Enhanced reader and method for enhancing reading text

Abstract

The invention relates to an enhanced reader and a method for enhanced reading of text. One subject matter of the present invention is an enhanced text reader comprising at least one controller capable of controlling an action associated with a portion of text, the action depending on a received neural signal. Thus, the user will not have to manipulate real or virtual content including text to trigger control of the action. This will help a user, including a disabled user, to read real or virtual content without barrier, but also depend on the environment in which the user reads content, especially in a working environment in which the user is manipulating tools or the like.

Description

Technical Field

[0001] The present invention relates to an enhanced reader and a method for enhanced reading of text. Background Art

[0002] When reading a paper book, highlighting text, taking notes, searching for the meaning of a word in a dictionary or marking a page requires the use of external equipment (pencil, paper, dictionary, bookmark), which necessitates stopping reading. In fact, manipulating an object other than the book necessitates being able to hold the book with only one hand, or even having to put it down.

[0003] Furthermore, highlighting and folding pages as bookmarks can damage the book, which is also not necessarily desirable.

[0004] Technologies such as e-books may facilitate certain actions, but have limitations and drawbacks. E-books require manipulation to access functionality (which may not be accessible to certain types of disabilities or in certain usage contexts).

[0005] Then, it is conceivable to use voice recognition. However, voice may not be used in environments that require discretion or in noisy environments.

[0006] Additionally, these techniques only work with e-books, not paper content or other reading media. Summary of the invention

[0007] One of the objects of the present invention is to provide an improvement over the prior art.

[0008] A subject of the invention is an enhanced text reader comprising at least one controller capable of controlling an action associated with a portion of a text, the action being dependent on a received neural signal.

[0009] Therefore, users will not have to manipulate real or virtual content, including text, to trigger controls for actions. This will help users (including users with disabilities) read real or virtual content without barriers, but it also depends on the context in which the user reads the content, especially in a work environment where the user is manipulating tools, etc.

[0010] Advantageously, part of the text is dependent on gaze tracking data from the user.

[0011] Thus, actions can be performed on the entire text or only on parts of it.

[0012] Advantageously, the portion of text is a text region captured from the gaze tracking data.

[0013] Thus, actions can be performed on text printed on real media.

[0014] Advantageously, the enhanced text reader comprises a gaze tracking device that provides gaze tracking data from a user.

[0015] Advantageously, the enhanced text reader comprises a text sensor capable of capturing a text region based on gaze tracking data, the captured text region constituting a portion of the text.

[0016] Advantageously, the augmented text reader comprises an analyser capable of determining a gesture of the user relative to a portion of the text from the received neural signals.

[0017] Thus, the controlled action corresponds to a real action that would be performed by the user's gesture if the gesture were real and the medium of the text were real.

[0018] Advantageously, the gesture is a real or simulated gesture.

[0019] Thus, even in situations where it is not possible to actually perform a gesture, the user can trigger a controller-controlled action by mentally simulating that gesture.

[0020] Advantageously, the controller controls one or more of the following:

[0021] - a text editor,

[0022] - Translator,

[0023] - dictionary,

[0024] - Mechanical manipulators of real text content,

[0025] - speech synthesizer,

[0026] - Augmented reality system.

[0027] Therefore, the controller controls respectively:

[0028] - functions for editing text, such as highlighting a part of the text, adding notes related to that part of the text, bookmarks, etc.,

[0029] - Translate a part of the text into a predefined language or a language selected by another neural signal,

[0030] - provide definitions of words corresponding to a part of the text, or even provide encyclopedia articles corresponding to the field covered by that part of the text,

[0031] - the movement of mechanical manipulators, in particular robotic arms (to turn pages, close content, open content on a bookmark, introduce a bookmark, fold pages, highlight text, etc.),

[0032] - text-to-audio reproduction of a portion of the text,

[0033] - Reproduce in augmented reality elements generated by other controlled devices (highlights, translations, definitions, bookmarks, etc.).

[0034] Advantageously, the enhanced text reader comprises one or more of these controlled devices.

[0035] Advantageously, the reader comprises a register capable of storing information generated by performing actions related to the text.

[0036] Thus, the user can subsequently revisit the text both in the published version of the text and in its user-enriched version.

[0037] Another subject of the invention is a method for enhanced reading of a text, comprising at least one control of an action associated with a portion of the text, the action being dependent on a received neural signal.

[0038] Advantageously, a method for enhanced reading of text comprises detecting a portion of the text by tracking a user's gaze.

[0039] Advantageously, the method for enhanced reading of text comprises storing information generated by an action on a portion of the text.

[0040] Advantageously, according to one embodiment of the invention, the various steps of the method according to the invention are implemented by software or a computer program, the software comprising software instructions intended to be executed by a data processor of the enhanced text reader and designed to control the execution of the various steps of the method.

[0041] Therefore, the invention also relates to a program comprising program code instructions for executing the steps of the method for enhancing the reading of text when said program is executed by a processor.

[0042] The program may use any programming language, and take the form of source code, object code, or a code between source code and object code, such as in partially compiled form, or in any other desired form. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The characteristics and advantages of the present invention will become more clearly apparent from a reading of the description given by way of example and the associated drawings, in which:

[0044] Figure 1 depicts a simplified diagram of an enhanced text reader according to the present invention,

[0045] Figure 2depicts a simplified diagram of an architecture including an enhanced text reader according to the present invention,

[0046] Figure 3 A simplified diagram of a method for enhancing reading of text according to the present invention is depicted. DETAILED DESCRIPTION

[0047] Figure 1 A simplified diagram of an enhanced text reader according to the present invention is depicted.

[0048] The augmented text reader 1 comprises at least one controller 10 capable of controlling cmd and an action ac associated with a portion of text ptx: cmd(a, ptxt), the action ac depending on the received neural signal sn. For example, the controller 10 controls the action ac by controlling the signal cmd: cmd(ac, ptxt).

[0049] Specifically, the text content 2 is read. When the region 21 of the text content 2 is read, if the augmented text reader 1 receives the neural signal sn, the augmented text reader 1 controls an action ac associated with a portion ptxt of the text included in the region 21 .

[0050] Text content refers to any physical or virtual media that includes text, such as paper books or electronic books, paper magazines or electronic magazines, or paper or digital posters, physical packaging of products, labels attached to objects or products, etc.

[0051] Then, the user does not manipulate the real or virtual content including text to trigger the control of the action. This helps users (including users with disabilities) to read the real or virtual content without obstacles, but it also depends on the context in which the user reads the content, especially in a work environment where the user is manipulating tools, etc.

[0052] Figure 2 A simplified diagram of an architecture including an enhanced text reader according to the present invention is shown.

[0053] The enhanced text reader 1 includes a controller 10. The controller 10 controls the cmd action ac on a portion of the text ptxt. It is worth noting that the portion of the text ptxt corresponds to the text content 2 (optionally, the real text content 2 R or dummy text content 2 V ) area 21, 21 R ,twenty one V The text in .

[0054] In particular, the control signal cmd controls the interactive device (especially for interacting with the real text content 2 R or dummy text content 2 VDevices for virtual interaction 3, 13, or for interacting with real text content 2 R Or a device for real interaction 7 with the reproduction of virtual text content 2V) actions ac on the text content 2.

[0055] Real interaction means physical interaction in a real environment. It is worth noting that physical interaction is performed on real text content such as paper books, or on reproduced virtual text content such as e-books displayed on tablets, smart phones, readers, etc.

[0056] And, virtual interaction means interaction in a virtual environment or in a virtual part of an augmented reality environment, respectively. For example, virtual interaction is performed on virtual text content in a virtual environment (such as an e-book reproduced in virtual reality or more simply on an e-reader), or does not act directly on real text content, but is performed in a virtual part of an augmented reality environment superimposed on real text content such as a paper book.

[0057] For example, the controlled action ac corresponds to the real interactive device 7 R real gestures, especially real gestures of automated real devices, such as robots or simpler mechanical arms or for manipulating real text content2 R or dummy text content 2 V Mechanical devices for use with printed books, especially electrical, electronic and / or automated page turners (especially for paper books and / or readers).

[0058] Alternatively, the controlled actions ac correspond to the virtual text content 2 in the virtual environment of the virtual interactive device 3, 13. V Or real text content 2 R Related virtual gestures, such as the functions of a virtual content editor, virtual gestures of an avatar in a virtual environment that reproduces virtual text content and / or virtual information (such as text highlighting, bookmarking, translation, definition of a portion of text, etc.) generated by virtual gestures superimposed on real text content. It is worth noting that the generated virtual information constitutes a virtual content superimposed on the real text content 2 R Virtual content on 32 V .

[0059] In particular, a portion of the text ptxt depends on the gaze tracking data d from the user sr Then, an action ac is performed on all or only part of a portion of the text ptxt. The gaze tracking device (also called gaze detector) 5, 35, 135 detects the movement of the user U, ie the movement of the gaze mr.

[0060] It is worth noting that the augmented text reader 1 receives gaze tracking data from an external gaze detector 5, 35 (e.g., from a gaze detector 35 integrated in the augmented reality head mounted device or glasses 3). sr Alternatively, the enhanced text reader 1 includes providing gaze tracking data from the user. sr A gaze detector 135 (also referred to as a gaze tracking device) is provided.

[0061] In particular, a portion of the text ptxt is obtained based on the gaze tracking data d sr The captured text region zc. Then, the action ac is performed in particular on the text printed on the real medium (also referred to as the real text content).

[0062] In particular, a text sensor 6, 36, 136 such as a camera may be configured to detect the presence of a text sensor 6, 36, 136 based on the gaze tracking data d sr An area of ​​the text 21 is captured and a captured text area zc is provided. Optionally, the gaze tracking device 5, 35, 135 and the text sensor 6, 36, 136 use the same visual sensor or sensors, in particular the same camera.

[0063] It is worth noting that the augmented text reader 1 receives the capture area zc from an external text sensor 6, 36 (e.g., from a text sensor 36 integrated in the augmented reality headset or glasses 3). Alternatively, the augmented text reader 1 includes a text sensor 136, in particular a text sensor capable of capturing the capture area zc based on the gaze tracking data d sr The camera captures the text region zc. The captured text region zc constitutes a part of the text ptxt.

[0064] In particular, the augmented text reader 1 comprises an analyzer 14, 141 capable of determining a gesture gd of a user relative to a portion of a text ptxt from the received neural signals sn.

[0065] The controlled action ac therefore corresponds to a real action that would be performed by the user's gesture gd if the gesture were real and the medium of the text were real.

[0066] In particular, the gesture gd is a real or simulated gesture. It is worth noting that the user, for example, uses their hands to really make a gesture at a distance from the real content or the distant content, and the neural interface 4 can detect a specific neural signal sn at the moment of making the gesture. The neural signal sn is transmitted to the analyzer 14, 141, which determines the real gesture made by the user and controls the action ac to perform the result of the real gesture on the text content. Therefore, everything that happens is as if the user makes the gesture directly on the text content. If the user cannot manipulate directly or at a distance because of disability or because their hands are occupied, the user psychologically simulates the gesture they expect to make: then, the gesture is called simulated. This psychological simulation of the gesture triggers a neural signal in the user's brain, which is equivalent to the neural signal triggered by the real gesture. The neural signal sn detected during the simulated gesture is transmitted to the analyzer 14, 141, which determines the real gesture that the user visualizes psychologically and controls the action ac to perform the result of the real gesture on the text content. Therefore, everything that happens is as if the user really makes the gesture directly on the text content. Thus, even in situations where it is not possible to actually perform a gesture, the user can trigger a controller-controlled action by mentally simulating that gesture.

[0067] In particular, the controller 10 controls one or more of the following controlled devices (not shown):

[0068] - Text editor 80, 180, 380,

[0069] - Translator 81, 181, 381, 781,

[0070] - Dictionary 82, 182, 382, ​​782,

[0071] - Real text content7 R Mechanical manipulators,

[0072] - Speech synthesizer 32,

[0073] - Augmented reality system3.

[0074] Therefore, the controller 10 controls respectively:

[0075] - functions for editing text, such as highlighting a part of the text, adding notes related to that part of the text, bookmarks, etc.,

[0076] - Translate a part of the text into a predefined language or a language selected by another neural signal,

[0077] - provide definitions of words corresponding to a part of the text, or even provide encyclopedia articles corresponding to the field covered by that part of the text,

[0078] - the movement of mechanical manipulators, in particular robotic arms (to turn pages, close content, open content on a bookmark, introduce a bookmark, fold pages, highlight text, etc.),

[0079] - text-to-audio reproduction of a portion of the text,

[0080] - Reproduce in augmented reality elements generated by other controlled devices (highlights, translations, definitions, bookmarks, etc.).

[0081] In particular, the enhanced text reader 1 comprises one or more interactive devices 3, 7 or even controlled devices, such as a controlled text management device 8, 18, 38, 78, in particular a text editor 80, 180, 380; a translator 81, 1801, 381, 781; and / or a dictionary 82, 1802, 382, ​​782; etc. Such text management devices constitute specific devices 8, 18, 180, 38, 78, 80, 1800, 380, 81, 1801, 381, 781, 82, 1802, 382, ​​782 or devices implemented in the system 8, 18, 180, 38, 78. The specific text management device or the text management system comprising such a text management device is associated with the device 1, 3, 78 for enhanced reading. R Different text management devices 8, 80, 81, 82 or text management devices 18, 180, 1800, 1801, 1802 implemented in the enhanced text reader 1 or text management devices 38, 380, 381, 382, ​​78, 870, 871, 872 implemented in the virtual interactive device 3 or the real interactive device 7.

[0082] In particular, the reader 1 comprises a register 181 capable of storing information i generated by performing actions ac related to the text. la . Thus, the user can subsequently revisit the text both in the published version of the text and in its user-enriched version.

[0083] In particular, the reader 1 includes a storage device 182 such as a memory or a database (also referred to as enhanced reading information i la A database of a storage device in which the reader stores information i generated by performing actions ac related to the text la Thus, when the text content 2 is read again by the virtual interactive device 3, the annotations (highlighting, annotations, bookmarks, etc.) performed by the user via the augmented reader 1 can then be reproduced.

[0084] In the case of a real interaction device 7 comprising a robotic arm, the real interaction device 7 comprises in particular a manipulation device 72, an axis 73 relative to which the manipulation device 72 can be moved (e.g. by vertical movement mv and / or horizontal movement mh), and / or a rod 71 placed between the axis 71 and the manipulation device. The manipulation device 72 is capable of interacting with the virtual text content 2 V Interaction, in particular with a device for rendering virtual text content, such as an electronic reader 32 R Interaction, or with real text content2 R Interaction, especially through manipulation of real textual content2 R The page and / or the actual text content 2 R The manipulation device 72 is in particular a controllable gripper. Optionally, the real interaction device 7 further comprises a text management device 78 and / or a projector 783, which is optionally implemented in the text management device 78 or connected to a text management device 8, 18 outside the real interaction device.

[0085] Consider that user U is reading text on text content 2. User U wants to highlight text in text area 21 of text content 2. They make a gesture to highlight text area 21 at a distance from text 2, or they mentally simulate highlighting text area 21. Neural interface 4 detects neural signal sn and transmits it to enhanced text reader 1. Enhanced text reader 1 receives the transmitted neural signal sn. It is worth noting that enhanced text reader 1 includes a receiver 11 for neural signal n , the receiver receives the transmitted neural signal sn.

[0086] The enhanced reader 1 comprises a controller 10. The controller 10 controls cmd an action ac associated with a portion of a text ptxt according to the received neural signal sn.

[0087] In particular, the enhanced text reader 1 determines the user's gesture gd based on the received neural signal sn. When the received neural signal sn is detected, the determined gesture gd corresponds to a gesture actually made by the user or a gesture psychologically simulated by the user. Then, the controller 10 controls the action ac cmd related to a part of the text ptxt according to the determined gesture gd. It is worth noting that the enhanced text reader 1 includes an analyzer 14, 141, which is capable of determining a gesture based on the neural signal.

[0088] Optionally, the enhanced text reader 1 or even the controller 10 generates an action ag to be controlled according to the received neural signal sn or even the determined gesture gd. In particular, the enhanced text reader 1 includes an action generator 14, 142, which is capable of generating an action ag to be controlled according to the received neural signal sn or even the determined gesture gd. For example, the enhanced text reader 1 includes an action generator 14, which includes an analyzer 141 and an actual action generator 142, and the analyzer 141 provides the actual action generator 142 with the gesture gd determined according to the neural signal sn.

[0089] The enhanced text reader 1 sends a control signal cmd to the real interactive device 7 or the virtual interactive device 3 directly or via the text management device 8 (not shown), 18. In particular, the enhanced reader 1 includes a control transmitter 11 i , the control transmitter can transmit a control signal cmd to the external devices 3 , 7 , 8 .

[0090] In particular, a portion of the text ptxt depends on gaze tracking data dsr. It is noted that the enhanced text reader 1 retrieves the gaze tracking data dsr; the enhanced text reader receives the gaze tracking data from an external gaze tracking device 5, 35 or the enhanced text reader obtains the gaze tracking data via an internal gaze tracking device 135.

[0091] In particular, the portion of the text ptxt corresponds to a text region zc captured according to the gaze tracking data dsr. It is worth noting that the enhanced text reader 1 retrieves the text region zc according to the gaze tracking data dsr; the enhanced text reader receives the gaze tracking data from an external text sensor 6, 36, or the enhanced text reader obtains the gaze tracking data via an internal text sensor 136. The sensor 6, 36, 136 is in particular a camera.

[0092] For example, the enhanced text reader 1 includes a receiver 11 for capturing data from a gaze tracking device 5, 35 and / or from a text sensor 6, 36. c Alternatively, the enhanced text reader 1 comprises a gaze tracking device 135 and / or a text sensor 136. Alternatively, the enhanced text reader 1 comprises a virtual interaction device 13 comprising a gaze tracking device 135 and / or a text sensor 136.

[0093] In particular, the enhanced text reader 1 determines a portion of the text ptxt based on the gaze tracking data dsr or even based on a text region zc captured based on the gaze tracking data dsr. It is worth noting that the enhanced text reader 1 includes a text detector 12, which is capable of determining the portion of the text ptxt. Optionally, the text detector 12 includes a character recognition device 120, which is capable of extracting the portion of the text ptxt from the captured image of the text region zc. Optionally, in an embodiment not shown, the text detector includes a gaze tracking device 135 and / or a text sensor 136.

[0094] In an embodiment not shown, the augmented or virtual reality device 3 includes a virtual interaction device 13, 33, a neural interface 34 and / or an augmented text reader 31. The virtual interaction device 13, 33 is a virtual interaction device 33 different from the augmented text reader 1 or a virtual interaction device 13 implemented in the augmented text reader 1, 31.

[0095] Figure 3 A simplified diagram of a method for enhancing reading of text according to the present invention is shown.

[0096] The method PLA for enhancing the reading of a text comprises at least one control signal cmd for an action ac associated with a portion of the text ptxt. The action ac depends on the received neural signal sn. In particular, the control CMD controls the action ac to be performed on the portion of the text ptxt by means of the control signal cmd: cmd(ac, ptxt). It is worth noting that the neural signal sn is received from a neural interface BI. The neural interface BI can, for example, capture neural signals in the brain of the user U.

[0097] In particular, the control CMD controls the interactive device TID and / or the text management Txt_MNGT. It is worth noting that the interactive device TID is controlled by the control CMD according to the enhanced reading information provided by the text management Txt_MNGT. la To control: cmd(i la ). In particular, the text management Txt_MNGT is implemented by the interactive device TID or consists of the enhanced reading method PLA.

[0098] In particular, the method PLA for enhancing the reading of a text comprises analyzing a neural signal NLZ to detect a real or simulated gesture of a user U from a neural signal sn received from a neural interface BI.

[0099] In particular, the enhanced reading method PLA comprises an action determination AG_DT, in particular depending on the detected gesture gd, for example by analyzing the neural signal NLZ. For example, this is an action that is previously associated with the detected gesture. In particular, the action determination AG_DT consults an action database BDAG (not shown) in which gesture-action pairs are stored after the gestures are associated with the actions. It is worth noting that, optionally before or when using the enhanced reading text PLA, the gesture-action pairs are predefined or established by learning (for example, if and when the user U and / or another user is able to make gestures directly on the text content), etc.

[0100] In particular, the method PLA for enhancing the reading of a text comprises a neural link LN (also called a neural signal interface step), which can exchange with the control CMD signals related to the neural signals sn received from the neural interface BI. It is worth noting that the neural link LN provides the control CMD with intermediate signals such as a detected gesture gd or an associated action ag, based on which the control CMD controls the action ac to be performed on a portion of the text ptxt. The neural link LN comprises, for example, an analysis NLZ and / or an action determination AG_DT.

[0101] In particular, the method PLA for enhancing the reading of a text comprises detecting a portion Txt_DTC of the text by tracking a gaze dsr of the user. It is worth noting that the gaze tracking data dsr are obtained by detecting a portion Txt_DTC of the text: for example, received from a gaze tracking device SSR or determined by a gaze tracking E_SV based on captured eye data dc related to the eyes of the user U. The gaze tracking E_SV optionally consists of the detection of a portion Txt_DTC of the text, or is implemented by the gaze tracking device SSR. In the case where the detection of a portion Txt_DTC of the text comprises the gaze tracking E_SV, they receive captured eye data dc from the eye sensor CR.

[0102] In particular, the gaze tracking data dsr obtained is used to capture a text area of ​​the CAPT text content T_DOC, in particular a text area zl that the user U is currently gazing at and / or reading. The captured text area CAPT provides a captured text area zc. In the case where the capture CAPT targets the text area zl that the user U is currently gazing at and / or reading, the captured text area zc corresponds to the text area zl that was being gazed at and / or read at the moment when the capture was controlled, for example by the gaze tracking data dsr obtained at that moment. It is worth noting that the detection of a portion xt_DTC of the text T includes the captured text area CAPT. Therefore, a portion of the text ptxt optionally corresponds to the captured text area zc.

[0103] In particular, the detection of a portion of text Txt_DTC includes text recognition Txt_RCG, in particular the recognition of written characters in the implementation image, such as alphabetic characters, symbols, etc. It is worth noting that the text recognition Txt_RCG receives, for example from the capture CAPT, a text region zc captured according to the gaze tracking data dsr, and recognizes a portion of text ptxt written in the captured text region zc.

[0104] In particular, the method PLA for enhancing the reading of a text comprises storing STCK information i generated by an action ac on a portion of the text ptxt la .

[0105] In particular, STCK is stored in a storage device such as a memory or a database BDLA (also known as enhanced reading information i la In the storage device, the enhanced reading method PLA stores information i generated by STCK by performing actions ac related to the text la。 Therefore, when the text content 2 is read again by the virtual interactive device 3, the annotations (highlighting, annotations, bookmarks, etc.) performed by the user through the enhanced reader 1 can be reproduced later.

[0106] In particular, the method PLA for enhancing the reading of a text comprises the implementation of IRA_GEN and actions ac associated with the text ptxt for generating enhanced reading information ila, in particular a generator of enhanced reading information controlled by a control signal cmd(ac, ptxt).

[0107] In particular, the method PLA for enhanced reading of a text comprises a text management Txt_MNGT (also called text editing) of performing an action on the text (optionally, an action ac controlled by a neural signal sn). Performing the controlled action ac on a portion of the text ptxt generates enhanced reading information i la Optionally, the text management Txt_MNGT includes generating enhanced reading information IRA_GEN and / or storing STCK.

[0108] The enhanced reading information generated thereby la Optionally used, in particular by the enhanced reading method PLA, to control cmd(i la ) virtual or real text interaction device TID. For example, the control signal cmd(i la ) The enhanced reading information i is controlled by the virtual text interaction device TID la The reproduction is in particular a visual and / or audio reproduction. In the case of a real text interaction device TID, the control signal cmd(i) comprising the enhanced reading information is transmitted by the real text interaction device TID itself or by the enhanced reading method PLA.la ) will be converted MVT_CNV into one or more control signals for one or more motorized elements constituting the real text interaction device TID. In particular, the control signals for the motorized elements control the movement of the motorized elements: direction, distance and / or angle, etc. Thus, the motorized elements constituting the mechanical arm of the real text interaction device TID can be controlled to turn pages in the reading direction or in the reverse reading direction, to pick up a highlighter and highlight a part of the text horizontally or vertically in the reading direction with the highlighter, or to fold the corner of the page, or to add a bookmark, etc.

[0109] Therefore, the invention also relates to a program comprising program code instructions for executing the steps of the method for enhancing the reading of text when said program is executed by a processor.

[0110] The present invention also relates to a medium. The information medium may be any entity or device capable of storing a program. For example, the medium may include a storage device, such as a ROM (e.g., a CD-ROM or a microelectronic circuit ROM), or a magnetic storage device (e.g., a floppy disk or a hard disk).

[0111] On the other hand, the information medium may be a transmissible medium, such as an electrical or optical signal, which may be routed via electrical or optical cables, by radio or by other means.The program according to the invention may in particular be downloaded from a network, in particular from the Internet.

[0112] Alternatively, the information medium may be an integrated circuit incorporating the program, the circuit being adapted to carry out or for carrying out the method in question.

[0113] In another embodiment, the present invention is implemented by software and / or hardware components. With this in mind, the term module may correspond to both software components and hardware components. A software component corresponds to one or more computer programs, one or more subroutines of a program, or more generally, to any element of a program or software that can implement a function or set of functions as described above. A hardware component corresponds to any element of a hardware component that can implement a function or set of functions.

[0114] Therefore, the enhanced reading text according to the present invention (whether implemented in the form of an enhanced text reader 1 or in the form of a method PLA for enhanced reading text) proposes combining a neural interface 4, BI (especially in the form of a head-mounted device BCI (direct neural interface, which can control objects connected by thought, i.e. EEG signals)) with at least gaze tracking 5, 35, 135, E_SV, SSR (also called eye tracking) or even a sensor 6, 36, 136 or capture CAPT (especially in the form of glasses equipped with a camera 36 and an eye tracking (gaze tracking) system 35).

[0115] The camera 36 of the glasses detects the text on the page. This applies to paper books as well as to electronic books. The glasses 3 are equipped with a gaze tracking system 35 which makes it possible to know which part of the text (ie which words) is being read.

[0116] In order to activate a function (from among those possible) by thought, the user U has to think about moving a limb or a muscle. Imagining moving a body part has the same effect in the motor cortex (an area of ​​the brain) as actually moving it. Thus, this movement or gesture (even if simulated) of the sn user can be detected via the EEG headset 4, BI, whose sensors are located in this brain area.

[0117] It is worth noting that by associating various movements or gestures gd or various neural signals sn corresponding to these movements with various actions ag, the user U mentally simulates (imagines) that raising their left arm will trigger the action ac of translating the last area of ​​the text being read. In the same way, the user U's simulated gestures of highlighting, marking pages, etc. (e.g., gestures of placing bookmarks, folding pages) will trigger the text interaction device 3, 7, TDI to highlight, mark pages, etc.

[0118] For the bookmarking function, another gesture of the user U may be associated with the marking of the page by the text interaction device 3,è,TDI, as the fact that the user (reader) U is concentrating on the page number. The camera 6,36,136 (for gaze tracking) will recognize the isolated number, and the information i la The data will be stored 181 , STCK, in an augmented reading device 1 or a virtual or augmented reality device 3 implementing the augmented reading method PLA with a memory 182 , BDLA.

[0119] The translation of a word or a series of texts can appear in augmented reality on the lenses of the glasses, or actually be played via an audio headset.

[0120] In addition to mass-market readers with the features mentioned above, in situations where it is not easy to free your hands (using gloves, on top of a tower, etc.), technicians can use the highlighting feature to store (and easily present) key words or passwords read on the hardware or operator manual. In the same environment, it may be very useful to easily translate certain instructions.

Claims

1. An enhanced text reader comprising at least one controller capable of controlling an action associated with a portion of text, the action being dependent on a received neural signal.

2. An enhanced text reader according to the preceding claim, wherein Part of this text depends on gaze tracking data from the user.

3. An enhanced text reader according to the preceding claim, wherein: The portion of the text is a text region captured according to the gaze tracking data.

4. The enhanced text reader according to any one of claims 2 and 3, wherein: The enhanced text reader includes a gaze tracking device that provides gaze tracking data from a user.

5. The enhanced text reader according to any one of claims 2 to 4, wherein: The enhanced text reader includes a text sensor capable of capturing a text region based on gaze tracking data, the captured text region constituting a portion of the text.

6. An enhanced text reader according to any one of the preceding claims, wherein: The augmented text reader includes an analyzer capable of determining a gesture of a user relative to a portion of the text based on the received neural signals.

7. An enhanced text reader according to the preceding claim, wherein: The gesture is a real or simulated gesture.

8. An enhanced text reader according to any one of the preceding claims, wherein: The controller controls one or more of the following devices: - a text editor, - Translator, - dictionary, - Mechanical manipulators of real text content, - speech synthesizer, - Augmented reality system.

9. An enhanced text reader according to the preceding claim, wherein: The enhanced text reader includes one or more of these controlled devices.

10. An enhanced text reader according to any one of the preceding claims, wherein: The reader includes a register capable of storing information generated by performing actions related to the text.

11. A method for enhanced reading of text, comprising at least one control of an action associated with a portion of the text, the action being dependent on a received neural signal.

12. Method for enhancing the reading of text according to the preceding claim, wherein: The reading method includes detecting a portion of the text by tracking a user's gaze.

13. A method for enhancing reading text according to any one of claims 11 and 12, wherein: The reading method includes storing information generated by the action on the portion of the text.

14. A program comprising program code instructions for executing the steps of the method for enhancing reading of text according to any one of claims 11 to 13 when the program is executed by a processor.

Images