Control device and control method for a smart desktop

Abstract

The application discloses a control device and a control method of an intelligent desktop, and the control device comprises a microphone for collecting audio signals, an amplification circuit for amplifying the audio signals collected by the microphone, a band-pass filter circuit for filtering the audio signals of non-human voice frequency bands, an audio output circuit for transmitting the audio signals of human voice frequency bands to an ADC pin of a chip for executing a speech recognition algorithm, and an interrupt trigger circuit for sending an interrupt trigger signal to an interrupt pin of the chip for executing the speech recognition algorithm in response to the received audio signals of the human voice frequency bands. The sound around the intelligent desktop is monitored without adding a coprocessor, and the ADC module of the processor is started only when the sound of a person speaking is detected, so that the processor does not need to be continuously in a starting state, and the processor only executes the speech recognition algorithm on the collected human voice signals, so that the processor is not frequently triggered by environmental noise, thereby reducing the resource consumption of the processor.

Description

Technical Field

[0001] This invention relates to furniture controllers, and more particularly to a control device and control method for an intelligent desktop. Background Technology

[0002] Smart desktops are smart furniture pieces that integrate multiple functions, such as wireless charging and ambient lighting. Due to the increased functionality, richer control methods are needed. For example, the applicant's earlier patent application (publication number CN209450059U) provides a solution for controlling smart desktop functions via touch buttons. Smart desktops can appear as standalone furniture, such as coffee tables, or as accessories to other smart furniture, such as deploying them on the armrests of smart sofas or dressing tables. This shows that smart desktops can be added as accessories to more smart furniture pieces to improve the overall integration of smart furniture. However, controlling smart desktops via buttons is still not smart enough; voice control is a direction for technological improvement in this field.

[0003] In voice control, power consumption and voice recognition accuracy generally need to be considered. Voice recognition requires continuously capturing sound and converting the captured sound signals into digital signals via an ADC module. The processor then executes a voice recognition algorithm to analyze these digital signals to determine if the captured sound contains a trigger word, or wake-up word, such as "hey, Siri." When the detected trigger word is found, the voice assistant program is activated. For example, the voice assistant program can control the corresponding light fixture to increase its brightness based on the command recognized from the voice, such as "increase the brightness of the lights."

[0004] It is evident that continuously monitoring the sound of the environment surrounding smart furniture results in high power consumption. To address this, Chinese patent CN113470641B discloses a solution: adding a coprocessor as a sound detector. While the main processor remains at low power, this coprocessor can still continuously monitor the voice signal and perform analysis solely on the coprocessor to determine the presence of trigger words. Only when a trigger word is detected is the main processor activated for further confirmation. This solution, by adding a coprocessor with lower power consumption than the main processor to replace the original continuous monitoring of the sound signal, reduces the overall power consumption for maintaining voice recognition functionality.

[0005] However, when trying to apply the above-mentioned solutions for reducing voice recognition power consumption to smart desktops and other smart furniture, the inventors found that the existing technology still needs improvement:

[0006] 1. An additional sound chip with data processing capabilities needs to be added to the control device of the smart desktop as a coprocessor in order to continuously monitor the sound around the smart desktop.

[0007] 2. Although the power consumption of the coprocessor is lower than that of the main processor, in order to convert each acquired analog voice signal into a digital signal and analyze it to determine whether there is a trigger word, the coprocessor must keep its ADC module running continuously, which increases the processor's resource overhead.

[0008] 3. In noisy environments, environmental noise is easily collected. For each piece of environmental noise, the coprocessor is frequently triggered to execute the algorithm for analysis, increasing the processor's resource overhead. Summary of the Invention

[0009] The purpose of this invention is to provide a control device and control method for a smart desktop, which monitors the sound around the smart desktop without adding a coprocessor, and only activates the processor's ADC module when it detects someone speaking, without having to be in a continuous startup state. At the same time, the processor only executes the speech recognition algorithm on the collected human voice signal, and will not be frequently triggered by environmental noise, thereby reducing the processor's resource consumption.

[0010] To achieve the above-mentioned objectives, a control device for a smart desktop is provided, the control device comprising:

[0011] A microphone is used to collect audio signals;

[0012] An amplifier circuit is used to amplify the audio signal captured by the microphone.

[0013] A bandpass filter circuit is used to filter audio signals in non-human voice frequency bands; the human voice frequency band range β is: 300Hz≤β≤5000Hz;

[0014] Audio output circuitry is used to transmit audio signals in the human voice frequency band to the ADC pin of the chip that executes the speech recognition algorithm.

[0015] An interrupt trigger circuit is used to send an interrupt trigger signal to the interrupt pin of the chip that executes the speech recognition algorithm in response to the received audio signal in the human voice frequency band.

[0016] The chip that executes the speech recognition algorithm is used to perform the following program:

[0017] When an interrupt initiated from the target interrupt pin is detected, the target ADC module is started according to preset parameters; the target interrupt pin is an interrupt pin connected to the interrupt trigger circuit, and the target ADC module is the ADC module corresponding to the ADC pin connected to the audio output circuit.

[0018] As a further improvement, the audio output circuit includes a voltage follower, the input of which is connected to the output of a bandpass filter circuit, and the output of which is connected to the ADC pin of a chip that executes a speech recognition algorithm.

[0019] As a further improvement, the interrupt trigger circuit includes a non-inverting amplifier, a rectifier unit, a normally closed relay circuit, and a falling edge signal circuit.

[0020] The input of the inverting amplifier is connected to the output of the bandpass filter circuit to amplify audio signals in the human voice frequency band;

[0021] The input terminal of the rectifier unit is connected to the output terminal of the non-inverting amplifier, and is used to rectify the audio signal in the human voice frequency band and output the rectified audio signal in the human voice frequency band to the falling edge signal circuit.

[0022] The falling edge signal circuit responds to the audio signal in the human voice frequency band received at the input terminal by sending a falling edge signal to the interrupt pin of the chip that executes the speech recognition algorithm as an interrupt trigger signal;

[0023] The normally closed relay circuit's drive unit responds to the high-level signal output by the chip's output pin, shutting off the connection between the falling edge signal circuit input and the rectifier unit output, thereby stopping the falling edge signal circuit from receiving audio signals in the human voice frequency band.

[0024] On the other hand, the present invention also provides a control method for a smart desktop, the method being applied to a chip executing a speech recognition algorithm, the chip executing the speech recognition algorithm being connected to the aforementioned control device for the smart desktop, the method comprising:

[0025] When an interrupt initiated from the target interrupt pin is detected, the target ADC module is started according to preset parameters; the target interrupt pin is an interrupt pin connected to the interrupt trigger circuit, and the target ADC module is the ADC module corresponding to the ADC pin connected to the audio output circuit.

[0026] As a further improvement, the method also includes:

[0027] When an interrupt is detected from the target interrupt pin, a countdown begins according to a preset duration; the remaining duration of the countdown is the remaining duration of the target ADC module being in the startup state.

[0028] Before the countdown ends, a high-level signal is continuously output through the target output pin; the target output pin is the output pin connected to the drive unit of the normally closed relay circuit.

[0029] When the countdown ends, the control target output pin stops outputting a high-level signal.

[0030] As a further improvement, the method also includes:

[0031] If a signal input is detected from the ADC module during the countdown, the countdown is reset.

[0032] As a further improvement, the control device for the smart desktop also includes a microphone array connected to a chip that performs a voice recognition algorithm. The smart desktop is mounted on the armrest of a sofa chair, and the method further includes:

[0033] When an interrupt is detected from the target interrupt pin, the ADC module connected to the microphone array is started according to preset parameters;

[0034] The sofa chair is controlled based on the audio signals collected by the microphone array.

[0035] As a further improvement, the method includes:

[0036] When the sofa chair is detected to switch from standby mode to use mode, the preset initial range is used as the response sound zone;

[0037] When the microphone array acquires the first speech signal in the response area, the current user sitting posture is marked as the initial sitting posture and the sound source coordinates of the first speech signal are calculated.

[0038] The spatial range corresponding to the sound source coordinates of the first speech signal is calculated based on the first voice region correction algorithm, and the spatial range is updated to the response voice region corresponding to the initial sitting posture.

[0039] When a first type of change in the user's sitting posture is detected, the response tone zone corresponding to the latest user sitting posture is calculated based on the second tone zone correction algorithm.

[0040] As a further improvement, the sofa chair includes a seat cushion and a backrest, a first pressure sensor array deployed on the seat cushion and a second pressure sensor array deployed on the backrest, wherein the initial sitting posture is the user sitting posture when only the first pressure sensor array on the seat cushion plane is triggered by the user.

[0041] The calculation of the spatial range corresponding to the sound source coordinates of the first speech signal based on the first voice region correction algorithm specifically includes:

[0042] The spatial range (x, y, z) corresponding to the sound source coordinates of the first speech signal is calculated using the following formula:

[0043]

[0044] in, In the initial sitting posture, the coordinates of the center point P0 of the geometric shape formed by the pressure sensors triggered by the user in the first pressure sensor array on the surface of the seat cushion are given. r is the distance from the center point P0 to the sound source coordinates of the first voice signal. θ is the preset human body swing angle, 0°≤θ≤45°.

[0045] As a further improvement, the first type of change in user posture means that only the first pressure sensor array on the seat cushion plane is triggered by the user before and after the change in user posture.

[0046] The calculation of the response tone range corresponding to the latest user sitting posture based on the second tone range correction algorithm specifically includes:

[0047] Obtain the coordinates of the centroid point P1 of the geometric shape formed by the pressure sensors triggered by the user in the first pressure sensor array on the seat cushion plane under the latest sitting posture.

[0048] Subtracting P0 from P1 gives the translation offset. ;

[0049] Add the translation offset to all coordinate points of the current response zone to obtain all coordinate points of the response zone corresponding to the latest sitting posture.

[0050] Beneficial effects:

[0051] The present invention provides a control device and control method for a smart desktop, which can monitor the sound around the smart desktop without adding a coprocessor, and only activate the processor's ADC module when it detects someone speaking, without having to be in a continuous startup state. At the same time, the processor only executes the speech recognition algorithm on the collected human voice signal, and will not be frequently triggered by environmental noise, thereby reducing the processor's resource consumption. Attached Figure Description

[0052] The present invention will be further described below with reference to the accompanying drawings and embodiments;

[0053] Figure 1 is a structural schematic diagram of a sofa chair provided in one embodiment.

[0054] Figure 2 is a schematic diagram of the first type of change in the user's sitting posture in Example 1.

[0055] Figure 3 is a schematic diagram of the contact area between the user and the sofa chair before the user's sitting posture changes in the first type in Example 1.

[0056] Figure 4 is a schematic diagram of the contact area between the user and the sofa chair after the user's sitting posture changes in the first type in Example 1.

[0057] Figure 5 is a schematic diagram of the response sound zone corresponding to the initial sitting posture in Example 1.

[0058] Figure 6 is a schematic diagram of the second type of change in the user's sitting posture in Example 2.

[0059] Figure 7 is a schematic diagram of the contact area between the user and the sofa chair before the second type of change in the user's sitting posture occurs in Example 2.

[0060] Figure 8 is a schematic diagram of the contact area between the user and the sofa chair after the user's sitting posture changes in the second type in Example 2.

[0061] Figure 9 is a schematic diagram of the third type of change in the user's sitting posture in Example 3.

[0062] Figure 10 is a schematic diagram of the contact area between the user and the sofa chair before the user's sitting posture undergoes a third type of change in Example 3.

[0063] Figure 11 is a schematic diagram of the contact area between the user and the sofa chair after the user's sitting posture undergoes a third type of change in Example 3.

[0064] Figure 12 is a schematic diagram of the third type of change in the user's sitting posture in Example 4.

[0065] Figure 13 is a schematic diagram of the contact area between the user and the sofa chair before the user's sitting posture undergoes a third type of change in Example 4.

[0066] Figure 14 is a schematic diagram of the contact area between the user and the sofa chair after the user's sitting posture undergoes a third type of change in Example 4.

[0067] Figure 15 is a schematic diagram of the fourth type of change in the user's sitting posture in Example 5.

[0068] Figure 16 is a flowchart illustrating one embodiment of a smart desktop control method.

[0069] Figure 17 This is a second flowchart illustrating a control method for a smart desktop provided in one embodiment.

[0070] Figure 18 This is a circuit block diagram of a control device for a smart desktop provided in one embodiment.

[0071] Figure 19 This is a circuit diagram of a control device for a smart desktop provided in one embodiment.

[0072] Figure 20 This is a circuit diagram of an interrupt trigger circuit in one embodiment. Detailed Implementation

[0073] Reference Figure 18 This embodiment provides a control device for a smart desktop, the control device comprising:

[0074] Microphone 11 is used to collect audio signals;

[0075] Amplifier circuit 12 is used to amplify the audio signal collected by microphone 11;

[0076] The bandpass filter circuit 13 is used to filter audio signals in non-human voice frequency bands; the human voice frequency band range β is: 300Hz≤β≤5000Hz;

[0077] Audio output circuit 14 is used to transmit audio signals in the human voice frequency band to the ADC pin of chip 16 that performs the speech recognition algorithm;

[0078] Interrupt trigger circuit 15 is used to send an interrupt trigger signal to the interrupt pin of chip 16 that executes speech recognition algorithm in response to the received audio signal in the human voice frequency band;

[0079] The chip 16, which executes the speech recognition algorithm, is used to perform the following program:

[0080] When an interrupt is detected from the target interrupt pin, the target ADC module is started according to preset parameters; the target interrupt pin is the interrupt pin connected to the interrupt trigger circuit 15, and the target ADC module is the ADC module corresponding to the ADC pin connected to the audio output circuit 14.

[0081] The control device for a smart desktop provided in this embodiment can monitor the sounds around the smart desktop without adding a coprocessor, and only activate the processor's ADC module when it detects someone speaking, without having to be continuously activated. At the same time, the processor only executes the speech recognition algorithm on the collected human voice signals, and will not be frequently triggered by environmental noise, thereby reducing the processor's resource consumption.

[0082] like Figure 19 As shown, the audio output circuit 14 includes a voltage follower, the input of which is connected to the output of the bandpass filter circuit 13, and the output of which is connected to the ADC pin of the chip 16 that executes the speech recognition algorithm.

[0083] like Figure 20 As shown, the interrupt trigger circuit 15 includes a non-inverting amplifier 151, a rectifier unit 152, a normally closed relay circuit 153, and a falling edge signal circuit 154.

[0084] The input terminal of the inverting amplifier 151 is connected to the output terminal of the bandpass filter circuit 13 to amplify audio signals in the human voice frequency band;

[0085] The input terminal of the rectifier unit 152 is connected to the output terminal of the in-phase amplifier 151, and is used to rectify the audio signal in the human voice frequency band and output the rectified audio signal in the human voice frequency band to the falling edge signal circuit 154.

[0086] The falling edge signal circuit 154 responds to the audio signal in the human voice frequency band received at the input terminal and sends a falling edge signal as an interrupt trigger signal to the interrupt pin of the chip 16 that executes the speech recognition algorithm;

[0087] The drive unit of the normally closed relay circuit 153 responds to the high-level signal output by the output pin of the chip 16 executing the speech recognition algorithm, and shuts off the connection between the input terminal of the falling edge signal circuit 154 and the output terminal of the rectifier unit 152, so as to stop the falling edge signal circuit 154 from receiving audio signals in the human voice frequency band.

[0088] It should be noted that in this embodiment, the audio signal of the human voice channel output by the bandpass filter current is divided into two paths. One path passes through the audio output circuit 14 to transmit the audio signal of the human voice channel to the ADC pin of the chip 16 executing the speech recognition algorithm, thereby controlling the smart desktop. The other path passes through the interrupt trigger circuit 15 to enable the chip 16 executing the speech recognition algorithm to start the target ADC module, thereby performing speech processing on the audio signal transmitted by the audio output circuit 14, in order to control the smart desktop.

[0089] On the other hand, in one embodiment, a control method for a smart desktop is also provided. The method is applied to a chip 16 that executes a speech recognition algorithm, the chip 16 being connected to the aforementioned control device for the smart desktop. The method includes:

[0090] When an interrupt is detected from the target interrupt pin, the target ADC module is started according to preset parameters; the target interrupt pin is the interrupt pin connected to the interrupt trigger circuit 15, and the target ADC module is the ADC module corresponding to the ADC pin connected to the audio output circuit 14.

[0091] Since only audio signals in the human voice frequency band can pass through the bandpass filter circuit 13, in this embodiment, the ADC module of chip 16 only starts when a human voice signal is detected, instead of running continuously. Because the ADC module does not start, there is no audio signal that chip 16 needs to process, saving chip 16 overhead. On the other hand, once a human voice signal is detected, the interrupt trigger circuit 15 will trigger chip 16 to start the corresponding ADC module, ensuring that the monitoring of human voice signals is not missed, and that the module will only respond to human voice signals, thus eliminating the possibility of no startup caused by environmental noise.

[0092] In one embodiment, the method further includes:

[0093] Step S401: When an interrupt initiated from the target interrupt pin is detected, a countdown begins according to a preset duration; the remaining duration of the countdown is the remaining duration of the target ADC module being in the startup state.

[0094] In step S402, before the countdown ends, a high-level signal is continuously output through the target output pin; the target output pin is the output pin connected to the drive unit of the normally closed relay circuit 153.

[0095] In step S403, when the countdown ends, the target output pin stops outputting a high-level signal.

[0096] like Figure 20 As shown, when a high-level signal is continuously output through the target output pin, the normally closed relay k will open, thus preventing the human voice signal collected by the microphone 11MIC from triggering an interrupt in the chip 16, thereby not affecting the chip 16's processing of the voice signal. Therefore, this embodiment provides a solution to the problem of frequent interruptions caused by the human voice signal in the circuit during the chip 16's processing of the human voice signal. When the preset duration is 3 minutes, that is, the remaining time for the ADC module to be in the start-up state is 3 minutes, and the countdown has 1 minute left, then the remaining time for the ADC module to be in the start-up state is 1 minute. If the countdown ends, the start-up state of the target ADC module needs to be stopped, and the audio signal input to the ADC pin should no longer be responded to. Since the ADC module's response to the audio signal has been stopped, the triggering capability of the interrupt trigger circuit 15 to the interrupt pin needs to be restored, that is, the target output pin is controlled to stop outputting a high-level signal. At this time, Vin is no longer high, so the electromagnet N is de-energized, the normally closed relay returns to the connected state, and the rectifier unit 152 and the falling edge signal circuit 154 are reconnected. Once microphone 11MIC detects an audio signal in the human voice frequency band again, the interrupt can be triggered again.

[0097] Specifically, the method further includes:

[0098] If a signal input is detected from the ADC module during the countdown, the countdown is reset.

[0099] Understandably, once the ADC module receives a voice signal in the human voice frequency band within a preset time, such as 3 minutes, the countdown should be reset to maintain continuous monitoring of the audio signal through the ADC module. Therefore, resetting the countdown can maintain continuous monitoring of the user's audio signal, ensuring continuous monitoring even when the user is speaking for a long time, thus improving the user experience.

[0100] On the other hand, the control device for the smart desktop also includes a microphone array connected to a chip 16 that executes a voice recognition algorithm. The smart desktop is mounted on the armrest of a sofa chair, and the method further includes:

[0101] When an interrupt is detected from the target interrupt pin, the ADC module connected to the microphone array is started according to preset parameters;

[0102] The sofa chair is controlled based on the audio signals collected by the microphone array.

[0103] Specifically, the control method for the sofa chair will be described below through Examples 1 to 5.

[0104] Before describing the embodiments in detail, in order to understand the contribution of the sofa chair control method proposed in this application to the prior art, it is necessary to briefly explain the relevant background art as follows:

[0105] Smart furniture offers intelligent control to improve user convenience. With integrated voice recognition, users simply speak commands to activate the furniture. The controller collects and recognizes the user's voice signal, then controls the furniture based on the recognition results without interrupting the user's current use of its functions. This eliminates the need to search for remote controls or physical buttons, significantly improving ease of use. For example, if a user is lying on a smart sofa with their eyes closed and wants to adjust its massage or heating functions, they can do so without opening their eyes or moving, simply by speaking the command to activate the corresponding function.

[0106] Smart furniture such as sofas and chairs, placed in living rooms or other common areas of the home, is often used by only one user at a time. When a user controls the furniture using voice recognition, they are susceptible to interference from other people speaking or television sounds in the same space. For example, the user's voice may mix with the voice of someone sitting next to the sofa or the sound of the television, causing interference between sound sources and making it difficult to effectively distinguish and extract the target sound source, thus reducing the clarity and quality of the voice signal. Research indicates that related technologies can utilize microphone arrays for sound source localization combined with beamforming technology to enhance the voice signal in a specific frequency range, enabling effective distinction and extraction of the target sound source, thereby improving the accuracy of voice recognition. For instance, Patent Document 1 discloses a scheme that uses microphone array technology to collect only the sound of a designated frequency range (main frequency range) for voice control and mask the remaining frequency ranges, which can improve the accuracy of voice recognition. Furthermore, Patent Document 1 also discloses a solution for user sound source crossing the sound zone due to user movement. That is, after the user moves to another sound zone, it is considered that the user's sound source has crossed from the previous main sound zone to another sound zone, so it is necessary to update the user's latest location to the main sound zone.

[0107] If the solution in Patent Document 1 is applied to smart furniture scenarios such as sofas and chairs, the area surrounded by the sofa and chair frame (including the outer side of the armrests and backrest) can be used as the main sound zone. By collecting and responding to the sound only in the main sound zone, the sound signal quality and speech recognition accuracy can be improved. Furthermore, when the user uses the sofa and chair (i.e., lying down or sitting on the sofa and chair), since the user does not move, the problem of the user's sound source crossing the sound zone as described in Patent Document 1 will not be encountered.

[0108] However, in the voice control scenario of sofa chairs, there is a problem of non-user sound source crossing the sound zone. That is, sofa chairs are usually placed in the living room and close to other chairs. Therefore, the heads of other people in the living room or sitting in chairs close to the sofa chair can easily touch the boundary of the main sound zone of the sofa chair, or even enter the main sound zone of the sofa chair. This phenomenon is defined as the non-user sound source crossing the sound zone problem.

[0109] Since smart furniture such as sofas and chairs are used in public spaces with multiple users, and there is a problem of non-user sound sources crossing the sound zone, the target speech collected from the main sound zone of the sofa and chair will include not only the user's voice, but also the voices of users sitting in chairs next to the sofa and chair, which will reduce the clarity and quality of the speech signal and the accuracy of speech recognition.

[0110] Patent Document 1, Chinese Patent, Publication No. CN111986678B, Patent Title: A Voice Acquisition Method and Device for Multi-channel Speech Recognition, Publication Date: 2023-12-29.

[0111] This invention provides an intelligent furniture controller and control method that can dynamically adjust the range of the intelligent furniture's response sound zone to match the user's mouth position based on the user's sitting posture. This results in a smaller response sound zone centered on the sound source, reducing the probability of non-user sound sources entering the response sound zone, thereby obtaining higher quality speech signals and improving speech recognition accuracy. The following examples 1 to 5 provide a detailed description.

[0112] Referring to Figure 1, the intelligent desktop control method provided in this application is applicable to the sofa chair in Figure 1. The sofa chair includes a seat cushion and a backrest, a first pressure sensor array deployed on the seat cushion, and a second pressure sensor array deployed on the backrest. As shown in Figure 1, the plane where the seat cushion is located is the xoy plane of the rectangular coordinate system calibrated by the microphone array, that is, the z component of the plane where the seat cushion is located is 0. The plane where the backrest is located is the yoz plane, that is, the x component of the plane where the backrest is located is 0. The origin O of the coordinate system is located at the intersection of the two planes. The backrest can rotate around the y-axis to adjust the angle of the backrest.

[0113] It's understandable that a microphone array can selectively receive sound from any specific area in space while blocking out other areas. This is primarily achieved through beamforming and sound source localization technologies. The specific implementation steps are as follows:

[0114] Sound source localization: First, the location of the target sound source needs to be determined. This is usually done by analyzing the sound signals captured by a microphone array. By using the time difference of arrival (TDOA) between the sound signals arriving at different microphones, the location of the sound source in space can be estimated.

[0115] Beamforming: Once the location of a sound source is determined, beamforming technology can be used to "point" it to that specific area. Beamforming is a signal processing technique that adjusts the signal from each microphone in a microphone array to amplify signals from a specific direction while suppressing signals from other directions. This method can create a highly directional sensing area, or "beam."

[0116] Digital signal processing: Beamforming is achieved through digital signal processing algorithms. These algorithms calculate how to adjust the signal from each microphone in the microphone array to focus on the target area. This typically involves time delay, weighting, and phase adjustment of the signal.

[0117] Dynamic adjustment: In practical applications, if the target sound source moves in space, the system can dynamically adjust the beam direction in order to continuously focus on the moving sound source.

[0118] The following description, in conjunction with the accompanying drawings and embodiments, illustrates the technical contributions of this application to the prior art.

[0119] Example 1:

[0120] As shown in Figure 16, this embodiment provides a control method for a smart desktop, the method including:

[0121] Step S101: When the sofa chair is detected to switch from standby mode to use mode, the preset initial range is used as the response sound zone.

[0122] Specifically, standby mode refers to the state where no user is sitting on the sofa chair, while usage mode refers to the state where a user is sitting on the sofa chair. The state can be determined 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, it is considered to be in usage mode; otherwise, it is considered to be in standby mode.

[0123] As shown in Figure 1, the initial range refers to the spatial range swept by the backrest plane along the positive x-direction when it moves to the side of the seat cushion with a larger x-value. The backrest height is set to 1m. When a normal adult user sits upright in the sofa chair, their mouth will be within the initial range. When the user needs to bend over while sitting in the sofa chair, their mouth will also be within the initial range. Therefore, using the preset initial range as the response sound zone ensures that only the speech signal within this initial range is collected as input to the speech recognition module, thereby improving speech signal quality and speech recognition accuracy.

[0124] Step S102: When the microphone array acquires the first speech signal in the response area, the current user sitting posture is marked as the initial sitting posture and the sound source coordinates of the first speech signal are calculated.

[0125] For example, if a user sits on a sofa at 14:23, the system detects that the sofa has switched from standby to active mode at 14:23, and the response sound range is the preset initial range. Two minutes later, at 14:25, the user speaks "Xiao Zhi, Xiao Zhi, start the heating function" within the response sound range, which is the first voice signal. Because the microphone array only collects and sends voice within the response sound range to the voice recognition module, the voice signal quality and voice recognition accuracy are improved. Through sound source localization technology, the coordinates of the sound source of the first voice signal, i.e., the mouth, in the Cartesian coordinate system calibrated by the microphone array can be calculated, which are the sound source coordinates.

[0126] Step S103: Calculate the spatial range corresponding to the sound source coordinates of the first speech signal based on the first voice range correction algorithm, and update the spatial range to the response voice range corresponding to the initial sitting posture.

[0127] The first-range correction algorithm is specifically given in Examples 1 and 2 below. By employing the first-range correction algorithm, the range of the response range can be adjusted. It can dynamically adjust the range of the sofa's response range according to the user's sitting posture to match the user's mouth position, resulting in a smaller response range centered on the sound source. This reduces the probability of non-user sound sources entering the response range, thereby obtaining higher quality speech signals and improving speech recognition accuracy.

[0128] Step S104: When a first type of change in the user's sitting posture is detected, the response tone zone corresponding to the latest user sitting posture is calculated based on the second tone zone correction algorithm.

[0129] Understandably, once the response sound range has been updated from its initial range to a spatial range that matches the initial sitting posture, the range of the response sound range will be dynamically adjusted immediately once a change in the user's sitting posture is detected. This ensures that the user can maintain the quality of the voice signal while dynamically using the sofa chair, thereby improving the accuracy of voice recognition.

[0130] As shown in Figure 2, the posture of a user sitting on a sofa without touching the backrest is defined as the first posture. In this posture, only the first pressure sensor array on the seat cushion plane is triggered by the user. In this embodiment, the initial sitting posture is the first posture.

[0131] In this embodiment, the calculation of the spatial range corresponding to the sound source coordinates of the first speech signal based on the first voice region correction algorithm specifically includes:

[0132] The spatial range (x, y, z) corresponding to the sound source coordinates of the first speech signal is calculated using the following formula:

[0133]

[0134] in, In the initial sitting posture, the coordinates of the center point P0 of the geometric shape formed by the pressure sensors triggered by the user in the first pressure sensor array on the surface of the seat cushion are given. r is the distance from the center point P0 to the sound source coordinates of the first voice signal. θ is the preset human body swing angle, 0°≤θ≤45°.

[0135] As shown in Figure 3, in the initial sitting posture, the four pressure sensors on the sofa chair near the x-axis, enclosed by the dashed box, are touched and pressure is applied. These four pressure sensors are connected by the solid lines in Figure 3 to form a quadrilateral, with its center of gravity at P0. It should be noted that the coordinates of each pressure sensor in the microphone array's calibrated coordinate system are pre-calibrated at the factory and written into the storage device, and can be retrieved at any time. As shown in Figure 5, the sound source coordinates of the first voice signal are Q, the dashed line represented by m is the seat cushion plane, i.e., the xoy plane, and S1 is used in Figure 5 to represent the coordinates of the center of gravity of the geometric shape formed by the pressure sensors triggered by the user. It can be seen that the distance from Q to S1 is the distance from the point where the user's buttocks contact the seat cushion to their mouth. Generally, when a user sits on a sofa in the same posture, they may bend over, lower their head, or turn their head. These actions will cause the user's mouth, i.e., the sound source position, to change. Therefore, Formula 1 reduces the response range from the initial range while still leaving room for upper body movement, without the need for frequent modifications to the response range. As shown in Figure 5, Formula 1 reduces the range of the response range from the hexahedron corresponding to the initial range to a cone-like range, improving the quality of the speech signal without the need for frequent modifications to the response range.

[0136] In this embodiment, the readings of the four pressure sensors in Figure 3 are used to represent the initial sitting posture. For example, when the pressure sensors on a sofa chair represent the user's sitting posture, the data structure of the user's sitting posture can be constructed by using whether the pressure sensors have readings. It is known that the first pressure sensor array (M1) has 12 pressure sensors and the second pressure sensor array (M2) has 16 pressure sensors. Each pressure sensor is numbered to obtain the user's sitting posture data represented by two binary arrays: M1=[000000011110], M2=[00000000000000000]. This data indicates that under the current user sitting posture, pressure sensors numbered 2, 3, 4, and 5 in the first pressure sensor array have readings, while the second pressure sensor array has not been triggered. As shown in Figure 4, the user's sitting posture data is M1=[000110011000], M2=[0000000000000000], indicating that under the current user sitting posture, pressure sensors numbered 4, 5, 8, and 9 in the first pressure sensor array are reading, while the second pressure sensor array is not triggered. Clearly, both Figures 3 and 4 belong to the first posture. When both belong to the first posture, any change in the user's sitting posture is called a first-type change.

[0137] Specifically, the first type of change in user posture refers to the situation where only the first pressure sensor array on the seat cushion surface is triggered by the user before and after the change in posture.

[0138] The calculation of the response tone range corresponding to the latest user sitting posture based on the second tone range correction algorithm specifically includes:

[0139] Step S201: Obtain the coordinates of the center point P1 of the geometric shape formed by the pressure sensors triggered by the user in the first pressure sensor array on the seat cushion plane under the latest sitting posture.

[0140] Figure 3 shows a schematic diagram before the user's sitting posture changes by the first type, and Figure 4 shows a schematic diagram after the user's sitting posture changes by the first type. It can be seen that the user maintains the first posture before and after the first type of change, but the user's buttocks have shifted position on the seat cushion plane. The change in user posture can be determined from the user's posture data. Given the coordinates of each sensor, P0 and p1 can be easily calculated using the method for finding the centroid of a geometric figure; this will not be elaborated upon here.

[0141] Step S202: Subtract P0 from P1 to obtain the translation offset. ;

[0142] Step S203: Add the translation offset to all coordinate points of the current response zone to obtain all coordinate points of the response zone corresponding to the latest sitting posture.

[0143] It is understandable that in steps S201 to S203, it is not necessary to use Formula 1 again to calculate all the coordinates of the response sound zone corresponding to the latest sitting posture after the user's sitting posture changes for the first time. Instead, a simple summation operation can be performed using the translation offset and the response sound zone before the first type of change (i.e., the current response sound zone in step S203). This reduces the amount of computation required to update the response sound zone and saves computer resources.

[0144] Furthermore, the method also includes:

[0145] Formula 1 was corrected using a third-range correction algorithm;

[0146] The revised formula is:

[0147]

[0148] Where d is the depth of the seat cushion sinking that was determined in advance through experiments;

[0149] Determine the seat cushion sink depth d using the following steps:

[0150] Acquire the pressure value measured by the first pressure sensor array on the seat cushion;

[0151] The seat cushion sinking depth d is determined by referring to the table based on the pressure value.

[0152] As shown in Figure 5, the dashed line represented by 'm' represents the seat cushion plane in standby mode, i.e., the x0y plane, while the dashed line represented by 'n' represents the seat cushion plane in use mode. It can be seen that the z-component of the 'n' plane is smaller than that of the 'm' plane, meaning that the seat cushion plane sinks when the user sits down. Formula 1 calculates the ideal state based on the seat cushion plane not sinking. Therefore, considering the sinking factor, a modified Formula 1 is needed. The sinking depth 'd' can be determined by looking up a table. The sinking depth is related not only to the user's weight but also to the sofa material. Therefore, manufacturers pre-test the sinking depth under different pressure values ​​for different sofa models before shipping to correct Formula 1, thereby improving the accuracy of the sound response zone division.

[0153] In one embodiment, the method further includes:

[0154] When the pressure value of the pressure sensor with the highest pressure value in the first pressure sensor array is greater than the difference between the pressure value of all other triggered pressure sensors, the coordinates of the pressure sensor with the highest pressure value are used as the coordinates of the center point of the geometric shape formed by the pressure sensors triggered by the user in the first pressure sensor array on the seat cushion plane under the user's sitting posture.

[0155] As shown in Figure 5, assuming four pressure sensors on the cushion are triggered in the first posture, and S1 in Figure 5 represents one of these pressure sensors with the largest value and a difference greater than the preset pressure difference between it and all other triggered pressure sensors, then S1 is directly used as the center of gravity. The reason is that when the user's head is in the center of the body, because the buttocks are convex on both sides and concave in the middle, both buttocks generally bear roughly the same weight. Therefore, two sets of pressure sensors on the cushion will generally have similar readings. At this time, the head is generally located between the two buttocks, and the center of gravity of the body's swing needs to be determined based on the geometric image's center of gravity, i.e., the coordinates of the center of gravity. When the body tilts, causing the head to be tilted to one side, the body's weight is mainly supported by one side of the buttocks, meaning the head is directly above that buttock. Therefore, the coordinates of pressure sensor S1, whose difference from all other triggered pressure sensors is greater than the preset pressure difference, can be directly used as the center of gravity of the body's swing. In other words, S1 is directly used as the coordinates of the center of gravity and substituted into Formula 1 to obtain a more accurate response range division effect.

[0156] Example 2

[0157] In this embodiment, the user's posture of sitting on the sofa chair with the backrest in contact with the backrest is defined as the second posture. At this time, the user's sitting posture is when both the first pressure sensor array on the seat cushion plane and the second pressure sensor array on the backrest are triggered by the user. In this embodiment, the initial sitting posture is the second posture.

[0158] The calculation of the spatial range corresponding to the sound source coordinates of the first speech signal based on the first voice region correction algorithm specifically includes:

[0159] The spatial range (x, y, z) corresponding to the sound source coordinates of the first speech signal is calculated using the following formula:

[0160]

[0161] in, Let R be the coordinates of the sound source of the first speech signal in the initial sitting position, R be the preset neck swing length (8cm≤R≤12cm), A, B, and C be the three components of the normal vector perpendicular to the plane of the backrest, and D be a constant obtained by substituting the coordinates of the plane of the backrest.

[0162] Unlike Example 1, which uses the buttocks as the center point of human body movement and calculates a cone-shaped range of motion allowing the user to bend over and lower their head without changing their sitting posture using Formula 1, this example considers the range of motion of the head (primarily the neck) when the user's backpack is in contact with the backrest and their back is not leaving the backrest. Instead of the range of motion of the waist considered in Example 1, this example prioritizes the range of motion of the head (primarily the neck) when the user's backpack is in contact with the backrest and their back is not leaving the backrest.

[0163] Therefore, in this embodiment, the range of the response sound zone calculated by Formula 2 is based on the mouth as the center and the length of the neck swing (the human neck is generally 8-12cm long) as the radius. First, the sphere is calculated. Then, the plane equation of the backrest plane is defined by the three components of the normal vector perpendicular to the plane of the backrest, A, B, and C. Simultaneously, the response sound zone is defined only at the intersection of the sphere and the front of the backrest (i.e., the side facing the user), because the area behind the backrest is not within the sofa and needs to be excluded. It can be understood that without adjusting the backrest tilt angle, the backrest plane is a yoz plane with a normal vector of (1,0,0), i.e., A=1, B=0, C=0. Substituting a coordinate on the backrest plane into this plane equation yields D.

[0164] In this embodiment, the response sound range set by Formula 2 is smaller than the initial range, which improves the quality of the voice signal. At the same time, it can leave room for head movement without changing the user's sitting posture, without the need to frequently modify the response sound range, thus reducing the consumption of computer resources.

[0165] Furthermore, the method also includes:

[0166] When a second type of change in the user's sitting posture is detected, the response tone zone corresponding to the latest user sitting posture is calculated based on the fourth tone zone correction algorithm. The second type of change in the user's sitting posture means that the second pressure sensor array on the backrest and the first pressure sensor array on the seat cushion are both triggered by the user before and after the change in the user's sitting posture.

[0167] The calculation of the response tone range corresponding to the latest user sitting posture based on the fourth tone range correction algorithm specifically includes:

[0168] Step S301: Obtain the coordinates of the center point P2 of the geometric shape formed by the pressure sensors triggered by the user in the second pressure sensor array on the backrest plane before the user's sitting posture changes.

[0169] Referring to Figure 7, before the second type of change in the user's sitting posture occurs, the user's sitting posture data is M1=[000000011110], M2=[0000000001100110].

[0170] Step S302: Obtain the coordinates of the center point P3 of the geometric shape formed by the pressure sensors triggered by the user in the second pressure sensor array on the backrest plane after the user's sitting posture changes.

[0171] Referring to Figure 8, after the user's sitting posture changes for the second time, the user's posture data is M1=[000110011000], M2=[0000011001100000].

[0172] Step S303: Subtract P2 from P3 to obtain the translation offset.

[0173] Step S304: Add the 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.

[0174] Figure 7 shows a schematic diagram before the user's sitting posture undergoes the second type of change, and Figure 8 shows a schematic diagram after the user's sitting posture undergoes the second type of change. It can be seen that the user maintains the second posture before and after the second type of change, but the user's back (due to the backpack causing head movement) shifts position on the backrest plane. The change in user posture can be determined using the user's posture data. Given the coordinates of each sensor, P2 and P3 can be easily calculated using the method for finding the centroid of a geometric figure; this will not be elaborated upon here.

[0175] It is understandable that in steps S301 to S304, it is not necessary to use Formula 2 again to calculate all the coordinate points of the response sound zone corresponding to the latest sitting posture after the user's sitting posture changes to the second type. Instead, a simple summation operation can be performed using the translation offset and the response sound zone before the second type of change (i.e., the current response sound zone in step S304). This reduces the amount of computation required to update the response sound zone and saves computer resources.

[0176] In one embodiment, the method further includes:

[0177] When a third type of change in the user's sitting posture is detected, the latest user sitting posture after the change is determined. The third type of change refers to the situation where the second pressure sensor array on the backrest is in a state triggered by the user and a state not triggered by the user before and after the change in the user's sitting posture. That is, the change in the user's sitting posture directly switches between the first posture and the second posture.

[0178] If the latest user sitting posture is the user sitting posture when only the first pressure sensor array on the seat cushion plane is triggered by the user, then the response tone zone corresponding to the latest user sitting posture is calculated based on the second tone zone correction algorithm.

[0179] If the latest user sitting posture is the 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 the user, then the response tone zone corresponding to the latest user sitting posture is calculated based on the fourth tone zone correction algorithm.

[0180] Specifically, in embodiment 3, as shown in Figure 9, the user switches from the first posture to the second posture, which is a third type of change. Specifically, the occurrence of the third type of change can be determined based on the user's sitting posture data. Referring to Figure 10, before the user's sitting posture undergoes the third type of change, the user's sitting posture data is M1=[000000011110], M2=[0000000000000000]. Referring to Figure 11, after the user's sitting posture undergoes the third type of change, the user's sitting posture data is M1=[000000011110], M2=[0000000001100110].

[0181] As can be seen from Examples 1 and 2, the response sound range of the user in the first posture or the second posture has been obtained respectively. Therefore, steps S201 to S203 (i.e., the second sound range correction algorithm) or steps S301 to S304 can be used directly to calculate the response sound range corresponding to the latest user sitting posture, so as to save computer overhead.

[0182] Specifically, in Example 4, as shown in Figure 12, the user switches from the second posture to the first posture, which is a third type of change. Specifically, the occurrence of the third type of change can be determined based on the user's sitting posture data. Referring to Figure 13, before the third type of change occurs, the user's sitting posture data is M1=[000110011000], M2=[0000011001100000]. Referring to Figure 14, after the third type of change occurs, the user's sitting posture data is M1=[000110011000], M2=[00000000000000000].

[0183] As can be seen from Examples 1 and 2, the response sound range of the user in the first posture or the second posture has been obtained respectively. Therefore, steps S201 to S203 (i.e., the second sound range correction algorithm) or steps S301 to S304 can be used directly to calculate the response sound range corresponding to the latest user sitting posture, so as to save computer overhead.

[0184] Example 5

[0185] As shown in Figure 15, in this embodiment, the method further includes:

[0186] When a fourth type of change in the user's sitting posture is detected, the response tone zone corresponding to the latest user sitting posture is calculated based on the fifth tone zone correction algorithm. The fourth type of change in the user's sitting posture refers to the change in the tilt angle of the backrest before and after the user's sitting posture changes when the second pressure sensor array on the backrest is triggered by the user.

[0187] The calculation of the response tone range corresponding to the latest user sitting posture based on the fifth tone range correction algorithm specifically includes:

[0188] Based on the change in the backrest tilt angle, determine the rotation matrix of the plane where the backrest is located before and after the change.

[0189] Based on the rotation matrix, all coordinate points of the current response sound zone are transformed to obtain all coordinate points of the response sound zone corresponding to the latest sitting posture;

[0190] The rotation matrix is:

[0191] α is the variation of the backrest tilt angle, 0°≤α≤60°.

[0192] It is understandable that when a user lies back on the sofa and does not move their backpack or buttocks, the position of their mouth will change as the backrest tilts. Therefore, the position of the response zone needs to be adjusted when the backrest tilts.

[0193] Specifically, in this embodiment, the backrest is rotated by an angle α around the y-axis. At this time, a rotation matrix of the plane rotating around the y-axis can be used to calculate the mapping relationship before and after the change in tilt angle, thereby speeding up the process of correcting the fourth type of change in pitch range.

[0194] For example, when a user is leaning against the backrest, which is the second posture, the corresponding response sound area (i.e., the response sound area when the backrest plane is at the adjusted tilt angle) has already been obtained in Example 2. If the backrest is rotated by an angle α, then a rotation matrix can be used to directly transform all the coordinates of the response sound area obtained in Example 2, thus converting it into the response sound area after the tilt angle is adjusted. For example, if α = 30 degrees, the new coordinates of point P(1, 2, 3) after rotating 30 degrees around the Y-axis are approximately (2.37, 2, 2.10).

[0195] In summary, as Figure 17 As shown, the user's sitting posture changes are divided into four types. Each type of change will use a corresponding vocal range correction algorithm to dynamically correct the range of the response vocal range, i.e., the five embodiments mentioned above, in order to obtain high-quality speech signals and thus improve the accuracy of speech recognition.

[0196] On the other hand, the present invention provides a sofa chair controller, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0197] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile 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 various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRA), direct RAM via Rambus (RDRA), direct memory bus dynamic RAM (DRDRAM), and dynamic RAM via Rambus (RDRAM), etc.

[0198] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A control method for an intelligent desktop, characterized in that, The method is applied to a chip that executes a speech recognition algorithm, the chip being connected to a control device of a smart desktop, and the method includes: When an interrupt is detected from the target interrupt pin, the target ADC module is started according to preset parameters; the target interrupt pin is an interrupt pin connected to the interrupt triggering circuit, and the target ADC module is the ADC module corresponding to the ADC pin connected to the audio output circuit. The control device of the smart desktop includes a microphone for acquiring audio signals; an amplifier circuit for amplifying the audio signals acquired by the microphone; a bandpass filter circuit for filtering audio signals in non-human voice frequency bands; the human voice frequency band range β is: 300Hz≤β≤5000Hz; an audio output circuit for transmitting the human voice frequency band audio signals to the ADC pin of the chip executing the speech recognition algorithm; an interrupt trigger circuit for sending an interrupt trigger signal to the interrupt pin of the chip executing the speech recognition algorithm in response to the received human voice frequency band audio signals; and a chip executing the speech recognition algorithm for executing the method. The interrupt trigger signal sent by the interrupt pin indicates that the method has detected an interrupt initiated from the target interrupt pin; The interrupt trigger circuit includes a non-inverting amplifier, a rectifier unit, a normally closed relay circuit, and a falling edge signal circuit. The input of the non-inverting amplifier is connected to the output of the bandpass filter circuit to amplify the audio signal in the human voice frequency band. The input of the rectifier unit is connected to the output of the non-inverting amplifier to rectify the audio signal in the human voice frequency band and output the rectified audio signal in the human voice frequency band to the falling edge signal circuit. In response to the audio signal in the human voice frequency band received at the input, the falling edge signal circuit sends a falling edge signal as an interrupt trigger signal to the interrupt pin of the chip executing the speech recognition algorithm. The drive unit of the normally closed relay circuit responds to the high-level signal output by the output pin of the chip executing the speech recognition algorithm, and shuts off the connection between the input of the falling edge signal circuit and the output of the rectifier unit to stop the falling edge signal circuit from receiving the audio signal in the human voice frequency band.

2. The control method for a smart desktop according to claim 1, characterized in that, The audio output circuit includes a voltage follower, the input of which is connected to the output of a bandpass filter circuit, and the output of which is connected to the ADC pin of a chip that executes a speech recognition algorithm.

3. The control method for a smart desktop according to claim 1, characterized in that, The method further includes: When an interrupt is detected from the target interrupt pin, a countdown begins according to a preset duration; the remaining duration of the countdown is the remaining duration of the target ADC module being in the startup state. Before the countdown ends, a high-level signal is continuously output through the target output pin; the target output pin is the output pin connected to the drive unit of the normally closed relay circuit. When the countdown ends, the control target output pin stops outputting a high-level signal.

4. The control method for a smart desktop according to claim 3, characterized in that, The method further includes: If a signal input is detected from the ADC module during the countdown, the countdown is reset.

5. The control method for a smart desktop according to claim 1, characterized in that, The control device for the smart desktop also includes a microphone array connected to a chip that executes a voice recognition algorithm. The smart desktop is mounted on the armrest of a sofa chair. The method further includes: When an interrupt is detected from the target interrupt pin, the ADC module connected to the microphone array is started according to preset parameters; The sofa chair is controlled based on the audio signals collected by the microphone array.

6. The control method for a smart desktop according to claim 5, characterized in that, The method includes: When the sofa chair is detected to switch from standby mode to use mode, the preset initial range is used as the response sound zone; When the microphone array acquires the first speech signal in the response area, the current user sitting posture is marked as the initial sitting posture and the sound source coordinates of the first speech signal are calculated. The spatial range corresponding to the sound source coordinates of the first speech signal is calculated based on the first voice region correction algorithm, and the spatial range is updated to the response voice region corresponding to the initial sitting posture. When a first type of change in the user's sitting posture is detected, the response tone zone corresponding to the latest user sitting posture is calculated based on the second tone zone correction algorithm.

7. The control method for a smart desktop according to claim 6, characterized in that, The sofa chair includes a seat cushion and a backrest, a first pressure sensor array deployed on the seat cushion, and a second pressure sensor array deployed on the backrest. The initial sitting posture is the user sitting posture when only the first pressure sensor array on the seat cushion plane is triggered by the user. The calculation of the spatial range corresponding to the sound source coordinates of the first speech signal based on the first voice region correction algorithm specifically includes: The spatial range (x, y, z) corresponding to the sound source coordinates of the first speech signal is calculated using the following formula: ； in, In the initial sitting posture, the coordinates of the center point P0 of the geometric shape formed by the pressure sensors triggered by the user in the first pressure sensor array on the surface of the seat cushion are given. r is the distance from the center point P0 to the sound source coordinates of the first voice signal. θ is the preset human body swing angle, 0°≤θ≤45°.

8. The control method for a smart desktop according to claim 7, characterized in that, The first type of change in user posture refers to the situation where only the first pressure sensor array on the seat cushion surface is triggered by the user before and after the change in user posture. The calculation of the response tone range corresponding to the latest user sitting posture based on the second tone range correction algorithm specifically includes: Obtain the coordinates of the centroid point P1 of the geometric shape formed by the pressure sensors triggered by the user in the first pressure sensor array on the seat cushion plane under the latest sitting posture. Subtracting P0 from P1 gives the translation offset. ; Add the translation offset to all coordinate points of the current response zone to obtain all coordinate points of the response zone corresponding to the latest sitting posture.

Images