Classifications

• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L12/00—Data switching networks
  • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
  • H04L12/2803—Home automation networks
  • H04L12/2823—Reporting information sensed by appliance or service execution status of appliance services in a home automation network
  • H04L12/2825—Reporting to a device located outside the home and the home network
• • G—PHYSICS
  • G01—MEASURING; TESTING
  • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
  • G01M99/00—Subject matter not provided for in other groups of this subclass
  • G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
• • G—PHYSICS
  • G01—MEASURING; TESTING
  • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
  • G01M7/00—Vibration-testing of structures; Shock-testing of structures
• • G—PHYSICS
  • G10—MUSICAL INSTRUMENTS; ACOUSTICS
  • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
  • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
  • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
  • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L12/00—Data switching networks
  • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
  • H04L12/2803—Home automation networks
  • H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
  • H04R1/00—Details of transducers, loudspeakers or microphones
  • H04R1/08—Mouthpieces; Microphones; Attachments therefor
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B7/00—Instruments for auscultation
  • A61B7/02—Stethoscopes
  • A61B7/04—Electric stethoscopes

Definitions

• the invention relates to the surveillance or the supervision of objects, in particular non-communicating objects.
• the home automation proposes to centralize the control of various electronic systems (heating, alarm, etc.) of the house, hotels, school, etc. to meet human needs for comfort, safety, etc. Nevertheless, if the smart home was able to meet certain needs by controlling the heating, the opening (doors, windows, shutters), the alarm, it did not generalize because it is unattractive because of the costs of setting square.
• the connected detectors are able to provide an answer to a simple question by detecting a simple, often binary state: active / inactive, open / closed, etc., of an object.
• a simple state can be defined as a normal operating state of an object and / or an element of an object: active / inactive, open / closed, operating mode.
• the detector is capable of indicating the simple states of the laundry: door open / closed, washing in progress or stopped, type of washing.
• Current connected detectors can not answer complex questions such as where are my keys? Why does my device no longer work? How can I get it back in working order?
• One of the aims of the present invention is to provide improvements over the state of the art.
• An object of the invention is a complex state detector relating to an object comprising an analyzer capable of determining a complex state relating to the object as a function of recognition of at least one sound emitted by the object.
• the recognized sound allows the detector to determine the complex state of an object, that is to say in particular an abnormal state of operation of the object or a state of the object that is not relative to its operation: for example its position on a surface, in a volume, the identity of the person having manipulated the object ...
• the complex state of the object is a complex state among the following: a state of abnormality of operation of the object, a relative position of the object, an identity of the manipulator of the object.
• the detector makes it possible to warn of a malfunction of the object even if the object is not intelligent, and / or to inform of a passive parameter relating to an object even if it is not intelligent, or even for passive objects: position in a closed or open volume (room, apartment, house, garden, etc.), identity of the manipulator, etc.
• the analyzer is able to determine a complex state of the object according to the recognition context of the sound emitted by the object.
• the analyzer is able to distinguish two complex states corresponding to the same recognized sound.
• a dishwasher noise may correspond to two states of the dishwasher: normal, abnormality.
• the context will allow the analyzer to determine which of the two states: normal, anomaly is the current state of the object.
• the recognized sound will correspond to a normal operating state whereas, in a context of stopping the dishwasher, the same recognized sound will correspond to a state of anomaly of operation
• the complex state of anomaly is a type of abnormality of operation of the object.
• the detector not only warns of a malfunction but in addition to the type of malfunction allowing the user or a supervisory device to correct, possibly, the malfunction of the object.
• the detector is a connected detector.
• the detector can communicate the detected complex state to a third party device, in particular a non-intelligent object supervisor for triggering an intervention of the user of the object, a technician, or a processing of a device supervisor in particular for transmitting a complex state function message to a communication device of a user, a technician and / or correct the malfunction when the complex state is a malfunction.
• a third party device in particular a non-intelligent object supervisor for triggering an intervention of the user of the object, a technician, or a processing of a device supervisor in particular for transmitting a complex state function message to a communication device of a user, a technician and / or correct the malfunction when the complex state is a malfunction.
• Another subject of the invention is an electronic ear comprising a first analyzer capable of recognizing at least one sound emitted by an object and a second analyzer able to diagnose the complex state of the object as a function of at least one recognized sound. .
• the electronic ear comprises a sound sensor capable of capturing at least one sound emitted by the object.
• a sound sensor capable of capturing at least one sound emitted by the object.
• the electronic ear comprises an object supervisor capable of determining at least one treatment to be performed as a function of the diagnosed complex state.
• the electronic ear makes it possible, thanks to the so-called supervisor of objects device, not only to diagnose a complex state, including an anomaly, but also to trigger an action according to this complex state: transmission of a message depending on the complex state diagnosed, correction of the anomaly diagnosed either by a human being or by the supervisor of the electronic ear (which controls in particular the object if it is intelligent, or a third device), or by a remote supervisor.
• the electronic ear comprises a communication interface capable of establishing a command-to-command communication of the supervisor, when the processing to be executed comprises a connection with a remote device.
• the electronic ear not only makes it possible to diagnose an anomaly but also to trigger its remote support: by a remote supervisory device, a user, a technician ...
• the electronic ear comprises fixators and is intended to be fixed on the object emitting the recognized sound
• the sensor is positioned in the part of the electronic ear close to the fixators and / or oriented in the electronic ear towards the plan formed by the fixers.
• the sound captured has less noise, that is to say, its sound from the environment of the object, plus its sound from the object itself allowing an improvement of the recognition by the first analyzer .
• An object of the invention is also a method for detecting complex states relating to an object comprising a diagnosis determining a complex state relating to the object as a function of recognition of at least one sound emitted by the object.
• An object of the invention is also a method for monitoring objects comprising a recognition of at least one sound emitted by an object and a diagnosis of the complex state of the object as a function of at least one recognized sound.
• An object of the invention is also an object supervision method comprising a determination of a processing to be performed as a function of the complex state diagnosed according to a recognition of at least one sound emitted by the object.
• the supervision method includes triggering the execution of the determined processing.
• the various steps of the method according to the invention are implemented by software or computer program, this software comprising software instructions intended to be executed by a data processor of a computer.
• device forming part of a complex state detector of an object and / or an electronic ear and being adapted to control the execution of the various steps of this method.
• the invention is therefore also directed to a program comprising program code instructions for performing the steps of the abnormality detection method and / or the object monitoring method when said program is executed by a processor.
• This program can use any programming language and be in the form of source code, object code or intermediate code between source code and object code such as in a partially compiled form or in any other desirable form.
• FIG. 1 a simplified diagram of a complex state detector according to the invention
• FIG. 2 a simplified diagram of an electronic ear according to the invention
• FIG. 3 a simplified diagram of the method for detecting complex states according to the invention
• FIG. 4 a simplified diagram of the method for monitoring objects according to the invention
• FIG. 5 a simplified diagram of the method of supervising objects according to the invention
• FIGS. 6a to 6c use case diagrams of the invention, respectively a detector or an electronic ear that can be fixed on an object, said detector or ear positioned on a refrigerator constituting the object, a detector or a multi-electronic ear -objects.
• complex states are meant the non-functional states of an object as opposed to the generally binary simple states which describe an operating state of the object: active / inactive, open / closed, operating mode.
• the complex states also called non-functional states, includes the operating anomaly states of the object, a relative position of the object, an identity of the manipulator of the object.
• object is meant a concrete thing that can be touched and assigned to a specific use.
• an object may be a household object such as a piece of furniture, but also a household appliance, an element of the house: door, window, shutter, etc.
• FIG. 1 illustrates a simplified diagram of a complex state detector according to the invention.
• the complex ST_DT detection method relating to an object 4 comprises an analyzer 202 able to determine a complex state ec relative to the object as a function of a recognition of at least one sound s emitted by the object 4.
• the its recognized sr allows the detector 20 to determine the complex state ec of an object 4, that is to say in particular an abnormal operating state of the object 4 or a state of the object 4 which is not not relative to its operation: for example its position on a surface, in a volume, the identity of the person having manipulated the object ...
• the complex state ec of the object 4 is a complex state among the following: an operating anomaly state of the object, a relative position of the object, an identity of the manipulator of the object.
• the detector 20 makes it possible to alert a malfunction of the object 4 even if the object 4 is not intelligent, and / or to inform of a passive parameter relating to an object 4 even if is not intelligent, or even for passive objects 4: position in a closed or open volume (room, apartment, house, garden, etc.), identity of the manipulator, etc.
• a passive parameter is a parameter different from an active parameter or activity parameter, that is to say from a parameter relating to the operation of the object 4.
• the analyzer 202 is able to determine a complex state ec of the object 4 as a function of the context of recognition of the sound s emitted by the object 4.
• the recognition of the sound is in particular carried out by a first analyzer January 1, 201 1 (the analyzer 202 then being named second analyzer).
• the analyzer 202 or second analyzer is able to distinguish two complex states corresponding to the same recognized sound sr following the context ex.
• a dishwasher noise may correspond to two dishwasher conditions: normal or abnormal.
• the context ex will allow the analyzer 202 to determine which of the two states: normal or anomaly is the current state of the object 4.
• the recognized sound sr will correspond to a normal operating state (simple state) whereas, in an ex context of stopping the dishwasher 4, the same recognized sound sr will correspond to a state of malfunction (complex state ec) .
• Natural or manufactured objects in our environment make noise during their operation (example: engine of a boat), during their use (example: the click of a ballpoint pen or the sound of a door closing) ), or during events (example: keys that are placed on a table).
• Some manufactured objects produce sounds during their operation so that the human being recognizes them and thus can deduce information on the state of the object (example of the end of cycle sound of a washing machine)
• the complex state ec of anomaly is a type of abnormality of operation of the object.
• the detector 20 not only makes it possible to warn of a malfunction but in addition to the type of malfunction allowing a user (in particular a user of the object 4) or a supervisory device 7 to correct, possibly, the malfunction of the object 4.
• the detector 20 is a connected detector.
• the detector 20 can communicate the detected complex state ec to a third party device 7, in particular a non-intelligent object supervisor for triggering an intervention of the user of the object, a technician, or a processing agent.
• a supervisory device in particular for transmitting a complex state function message to a communication device of a user, a technician and / or correcting the malfunction when the complex state is a malfunction.
• the sound s emitted by the object 4 is captured either by a sensor 10 external to the detector 20, or a sensor 2010 implemented in the detector 20. By a sound is heard not only the sounds audible by the human but also any other vibrations perceived by a living being or a machine so also infrasound, ultrasound but also mechanical vibrations ...
• the sound captured sc is supplied to a first analyzer January 1, 201 1 able to recognize sounds, that is to say, to identify the movement, friction, etc.. of the object 4 at the origin of the sound (closing of door, laying of key on a table, noise of electric motor, etc.).
• This first sound recognition analyzer 1 1, 201 1 is either a first external analyzer 1 1 to the detector 20, or a first analyzer 201 1 implemented in the detector 20.
• the sensor 10, 2010 and the first analyzer January 1, 201 1 are implemented in the same sound processing device 1, 201 which is either an external processing device 1 to the detector 20, or a processing device 201 implemented in the detector 20.
• a third analyzer 6, 206 called context analyzer provides the second analyzer 202 said complex state analyzer the context ex in which the sound sr has been recognized.
• the context analyzer 6, 206 is either an external analyzer 6 to the detector 20 or an analyzer 206 implemented in the detector 20.
• the context analyzer notably receives information relating t (s) at the time of capture of the sound.
• the detector 20 comprises a transmitter 203 capable of transmitting to a third device 7.
• the transmitter 203 can transmit either the detected complex state ec, or a message comprising or function of the complex state detected mssg (ec ), etc.
• the third-party device 7 can implement processing according to the complex state ec received or simply display / reproduce this information for the user of the third-party device 7.
• the third-party device 7 can be a simple screen of display, a smartphone, a computer of the user of the object or of a third party user (parent, technician, etc.), a server or device for providing service in an Internet network, etc.
• Figure 2 illustrates a simplified diagram of an electronic ear according to the invention.
• the electronic ear 2 comprises a first analyzer 21 capable of recognizing at least one sound emitted by an object 4 and a second analyzer 22 able to diagnose the complex state ee of the object 4 as a function of at least one recognized sound sr.
• the recognized sound sr allows the electronic ear 2 to determine the complex state ec of an object 4, that is to say in particular an abnormal operating state of the object 4 or a state of the object 4 which is not related to its operation: for example its position on a surface, in a volume, the identity of the person having manipulated the object ...
• the complex state ec of the object 4 is a complex state among the following: a state of anomaly relative to the object, a relative position of the object, an identity of the manipulator of the object, etc. .
• the electronic ear 2 can alert a malfunction of the object 4 even if the object 4 is not intelligent, and / or inform a passive parameter relating to an object 4 even s it is not intelligent, or even for passive objects: position in a closed or open volume (room, apartment, house, garden, etc.), identity of the manipulator, etc.
• a passive parameter is a parameter different from an active parameter or activity parameter, that is to say from a parameter relating to the operation of the object 4.
• the complex state ec of anomaly is a type of anomaly relating to the object.
• the electronic ear 2 not only makes it possible to warn of a malfunction but in addition to the type of malfunction allowing a user (in particular a user of the object 4) or a supervisory device 7 to correct, if necessary, the malfunction of the object 4.
• the second analyzer 22 is able to diagnose a complex state ec of the object according to the context ex of recognition of the sound s emitted by the object 4.
• the complex state diagnosed ec will not be the same depending on the context ex.
• a sound of the apparatus 4 will correspond to a normal operating state (simple state)
• a context ex of the closed door apparatus 4 even its s will be diagnosed as corresponding to a state of anomaly (complex state ec).
• the electronic ear 2 comprises a sound sensor 210 capable of capturing at least one sound emitted by the object 4.
• the errors related to the degradation of the sound during the transmission between the sensor 210 and the first analyzer 21 performing the recognition of sound are deleted.
• the electronic ear 2 comprises an object supervisor 25 capable of determining at least one trt treatment to be executed as a function of the complex state diagnosed ec.
• the electronic ear 2 makes it possible, by virtue of the so-called object supervisor device 25, not only to diagnose a complex state ec, notably an anomaly, but also to trigger an action trt as a function of this complex state: transmission of a message mssg function of the complex state diagnosed, correction of the anomaly diagnosed either by a human being or by the supervisor of the electronic ear (which commands in particular either the object if it is intelligent, or a third-party device), either by a remote supervisor.
• the electronic ear 2 comprises a communication interface 23 adapted to establish a communication on command cmd of the supervisor 25, when the processing to be performed comprises a connection with a remote device 7.
• the communication interface or transmitter 23 can in particular transmit either the detected complex state ec, or a message comprising or function of the detected complex state mssg (ec), etc.
• the third-party device 7 can implement processing according to the complex state ec received or simply display / reproduce this information for the user of the third-party device 7.
• the third-party device 7 can be a simple screen of display, a smartphone, a computer of the user of the object or of a third party user (parent, technician, etc.), a server or device for providing service in an Internet network, etc.
• the electronic ear 2 not only makes it possible to diagnose an anomaly but also to trigger its remote support: by a remote supervisory device, a user, a technician ...
• the electronic ear 2 comprises fasteners 28 adapted to allow attachment of the electronic ear 2 at least temporarily on an object: the object 4 or another object of the environment E of the object 4.
• the electronic ear 2 makes it possible to detect the complex states of several objects 4 present in the same environment E. And, the recognition of the first analyzer 21 and / or the diagnosis of the second analyzer 22 are not disturbed by a displacement of the electronic ear 2.
• the electronic ear 2 includes fixers 28 (shown in Figure 6a) and is intended to be fixed on the object 4 emitting the s recognized s.
• the sensor 210 is positioned in the part of the electronic ear 2 close to the fixators 28 and / or oriented in the electronic ear 2 towards the plane formed by the fasteners 28.
• the sound captured has less noise, that is to say from its source:
• the electronic ear comprises a complex ST_DT detection method relating to an object 4 implementing the second analyzer 202 capable of determining a complex state ec relative to the object as a function of a recognition of at least one sound emitted by the object 4.
• the electronic ear 2 is a connected electronic ear.
• the complex states diagnosed are transmitted to the Internet to be stored and store a history of the object 4.
• the electronic ear 2 can thus communicate the detected complex state ec to a third device 7, including a non-intelligent object supervisor to trigger an intervention of the user of the object, a technician, or a processing of a supervisory device, in particular for transmitting a message depending on the complex state to a communication device of a user, a technician and / or correcting the malfunction when the complex state is a malfunction.
• the sound s emitted by the object 4 is captured either by a sensor 10 external to the electronic ear 2, or a sensor 210 implemented in the electronic ear 2.
• a sound is heard not only the sounds audible by the being human but also all other vibrations perceived by a living being or a machine so also infrasound, ultrasound but also mechanical vibration ...
• the sound captured sc is provided to the first analyzer 21 able to recognize sounds, that is to say to identify movement, friction, etc. of the object 4 at the origin of the sound (closing of door, laying of key on a table, noise of electric motor, etc.).
• the sensor 10, 210 and the first analyzer 21 are implemented in the same sound processing device (not shown) which is a processing device implemented in the electronic ear 2.
• the first analyzer 21 performs sound recognition according to the context in which the sound is emitted and / or captured.
• the sound recognition takes into account the environment in which the sound is emitted and / or captured: such as the position of the electronic ear 2 relative to the object 4 (orientation, distance, displacement %), the type of environment (room volume, latent sound level Certainly, etc.
• the first analyzer 21 includes a filter (not shown) capable of suppressing environmental noise depending on the context in which the sound is emitted and / or captured.
• the filter of the first analyzer 21 is able to remove all or part of the noise related to a displacement of the object 4 and / or the electronic ear 2.
• a third analyzer 6, 26 said context analyzer provides the second analyzer 22 said complex state analyzer context ex in which the sound sr has been recognized.
• the context analyzer 6, 26 is either an external analyzer 6 at the electronic ear 2, or an analyzer 26 implemented in the electronic ear 2.
• the context analyzer notably receives information relating to t (s) at the time of the capture of the sound, for example of a clock or a time stamp of the sensor 10, 2010, information relating to the position of the object 4 during the transmission of the sound captured, and other information relating to the object 4 environment, in particular information relating to the sound environment of the object 4 when capturing the emitted sound (provided by the sensor 10, 2010 or one of the other sensors present in the environment E of object 4) or information relating to the previous states ep of object 4 (simple states and / or complex ec).
• FIG. 3 illustrates a simplified diagram of the method for detecting complex states according to the invention.
• the method for detecting complex states relating to an object ST_DT comprises a diagnosis DG determining a complex state ec relative to the object as a function of an S_RCG recognition of at least one sound s emitted by the object O.
• the recognized sound sr allows the detection method ST_DT to determine the complex state ec of an object O, that is to say in particular an abnormal operating state of the object O or a state of the object O which is not relative to its operation: for example its position on a surface, in a volume, the identity of the person having manipulated the object ...
• the complex state ec of the object O is a complex state among the following: a state of anomaly of operation of the object, a relative position of the object, an identity of the manipulator of the object.
• the detection method ST_DT makes it possible to alert a malfunction of the object O even if the object O is not intelligent, and / or to inform of a passive parameter relating to an object O even it is not intelligent, or even for passive O objects: position in a closed or open volume (room, apartment, house, garden, etc.), identity of the manipulator, etc.
• a passive parameter is a parameter different from an active parameter or activity parameter, that is to say from a parameter relating to the operation of the object O.
• the diagnosis DG is able to determine a complex state ec of the object O as a function of the recognition context S_RCG of the sound s emitted by the object O.
• the diagnosis DG is able to distinguish two corresponding complex states. to the same recognized sound according to the context ex.
• a dishwasher noise may correspond to two dishwasher conditions: normal or abnormal.
• the context ex will allow the diagnosis DG to determine which of the two states: normal or anomaly is the current state of the object O.
• the sound Recognized sr will correspond to a normal state of operation (simple state) while, in an ex context of stopping the dishwasher 4, the same sound recognized sr will correspond to a state of malfunction (complex state ec).
• the complex state ec of anomaly is a type of abnormality of operation of the object.
• the detection method ST_DT not only makes it possible to warn of a malfunction but in addition to the type of malfunction allowing a user (particularly a user of the object O) or a supervisory device DD to correct, if necessary, the malfunction of object O.
• the diagnosis DG receives one or more recognized sounds sp. - .sr n , of the object O and uses at least one of the recognized sounds to determine the complex state of the object O.
• the DG diagnosis using several recognized sounds eh. .eG h of an object O to determine a complex state eç comprises a step of merging the recognized sounds SR_FU followed by a modeling step SR_MD of the merged sound signal making it possible to determine from a database of states ST_BDD , the complex state ec corresponding to the fused sound signal sf.
• the sound s emitted by the object O is captured during a capture of its S_CPT implemented either by a method external to the detection method ST_DT, in particular a sound recognition method S_RCG, or by the detection method ST_DT of complex states.
• a sound is heard not only the sounds audible by the human being but also all other vibrations perceived by a living being or a machine so also infrasound, ultrasound but also mechanical vibration ...
• the sound captured sc is provided to a sound recognition S_RCG able to recognize sounds, that is to say to identify the movement, the friction, etc. of the object O at the origin of the sound (closing of door, laying of key on a table, noise of electric motor, etc.).
• This recognition of its S_RCG is carried out either by a method external to the detection method ST_DT, in particular a method of sound recognition S_RCG, or by the method of detection ST_DT of complex states.
• the capture of its S_CPT and the sound recognition S_RCG are implemented by the same sound processing method which is either a process external to the ST_DT detection method, or a processing method implemented by the method of ST_DT detection.
• an analysis of the context CX_NZ (not illustrated in FIG. 4) provides the diagnostic DG determining a complex state ec the context ex in which the sound sr has been recognized.
• the context analysis CX_NZ is either an external analysis to the ST_DT detection method, or an analysis implemented by the ST_DT detection method.
• the context analysis CX_NZ notably receives information relating to t (s) at the time of capturing the sound s for example of a timestamp H (not shown) of the capture of the sound S_CPT, information relating to the position of the object O during the transmission of the captured sound, and other information relating to the environment of the object O, in particular information relating to the sound environment of the object O during the capture of the Issued s (provided by the sound capture S_CPT or another capture SE_CPT relating to the environment E of the object O (not shown)) or information relating to the previous states ep of the object O (simple and / or complex states ec).
• the detection method ST_DT comprises a transmission EC_TR (not shown) capable of transmitting, in particular the diagnosed complex state, to a third device 7.
• the transmission EC_TR can transmit either the detected complex state ec, or a message comprising or function of the complex state detected mssg (ec), etc. So the third party device DD can implement processing according to the complex state ec received or simply display / reproduce this information to the user of the third-party device 7.
• FIG. 4 illustrates a simplified diagram of the object monitoring method according to the invention.
• An object of the invention is also a method for monitoring OMNT objects comprising an S_RCG recognition of at least one sound s ⁇ .s ,, emitted by an object O and a diagnosis DG of the complex state ec of the object O according to at least one recognized sound sr- ! ... sr n .
• the OMNT object monitoring method comprises a sound recognition S_RCG capable of recognizing at least one sound emitted by an object O and a diagnosis DG capable of determining the complex state ec of the object O as a function of at least one his recognized sr.
• the recognized sound sr enables the OMNT object monitoring method to determine the complex state ec of an object O, that is to say in particular an abnormal operating state of the object O or a state of the object O which is not relative to its operation: for example its position on a surface, in a volume, the identity of the person having manipulated the object ...
• the complex state ec of the object O is a complex state among the following: a state of anomaly relative to the object, a relative position of the object, an identity of the manipulator of the object, etc. .
• the method for monitoring OMNT objects makes it possible to warn of a malfunction of the object O even if the object O is not intelligent, and / or to inform of a passive parameter relating to an object O even if it is not intelligent, or even for O passive objects: position in a closed or open volume (room, apartment, house, garden, etc.), identity of the manipulator, etc.
• a passive parameter is a parameter different from an active parameter or activity parameter, that is to say from a parameter relating to the operation of the object O.
• the complex state ec of anomaly is a type of anomaly relating to the object.
• the OMNT object monitoring method not only makes it possible to warn of a malfunction but in addition to the type of malfunction allowing a user (particularly a user of the object O) or a supervisory device DD to correct, possibly the malfunction of the object O.
• the diagnosis DG is able to determine a complex state ec of the object O as a function of the context ex of recognition of the sound s emitted by the object O.
• the complex state diagnosed ec will not be the same depending on the context ex.
• a sound of the apparatus O will correspond to a normal operating state (simple state), whereas in a context ex of the apparatus O door closed, even its s will be diagnosed as corresponding to a state of anomaly (complex state ec).
• the OMNT object monitoring method comprises a sound capture step S_CPT capable of capturing at least one sound emitted by the object O.
• the diagnosis DG receives one or more recognized sounds SR. - .sr n , of the object O and uses at least one of the recognized sounds to determine the complex state of the object O.
• the sound recognition S_RCG comprises a step of sorting the captured sounds S_CL followed by a modeling step S_MD of the captured sound classified s cc1 ... s ccn to determine from a sound database SR_BDD, the recognized sound sp. - .sr n corresponding to the captured sound classified s cc1 ... s ccn .
• the sound recognition S_RCG is made according to the context in which the sound is emitted and / or captured.
• the sound recognition takes into account the environment in which the sound is emitted and / or captured: such as the position of the electronic ear 2 relative to the object 4 (orientation, distance, displacement %), the type of environment (room volume, latent sound level Certainly, etc.
• the sound recognition S_RCG filters (not illustrated) an environmental noise depending on the context in which the sound is emitted and / or captured. For example, this filtering is able to remove all or part of the noise related to a displacement of the object 4 and / or the electronic ear 2.
• the diagnosis DG comprises a modeling step SR_MD of the recognized sound signal making it possible to determine from a database of states ST_BDD, the complex state ec corresponding to the recognized sound signal.
• the diagnosis DG comprises a step of merging the recognized sounds SR_FU followed by the modeling step SR_MD of the fused sound signal making it possible to determine from a base of state data ST_BDD, the complex state ec corresponding to the fused sound signal sf.
• the OMNT object monitoring method comprises a supervision of OMGT objects (not illustrated in FIG. 4) comprising at least one step of determining TRT_DT of at least one trt processing to be executed as a function of the complex state diagnosed ec.
• the OMNT object monitoring method makes it possible, by means of OMGT object supervision, not only to diagnose a complex state ec, notably an anomaly, but also to trigger an action trt as a function of this complex state: EM transmission of a message mssg function of the complex state diagnosed, correction of the anomaly diagnosed either by a human being or by the OMGT supervision of OMNT object monitoring method (which commands in particular the object O if it is intelligent, either a third-party device DD), or by a remote supervisor DD.
• the OMNT object monitoring method comprises a transmission EM capable of establishing a command-only communication cmd of the OMGT supervision method, when the processing to be executed comprises a connection with a remote device 7.
• the step of emission EM may emit either the detected complex state ec, or a message comprising or function of the complex state detected mssg (ec), etc.
• the third party device DD may implement a processing according to the complex state ec received or simply display / reproduce this information for the user of the third party device DD.
• the third party device DD may be a simple display screen, a smartphone, a computer of the user of the object or a third party user (parent, technician, etc.), a server or service provision device in an Internet network, etc.
• the OMNT object monitoring method not only makes it possible to diagnose an anomaly but also to trigger its remote support: by a remote supervisory device, a user, a technician ...
• the OMNT monitoring method comprises a complex ST_DT detection method relating to an object O implementing a diagnosis DG capable of determining a complex state ec relative to the object according to an S_RCG recognition of at least one sound s issued by the object O.
• the OMNT object monitoring method comprises an ALT, EM communication of the complex state detected ec to a third party device DD, in particular a non-intelligent object supervisor for triggering an intervention by the user of the object, a technician, or a processing of a supervisory device including transmitting a complex state function message to a communication device of a user, a technician and / or correct the malfunction when the state complex is a malfunction.
• the ALT communication of the complex ec state diagnosed can be performed by modifying a predetermined indicator (led ...), by displaying a message on a screen, by vocalizing a message by means of a -parlivities, a device implementing the OMNT monitoring method, including an electronic ear 2.
• the sound s emitted by the object O is captured during an S_CPT sound capture implemented either by a method external to the OMNT monitoring method, or by the OMNT monitoring method.
• an S_CPT sound capture implemented either by a method external to the OMNT monitoring method, or by the OMNT monitoring method.
• a sound is heard not only the sounds audible by the human being but also all other vibrations perceived by a living being or a machine so also infrasound, ultrasound but also mechanical vibration ...
• the sound captured sc is provided to a recognition S_RCG sound capable of recognizing sounds, that is to say, to identify movement, friction, etc. of the object O at the origin of the sound (closing of door, laying of key on a table, noise of electric motor, etc.).
• S_CPT capture and S_RCG sound recognition are implemented by the same sound processing method (not shown) which is a processing method implemented by the OMNT monitoring method.
• a context analysis CX_NZ provides the diagnostic DG the ex context in which the sound sr has been recognized.
• the context analysis CX_NZ is implemented either by an analysis method external to the OMNT monitoring method, or by the OMNT monitoring method.
• the context analysis CX_NZ notably receives information relating t (s) at the time of capturing the sound s for example from a clock or a time stamp of the sensor 10, 2010, information relating to the position of the object O during the transmission of the captured sound, and other information relating to the environment of the object O, in particular information relating to the sound environment of the object O during the capture of the transmitted sound (provided by the sensor 10, 2010 or one of other sensors present in the environment E of the object O) or information relating to the previous states ep of the object O (simple states and / or complexes ec).
• the context analysis CX_NZ receives at least one signal, in particular sound, said environmental signals se, emitted by the environment E of the object O and performs a recognition of these environmental signals SE_RCG.
• the context ex provides to the DG diagnosis by context analysis CX_NZ will include the recognized signal ser.
• the context analysis CX_NZ notably comprises a fusion step E_FU providing the context ex.
• FIG. 5 illustrates a simplified diagram of the method of supervising objects according to the invention.
• An object of the invention is also a method for supervising OMGT objects comprising a determination of a processing to be executed TRT_DT as a function of the complex state diagnosed ec as a function of an SRCG recognition of at least one transmitted sound by the object O.
• the determination of the processing to be performed provides either an identifier of a treatment to execute trtjd, or the treatment to be executed trt, especially in the form of a sequence of steps of a treatment method to be put implement or instructions of an executable program including a processor.
• the supervision method comprises a GN generation of a treatment according to the complex state diagnosed ec of the object O.
• the OMGT supervision method includes triggering the execution of the determined processing TRT_X.
• the generation of the GN processing is either implemented by the determination of the TRT_DT processing (not illustrated), either following the TRT_DT processing determination, or by the triggering of a TRT_X processing operation (illustrated in FIG. 5).
• the processing determination controls the GN generation of a specific processing, in particular by providing the identifier of the processing to be generated trtjd.
• the OMGT supervision method verifies I? if the treatment is to be performed by the supervision method. If this is the case [Y], the supervision method comprises a step of executing the determined processing trt (in particular generated GN or recovered (not shown) in a processing database (not shown) by the OMGT supervision method or the TRT_DT processing determination ). The verification I?
• the supervision method comprises a step of transmitting the triggering of the execution of the determined processing trt (in particular generated GN or recovered (not shown) in a processing database (not shown) by the OMGT supervision method or TRT_DT processing determination ).
• the verification I? triggers em_trg the emission EM, by the OMGT supervision method, of a command, a message comprising either the identifier of the determined processing, or the trt treatment determined, or a recovery address of the determined processing, destination or a remote device DD.
• the OMGT supervision method is implemented by the electronic ear 2 implementing the complex state DG diagnosis ec of the object O.
• the OMGT monitoring method can also be used. comprise the diagnosis DG, and possibly the sound recognition S_RCG and / or the context analysis CX_NZ, as described with reference to FIGS. 3 or 4.
• the OMGT supervision method is implemented by a third device distinct from the electronic ear 2, in particular a smartphone, a tablet, a computer or a supervisor of complex state detectors 20 and / or
• the complex state detector 20 implements the detection method ST_DT described in FIG. 3 where the electronic ear 2 implements the OMNT monitoring method described in FIG. dialogue with the supervisory method to which it (the ST_DT detection method or the OMNT monitoring method) provides the diagnosed complex state ec.
• a particular embodiment of at least one method according to the invention: ST_DT detection method, and / or OMNT monitoring method, and / or OMGT supervision method, is a program comprising program code instructions for the performing the steps of the abnormality detection method and / or the object monitoring method and / or the supervision method when said program is executed by a processor.
• solutions develop to exploit the vision (image, video) and to recognize objects in these visual contents.
• vision image, video
• Few solutions based on sound can identify objects, their state or events associated with these objects, technically we must go through solutions based vision (cameras).
• the only solutions that appear are hyper specialized, are limited to long sound events and rather related to security (habitat), not the detection of an object and its state.
• the invention proposes, in particular for responding to this lack, a detector of complex states of objects comprising an analyzer capable of determining a complex state relating to the object as a function of a recognition of at least one sound emitted by the 'object.
• FIGS. 6a and 6b illustrate diagrams of a use case of the invention: respectively a detector or an electronic ear that can be fixed on an object, said detector or ear positioned on a refrigerator constituting the object.
• the detector 20 or the electronic ear 2 comprises at least one sensor 210 including a microphone, including directional to limit the capture of sound not coming from the object and therefore constituting a noise.
• the detector 20 or the electronic ear 2 comprises fixators, such as magnets 28a for fixing the electronic ear 2 to an object 4 having at least one metal outer surface; suction cups 28b for attachment to an object having a non-metallic flat outer surface ...
• the detector 20 or the electronic ear 2 comprises at least one light indicator 27, such as an LED, for displaying a predetermined complex state ec including a given light indicator corresponding to a predetermined complex state (the ignition of the LED meaning that the object is then in the corresponding complex state) or a light can take several colors: a color of the LED is associated with a predetermined complex state, etc.
• a light indicator 27 such as an LED
• the detector 20 or the electronic ear 2 comprises at least one socket 29, in particular a power socket and / or socket for connecting a cable for a data link to a smartphone, a tablet ...
• the detector 20 or the electronic ear 2 comprises an activation button (or on / off button) for managing the power consumption of the detector 20 or the electronic ear 2 and also to limit the periods of time during which the diagnosis of complex states is performed (no night diagnosis or for certain objects when the user is not in the room or the dwelling where the object is ). Thanks to the magnets 28a and / or the suction cup 28b, the detector 20 or the electronic ear 20 is positioned on the object 4, in our example the fridge. This makes it possible to devote the diagnosis implemented by the electronic ear 2 to the complex states of this object 4: the fridge.
• the electronic ear 2 illustrated in Figures 6a and 6b positionable on the object 4 is also called “ear patch” or “gold ear patch” with reference to submarines detecting submerged entities according to the sound produced by their moving in the water.
• ear patch or “gold ear patch” with reference to submarines detecting submerged entities according to the sound produced by their moving in the water.
• the electronic ear 2 consists, for example, of a physical object (the patch) that will make measurements (captured sounds, possibly recognize them) and an algorithm that will analyze these measurements to calculate a probability of deviance to a "normal" state model (or approximation to another state): that is, an algorithm for diagnosing complex states.
• the patch comprises in particular a sensor, such as a microphone 210, which captures and / or records the sounds and vibrations of the apparatus 4 (the vibration analysis can make it possible to identify these vibrations as a context [eg the sound when the door of the object closes] or as the element to be analyzed [which is an input like audible sound]).
• the information from the sounds and vibrations picked up is compared to models and thus makes it possible to identify the correct operation or the risk of malfunction of the object during a diagnosis.
• These models may take into account the context, especially the time and the day of the sound / vibration events.
• a user can position the electronic ear 2 on a first object O which he wishes to check the complex state, in this case the fridge.
• the electronic ear 2 detecting a complex state of anomaly may possibly indicate an anomaly through the indicator, or send a message to a communication terminal of the user with an identifier of the anomaly, or trigger a search of the page of the manual of the object relating to the detected anomaly to send it to and / or display it on a communication terminal of the user (tablet, smartphone, television ...), or trigger a setting relationship with a support platform (human assistance and / or artificial intelligence) specific to the anomaly (so the user does not waste time explaining the problem), or trigger a command of the parts to change depending on the anomaly detected and / or making an appointment with a technician.
• a support platform human assistance and / or artificial intelligence
• the electronic ear 2 is not dedicated to a specific object (in this case the fridge) because its analyzers (first and / or second) allow it to detect complex states of several different objects.
• the user having completed the management of the refrigerator may position at another time (ie immediately or later) the electronic ear 2 on another device (not shown) to be supported.
• Figure 6c illustrates a multi-object detector or electronic ear.
• the electronic ear 2 is in this case placed in a room (for example on a table) to diagnose the complex states of several objects: the table 04, the hob 02, the oven 03, the vacuum cleaner 01 .. which emit sounds: respectively the sounds s4, s2, s3, s1 1 and s12.
• the electronic ear 2 illustrated in FIG. 6c will not audit the objects on which it is placed, but detect the objects 01, 02, 03 ... in its environment and / or an object 05 that interact with each other. the object 04 on which the patch is present.
• the electronic ear 2 detects the interaction of an object 05 with the object 04 on which it is present, it is also called table patch - gold ear or electronic ear table. It then responds to different issues, depending on the reference models that are used:
• the object audit 05 placed or in interaction with the object / surface 04 on which the patch 2 is deposited.
• a patch example of a non-solid material : fluids, example of small objects or too complex design: toys, mechanical parts, etc. example of objects moving on a surface.
• the electronic ear 2 of FIG. 6c notably comprises a physical device and implements a complex state detection algorithm.
• the physical device comprises in particular a sensor of audio signals and / or vibrations, and / or timestamp, that is to say y associated with the signal captured a timestamp information ("timestamp" in English such as (time / min and day)).
• the electronic ear can identify objects 05 placed or moved on the furniture or surface 04 (example of a table, a vacuum pocket, a bedside table, a parquet floor).
• the electronic ear 2 can recognize the arrival of a new object (deposit of key ring on a table, deposit of mail on a table, deposit of a plate on a table etc.) or an event of an object (bunch of keys that we pick up, stack of letters that we move, etc.).
• the electronic ear 2 detects the objects 01, 02, 03 at its listening range, it is also called remote patch - Golden ear or remote electronic ear.
• This electronic ear 2 is a patch "Golden ear" as shown in Figures 6a and 6b but not positioned on a listened object 01, 02, 03.
• the electronic ear 2 captures the audio signals and / or vibrations, and / or determines the timestamp of the captured signals (hour / min and day). It makes it possible to identify the objects 01, 02, 03 at its listening range (noise of a refrigerator, sound of the alarm of a washing machine, beep of a 02 hob, etc.). It can detect the events of these objects (hob lit 02, washing machine that has completed its cycle, etc.) or the state of an object (Fridge that begins to purr, AC adapter that begins to do noise, etc.).
• This remote electronic ear 2 is either a stand-alone object or a feature of an existing object (for example a smart speaker like Orange Djingo, Google Home (registered trademarks), etc.) or software on a computer or smartphone type device . It can thus be embedded in a connected enclosure or on a ceiling lamp (for example: luminaires or smoke detector, etc.).
• the same electronic ear 2 may also have the two functions of remote electronic ear and / or electronic table ear.
• the electronic ear can be mobile, that is to say listen and diagnose complex states of at least one object while the electronic ear moves.
• This mobile electronic ear also called “mobile gold ear” and can move a "remote patch gold ear” as shown in Figure 6c on a "listening" area (observation). He can listen when he is moving or when he is motionless. There are two modes of listening which are different, the listening in displacement will not be able to detect the same types of information that when it is static, because of the noise related to the displacement.
• the mobile electronic ear has a first specific analyzer to listen to certain models of sound / noise adapted to the listening mode especially on the move.
• the first analyzer of a mobile electronic ear will include a filter (all or part) of the noise related to the displacement of the electronic ear.
• the displacement of the electronic ear can be done on Earth (wheels, tracks), in the air (drone), on cable, on the water (float, dinghy, boat, etc.).
• the invention also relates to a support.
• the information carrier may be any entity or device capable of storing the program.
• the medium may include storage means, such as a ROM, for example a CD ROM or a microelectronic circuit ROM or a magnetic recording means, for example a diskette or a hard disk.
• the information medium can be a transmissible medium such as an electrical or optical signal that can be conveyed via an electrical or optical cable, by radio or by other means.
• the program according to the invention may in particular be downloaded to a network, particularly of the Internet type.
• the information carrier may be an integrated circuit in which the program is incorporated, the circuit being adapted to execute or to be used in the execution of the method in question.
• the invention is implemented by means of software and / or hardware components.
• module can correspond to a software component or a hardware component as well.
• a software component corresponds to one or more computer programs, one or more subroutines of a program, or more generally to any element of a program or software capable of implementing a function or a program. function set as described above.
• a hardware component corresponds to any element of a hardware set (or hardware) capable of implementing a function or a set of functions.

Landscapes

• Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• Signal Processing (AREA)
• Automation & Control Theory (AREA)
• Acoustics & Sound (AREA)
• General Physics & Mathematics (AREA)
• Computer Networks & Wireless Communication (AREA)
• Audiology, Speech & Language Pathology (AREA)
• Human Computer Interaction (AREA)
• Multimedia (AREA)
• Health & Medical Sciences (AREA)
• Computational Linguistics (AREA)
• Emergency Alarm Devices (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=63637958

Family Applications (1)

Country Status (4)

Families Citing this family (1)

Family Cites Families (17)

• 2018
  • 2018-04-26 FR FR1853673A patent/FR3080726A1/fr not_active Withdrawn
• 2019
  • 2019-04-25 EP EP19733841.1A patent/EP3785404A1/de not_active Withdrawn
  • 2019-04-25 US US17/049,904 patent/US20210239576A1/en active Pending
  • 2019-04-25 WO PCT/FR2019/050975 patent/WO2019207254A1/fr not_active Ceased

Also Published As

Similar Documents

Legal Events