CN117636858B - Intelligent furniture controller and control method - Google Patents
Intelligent furniture controller and control method Download PDFInfo
- Publication number
- CN117636858B CN117636858B CN202410103069.0A CN202410103069A CN117636858B CN 117636858 B CN117636858 B CN 117636858B CN 202410103069 A CN202410103069 A CN 202410103069A CN 117636858 B CN117636858 B CN 117636858B
- Authority
- CN
- China
- Prior art keywords
- user
- sitting posture
- pressure sensor
- zone
- backrest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000004044 response Effects 0.000 claims abstract description 104
- 230000008859 change Effects 0.000 claims abstract description 75
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 45
- 238000012937 correction Methods 0.000 claims abstract description 43
- 230000036544 posture Effects 0.000 claims description 177
- 230000001960 triggered effect Effects 0.000 claims description 53
- 230000005484 gravity Effects 0.000 claims description 25
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000013519 translation Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 7
- 238000003491 array Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 5
- 238000002474 experimental method Methods 0.000 claims description 4
- 210000003128 head Anatomy 0.000 description 11
- 210000001217 buttock Anatomy 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000006872 improvement Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 3
- 230000004807 localization Effects 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000005236 sound signal Effects 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses an intelligent furniture controller and a control method, wherein the method comprises the following steps: when detecting that the intelligent furniture is switched from the standby state to the use state, taking a preset initial range as a response sound area; when the microphone array collects a first voice signal of the response voice zone, marking the current sitting posture of the user as an initial sitting posture and calculating the sound source coordinates of the first voice signal; calculating a space range corresponding to the sound source coordinates of the first voice signal based on a first sound zone correction algorithm, and updating the space range into a response sound zone corresponding to the initial sitting posture; when the first type of change of the sitting posture of the user is detected, calculating a response voice zone corresponding to the latest sitting posture of the user based on a second voice zone correction algorithm. According to the method, the range of the response sound zone of the intelligent furniture can be dynamically adjusted according to the sitting posture of the user to be matched with the mouth position of the user, so that the response sound zone with a smaller range centering on the sound source is obtained, the probability that the non-user sound source enters the response sound zone is reduced, and the accuracy of voice recognition is improved.
Description
Technical Field
The invention relates to a furniture controller, in particular to an intelligent furniture controller and a control method.
Background
The intelligent furniture provides intelligent control and aims at improving convenience of user operation, after intelligent furniture integrates voice recognition, a user only needs to speak a trigger instruction through voice in the process of using the intelligent furniture, and a controller of the intelligent furniture can control the intelligent furniture according to a voice recognition result through collecting voice signals of the user and performing voice recognition, so that the current use process of the intelligent furniture function of the user cannot be influenced. That is, the user no longer needs to search a remote controller or entity buttons to operate the functions, so that the convenience of user operation is improved. For example, when the user wants to adjust the massage function and the heating function of the couch after lying on the intelligent couch with his eyes closed, he or she can directly control the couch to execute the corresponding heating function by speaking the trigger command through voice without opening his or her eyes and moving.
Intelligent furniture such as couch is placed in living room as family public space, only one user at a time, and when the user uses the intelligent furniture and uses voice recognition to perform function control, the intelligent furniture is easy to be interfered by speaking sound or television sound of other people in the same space. For example, a user speaking sound or a television playing sound is mixed with the user sound in a chair next to a couch, resulting in interference between sound sources, so that a target sound source cannot be effectively distinguished and extracted, reducing the definition and quality of a voice signal. Through retrieval, the sound source localization of the microphone array and the Beamforming (Beamforming) technology can be utilized in the related art to enhance the voice signal of the designated sound zone, so that the target sound source can be effectively distinguished and extracted, and the accuracy of voice recognition is improved. As disclosed in patent document 1, a microphone array technique can be employed to realize a scheme of collecting only sounds of a specified sound zone (main sound zone) for voice control and masking the remaining sound zone, which can improve the accuracy of voice recognition. Further, patent document 1 discloses a solution in which a user sound source crosses a sound zone due to movement of the user, that is, after the user moves to another sound zone, it is considered that the user sound source crosses another sound zone from a previous main sound zone, so that it is necessary to update the latest position where the user is located as the main sound zone.
If the solution of patent document 1 is applied to smart furniture scenes such as a couch, an area surrounded by a frame of the couch (including armrests of the couch, an outer side surface of a backrest, etc.) can be used as a main sound zone, by collecting and responding only to sound of the main sound zone, sound signal quality and speech recognition accuracy can be improved, and when a user uses the couch (i.e., a state of lying on the couch or sitting on the couch), the problem of a user sound source crossing the sound zone in patent document 1 is not faced because the user does not move.
However, in the voice control scene of the couch, there is a problem that the non-user sound source spans the sound zone, that is, the couch is generally arranged in the living room and is closely adjacent to other chairs, so that the head of other people moving in the living room or sitting on the chair next to the couch is easily adjacent to the boundary of the main sound zone of the couch, even into the main sound zone of the couch, which is defined as the non-user sound source spans the sound zone problem.
Because the use scene of intelligent furniture such as couch is the multi-person scene in public space to there is non-user's sound source quartic district problem, can lead to the target pronunciation that gathers from the main sound district of couch apart from including user's sound, also mix the user speaking sound on the chair next to couch, reduce definition and quality and the speech recognition accuracy of speech signal.
Patent document 1, chinese patent, publication No. CN111986678B, patent name, a voice acquisition method and device for multipath voice recognition, publication date, 2023-12-29.
Disclosure of Invention
The invention aims to provide an intelligent furniture controller and a control method, which can dynamically adjust the range of a response sound zone of intelligent furniture to be matched with the position of a mouth of a user according to the sitting posture of the user to obtain a response sound zone with a smaller range taking a sound source as a center, reduce the probability of a non-user sound source entering the response sound zone, further obtain a voice signal with higher quality and improve the accuracy of voice recognition.
To achieve the above object, there is provided an intelligent furniture control method, the method comprising:
when detecting that the intelligent furniture is switched from the standby state to the use state, taking a preset initial range as a response sound area;
when the microphone array collects a first voice signal of the response voice zone, marking the current sitting posture of the user as an initial sitting posture and calculating the sound source coordinates of the first voice signal;
calculating a space range corresponding to the sound source coordinates of the first voice signal based on a first sound zone correction algorithm, and updating the space range into a response sound zone corresponding to the initial sitting posture;
When the first type of change of the sitting posture of the user is detected, calculating a response voice zone corresponding to the latest sitting posture of the user based on a second voice zone correction algorithm.
As a further improvement, the intelligent furniture comprises a cushion and a backrest, a first pressure sensor array arranged on the cushion and a second pressure sensor array arranged on the backrest, wherein the initial sitting posture is the sitting posture of a user when only the first pressure sensor array on the plane of the cushion is triggered by the user;
the calculating the spatial range corresponding to the sound source coordinates of the first voice signal based on the first sound zone correction algorithm specifically includes:
calculating a spatial range (x, y, z) corresponding to the sound source coordinates of the first speech signal according to the following formula:
wherein,in order to initiate the coordinate of the gravity center point P0 of the geometric figure formed by the pressure sensors triggered by the user in the first pressure sensor array on the cushion plane in the sitting posture state, r is the distance from the gravity center point P0 to the sound source coordinate of the first voice signal, and θ is a preset human body swing angle, and θ is more than or equal to 0 ° and less than or equal to 45 °.
As a further improvement, the first type of change of the sitting posture of the user means that only the first pressure sensor array on the plane of the cushion is triggered by the user before and after the change of the sitting posture of the user;
The second voice zone correction algorithm based on the response voice zone corresponding to the latest sitting posture of the user is calculated, and the method specifically comprises the following steps:
acquiring coordinates of a gravity center point P1 of a geometric figure formed by a pressure sensor triggered by a user in a first pressure sensor array on a cushion plane in the latest sitting posture state;
subtracting P0 from P1 to obtain a translation offset；
And adding translation offset to all coordinate points of the current response sound zone to obtain all coordinate points of the response sound zone corresponding to the latest sitting posture.
As a further improvement, the method further comprises:
correcting the formula I by using a third sound zone correction algorithm;
the corrected formula one is:
wherein d is the sinking depth of the cushion which is determined in advance through experiments;
the sinking depth d of the cushion is determined by the following steps:
acquiring a pressure value measured by a first pressure sensor array on a cushion;
and determining the sinking depth d of the cushion according to the table look-up of the pressure value.
As a further improvement, the method further comprises:
when the difference value between the pressure value of the pressure sensor with the largest pressure value in the first pressure sensor array and all other triggered pressure sensors is larger than the preset pressure difference value, taking the coordinate point of the pressure sensor with the largest pressure value as the coordinate of the gravity center point of the geometric figure formed by the pressure sensors triggered by the user in the first pressure sensor array on the cushion plane under the sitting posture of the user.
As a further improvement, the intelligent furniture comprises a cushion and a backrest, a first pressure sensor array arranged on the cushion and a second pressure sensor array arranged on the backrest, wherein the initial sitting posture is the sitting posture of a user when the first pressure sensor array on the cushion plane and the second pressure sensor array on the backrest are triggered by the user at the same time;
the calculating the spatial range corresponding to the sound source coordinates of the first voice signal based on the first sound zone correction algorithm specifically includes:
calculating a spatial range (x, y, z) corresponding to the sound source coordinates of the first speech signal according to the following formula II:
wherein,in order to initiate the sound source coordinate of the first voice signal under the sitting posture state, R is the preset neck swinging length, R is more than or equal to 8cm and less than or equal to 12cm, A, B and C are three components of normal vectors perpendicular to the plane of the backrest, and D is a constant obtained after the coordinate of the plane of the backrest is brought in.
As a further improvement, the method further comprises:
when the second type of change of the sitting posture of the user is detected, calculating a response voice zone corresponding to the latest sitting posture of the user based on a fourth voice zone correction algorithm; the second type of change of the sitting postures of the users means that the second pressure sensor arrays on the backrest are triggered by the users before and after the sitting postures of the users are changed, and the first pressure sensor arrays on the cushion plane are triggered by the users;
The calculating the response voice zone corresponding to the latest sitting posture of the user based on the fourth voice zone correction algorithm specifically comprises the following steps:
acquiring coordinates of a gravity center point P2 of a geometric figure formed by a pressure sensor triggered by a user in a second pressure sensor array on a backrest plane before the sitting posture of the user is changed;
acquiring coordinates of a gravity center point P3 of a geometric figure formed by a pressure sensor triggered by a user in a second pressure sensor array on a backrest plane after the sitting posture of the user is changed;
subtracting P2 from P3 to obtain a translation offset;
and adding translation offset to all coordinate points of the current response sound zone to obtain all coordinate points of the response sound zone corresponding to the latest sitting posture.
As a further improvement, the method further comprises:
when detecting that the sitting posture of the user changes in the third type, determining the latest sitting posture of the user after the change; the third type of change means that the second pressure sensor array on the backrest is respectively in a state of being triggered by the user and not triggered by the user before and after the sitting posture of the user is changed;
if the latest user sitting posture is the user sitting posture when only the first pressure sensor array on the cushion plane is triggered by the user, calculating a response voice zone corresponding to the latest user sitting posture based on a second voice zone correction algorithm;
If the latest user sitting posture is the user sitting posture when the first pressure sensor array on the cushion plane and the second pressure sensor array on the backrest are triggered by the user at the same time, calculating a response sound zone corresponding to the latest user sitting posture based on a fourth sound zone correction algorithm.
As a further improvement, the method further comprises:
when the fourth type of change of the sitting posture of the user is detected, calculating a response voice zone corresponding to the latest sitting posture of the user based on a fifth voice zone correction algorithm; the fourth type of change of the sitting posture of the user means that the inclination angle of the backrest changes before and after the sitting posture of the user is changed under the condition that the second pressure sensor array on the backrest is triggered by the user;
the fifth voice zone-based correction algorithm calculates a response voice zone corresponding to the latest sitting posture of the user, and specifically comprises the following steps:
determining a rotation matrix of a plane in which the backrest is located before and after the change based on the change of the inclination angle of the backrest;
converting all coordinate points of the current response sound zone based on the rotation matrix to obtain all coordinate points of the response sound zone corresponding to the latest sitting posture;
wherein the rotation matrix is:
alpha is the variation value of the backrest inclination angle, and alpha is more than or equal to 0 degree and less than or equal to 60 degrees.
In another aspect, the present invention provides a smart furniture controller comprising a memory, a processor and a computer program stored on the memory, the processor executing the computer program to perform the steps of the above method.
The beneficial effects are that:
according to the intelligent furniture controller and the control method, the range of the response sound zone of the intelligent furniture can be dynamically adjusted according to the sitting posture of the user to be matched with the mouth position of the user, the response sound zone with a smaller range taking the sound source as the center is obtained, the probability that a non-user sound source enters the response sound zone is reduced, therefore, a voice signal with higher quality is obtained, and the voice recognition accuracy is improved.
Drawings
The invention is further described below with reference to the drawings and examples;
fig. 1 is a schematic view of a couch according to an embodiment.
Fig. 2 is a schematic diagram of a first type of change in the sitting position of the user in example 1.
Fig. 3 is a schematic view showing the contact area between the user and the couch before the sitting position of the user is changed in the first kind in embodiment 1.
Fig. 4 is a schematic view showing the contact area between the user and the couch after the first type of change in the sitting position of the user in example 1.
Fig. 5 is a schematic diagram of a response sound zone corresponding to the initial sitting posture in example 1.
Fig. 6 is a schematic diagram showing a second type of change in the sitting posture of the user in example 2.
Fig. 7 is a schematic view showing the contact area between the user and the couch before the second type of change in the sitting position of the user in embodiment 2.
Fig. 8 is a schematic view showing the contact area between the user and the couch after the second type of change in the sitting position of the user in example 2.
Fig. 9 is a schematic diagram of a third type of change in the sitting posture of the user in example 3.
Fig. 10 is a schematic view showing the contact area between the user and the couch before the third type of change in the sitting position of the user in example 3.
Fig. 11 is a schematic view showing the contact area between the user and the couch after the third type of change in the sitting position of the user in example 3.
Fig. 12 is a schematic view showing a third type of change in the sitting posture of the user in example 4.
Fig. 13 is a schematic view showing the contact area between the user and the couch before the third type of change in the sitting position of the user in example 4.
Fig. 14 is a schematic view showing the contact area between the user and the couch after the third type of change in the sitting position of the user in example 4.
Fig. 15 is a schematic view showing a fourth type of change in sitting posture of the user in example 5.
Fig. 16 is a schematic flow chart of a smart furniture control method according to an embodiment.
FIG. 17 is a second flow chart of a smart furniture control method according to an embodiment.
Detailed Description
Referring to fig. 1, the intelligent furniture control method provided by the present application is applicable to the couch of fig. 1, which includes a seat cushion and a backrest, a first pressure sensor array disposed on the seat cushion, and a second pressure sensor array disposed on the backrest. As shown in fig. 1, the plane of the seat cushion is the xoy plane of the rectangular coordinate system calibrated by the microphone array, that is, the z component of the plane of the seat cushion is 0, the plane of the backrest is the yoz plane, that is, the x component of the plane of the backrest is 0, and the origin O of the coordinate system is at the intersection point of the two planes, so that the backrest can rotate around the y axis to adjust the angle of the backrest.
It will be appreciated that by means of the microphone array, sound from any particular region of space may be selected for reception while other regions are masked. This is mainly achieved by Beamforming (Beamforming) techniques and sound source localization techniques. The specific implementation steps are as follows:
sound source localization: first, the position of the target sound source needs to be determined. This is typically done by analyzing the sound signals captured by the microphone array. With the time difference (Time Difference of Arrival, TDOA) between the sound signals arriving at the different microphones, the position of the sound source in space can be estimated.
Beamforming): once the location of the sound source is determined, beamforming techniques may be used to "point" to this particular region. Beamforming is a signal processing technique that causes signals from a particular direction to be enhanced and signals from other directions to be suppressed by adjusting the signal for each microphone in the microphone array. This approach can create a highly directional sensing region, i.e., a "beam".
Digital signal processing: beamforming is implemented by digital signal processing algorithms. These algorithms calculate how to adjust the signal of each microphone in the microphone array to focus on the target area. This typically involves time delay, weighting and phase adjustment of the signal.
Dynamic adjustment: in practice, if the target sound source is moving in space, the system can dynamically adjust the beam pointing direction to continue focusing on the moving sound source.
Technical contributions of the present application to the prior art are described below in connection with the figures and examples.
Example 1:
as shown in fig. 16, the present embodiment provides a smart furniture control method, which includes:
step S101, when the intelligent furniture is detected to be switched from the standby state to the use state, the preset initial range is used as a response sound zone.
Specifically, the standby state refers to a state that no user sits on the couch, the use state refers to a state that a user sits on the couch, the judgment of the state can be realized by whether the first pressure sensor array is triggered, for example, if one or more pressure sensors in the first pressure sensor array have readings, the user is considered to be in the use state, and otherwise, the user is considered to be in the standby state.
As shown in fig. 1, the initial range refers to the range of the space swept by the backrest plane when moving in the positive x direction to the side where the x value of the seat cushion is larger, the height of the backrest is set to 1m, and the mouth of a normal adult user is located within the initial range when sitting upright on the couch. When a user sits on the couch and needs to bend down, the mouth of the user is also in the initial range. Therefore, the preset initial range is used as the response voice zone, so that only the voice signals in the initial range can be collected as the input of the voice recognition module, the voice signal quality is improved, and the voice recognition accuracy is improved.
In step S102, when the microphone array collects the first voice signal of the response voice zone, the current sitting posture of the user is marked as an initial sitting posture and the sound source coordinates of the first voice signal are calculated.
By way of example, the user at 14:23 are seated on the couch, so at 14:23 detects that the intelligent furniture is switched from the standby state to the use state, and the response sound zone at the moment is a preset initial range. After the user sits down for 2 minutes, 14:25, the user sends out voice "wisdom and wisdom in the response voice zone through the mouth, and starts the heating function", namely the first voice signal, and the microphone array only collects voice in the response voice zone and sends the voice to the voice recognition module, so that the voice signal quality and the voice recognition accuracy can be improved. Through the sound source positioning technology, the coordinates of the sound source of the first voice signal, namely the mouth, in the rectangular coordinate system calibrated by the microphone array, namely the sound source coordinates, can be calculated.
Step S103, calculating a space range corresponding to the sound source coordinates of the first voice signal based on the first sound zone correction algorithm, and updating the space range to a response sound zone corresponding to the initial sitting posture.
The first volume modification algorithm is specifically given in embodiments 1 and 2 below. The range of the response sound zone can be adjusted by adopting the first sound zone correction algorithm, the range of the response sound zone of the intelligent furniture can be dynamically adjusted according to the sitting posture of the user to be matched with the mouth position of the user, the response sound zone with a smaller range taking the sound source as the center is obtained, the probability that a non-user sound source enters the response sound zone is reduced, a voice signal with higher quality is obtained, and the voice recognition accuracy is improved.
Step S104, when the first type of change of the sitting posture of the user is detected, calculating a response voice zone corresponding to the latest sitting posture of the user based on the second voice zone correction algorithm.
It will be appreciated that after the response volume has been updated from the initial range to a spatial range that matches the initial sitting position, the range of the response volume is dynamically modified immediately upon detection of a change in the user's sitting position to ensure that the user can continue to maintain speech signal quality during dynamic use of the couch, thereby improving speech recognition accuracy.
As shown in fig. 2, the posture in which the user sits on the couch without touching the backrest is defined as a first posture, at which time only the first pressure sensor array on the cushion plane is triggered by the user's sitting posture. In this embodiment, the initial sitting posture is the first posture.
In this embodiment, the calculating, based on the first sound zone correction algorithm, a spatial range corresponding to a sound source coordinate of the first speech signal specifically includes:
calculating a spatial range (x, y, z) corresponding to the sound source coordinates of the first speech signal according to the following formula:
wherein,in order to initiate the coordinate of the gravity center point P0 of the geometric figure formed by the pressure sensors triggered by the user in the first pressure sensor array on the cushion plane in the sitting posture state, r is the distance from the gravity center point P0 to the sound source coordinate of the first voice signal, and θ is a preset human body swing angle, and θ is more than or equal to 0 ° and less than or equal to 45 °.
As shown in fig. 3, in the initial sitting posture, the couch is close to the x-axis, 4 pressure sensors enclosed by a dotted line box are contacted by the user and apply pressure, and the contacted 4 pressure sensors are connected into a quadrangle with a center of gravity P0 by a solid line in fig. 3. It should be noted that, the coordinates of each pressure sensor in the coordinate system calibrated by the microphone array are calibrated before leaving the factory and written into the storage device, and can be read at any time. As shown in fig. 5, the coordinates of the sound source of the first speech signal are Q, the dashed line denoted by m is the cushion plane, that is, the xoy plane, and S1 is used to represent the coordinates of the center of gravity point of the geometric figure composed of the pressure sensor triggered by the user in fig. 5. It is known that the distance from Q to S1 is the distance from the contact position of the buttocks of the user with the seat cushion to the mouth, and generally, when the user sits on the sofa while sitting in a constant position, the user may bend down, lower the head or turn the head, and the like, which may cause the mouth of the user, i.e. the position of the source of the sound to change, so that the response sound area is narrowed from the initial range through the formula one, and the activity allowance conforming to the upper body of the human body is left without frequently modifying the response sound area. As shown in fig. 5, by reducing the range of the response audio from the hexahedron corresponding to the initial range to a cone-like range according to the first formula, the quality of the voice signal is improved, and the response audio does not need to be frequently modified.
In this embodiment, the status of the readings of the 4 pressure sensors in fig. 3 is used to indicate an initial sitting posture. For example, when the pressure sensor on the couch indicates the sitting posture of the user, the data structure of the sitting posture of the user can be constructed by using whether the pressure sensor has readings, the first pressure sensor array (M1) is known to have 12 pressure sensors, the second pressure sensor array (M2) is known to have 16 pressure sensors, the pressure sensors are numbered, the user sitting posture data represented by two binary groups is obtained, M1= [000000011110], M2= [0000000000000000], the data indicates that the pressure sensors numbered 2, 3, 4 and 5 in the first pressure sensor array have readings when the user sits at present, and the second pressure sensor array is not triggered. As shown in fig. 4, the user sitting posture data is m1= [000110011000], m2= [0000000000000000], and the data indicates that the pressure sensors numbered 4, 5, 8 and 9 in the first pressure sensor array have readings under the current user sitting posture, and the second pressure sensor array is not triggered. It is apparent that both figures 3 and 4 belong to the first posture and that in the case of both belonging to the first posture, the changes in the sitting position of the user that occur are referred to as first type of changes.
Specifically, the first type of change in the sitting position of the user means that only the first pressure sensor array on the plane of the cushion is triggered by the user before and after the change in the sitting position of the user.
The second voice zone correction algorithm based on the response voice zone corresponding to the latest sitting posture of the user is calculated, and the method specifically comprises the following steps:
in step S201, the coordinates of the center of gravity point P1 of the geometric figure of the pressure sensor triggered by the user in the first pressure sensor array on the cushion plane in the latest sitting posture state are obtained.
Fig. 3 is a schematic diagram of the sitting postures of the user before the first type of change, and fig. 4 is a schematic diagram of the sitting postures of the user after the first type of change, which shows that the first posture is maintained before and after the first type of change of the sitting postures of the user, but the buttocks of the user move on the plane of the cushion, and the sitting postures of the user can be judged to be changed according to the sitting postures data of the user. The coordinates of each sensor are known, and P0 and P1 can be easily obtained according to the method for obtaining the geometric centroid, which is not described here again.
Step S202, subtracting P0 from P1 to obtain a translational offset；
And step S203, adding translation offset to all coordinate points of the current response sound zone to obtain all coordinate points of the response sound zone corresponding to the latest sitting posture.
It can be understood that in step S201 to step S203, it is not necessary to calculate all coordinate points of the response sound area corresponding to the latest sitting posture by using the formula one again after the first type of change occurs in the sitting posture of the user, but only the translation offset is directly used to perform simple addition operation with the response sound area before the first type of change occurs (i.e., the current response sound area in step S203), so that the operation amount of updating the response sound area is reduced, and the computer resources are saved.
Further, the method further comprises:
correcting the formula I by using a third sound zone correction algorithm;
the corrected formula one is:
wherein d is the sinking depth of the cushion which is determined in advance through experiments;
the sinking depth d of the cushion is determined by the following steps:
acquiring a pressure value measured by a first pressure sensor array on a cushion;
and determining the sinking depth d of the cushion according to the table look-up of the pressure value.
As shown in fig. 5, the dashed line denoted by m is the cushion plane in the standby state, that is, the x0y plane, and the dashed line denoted by n is the cushion plane in the use state, it can be seen that the z component of the n plane is smaller than the z component of the m plane, which means that the cushion plane is sunk when the user sits down, and the ideal state calculation is performed by using the cushion plane that is not sunk in the formula one, so that the formula one after correction needs to be adopted in consideration of the sinking factor. The sinking depth d can be determined by looking up a table, and is not only related to the weight of a user, but also related to the material of the sofa, so that manufacturers can pre-determine the sinking depth of different models of sofa under different pressure values through experiments before leaving the factory, and the sinking depth d is used for correcting the formula I, thereby improving the precision of dividing the response sound zone.
In one embodiment, the method further comprises:
when the difference value between the pressure value of the pressure sensor with the largest pressure value in the first pressure sensor array and all other triggered pressure sensors is larger than the preset pressure difference value, taking the coordinate point of the pressure sensor with the largest pressure value as the coordinate of the gravity center point of the geometric figure formed by the pressure sensors triggered by the user in the first pressure sensor array on the cushion plane under the sitting posture of the user.
It will be understood that, as shown in fig. 5, assuming that in the first posture, the cushion has 4 pressure sensors triggered, and S1 in fig. 5 indicates that one of the pressure sensors has the largest value and the difference from all other pressure sensors triggered is greater than the preset pressure difference, S1 is directly taken as the center of gravity point. The reason is that when the user's head is positioned in the middle of the body, the buttocks are formed by protruding two sides and concave in the middle, so that the two buttocks bear almost the same weight, the pressure sensor on the cushion generally has two groups of sensors with readings almost same as that of the two groups of sensors, and the head is positioned in the middle of the two buttocks generally, so that the center of sphere of the swing of the human body, namely the center of gravity point coordinate, needs to be determined according to the center of gravity of the geometric image. When the human body tilts to enable the head to deviate to a certain side, the weight of the human body mainly supports the buttocks at a certain side, which means that the head is just above the buttocks of a certain flap, so that the coordinate of the pressure sensor S1, which is triggered by all other pressure sensors respectively and has a difference larger than a preset pressure difference, can be directly used as the center of sphere of the swing of the human body, namely the coordinate of the gravity center of the S1 is directly used as the coordinate of the gravity center to be brought into a formula I, and a more accurate response sound distinguishing effect is obtained.
Example 2
In this embodiment, the posture in which the user touches the backrest to sit on the couch is defined as the second posture, at which time the user sits when both the first pressure sensor array on the cushion plane and the second pressure sensor array on the backrest are simultaneously triggered by the user. In this embodiment, the initial sitting posture is the second posture.
The calculating the spatial range corresponding to the sound source coordinates of the first voice signal based on the first sound zone correction algorithm specifically includes:
calculating a spatial range (x, y, z) corresponding to the sound source coordinates of the first speech signal according to the following formula II:
wherein,in order to initiate the sound source coordinate of the first voice signal under the sitting posture state, R is the preset neck swinging length, R is more than or equal to 8cm and less than or equal to 12cm, A, B and C are three components of normal vectors perpendicular to the plane of the backrest, and D is a constant obtained after the coordinate of the plane of the backrest is brought in.
Unlike in embodiment 1, the hip is taken as the center point of the swing of the human body, and the cone-like range for allowing the user to bend down and move with low head without changing the sitting posture of the user is obtained as the response sound zone by the formula one. In the present embodiment, in the case where the user's backpack contacts the backrest and the back does not leave the backrest, the setting tone region should mainly consider the range of motion of the head (the movable organ is mainly the neck), not the range of motion of the waist as considered in embodiment 1.
Therefore, in this embodiment, the range of the response sound zone as determined by the formula two is that the mouth is taken as the center of sphere, the swing length of the neck (the neck of a person is generally 8-12cm long) is taken as the radius, the sphere is firstly determined, then the plane equation of the backrest plane is defined by three components of the normal vector perpendicular to the plane of the backrest through A, B and C, and meanwhile, the position where the sphere intersects the front face (i.e. the face facing the user) of the backrest is defined as the response sound zone, because the range at the back of the backrest is not in the sofa and is the range to be excluded. It will be appreciated that without adjusting the angle of inclination of the backrest, the backrest plane is yoz and the normal vector is (1, 0), i.e. a=1, b=0, c=0. And D can be found by taking a coordinate on the plane of the backrest into the plane equation.
In this embodiment, the range of the response voice zone set by the formula two is reduced compared with the initial range, so that the voice signal quality is improved, and meanwhile, the allowance for head activity can be reserved under the condition that the sitting posture of the user is not changed, the range of the response voice zone is not required to be frequently modified, and the cost for computer resources is reduced.
Further, the method further comprises:
when the second type of change of the sitting posture of the user is detected, calculating a response voice zone corresponding to the latest sitting posture of the user based on a fourth voice zone correction algorithm; the second type of change of the sitting postures of the users means that the second pressure sensor arrays on the backrest are triggered by the users before and after the change of the sitting postures of the users, and the first pressure sensor arrays on the cushion plane are triggered by the users.
The calculating the response voice zone corresponding to the latest sitting posture of the user based on the fourth voice zone correction algorithm specifically comprises the following steps:
step S301, acquiring coordinates of a center of gravity point P2 of a geometric figure of a pressure sensor triggered by a user in a second pressure sensor array on a backrest plane before a sitting posture of the user is changed.
Referring to fig. 7, the user sitting posture data is m1= [000000011110], m2= [0000000001100110] at this time before the second type of change in the user sitting posture occurs.
Step S302, acquiring coordinates of a center of gravity point P3 of a geometric figure of a user-triggered pressure sensor in a second pressure sensor array on the backrest plane after the sitting posture of the user is changed.
Referring to fig. 8, after the second change occurs in the user sitting, the user sitting data is m1= [000110011000], m2= [0000011001100000].
In step S303, P2 is subtracted from P3 to obtain the translational offset.
And step S304, adding translational offset to all coordinate points of the current response sound zone to obtain all coordinate points of the response sound zone corresponding to the latest sitting posture.
Fig. 7 is a schematic diagram of the user's sitting posture before the second type of change, and fig. 8 is a schematic diagram of the user's sitting posture after the second type of change, which shows that the user's back (knapsack will drive the head to move) moves on the backrest plane while the user's sitting posture maintains the second posture before and after the second type of change, and the user's sitting posture can be determined to change according to the user's sitting posture data. The coordinates of each sensor are known, and P2 and P3 can be easily obtained according to the method for obtaining the geometric centroid, which is not described here again.
It can be understood that in step S301 to step S304, it is not necessary to re-use the formula two to calculate all coordinate points of the response sound zone corresponding to the latest sitting posture after the second type of change occurs in the sitting posture of the user, but only simply add the translation offset to the response sound zone before the second type of change occurs (i.e., the current response sound zone in step S304), so as to reduce the operation amount of updating the response sound zone and save computer resources.
In one embodiment, the method further comprises:
when detecting that the sitting posture of the user changes in the third type, determining the latest sitting posture of the user after the change; the third type of change is that the second pressure sensor array on the backrest is in a user-activated and non-user-activated state, respectively, before and after the user's sitting position is changed. I.e. a change in the user's sitting position that is directly switched between the first and second posture.
If the latest user sitting posture is the user sitting posture when only the first pressure sensor array on the cushion plane is triggered by the user, calculating a response voice zone corresponding to the latest user sitting posture based on a second voice zone correction algorithm;
if the latest user sitting posture is the user sitting posture when the first pressure sensor array on the cushion plane and the second pressure sensor array on the backrest are triggered by the user at the same time, calculating a response sound zone corresponding to the latest user sitting posture based on a fourth sound zone correction algorithm.
Specifically, in embodiment 3, as shown in fig. 9, the user switches from the first posture to the second posture, that is, the third type of change occurs. Specifically, the occurrence of the third type of change may be determined based on the user's sitting posture data. Referring to fig. 10, before the third type of change occurs in the user's sitting posture, the user's sitting posture data is m1= [000000011110], m2= [0000000000000000]. Referring to fig. 11, after the third change occurs in the user sitting, the user sitting data is m1= [000000011110], m2= [0000000001100110].
As can be seen from embodiments 1 and 2, the response volume ranges of the user in the first posture or the second posture are obtained, so steps S201 to S203 (i.e. the second volume correction algorithm) or steps S301 to S304 can be directly used to calculate the response volume corresponding to the latest sitting posture of the user, so as to save the computer overhead.
Specifically, in embodiment 4, as shown in fig. 12, the user switches from the second posture to the first posture, that is, the third type of change occurs. Specifically, the occurrence of the third type of change may be determined based on the user's sitting posture data. Referring to fig. 13, the user sitting posture data is m1= [000110011000], m2= [0000011001100000] at this time before the third type of change occurs in the user sitting posture. After the third change occurs in the user sitting, the user sitting data is m1= [000110011000], m2= [0000000000000000] with reference to fig. 14.
As can be seen from embodiments 1 and 2, the response volume ranges of the user in the first posture or the second posture are obtained, so steps S201 to S203 (i.e. the second volume correction algorithm) or steps S301 to S304 can be directly used to calculate the response volume corresponding to the latest sitting posture of the user, so as to save the computer overhead.
Example 5
As shown in fig. 15, in this embodiment, the method further includes:
when the fourth type of change of the sitting posture of the user is detected, calculating a response voice zone corresponding to the latest sitting posture of the user based on a fifth voice zone correction algorithm; the fourth type of change of the sitting posture of the user means that the inclination angle of the backrest changes before and after the sitting posture of the user is changed under the condition that the second pressure sensor array on the backrest is triggered by the user;
the fifth voice zone-based correction algorithm calculates a response voice zone corresponding to the latest sitting posture of the user, and specifically comprises the following steps:
determining a rotation matrix of a plane in which the backrest is located before and after the change based on the change of the inclination angle of the backrest;
converting all coordinate points of the current response sound zone based on the rotation matrix to obtain all coordinate points of the response sound zone corresponding to the latest sitting posture;
wherein the rotation matrix is:
Alpha is the variation value of the backrest inclination angle, and alpha is more than or equal to 0 degree and less than or equal to 60 degrees.
It will be appreciated that the user will also change his mouth position with the change in the angle of inclination of the back without moving the backpack or buttocks after lying on the back of the sofa, and therefore will also need to correct the position of the response zone when the angle of inclination of the back is changed.
Specifically, in this embodiment, the backrest rotates around the y-axis by an angle α, and at this time, a rotation matrix in which the plane rotates around the y-axis may be used to calculate the mapping relationship before and after the change of the inclination angle, so as to accelerate the process of correcting the audio region for the fourth type of change.
For example, the user leans against the backrest in the second posture, the corresponding response sound zone (i.e., the response sound zone when the backrest plane is the pitch angle) has been obtained in embodiment 2, and if the backrest rotates by the angle α, all coordinates of the response sound zone obtained in embodiment 2 can be directly transformed by using the rotation matrix, and the response sound zone after the pitch angle is adjusted can be converted. For example, α=30 degrees, and the new coordinate of the point P (1, 2, 3) after 30 degrees of rotation around the Y axis is about (2.37, 2, 2.10).
In summary, as shown in fig. 17, the sitting posture change of the user is divided into four types, and each type of transformation adopts a corresponding voice region correction algorithm to dynamically correct the range of the response voice region, i.e. the embodiment 5 above, so as to obtain a high-quality voice signal, thereby improving the accuracy of voice recognition.
In another aspect, the present invention provides a smart furniture controller comprising a memory, a processor and a computer program stored on the memory, the processor executing the computer program to perform the steps of the above method.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRA), memory bus direct RAM (RDRA), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
Claims (10)
1. A smart furniture control method, the method comprising:
when detecting that the intelligent furniture is switched from the standby state to the use state, taking a preset initial range as a response sound area;
when the microphone array collects a first voice signal of the response voice zone, marking the current sitting posture of the user as an initial sitting posture and calculating the sound source coordinates of the first voice signal;
calculating a space range corresponding to the sound source coordinates of the first voice signal based on a first sound zone correction algorithm, and updating the space range into a response sound zone corresponding to the initial sitting posture;
when the first type of change of the sitting posture of the user is detected, calculating a response voice zone corresponding to the latest sitting posture of the user based on a second voice zone correction algorithm.
2. The intelligent furniture control method of claim 1, wherein the intelligent furniture comprises a seat cushion and a backrest, a first array of pressure sensors disposed on the seat cushion, and a second array of pressure sensors disposed on the backrest, wherein the initial sitting position is a user sitting position when only the first array of pressure sensors on the plane of the seat cushion is triggered by a user;
The calculating the spatial range corresponding to the sound source coordinates of the first voice signal based on the first sound zone correction algorithm specifically includes:
calculating a spatial range (x, y, z) corresponding to the sound source coordinates of the first speech signal according to the following formula:
wherein (1)>In order to initiate the coordinate of the gravity center point P0 of the geometric figure formed by the pressure sensors triggered by the user in the first pressure sensor array on the cushion plane in the sitting posture state, r is the distance from the gravity center point P0 to the sound source coordinate of the first voice signal, and θ is a preset human body swing angle, and θ is more than or equal to 0 ° and less than or equal to 45 °.
3. The intelligent furniture control method according to claim 2, wherein the first type of change of the sitting posture of the user means that only the first pressure sensor array on the plane of the cushion is triggered by the user before and after the sitting posture of the user is changed;
the second voice zone correction algorithm based on the response voice zone corresponding to the latest sitting posture of the user is calculated, and the method specifically comprises the following steps:
acquiring coordinates of a gravity center point P1 of a geometric figure formed by a pressure sensor triggered by a user in a first pressure sensor array on a cushion plane in the latest sitting posture state;
subtracting P0 from P1 to obtain a translation offset；
And adding translation offset to all coordinate points of the current response sound zone to obtain all coordinate points of the response sound zone corresponding to the latest sitting posture.
4. A method of intelligent furniture control according to claim 2, wherein the method further comprises:
correcting the formula I by using a third sound zone correction algorithm;
the corrected formula one is:
wherein d is the sinking depth of the cushion which is determined in advance through experiments;
the sinking depth d of the cushion is determined by the following steps:
acquiring a pressure value measured by a first pressure sensor array on a cushion;
and determining the sinking depth d of the cushion according to the table look-up of the pressure value.
5. A method of intelligent furniture control according to claim 2, wherein the method further comprises:
when the difference value between the pressure value of the pressure sensor with the largest pressure value in the first pressure sensor array and all other triggered pressure sensors is larger than the preset pressure difference value, taking the coordinate point of the pressure sensor with the largest pressure value as the coordinate of the gravity center point of the geometric figure formed by the pressure sensors triggered by the user in the first pressure sensor array on the cushion plane under the sitting posture of the user.
6. The intelligent furniture control method of claim 1, wherein the intelligent furniture comprises a seat cushion and a backrest, a first pressure sensor array disposed on the seat cushion, and a second pressure sensor array disposed on the backrest, wherein the initial sitting posture is a user sitting posture when both the first pressure sensor array on the seat cushion plane and the second pressure sensor array on the backrest are triggered by a user at the same time;
The calculating the spatial range corresponding to the sound source coordinates of the first voice signal based on the first sound zone correction algorithm specifically includes:
calculating a spatial range (x, y, z) corresponding to the sound source coordinates of the first speech signal according to the following formula II:
wherein (1)>In order to initiate the sound source coordinate of the first voice signal under the sitting posture state, R is the preset neck swinging length, R is more than or equal to 8cm and less than or equal to 12cm, A, B and C are three components of normal vectors perpendicular to the plane of the backrest, and D is a constant obtained after the coordinate of the plane of the backrest is brought in.
7. The intelligent furniture control method of claim 6, further comprising:
when the second type of change of the sitting posture of the user is detected, calculating a response voice zone corresponding to the latest sitting posture of the user based on a fourth voice zone correction algorithm; the second type of change of the sitting postures of the users means that the second pressure sensor arrays on the backrest are triggered by the users before and after the sitting postures of the users are changed, and the first pressure sensor arrays on the cushion plane are triggered by the users;
the calculating the response voice zone corresponding to the latest sitting posture of the user based on the fourth voice zone correction algorithm specifically comprises the following steps:
acquiring coordinates of a gravity center point P2 of a geometric figure formed by a pressure sensor triggered by a user in a second pressure sensor array on a backrest plane before the sitting posture of the user is changed;
Acquiring coordinates of a gravity center point P3 of a geometric figure formed by a pressure sensor triggered by a user in a second pressure sensor array on a backrest plane after the sitting posture of the user is changed;
subtracting P2 from P3 to obtain a translation offset;
and adding translation offset to all coordinate points of the current response sound zone to obtain all coordinate points of the response sound zone corresponding to the latest sitting posture.
8. A method of intelligent furniture control according to claim 3 or 6, wherein the method further comprises:
when detecting that the sitting posture of the user changes in the third type, determining the latest sitting posture of the user after the change; the third type of change means that the second pressure sensor array on the backrest is respectively in a state of being triggered by the user and not triggered by the user before and after the sitting posture of the user is changed;
if the latest user sitting posture is the user sitting posture when only the first pressure sensor array on the cushion plane is triggered by the user, calculating a response voice zone corresponding to the latest user sitting posture based on a second voice zone correction algorithm;
if the latest user sitting posture is the user sitting posture when the first pressure sensor array on the cushion plane and the second pressure sensor array on the backrest are triggered by the user at the same time, calculating a response sound zone corresponding to the latest user sitting posture based on a fourth sound zone correction algorithm.
9. A method of intelligent furniture control according to claim 3 or 6, wherein the method further comprises:
when the fourth type of change of the sitting posture of the user is detected, calculating a response voice zone corresponding to the latest sitting posture of the user based on a fifth voice zone correction algorithm; the fourth type of change of the sitting posture of the user means that the inclination angle of the backrest changes before and after the sitting posture of the user is changed under the condition that the second pressure sensor array on the backrest is triggered by the user;
the fifth voice zone-based correction algorithm calculates a response voice zone corresponding to the latest sitting posture of the user, and specifically comprises the following steps:
determining a rotation matrix of a plane in which the backrest is located before and after the change based on the change of the inclination angle of the backrest;
converting all coordinate points of the current response sound zone based on the rotation matrix to obtain all coordinate points of the response sound zone corresponding to the latest sitting posture;
wherein the rotation matrix is:alpha is the variation value of the backrest inclination angle, and alpha is more than or equal to 0 degree and less than or equal to 60 degrees.
10. A smart furniture controller comprising a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410103069.0A CN117636858B (en) | 2024-01-25 | 2024-01-25 | Intelligent furniture controller and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410103069.0A CN117636858B (en) | 2024-01-25 | 2024-01-25 | Intelligent furniture controller and control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117636858A CN117636858A (en) | 2024-03-01 |
| CN117636858B true CN117636858B (en) | 2024-03-29 |
Family
ID=90035792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410103069.0A Active CN117636858B (en) | 2024-01-25 | 2024-01-25 | Intelligent furniture controller and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117636858B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1473964A2 (en) * | 2003-05-02 | 2004-11-03 | Samsung Electronics Co., Ltd. | Microphone array, method to process signals from this microphone array and speech recognition method and system using the same |
| CN113841421A (en) * | 2019-03-21 | 2021-12-24 | 舒尔获得控股公司 | Auto-focus, in-region auto-focus, and auto-configuration of beamforming microphone lobes with suppression |
| CN115691490A (en) * | 2022-10-09 | 2023-02-03 | 蔚来汽车科技(安徽)有限公司 | Method for dynamically switching sound zone, voice interaction method, equipment, medium and vehicle |
| CN116863928A (en) * | 2023-07-31 | 2023-10-10 | 华人运通(上海)云计算科技有限公司 | Speech recognition method, system, device, medium and vehicle |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190107288A (en) * | 2019-08-30 | 2019-09-19 | 엘지전자 주식회사 | Method for controlling vehicle based on speaker recognition and intelligent vehicle |
-
2024
- 2024-01-25 CN CN202410103069.0A patent/CN117636858B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1473964A2 (en) * | 2003-05-02 | 2004-11-03 | Samsung Electronics Co., Ltd. | Microphone array, method to process signals from this microphone array and speech recognition method and system using the same |
| CN113841421A (en) * | 2019-03-21 | 2021-12-24 | 舒尔获得控股公司 | Auto-focus, in-region auto-focus, and auto-configuration of beamforming microphone lobes with suppression |
| CN115691490A (en) * | 2022-10-09 | 2023-02-03 | 蔚来汽车科技(安徽)有限公司 | Method for dynamically switching sound zone, voice interaction method, equipment, medium and vehicle |
| CN116863928A (en) * | 2023-07-31 | 2023-10-10 | 华人运通(上海)云计算科技有限公司 | Speech recognition method, system, device, medium and vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117636858A (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7071297B2 (en) | How to generate customized spatial audio with head tracking | |
| US10638842B2 (en) | Smart seat and control method for the same | |
| US10132519B2 (en) | Air conditioning system | |
| US9595251B2 (en) | Sound placement of comfort zones | |
| JP7194271B2 (en) | Near-field audio rendering | |
| CN117636858B (en) | Intelligent furniture controller and control method | |
| JP2004519721A (en) | Automatic azimuth positioning of display depending on viewer location | |
| KR20160110260A (en) | Method for determining an x-ray tube current profile, computer program, data carrier and x-ray image recording device | |
| CN112199846A (en) | System for analyzing and customizing mattress based on three-dimensional human body reconstruction technology | |
| US11737685B2 (en) | Posture identifying device, posture identifying system, and posture identifying method | |
| Engwall | Are static MRI measurements representative of dynamic speech? results from a comparative study using MRI, EPG and EMA. | |
| WO2015045844A1 (en) | Robot, control method, and program | |
| CN114557566A (en) | Bed body posture adjusting system and method, storage medium and electronic equipment | |
| US20240051475A1 (en) | Display adjustment method and apparatus | |
| CN117809637A (en) | Control device and control method for intelligent desktop | |
| WO2013015529A1 (en) | Chair, and seat pad for measuring seated posture and for exercise | |
| Touretzky et al. | Deforming the hippocampal map | |
| KR102268667B1 (en) | Customized posture correction cusion, customized posture correction system, and method thereof | |
| CN113341748A (en) | Sofa intelligent control method and system based on posture and storage medium | |
| CN116772389A (en) | Air conditioner control method and device, electronic equipment and storage medium | |
| WO2023133172A1 (en) | User tracking headrest audio control | |
| US11117049B2 (en) | Computer cockpit for different body shapes of user | |
| CN111035176A (en) | Intelligent posture adjusting sofa and control method thereof | |
| CN114688699A (en) | Air conditioner control method and device, air conditioner and storage medium | |
| CN112315257A (en) | Mattress system based on optimal transmission |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |