Method and device for determining responding device

Abstract

The present invention discloses a method and apparatus for determining a responding device. The method comprises: when M devices receive the same voice control signal, if the signal-to-noise ratio of the voice control signal on N of the M devices meets a preset judgment condition, obtaining a distance value between each of the M devices and the sound source; determining an average distance value of the M devices based on the distance value of each of the M devices; and selecting a device from the N devices as the sole responding device to the voice control signal based on the average distance value; wherein M and N are both integers greater than or equal to 2, and N is equal to or less than M. The technical solution provided by the present invention aims to solve the problem in the prior art that the actual response of devices in voice control scenarios does not meet the requirements.

Description

Technical Field

[0001] The present invention relates to the field of electrical equipment, and in particular to a method and device for determining a response device. Background Art

[0002] In a smart home system, when there are multiple devices with voice response functions in the same space, when a voice wake-up command is given, only one device can be controlled to wake up, that is, the unique wake-up function, to facilitate voice control.

[0003] In actual applications, the user plans to wake up device A, but the device actually woke up is device B, resulting in a problem in which the actual response does not meet the requirements. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method and apparatus for determining a responding device, aiming to solve the problem in the prior art that the actual response of a device in a voice control scenario does not meet the requirements.

[0005] To achieve the above object, the present invention proposes a method for determining a responding device, characterized by comprising:

[0006] When M devices receive the same voice control signal, if the signal-to-noise ratio of the voice control signal received by N of the M devices meets a preset judgment condition, obtain the distance value between each of the M devices and the sound source position;

[0007] Determine an average distance value of the M devices based on the distance value of each device in the M devices;

[0008] selecting, according to the average distance value, a device from the N devices as the only device that responds to the voice control signal;

[0009] Wherein, M and N are both integers greater than or equal to 2, and N is equal to or less than M.

[0010] Preferably, the method further comprises:

[0011] Determine whether the M devices are in the same network;

[0012] When the M devices are not in the same network, obtaining the distance value between each of the M devices and the sound source position is not allowed.

[0013] Preferably, the method further comprises:

[0014] Detecting whether the unique response function of the M devices is enabled;

[0015] When the device is not in use, it is not allowed to obtain the distance value between each of the M devices and the sound source position.

[0016] Preferably, the network where the M devices are located and / or the usage status of the unique response function are obtained through messages broadcast by the M devices.

[0017] Preferably, the method further comprises:

[0018] Select one device from M devices as the broadcasting device;

[0019] controlling) the broadcasting device to send a first message, wherein the first message includes the device identification of the broadcasting device and the network identification of the network; and / or configuring the use status of the unique response function of the broadcasting device to be enabled, and after completing the configuration operation, controlling the broadcasting device to broadcast a second message, wherein the second message includes the device identification of the broadcasting device and the use status of the unique response function;

[0020] A response message is received to a message broadcast by a broadcasting device.

[0021] Preferably, obtaining the distance value between each of the M devices and the sound source position includes:

[0022] Determining, for each of the M devices, a time difference between a reception time and a transmission time of the voice control signal;

[0023] A distance value corresponding to the respective time difference value is determined for each of the M devices.

[0024] Preferably, the time difference is obtained by the following methods, including:

[0025] Acquire a first signal energy value of the voice control signal output at the sound source position; and a second signal energy value of the voice control signal received by the device;

[0026] A cross-correlation value between the first signal energy value and the second signal energy value is calculated to obtain the time difference.

[0027] Preferably, selecting a device from the N devices as the only device responding to the voice control signal according to the average distance value includes:

[0028] Determine whether the distance value of each device in the N devices is less than the average distance value, and obtain a determination result corresponding to each device;

[0029] From the devices whose judgment result is that the distance value is less than the average distance value, a unique device that responds to the voice control signal is selected.

[0030] Preferably, the method further comprises:

[0031] The device that is the only responding device is notified to perform a response operation.

[0032] Preferably, it is applied to a central device among M devices, wherein the central device is determined according to resource information of the M devices.

[0033] A storage medium, characterized in that a computer program is stored in the storage medium, wherein the computer program is configured to execute any of the methods described above when running.

[0034] An electronic device comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute any of the methods described above.

[0035] A device for determining a response device, characterized by comprising the electronic device described above.

[0036] In the technical solution of the present invention, when M devices receive the same voice control signal, if the signal-to-noise ratio of the voice control signals on N devices meets a preset judgment condition, the distance value between each of the M devices and the sound source position is obtained, and based on the distance value of each of the M devices, the average distance value of the M devices is determined. Based on the average distance value, one device is selected from the N devices as the only device that responds to the voice control signal, thereby achieving the selection of the only responding device based on the average distance value of the M devices and improving the accuracy of determining the only responding device. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0038] Figure 1 A flowchart of a method for determining a responding device provided in Example 1 of the present application;

[0039] Figure 2 A flowchart of a method for determining a responding device provided in Example 2 of the present application;

[0040] Figure 3 A flowchart of a method for determining a responding device provided in Example 3 of the present application;

[0041] Figure 4 A flowchart of a method for determining a responding device provided in Embodiment 4 of the present application;

[0042] Figure 5 This is a flowchart of the method for determining the responding device provided in Example 5 of the present application.

[0043] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0045] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0046] In addition, the terms "first," "second," and so on, used in this disclosure are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referenced. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this disclosure, "plurality" means at least two, such as two or three, unless otherwise specifically defined.

[0047] In the present invention, unless otherwise specified or limited, the terms "connection" and "fixation" should be understood in a broad sense. For example, "fixation" can mean fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; internal communication between two elements or interaction between two elements, unless otherwise specified. Those skilled in the art will be able to understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0048] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in this field can implement it. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0049] After analyzing the existing technology, it is found that the reasons for the above problems are as follows:

[0050] The existing method of determining the only wake-up device is based on the signal-to-noise ratio (SNR) of the current environment. For example, the device with the largest SNR value can be set as the only wake-up device.

[0051] If the above method is used, when there are multiple devices with the largest signal-to-noise ratio values, it is impossible to select a unique wake-up device, and it is easy to select an incorrect unique wake-up device.

[0052] In addition, after selecting the wrong response device, due to the failure to take timely action, the wrong selection situation continues to occur in subsequent selections, further aggravating the occurrence of the device wrong selection problem.

[0053] Based on the above analysis, the embodiments of the present application provide the following solutions, including:

[0054] Example 1

[0055] Figure 1 This is a flow chart of the method for determining the response device provided in Example 1 of this application. Figure 1 As shown, the method includes:

[0056] Step 101: When M devices receive the same voice control signal, if the SNR of the voice control signal received by N devices meets a preset judgment condition, obtain the distance value between each of the M devices and the sound source position;

[0057] Wherein, M≥N≥2, and M and N are both integers;

[0058] In one exemplary embodiment, M devices all have voice response capabilities. For example, the M devices are household appliances located in the same space, such as an air conditioner, a television, a refrigerator, and a smart speaker. For example, there may be an air conditioner, a television, and a smart speaker in the same space; or there may be two air conditioners and one television in the same space.

[0059] In an exemplary embodiment, the voice control command may be a wake-up command, a parameter setting command, or a power on / off command.

[0060] In an exemplary embodiment, the judgment condition is used to screen candidate devices that may serve as the only responding device, and the number N of the candidate devices is at least two.

[0061] The judgment conditions are described below using the maximum SNR value A among M devices as an example. The judgment conditions include:

[0062] Condition 1: The device with the highest SNR among all devices;

[0063] Condition 2: The judgment condition is that the device with the maximum SNR value and the device whose SNR among all devices meets the preset difference condition;

[0064] Among them, if there are at least two devices with an SNR value of A, at least one of condition 1 and condition 2 can be selected as the judgment condition; if there is only one device with an SNR value of A, only condition 1 can be selected as the judgment condition.

[0065] The selection of the judgment conditions based on the above situation can ensure that there are at least two devices as alternatives.

[0066] In condition 2, the difference condition is a ratio threshold, and the ratio threshold is used to determine whether the SNR value of the device is close to the maximum value;

[0067] For example, the difference between the SNR value and the maximum SNR value of a certain device is calculated, and then the ratio of the difference to the maximum SNR value is calculated to obtain the ratio information; if the ratio information is less than the ratio threshold, it means that the SNR value of the device is close to the maximum SNR value and can be used as an alternative device; otherwise, it means that the SNR value of the device is not close to the maximum SNR value and cannot be used as an alternative device.

[0068] In an exemplary embodiment, the distance between the device and the sound source can be obtained by each device through self-testing. All distance testing methods in the prior art are applicable to this step.

[0069] Step 102: Determine the average distance value corresponding to the M devices based on the distance value of each device;

[0070] In an exemplary embodiment, the average distance value of the M devices may be obtained by calculating the sum of the M distance values and then calculating the ratio of the sum to the value M.

[0071] Step 103: Select one device from the N devices as the only device that responds to the voice control signal based on the average distance value;

[0072] Based on the usage habits of voice control operations, it is known that the voice control instructions at the sound source location are usually operated on devices around the sound source location. Therefore, the N devices as candidate devices can be screened based on the average distance value to determine the only responding device.

[0073] Compared with the prior art that screens unique responding devices based solely on SNR values, the solution provided in the embodiment of the present invention combines the average distance values of M devices for further screening, further constraining the conditions for determining the unique responding device, thereby improving the accuracy of determining the unique responding device.

[0074] It should be noted that the above method is applied to the central device among M devices, that is, one device selected from the M devices is used as the central device (also called a server device), and the other M-1 devices are used as edge devices.

[0075] The selection of the central device is completed before receiving the voice control signal.

[0076] Here, one device may be pre-selected as the central device; or the central device may be determined from M devices according to a preset selection condition.

[0077] The selection criteria may be device resource information; this resource information is used to determine the computing power or processing power of each device, or to determine the size of the device's currently idle resources. For example, the device with the greatest computing power may be selected as the central device; or the device with the greatest currently idle resources may be selected as the central device. The device's resources may be at least one of computing resources, storage resources, and network resources.

[0078] The selection of the central device may be performed periodically to ensure that the determined central device complies with the resource information of the current M devices.

[0079] The method provided in the embodiment of the present application is as follows: when M devices receive the same voice control signal, if the signal-to-noise ratio of the voice control signal received by N devices meets the preset judgment condition, the distance value between each device in the M devices and the sound source position is obtained, and the average distance value corresponding to the M devices is determined based on the distance value of each device; based on the average distance value, one device is selected from the N devices as the only device that responds to the voice control signal, thereby realizing the selection of the only responding device based on the average distance value of the M devices, and improving the accuracy of determining the only responding device

[0080] Example 2

[0081] Figure 2 This is a flow chart of the method for determining the responding device provided in the second embodiment of the present application. Figure 2 As shown, the method includes:

[0082] Step 201: Determine whether the M devices are in the same network;

[0083] Wherein, M≥2, and M is an integer;

[0084] In one exemplary embodiment, M devices all have voice response capabilities. For example, the M devices are household appliances located in the same space, such as an air conditioner, a television, a refrigerator, and a smart speaker. For example, there may be an air conditioner, a television, and a smart speaker in the same space; or there may be two air conditioners and one television in the same space.

[0085] In an exemplary embodiment, a device identification list of devices connected to a preset network is pre-stored, and the device identification list and the device identifications of the M devices are used to determine whether they are in the same network.

[0086] The network where the M devices are located can be obtained through the broadcast messages sent by each device.

[0087] If the M devices are in the same network, step 202 is executed; otherwise, the process ends.

[0088] By judging whether the M devices are in the same network, and thus determining whether the M devices are in the same spatial range, devices irrelevant to the control object of the voice control signal can be effectively excluded, thereby improving the accuracy of the determined unique response device.

[0089] Step 202: Determine whether the unique response function set on the M devices is enabled;

[0090] When the unique response functions set on the M devices are all in the enabled state, step 203 is executed; otherwise, the process ends.

[0091] Before determining the unique response device, the unique response function of each device is controlled to be turned on, which can ensure that only one device responds to the voice control signal and reduce the influence of devices that do not turn on the unique response function on the determination result.

[0092] For example, consider a scenario where there are three devices in a room: device 1, device 2, and device 3. The unique response function for devices 1 and 2 is enabled, while the unique response function for device 3 is disabled. If device 1 is determined to be the only device responding to a voice control signal, and device 3 doesn't have the unique response function enabled, it will automatically respond to the voice control signal. This means that both the device without the unique response function enabled and the identified unique device will respond, which doesn't meet actual requirements.

[0093] The present invention can effectively avoid the occurrence of the above situation by detecting that the unique response functions of M devices are all turned on.

[0094] Step 203: When M devices receive the same voice control signal, if the SNR of the voice control signal received by N devices meets a preset judgment condition, obtain the distance value between each of the M devices and the sound source position;

[0095] Wherein, M≥N≥2, and N is an integer;

[0096] In an exemplary embodiment, the voice control command may be a wake-up command, a parameter setting command, or a power on / off command.

[0097] In an exemplary embodiment, the judgment condition is used to screen candidate devices that may serve as the only responding device, and the number N of the candidate devices is at least two.

[0098] The judgment conditions are described below using the maximum SNR value A among M devices as an example. The judgment conditions include:

[0099] Condition 1: The device with the highest SNR among all devices;

[0100] Condition 2: The judgment condition is that the device with the maximum SNR value and the device whose SNR among all devices meets the preset difference condition;

[0101] Among them, if there are at least two devices with an SNR value of A, at least one of condition 1 and the condition can be selected as the judgment condition; if there is only one device with an SNR value of A, only condition 1 can be selected as the judgment condition.

[0102] The selection of the judgment conditions based on the above situation can ensure that there are at least two devices as alternatives.

[0103] In condition 2, the difference condition is a ratio threshold, and the ratio threshold is used to determine whether the SNR value of the device is close to the maximum value;

[0104] For example, the difference between the SNR value and the maximum SNR value of a certain device is calculated, and then the ratio of the difference to the maximum SNR value is calculated to obtain the ratio information; if the ratio information is less than the ratio threshold, it means that the SNR value of the device is close to the maximum SNR value and can be used as an alternative device; otherwise, it means that the SNR value of the device is not close to the maximum SNR value and cannot be used as an alternative device.

[0105] In an exemplary embodiment, the distance between the device and the sound source can be obtained by each device through self-testing. All distance testing methods in the prior art are applicable to this step.

[0106] Step 204: Determine the average distance value corresponding to the M devices based on the distance value of each device;

[0107] In an exemplary embodiment, the average distance value of the M devices may be obtained by calculating the sum of the M distance values and then calculating the ratio of the sum to the value M.

[0108] Step 205: Select one device from the N devices as the only device that responds to the voice control signal based on the average distance value;

[0109] Based on the usage habits of voice control operations, it is known that the voice control instructions at the sound source location are usually operated on devices around the sound source location. Therefore, the N devices as candidate devices can be screened based on the average distance value to determine the only responding device.

[0110] Compared with the prior art that only screens unique responding devices based on SNR values, the solution provided by the embodiment of the present invention combines the average distance value of M devices for further screening, further constraining the determination conditions of the unique responding device, thereby improving the accuracy of determining the unique responding device.

[0111] It should be noted that the above method is applied to the central device among M devices, that is, one device selected from the M devices is used as the central device (also called a server device), and the other M-1 devices are used as edge devices.

[0112] The selection of the central device is completed before receiving the voice control signal.

[0113] Here, one device may be pre-selected as the central device; or the central device may be determined from M devices according to a preset selection condition.

[0114] The selection criteria may be device resource information; this resource information is used to determine the computing power or processing power of each device, or to determine the size of the device's currently idle resources. For example, the device with the greatest computing power may be selected as the central device; or the device with the greatest currently idle resources may be selected as the central device. The device's resources may be at least one of computing resources, storage resources, and network resources.

[0115] The selection of the central device may be performed periodically to ensure that the determined central device complies with the resource information of the current M devices.

[0116] The method provided in an embodiment of the present application is as follows: when M devices receive the same voice control signal, if the signal-to-noise ratio of the voice control signal received by N devices meets a preset judgment condition, the distance value between each device in the M devices and the sound source position is obtained, and based on the distance value of each device, the average distance value corresponding to the M devices is determined; based on the average distance value, a device is selected from the N devices as the unique response device to the voice control signal, thereby achieving the selection of the unique response device based on the average distance value of the M devices, and improving the accuracy of determining the unique response device. By determining whether the M devices are in the same network, and thus determining whether the M devices are in the same spatial range, devices unrelated to the control object of the voice control signal can be effectively excluded, thereby improving the accuracy of the determined unique response device. Before determining the unique response device, the unique response function of each device is controlled to be enabled, which can ensure that only one device responds to the voice control signal and reduce the impact of devices that do not have the unique response function enabled on the determination result.

[0117] Example 3

[0118] Figure 3 This is a flow chart of the method for determining the responding device provided in Example 3 of this application. Figure 3 As shown, the method includes:

[0119] Step 301: Select a device as a broadcast device;

[0120] In an exemplary embodiment, the broadcasting device may be pre-set; or, after detecting a voice control signal, randomly selected; or, after detecting a voice control signal, determined according to a preset selection strategy.

[0121] Step 302: Configure the broadcast device's unique response function to be enabled.

[0122] Step 303: Control the broadcast device to send a broadcast message, where the broadcast message includes the device identifier of the broadcast device, the network identifier of the network, and whether the unique response function is enabled;

[0123] The broadcast device may send the broadcast message based on the User Datagram Protocol (UDP).

[0124] Step 304: Receive a response message corresponding to the broadcast message;

[0125] Since the device receiving the broadcast message will feed back a response message based on the format of the broadcast message, each response message includes the device identifier of the sender of the response message, the network identifier of the network, and whether the unique response function is enabled.

[0126] The use of broadcast messages to complete information collection is highly effective and simple to implement.

[0127] Step 305: Determine whether the M devices are in the same network based on the broadcast message and the response message; and whether the unique response function set on the M devices is enabled.

[0128] Wherein, M≥2, and M is an integer;

[0129] In one exemplary embodiment, M devices all have voice response capabilities. For example, the M devices are household appliances located in the same space, such as an air conditioner, a television, a refrigerator, and a smart speaker. For example, there may be an air conditioner, a television, and a smart speaker in the same space; or there may be two air conditioners and one television in the same space.

[0130] In an exemplary embodiment, a device identification list of devices connected to a preset network is pre-stored, and the device identification list and the device identifications of the M devices are used to determine whether they are in the same network.

[0131] By judging whether the M devices are in the same network, and thus determining whether the M devices are in the same spatial range, devices irrelevant to the control object of the voice control signal can be effectively excluded, thereby improving the accuracy of the determined unique response device.

[0132] Before determining the unique response device, the unique response function of each device is controlled to be turned on, which can ensure that only one device responds to the voice control signal and reduce the influence of devices that do not turn on the unique response function on the determination result.

[0133] For example, consider a scenario where there are three devices in a room: device 1, device 2, and device 3. The unique response function for devices 1 and 2 is enabled, while the unique response function for device 3 is disabled. If device 1 is determined to be the only device responding to a voice control signal, and device 3 doesn't have the unique response function enabled, it will automatically respond to the voice control signal. This means that both the device without the unique response function enabled and the identified unique device will respond, which doesn't meet actual requirements.

[0134] The present invention can effectively avoid the occurrence of the above situation by detecting that the unique response functions of M devices are all turned on.

[0135] If the M devices are in the same network and the unique response function is enabled, step 306 is executed; otherwise, the process ends.

[0136] Step 306: When the M devices receive the same voice control signal, if the SNR of the voice control signal received by the N devices meets a preset judgment condition, obtain the distance value between each of the M devices and the sound source position;

[0137] Wherein, M≥N≥2, and N is an integer;

[0138] In an exemplary embodiment, the voice control command may be a wake-up command, a parameter setting command, or a power on / off command.

[0139] In an exemplary embodiment, the judgment condition is used to screen candidate devices that may serve as the only responding device, and the number N of the candidate devices is at least two.

[0140] The judgment conditions are described below using the maximum SNR value A among M devices as an example. The judgment conditions include:

[0141] Condition 1: The device with the highest SNR among all devices;

[0142] Condition 2: The judgment condition is that the device with the maximum SNR value and the device whose SNR among all devices meets the preset difference condition;

[0143] Among them, if there are at least two devices with an SNR value of A, at least one of condition 1 and the condition can be selected as the judgment condition; if there is only one device with an SNR value of A, only condition 1 can be selected as the judgment condition.

[0144] The selection of the judgment conditions based on the above situation can ensure that there are at least two devices as alternatives.

[0145] In condition 2, the difference condition is a ratio threshold, and the ratio threshold is used to determine whether the SNR value of the device is close to the maximum value;

[0146] For example, the difference between the SNR value and the maximum SNR value of a certain device is calculated, and then the ratio of the difference to the maximum SNR value is calculated to obtain the ratio information; if the ratio information is less than the ratio threshold, it means that the SNR value of the device is close to the maximum SNR value and can be used as an alternative device; otherwise, it means that the SNR value of the device is not close to the maximum SNR value and cannot be used as an alternative device.

[0147] In an exemplary embodiment, the distance between the device and the sound source can be obtained by each device through self-testing. All distance testing methods in the prior art are applicable to this step.

[0148] Step 307: Determine the average distance value corresponding to the M devices based on the distance value of each device;

[0149] In an exemplary embodiment, the average distance value of the M devices may be obtained by calculating the sum of the M distance values and then calculating the ratio of the sum to the value M.

[0150] Step 308: Select one device from the N devices as the only device that responds to the voice control signal based on the average distance value;

[0151] Based on the usage habits of voice control operations, it is known that the voice control instructions at the sound source location are usually operated on devices around the sound source location. Therefore, the N devices as candidate devices can be screened based on the average distance value to determine the only responding device.

[0152] Compared with the prior art that screens unique responding devices based solely on SNR values, the solution provided in the embodiment of the present invention combines the average distance values of M devices for further screening, further constraining the conditions for determining the unique responding device, thereby improving the accuracy of determining the unique responding device.

[0153] It should be noted that the above method is applied to the central device among M devices, that is, one device selected from the M devices is used as the central device (also called a server device), and the other M-1 devices are used as edge devices.

[0154] The selection of the central device is completed before receiving the voice control signal.

[0155] Here, one device may be pre-selected as the central device; or the central device may be determined from M devices according to a preset selection condition.

[0156] The selection criteria may be device resource information; this resource information is used to determine the computing power or processing power of each device, or to determine the size of the device's currently idle resources. For example, the device with the greatest computing power may be selected as the central device; or the device with the greatest currently idle resources may be selected as the central device. The device's resources may be at least one of computing resources, storage resources, and network resources.

[0157] The selection of the central device may be performed periodically to ensure that the determined central device complies with the resource information of the current M devices.

[0158] The method provided in an embodiment of the present application is as follows: when M devices receive the same voice control signal, if the signal-to-noise ratio of the voice control signal received by N devices meets a preset judgment condition, the distance value between each device in the M devices and the sound source position is obtained, and based on the distance value of each device, the average distance value corresponding to the M devices is determined; based on the average distance value, one device is selected from the N devices as the only response device to the voice control signal, thereby realizing the selection of the only response device based on the average distance value of the M devices, and improving the accuracy of determining the only response device. By judging whether the M devices are in the same network, and thus determining whether the M devices are in the same spatial range, it is possible to effectively exclude devices that are not related to the control object of the voice control signal, thereby improving the accuracy of the determined only response device. Before determining the only response device, the unique response function of each device is controlled to be turned on, which can ensure that only one device responds to the voice control signal, reducing the impact of devices that do not have the unique response function turned on on the determination result. The use of broadcast messages to complete information collection is highly effective and simple to implement.

[0159] Example 4

[0160] Figure 4 This is a flow chart of the method for determining the response device provided in the fourth embodiment of the present application. Figure 4 As shown, the method includes:

[0161] Step 401: Select a device as a broadcast device;

[0162] In an exemplary embodiment, the broadcasting device may be pre-set; or, after detecting a voice control signal, randomly selected; or, after detecting a voice control signal, determined according to a preset selection strategy.

[0163] Step 402: Configure the broadcast device's unique response function to be enabled.

[0164] Step 403: Control the broadcast device to send a broadcast message, where the broadcast message includes the device identifier of the broadcast device, the network identifier of the network, and whether the unique response function is enabled;

[0165] The broadcast device may send the broadcast message based on the User Datagram Protocol (UDP).

[0166] Step 404: Receive a response message corresponding to the broadcast message;

[0167] Since the device receiving the broadcast message will feed back a response message based on the format of the broadcast message, each response message includes the device identifier of the sender of the response message, the network identifier of the network, and whether the unique response function is enabled.

[0168] The use of broadcast messages to complete information collection is highly effective and simple to implement.

[0169] Step 405: Determine whether the M devices are in the same network based on the broadcast message and the response message; and whether the unique response function set on the M devices is enabled.

[0170] Wherein, M≥2, and M is an integer;

[0171] In one exemplary embodiment, M devices all have voice response capabilities. For example, the M devices are household appliances located in the same space, such as an air conditioner, a television, a refrigerator, and a smart speaker. For example, there may be an air conditioner, a television, and a smart speaker in the same space; or there may be two air conditioners and one television in the same space.

[0172] In an exemplary embodiment, a device identification list of devices connected to a preset network is pre-stored, and the device identification list and the device identifications of the M devices are used to determine whether they are in the same network.

[0173] By judging whether the M devices are in the same network, and thus determining whether the M devices are in the same spatial range, devices irrelevant to the control object of the voice control signal can be effectively excluded, thereby improving the accuracy of the determined unique response device.

[0174] Before determining the unique response device, the unique response function of each device is controlled to be turned on, which can ensure that only one device responds to the voice control signal and reduce the influence of devices that do not turn on the unique response function on the determination result.

[0175] For example, consider a scenario where there are three devices in a room: device 1, device 2, and device 3. The unique response function for devices 1 and 2 is enabled, while the unique response function for device 3 is disabled. If device 1 is determined to be the only device responding to a voice control signal, and device 3 doesn't have the unique response function enabled, it will automatically respond to the voice control signal. This means that both the device without the unique response function enabled and the identified unique device will respond, which doesn't meet actual requirements.

[0176] The present invention can effectively avoid the occurrence of the above situation by detecting that the unique response functions of M devices are all turned on.

[0177] If the M devices are in the same network and the unique response function is enabled, step 406 is executed; otherwise, the process ends.

[0178] Step 406: When the M devices receive the same voice control signal, if the SNR of the voice control signal received by the N devices meets a preset judgment condition, determine the time difference between the reception time and the transmission time of the voice control signal for each of the M devices;

[0179] Wherein, M≥N≥2, and N is an integer;

[0180] In an exemplary embodiment, the voice control command may be a wake-up command, a parameter setting command, or a power on / off command.

[0181] In an exemplary embodiment, the judgment condition is used to screen candidate devices that may serve as the only responding device, and the number N of the candidate devices is at least two.

[0182] In an exemplary embodiment, a first signal energy value and a second signal energy value are obtained, wherein the first signal energy value is the energy value when the voice control signal is output; the second signal energy value is the energy value when the voice control signal is received; and a cross-correlation value is calculated for the first signal energy value and the second signal energy value to obtain a time difference.

[0183] Among them, the energy value s of the voice control signal at time t is r The expression of (t) is as follows:

[0184] s r (t) = Af s (t-t0)+n0(t);

[0185] Among them, A represents the coefficient, f s represents the amplitude, t0 is the initial time value, and n0 is the noise energy value;

[0186] Based on the expression, the time difference R between receiving and sending audio is obtained by performing cross-correlation operation on the received signal and the sent signal. r,s (t).

[0187]

[0188] Step 407: Determine the distance between each of the M devices and the sound source based on the time difference between each of the M devices and a preset propagation speed value;

[0189] D=(T r- T s )V sound =R r,s (t)V sound

[0190] Where D represents the distance value, T r Indicates the reception time of the voice control signal, Ts Indicates the sending time of the voice control signal, V sound Indicates the propagation speed value.

[0191] Step 408: Determine the average distance value corresponding to the M devices based on the distance value of each device;

[0192] In an exemplary embodiment, the average distance value of the M devices may be obtained by calculating the sum of the M distance values and then calculating the ratio of the sum to the value M.

[0193] Step 409: Select one device from the N devices as the only device that responds to the voice control signal based on the average distance value;

[0194] Based on the usage habits of voice control operations, it is known that the voice control instructions at the sound source location are usually operated on devices around the sound source location. Therefore, the N devices as candidate devices can be screened based on the average distance value to determine the only responding device.

[0195] In an exemplary embodiment, the distance value of each device in the N devices is compared with the average distance value to obtain a comparison result corresponding to each device, and a unique response device is selected for the voice control signal from the devices whose comparison results are less than the average distance value.

[0196] If the device's distance value is less than or equal to the average distance value, it indicates that the device is close to the sound source and has a high probability of being the only responding device. Conversely, if the device's distance value is greater than the average distance value, it indicates that the device is far from the sound source and has a low probability of being the only responding device. Therefore, a single responding device can be selected from the N candidate devices based on the average distance value.

[0197] Compared with the prior art that only screens unique responding devices based on SNR values, the solution provided by the embodiment of the present invention combines the average distance value of M devices for further screening, further constraining the determination conditions of the unique responding device, thereby improving the accuracy of determining the unique responding device.

[0198] Step 410: Notify the device that is the only responding device to perform a response operation.

[0199] In an exemplary embodiment, the notification may be sent to M devices, so that the M devices determine that the process of determining the only responding device has ended based on the notification, thereby facilitating unified management of the devices.

[0200] It should be noted that the above method is applied to the central device among M devices, that is, one device selected from the M devices is used as the central device (also called a server device), and the other M-1 devices are used as edge devices.

[0201] The selection of the central device is completed before receiving the voice control signal.

[0202] Here, one device may be pre-selected as the central device; or the central device may be determined from M devices according to a preset selection condition.

[0203] The selection criteria may be device resource information; this resource information is used to determine the computing power or processing power of each device, or to determine the size of the device's currently idle resources. For example, the device with the greatest computing power may be selected as the central device; or the device with the greatest currently idle resources may be selected as the central device. The device's resources may be at least one of computing resources, storage resources, and network resources.

[0204] The selection of the central device may be performed periodically to ensure that the determined central device complies with the resource information of the current M devices.

[0205] The method provided in an embodiment of the present application, when M devices receive the same voice control signal, if the signal-to-noise ratio of the voice control signal received by N devices meets a preset judgment condition, obtains the distance value between each of the M devices and the sound source location, and determines the average distance value corresponding to the M devices based on the distance value of each device. Based on the average distance value, a device is selected from the N devices as the unique responding device to the voice control signal. This achieves the selection of the unique responding device based on the average distance value of the M devices, improving the accuracy of determining the unique responding device. By determining whether the M devices are in the same network and thus whether the M devices are in the same spatial range, devices unrelated to the control target of the voice control signal can be effectively excluded, thereby improving the accuracy of the determined unique responding device. Before determining the unique responding device, the unique response function of each device is enabled. This ensures that only one device responds to the voice control signal, reducing the impact of devices without the unique response function on the determination result. Using broadcast messages to complete information collection is highly effective and simple to implement. Using information about changes in signal energy values to determine transmission time, and thus the distance value between the device and the sound source location, is convenient and simple to implement.

[0206] Example 5

[0207] Figure 5 This is a flow chart of a method for determining a response device provided in an embodiment of the present application. Figure 5 As shown, the method includes:

[0208] Step 501: Enable the unique response function for the selected device A, where the mode of enabling the function can be set via voice.

[0209] The device A is a pre-selected central device, which may be pre-configured or selected from devices in the current local area network according to preset selection conditions.

[0210] Step 502: After receiving the voice wake-up word, device A searches for all devices in the current local area network that support unique responses through UDP multicast information;

[0211] UDP multicast information includes:

[0212] (1) Device information: including appliance category, SN number, IP address, and discovering all devices in the local area network that support unique wake-up;

[0213] (2) Unique wake-up switch update information, used to notify other devices in the local area network to update the unique response function to the on state.

[0214] Step 503: Receive response information to the multicast information feedback from other devices in the current local area network;

[0215] Step 504: Based on the response information of other devices, determine whether all devices supporting unique response in the current local area network have enabled the unique response function.

[0216] If yes, proceed to step 505; otherwise, continue to execute steps 503 and 504 until all devices supporting unique response in the current local area network have enabled the unique response function.

[0217] Step 505: Calculate the SNR of the voice signal of the wake-up word received by all devices in the local area network;

[0218] Here, description is made by taking as an example that the number of devices with the maximum SNR is at least two.

[0219]

[0220] Where SNR is the signal-to-noise ratio (dB); s(t) is the amplitude of the speech signal, ∑ t s(t) 2 is the pure speech energy; n(t) is the noise amplitude, ∑ t n(t) 2 is the noise energy.

[0221] Step 506: Calculate the distance D between all devices in the current local area network and the sound source location;

[0222] D=(T r -T s )V sound =R r,s (t)V sound

[0223] In the above expression, T s Indicates the time when the sound is emitted, T r The time when the sound is received, V sound The speed of sound in air, R r,s (t) represents the time difference between the sound reception and the sound emission;

[0224] For example, let's take the case where the sound propagation process only experiences amplitude attenuation, time delay, and superimposed noise. The energy value of the signal is as follows:

[0225] s r (t) = Af s (t-t0)+n0(t)

[0226] The received signal energy is cross-correlated with the transmitted signal energy to obtain the time difference between the received and transmitted audio as follows:

[0227]

[0228] Step 507: Calculate the average distance D between the current local area network device and the sound source location. avr ;

[0229]

[0230] Where M is the number of devices in the network.

[0231] Step 508: Determine the unique responding device based on the SNR and the average distance value;

[0232] In the same environment, the energy of noise is basically the same. Therefore, the larger the SNR, the louder the sound, the stronger the energy, and the closer the distance to the device. If all judgments are made according to this strategy, it will cause the problem of non-proximity response. Therefore, the device with the largest SNR value is selected, and the distance D from the device to the sound source is determined to be greater than the average distance value D. avr If it is greater than the average distance, the device is a non-responding device; if it is less than the average distance, the device is the only responding device.

[0233] The method provided in Example 5 of the present application utilizes the average distance value of the distance values of all devices in the space to the sound source position, combined with the SNR value, to achieve a multi-information fusion method to uniquely respond to the trackside milk egg of the device, which can significantly improve the problem of non-unique response and non-proximal response.

[0234] An embodiment of the present invention provides a storage medium storing a computer program. When the computer program is executed, any of the above methods can be executed.

[0235] An embodiment of the present invention provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor can execute any of the above methods when running the computer program in the memory.

[0236] An embodiment of the present invention provides a device for determining a response device, including the electronic device described above. The electronic device can be set as an independent module on a device with a voice response function, or integrated into a processor of a device with a voice response function, for determining whether the device serves as a response device for a voice control signal.

[0237] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. All equivalent structural transformations made based on the contents of the present invention's description and drawings, or direct / indirect applications in other related technical fields, are included in the patent protection scope of the present invention.

Claims

1. A method for determining a response device, characterized in that: include: When M devices receive the same voice control signal, if the signal-to-noise ratio of the voice control signal received by N of the M devices meets a preset judgment condition, obtain the distance value between each of the M devices and the sound source position; Determine an average distance value of the M devices based on the distance value of each device in the M devices; selecting, according to the average distance value, a device from the N devices as the only device that responds to the voice control signal; The method further comprises: Detecting whether the unique response function of the M devices is enabled; When the device is not in use, it is not allowed to obtain the distance value between each of the M devices and the sound source; Wherein, M and N are both integers greater than or equal to 2, and N is equal to or less than M.

2. The method according to claim 1, wherein The method further comprises: Determine whether the M devices are in the same network; When the M devices are not in the same network, obtaining the distance value between each of the M devices and the sound source position is not allowed.

3. The method according to claim 1 or 2, wherein: The network where the M devices are located and / or the usage status of the unique response function are obtained through messages broadcast by the M devices.

4. The method according to claim 3, wherein The method further comprises: Select one device from M devices as the broadcasting device; controlling the broadcasting device to send a first message, wherein the first message includes a device identifier of the broadcasting device and a network identifier of the network; and / or configuring a unique response function of the broadcasting device to be enabled, and after completing the configuration operation, controlling the broadcasting device to broadcast a second message, wherein the second message includes the device identifier of the broadcasting device and the usage status of the unique response function; A response message is received to a message broadcast by a broadcasting device.

5. The method according to claim 1, wherein The obtaining of the distance between each of the M devices and the sound source position includes: Determining, for each of the M devices, a time difference between a reception time and a transmission time of the voice control signal; A distance value corresponding to the respective time difference value is determined for each of the M devices.

6. The method according to claim 5, wherein The time difference is obtained by: Acquire a first signal energy value of the voice control signal output at the sound source position; and a second signal energy value of the voice control signal received by the device; A cross-correlation value between the first signal energy value and the second signal energy value is calculated to obtain the time difference.

7. The method according to claim 1, wherein The step of selecting, according to the average distance value, a device from the N devices as the only device that responds to the voice control signal comprises: Determine whether the distance value of each device in the N devices is less than the average distance value, and obtain a determination result corresponding to each device; From the devices whose judgment result is that the distance value is less than the average distance value, a unique device that responds to the voice control signal is selected.

8. The method according to claim 1, wherein The method further comprises: The device that is the only responding device is notified to perform a response operation.

9. The method according to claim 1, wherein The method is applied to a central device among M devices, wherein the central device is determined according to resource information of the M devices.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 9 when executed.

11. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 9.

12. A device for determining a response device, characterized in that: Comprising the electronic device as claimed in claim 11.

Images