence (so as to make it shorter or to translate a feeling expressed in the “second sequence”, by reducing the negative impact for a recipient or in a more modest manner for the user.

[0138] Alternatively, such a visual element can be inserted in addition to the sequence in question (in order to lighten or, on the contrary, strengthen the emotional impact for a recipient of the sequence in question, for example).

[0139] As illustrated in Figure 3, the method 300 may comprise at least one generation 360 of a multimedia element from a “second sequence” originating from the original sequence. For example, in certain embodiments, a multimedia element may be generated for each textual sequence originating from an original sequence. According to another example, only certain textual sequences may give rise to the generation of a multimedia element. For example, textual sequences corresponding to semantically poor portions (for example polite formulas) of the original sequence may not give rise to any generation of a multimedia element. In certain embodiments, the generated multimedia element may have a format adapted to a communication tool (for example an application 170 dedicated at least partially to the method executing at least partially on the device 200) to be used for its sending.

[0140] In other embodiments, where the multimedia elements may have different formats depending on the sequences considered, the communication tool to be used for sending will instead depend on the format of the multimedia element.

[0141] In the example of figures 3 and 4, the multimedia element 400 is suitable for sending via a messaging tool, for example an application dedicated at least partially to the method running at least partially on the device 200, and is presented in such a way as to promote rapid consumption of the multimedia element by one of its recipients.

[0142] For example, the rendering of the multimedia element may be similar to that of ephemeral messages (or "stories") that can be published via widespread social networks. Such a rendering therefore offers advantages in terms of accessibility for its recipients, since it may present similarities with a rendering to which the intended recipient(s) of the multimedia element are likely accustomed.

[0143] In the example of figure 4, the multimedia element 400 can be generated from a text sequence 410 obtained 340 by transposition 342 of an original sequence (not illustrated in figure 4), from a visual element 420 obtained from the text sequence 410 and from an action button 430 making it possible to simply call the contact C cited in the text sequence.

[0144] It is noted that the relative positioning 361 of the components of a multimedia element may depend on the embodiments. In particular, in certain embodiments, it may take into account the characteristics (size, shape, pixel occupancy, color, etc.) of the components of the multimedia element. For example, the relative positioning of the components of the multimedia element may implement, in certain embodiments, at least certain concepts similar to those of French patent application FR2306803 by the same inventors.

[0145] As illustrated in Figure 3, the method may include in some embodiments, a confirmation 370 before sending the generated multimedia element. The confirmation 370 may include a rendering 371, on at least one user interface of the device 200, of at least one generated multimedia element (for example of each multimedia element generated for an original sequence).

[0146] Such rendering may allow a user of the method to verify the generated multimedia elements before sending them to at least one recipient.

[0147] In some embodiments, the method may include proposing at least one action relating to a media element rendered on the user interface. Examples of potentially proposed actions on a media element are validating the media element, deleting the media element, modifying the media element, and / or receiving a command for such an action. Other proposed actions may relate to validating (or modifying) a timeline for sending media elements of the same original sequence.

[0148] In some embodiments, the rendering of media elements generated in connection with an original sequence may take into account the importance level of the second sequences to which they relate. For example, the media elements may be rendered in descending order of importance (the media element having a level corresponding to the highest importance being rendered before any media element having a level corresponding to the lowest importance). In such embodiments, the user may have the possibility of validating the corresponding sendings of the media elements as they are rendered. Such embodiments may help to save time in the event of an emergency in processing certain portions of an original sequence.

[0149] Such embodiments can help a user to modify a content element at his convenience before its validation and / or to filter the multimedia elements which will be sent.

[0150] This rendering, and / or these proposals for action(s) and reception of command may be optional in certain embodiments.

[0151] Finally, after possible validation 372, the method 300 may comprise a sending 380 of the (validated) multimedia elements to at least one recipient. This sending 380 may use, in certain embodiments, an application dedicated at least partially to the method (a client of this application running for example on the device 200), and exchanging with application modules dedicated at least partially to the method, running remotely (in the example of FIG. 1 on the server 140 of the system 100 and more generally in the “cloud” for example), and communicating with other client application(s) running on the device(s) receiving the multimedia element.

[0152] It is noted that the communication tool used for sending at least one multimedia element (the client application dedicated at least partially to the method in the example of figure 1) can take into account a profile of the user and / or a profile accessible to the device 200 and relating to at least one recipient of the multimedia element.

[0153] It should be noted that optionally, recipients can interact directly with the multimedia elements received via the multimedia element widgets, or other elements (likes, comments) linked to the communication tool used (for example “likes” for sendings via Instagram ©).

[0154] In some embodiments, the method may include receiving, by the user of the method (and provider of the original sequence), a report relating to at least one interaction of the recipient with the multimedia element. This report may indicate a consumption of the multimedia element by the recipient. It may also report the use of at least one actuator of the multimedia element by a recipient of the multimedia element.

[0155] Such an embodiment may allow the sender of the original sequence to know whether the recipient has actually undertaken processing of the message.

[0156] In certain embodiments, the feedback relating to a recipient (response from this recipient or report of consumption of the multimedia element or use of an actuator of the multimedia element by this recipient) can be received 390 from the user (provider of the original sequence from which the multimedia element originates) from the client application dedicated at least partially to the method running on the device 200.

[0157] In some embodiments, the feedback relating to a recipient may be received 390 from the user from the tool via which the original sequence was sent as discussed above in connection with the actuators. For example, if the original sequence comes from the Microsoft Team © tool, or from Slack ©, or from Outlook © mail, and the method was invoked from this tool, or from a third-party tool having knowledge of the tool from which the original sequence comes, the response from a recipient may also reach the user via the tool (Microsoft Team ©, Slack ©, Outlook © mail respectively) from which the original sequence comes.For example: if a user decides to invoke the method of the present application via a messaging tool, by providing as input a draft of an electronic message (email for example), or the body of such an electronic message, the body of the email can be cut into shorter text sequence(s), the recipients of each sequence being chosen either from the recipients indicated in a dedicated field (“To”, “Copy”,.) of the draft, if they exist, or by analysis of the sequence in question (to try to deduce a recipient). Subsequently, when one of the recipients consumes the multimedia element sent containing the sequence in question and reacts to this consumption by using an actuator of this multimedia element, the use of the actuator by the recipient can cause, in addition to the action initiated by the actuator, the automatic transmission of an electronic message to the user via his messaging tool.

[0158] In such an embodiment, the report can be received by the client application implementing at least partially the method (or alternatively by the central application implementing at least partially the method) then transmitted to the tool (Teams ©, Outlook © etc.) used to generate the original sequence.

[0159] Depending on the embodiments, the recipient may or may not be informed of this automatic report.

[0160] Figure 5 illustrates a representative timing diagram of an example of distributed implementation of the method of the present application, in the system 100 of Figure 1. The steps of the method already commented on in connection with Figure 3 are cited below with the numerical reference of Figure 3. It is noted that in Figure 5 the optional steps of obtaining 320 at least one piece of additional information, of transcription 330, and of confirmation 370 of the method 300 have not been illustrated for simplicity.

[0161] In the example of Figure 5, the device 200 transmitting the original sequence is a first device 130 of the system 100 on which a client application 170 is running.

[0162] As illustrated, the client application 170 of the device 100 obtains 310 at least one textual or audio sequence to be processed (original sequence), as already explained in connection with FIG. 3. This original sequence is transmitted 510 to a central application 180 located on the server 140. This central application 180 notably comprises an extraction module 181. The extraction module 181 obtains 340 at least one second sequence from the original sequence obtained 310 and adds 350 at least one visual element (image, actuator, etc.) as a function of this second sequence and then transmits 520 this second sequence and this at least one visual element to a conversion module 182 which generates 360 the multimedia element and transmits it 380 to at least one client application 172 of at least one recipient device (the device 132 in our example).The client application 172 of the device 132 presents 530 the multimedia element on its user interface (for example, the multimedia element can be added to a list of multimedia elements received by the client application 172 and made available to the user of the device 132). Upon consumption of the multimedia element, the client application 172 of the device 132 notifies 540 a module 183 for managing consumption of multimedia elements of the central application 180. The device 200 receives 390 a report of the consumption of the multimedia element by the recipient 130 (via, for example, the communication tool (or channel) which was used to generate the original sequence obtained 310.

Claims

CLAIMS 1. Method for at least partially automatic creation of a multimedia element, said method comprising: obtaining (310) a first textual or audio sequence via a user interface of a first communication device, generating (360) at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second textual sequence obtained from the first sequence and at least one visual element; sending (380) said generated multimedia element via said first communication tool to said at least one first recipient.

2. Method according to claim 1 wherein at least one said visual element depends on said first sequence.

3. Method according to claim 1 or 2 wherein at least one said visual element is a visual background of said multimedia element.

4. Method according to any one of claims 1 to 3 wherein the method comprises an automatic selection of at least a first visual element of said multimedia element from among visual contents of a library of visual contents based on a semantic similarity between descriptors of said visual contents of the library and the second textual sequence.

5. Method according to any one of claims 1 to 4 wherein said first recipient is a function of said first sequence.

6. Method according to any one of claims 1 to 5 wherein the method comprises an association with said multimedia element of a generation context of said multimedia element.

7. The method of claim 6 wherein the method comprises storing said multimedia element and said associated generation context upon said sending.

8. Method according to any one of claims 1 to 7 wherein said multimedia element further comprises at least one actuator depending on said second text sequence.

9. The method of claim 8 wherein said actuator initiates communication with a second recipient designated in said second text sequence.

10. The method of claim 8 wherein said actuator initiates a communication to a communication device of a user of said first communication device.

11. Method according to claim 9 or 10 wherein said initiated communication is a communication via said first communication tool.

12. Method according to claim 9 or 10 wherein said initiated communication is a communication via a second communication tool used for obtaining said first sequence.

13. Method according to any one of claims 1 to 12 wherein said second sequence is positioned in juxtaposition with respect to at least one of said visual element of said multimedia element.

14. Method according to any one of claims 1 to 13 wherein said method comprises proposing a plurality of multimedia elements obtained from said first sequence.

15. Electronic device (200) comprising at least one microprocessor, said microprocessor being adapted for at least partially automatic creation of a multimedia element, said creation comprising: obtaining (310) a first textual or audio sequence via a user interface of a first communication device, generating (360) at least one multimedia element adapted to be sent via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second textual sequence obtained from the first sequence and at least one visual element; sending (380) said generated multimedia element via said first communication tool to said at least one first recipient.

16. Server (140) of a communication network comprising at least one microprocessor adapted to: - a reception, via a first communication tool, of at least one multimedia element comprising at least one textual sequence and at least one visual element; and of at least one creation context associated with said at least one multimedia element, said creation context comprising at least: • a designation of a device transmitting said multimedia element, • a designation of at least one device receiving said multimedia element, • at least one so-called original textual or audio sequence which reformulates at least in part said textual sequence and • a designation of at least one second communication tool used to obtain said original sequence; a transmission (380) to said at least one recipient device of said multimedia element; upon receipt (540) of feedback relating to a consumption of content by said recipient, transmission of said feedback to a device of a user of said transmitting device using said second communication tool.

17. Computer program comprising instructions for implementing, when said program is executed by a processor of an electronic device, a method for at least partially automatic creation of a multimedia element, said method comprising: obtaining a first text or audio sequence via a user interface of a first communication device, generation of at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second text sequence obtained from the first sequence and at least one visual element, sending said multimedia element via said first communication tool to said at least one first recipient.

18. Computer program comprising instructions for implementing, when said program is executed by a processor of a server of a communications network, a method comprising: - a reception, via a first communication tool, of at least one multimedia element comprising at least one textual sequence and at least one visual element; and of at least one creation context associated with said at least one multimedia element, said creation context comprising at least: • a designation of a device transmitting said multimedia element, • a designation of at least one device receiving said multimedia element, • at least one so-called original textual or audio sequence which reformulates at least in part said textual sequence and • a designation of at least one second communication tool used to obtain said original sequence; a transmission (380) to said at least one recipient device of said multimedia element; upon receipt (540) of feedback relating to a consumption of content by said recipient, transmission of said feedback to a device of a user of said transmitting device using said second communication tool.

19. Recording medium readable by a processor of an electronic device and on which is recorded a computer program comprising instructions for implementing, when said program is executed by said processor, a method for at least partially automatic creation of a multimedia element, said method comprising: obtaining a first textual or audio sequence via a user interface of a first communication device, generating at least one multimedia element suitable for sending via at least one first communication tool to at least one first recipient, said multimedia element being generated automatically and comprising a second textual sequence obtained from the first sequence and at least one visual element; sending said multimedia element via said first communication tool to said at least one first recipient.

20. Recording medium readable by a processor of a server of a communications network and on which is recorded a computer program comprising instructions for the implementation, when said program is executed by said processor, of a method comprising: - a reception, via a first communication tool, of at least one multimedia element comprising at least one textual sequence and at least one visual element; and of at least one creation context associated with said at least one multimedia element, said creation context comprising at least: • a designation of a device transmitting said multimedia element, • a designation of at least one device receiving said multimedia element, • at least one so-called original textual or audio sequence which reformulates at least in part said textual sequence and • a designation of at least one second communication tool used to obtain said original sequence; a transmission to said at least one recipient device of said multimedia element; upon receipt of feedback relating to consumption of content by said recipient, transmission of said feedback to a device of a user of said transmitting device using said second communication tool.

Images