Election Method and System for Interactive Voice Devices

Abstract

The embodiments of this specification provide a method and system for electing an interactive voice device. The method includes: when each voice device picks up a preset wake-up word issued by a user, calculating a corresponding score value and determining whether the score value is higher than the score value threshold corresponding to the voice device; if so, generating an election participation request according to the score value of the voice device and sending it to the decision-making device; the decision-making device elects a voice device from the voice devices that send the election participation requests as the response voice device for this wake-up request according to the score values in each election participation request. The present invention makes the control of smart home appliances in the home convenient and flexible.

Description

Technical Field

[0001] One or more embodiments of this specification relate to the technical field of voice devices, and in particular, to a method and system for electing an interactive voice device. Background Art

[0002] Voice recognition technology is the most widely used human-computer interaction technology at present. Users issue voice commands to control voice devices to perform corresponding operations. For example, controlling an air conditioner to turn on or off. The entire process of voice interaction control includes several key links: voice wake-up, sending voice commands, device execution of actions, and device voice feedback. Voice wake-up means pre-setting one or more proprietary words for a voice device. Users can activate the voice device in the wake-up waiting state through this proprietary word and enter the voice command recognition waiting state. Users can further issue various voice commands. After receiving the commands, the voice device executes the corresponding command actions and feeds back the result of the command execution through the built-in playback component of the device to prompt the user.

[0003] However, there are multiple smart home appliances in a household. When a user at a certain location wants to control a smart home appliance that is relatively far away, the user needs to walk to the location of a certain smart home appliance to issue a command, and then the smart home appliance will execute the command. For example, when the user is in the bathroom and wants to control the TV in the living room to turn off, the voice picked up by the user in the bathroom has a relatively poor effect, and the control effect on the TV in the living room is relatively poor at this time. The user can only walk near the TV to issue a command. It can be seen that this control method is very inconvenient and inflexible. Summary of the Invention

[0004] One or more embodiments of this specification describe a method and system for electing an interactive voice device.

[0005] In a first aspect, this specification provides a method for electing an interactive voice device. At least two voice devices are distributed in the entire space of a household. The at least two voice devices include smart home appliances. The voice modules in the smart home appliances have the functions of voice pickup and voice feedback. The at least two voice devices are all communicatively connected to a cloud platform for controlling voice devices in the entire space; the method includes:

[0006] When each voice device picks up a preset wake-up word issued by a user, it calculates a corresponding score value and determines whether the score value is higher than the score value threshold corresponding to the voice device; if so, it generates the election participation request according to the score value of the voice device and sends the election participation request to a decision-making device; wherein, the decision-making device is a smart home appliance among the at least two voice devices, and the score value is used to represent the probability that the user wakes up the voice device.

[0007] The decision-making device elects a voice device from each of the voice devices that send the election participation requests as the response voice device for the current wake-up request according to the score values in each of the election participation requests; wherein, the response voice device is used to pick up the voice task issued by the user after the preset wake-up word, and send the picked-up voice task to the cloud platform, so that the cloud platform parses the voice task and sends the task obtained after parsing to the corresponding target smart home appliance for execution.

[0008] In a second aspect, an election system for an interactive voice device provided by an embodiment of the present invention includes at least two voice devices and a cloud platform distributed in the entire space of a home. The at least two voice devices include smart home appliances. The voice module in the smart home appliances has functions of voice pickup and voice feedback. The at least two voice devices are all communicatively connected to the cloud platform; the cloud platform is used to control the voice devices in the entire space; wherein:

[0009] Each voice device is configured to: when picking up a preset wake-up word issued by the user, calculate a corresponding score value, and determine whether the score value is higher than the score value threshold corresponding to the voice device; if so, generate the election participation request according to the score value of the voice device, and send the election participation request to the decision-making device; wherein, the decision-making device is a smart home appliance among the at least two voice devices, and the score value is used to represent the probability that the user wakes up the voice device.

[0010] The decision-making device is configured to: elect a voice device from each of the voice devices that send the election participation requests as the response voice device for the current wake-up request according to the score values in each of the election participation requests; wherein, the response voice device is used to pick up the voice task issued by the user after the preset wake-up word, and send the picked-up voice task to the cloud platform, so that the cloud platform parses the voice task and sends the task obtained after parsing to the corresponding target smart home appliance for execution.

[0011] The election method and system for an interactive voice device provided by the embodiments of this specification have the following beneficial effects:

[0012] (1) In the embodiments of the present invention, a voice device has a corresponding score value threshold. When the voice device picks up the wake-up word, it will calculate the score value, and then compare its score value with its score value threshold. Only when the score value is higher than the score value threshold will it generate an election participation request. Because when the score value is less than or equal to the score value threshold, the probability that the voice device is selected is very low, so there is no need to participate in the election. In this way, low-probability voice devices can be filtered out, reducing the computing pressure on the decision-making device, reducing the data transmission volume, and improving the working efficiency of the decision-making device.

[0013] (2) The final decision-making device elects one voice device from among the various voice devices that sent the election participation request as the response voice device for this wake-up request. After determining the response voice device, the voice command of the user is picked up by using this response voice device, and then the voice command is sent to the cloud platform. After the cloud platform analyzes the voice command, the target smart home appliance is determined according to the analysis content, and then the corresponding processing is performed by using this target smart home appliance. The response voice device and the target smart home appliance may not be in the same space, and the user does not have to walk to the location of the target smart home appliance to control the target smart home appliance. For example, when the user issues a command to turn off the TV in the living room in the bathroom, the voice terminal in the bathroom picks up this command and sends it to the cloud platform, and the cloud platform then controls the TV in the living room to turn off. It can be seen that the embodiments of the present invention can make the control of smart home appliances in the home convenient and flexible, and can greatly improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present specification. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0015] Figure 1 It is a schematic flowchart of the method for electing an interactive voice device in an embodiment of the present specification;

[0016] Figure 2 It is a schematic diagram of the distribution of various smart home appliances in the entire space of a family in an embodiment of the present specification;

[0017] Figure 3a It is a schematic diagram of a voice terminal in an embodiment of the present invention;

[0018] Figure 3b It is a schematic diagram of the distribution of various smart home appliances and various voice terminals in the entire space of a family in an embodiment of the present invention;

[0019] Figure 4 It is a structural block diagram of an interactive voice device election system in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The following describes the solutions provided in the present specification in conjunction with the drawings.

[0021] In a first aspect, an embodiment of the present invention provides a method for electing an interactive voice device.

[0022] The applicable scenarios of the solution provided by the embodiments of the present invention may include, but are not limited to, the following scenarios:

[0023] There are multiple voice devices distributed within a household, and these voice devices include various smart home appliances. For example, refer to Figure 2 , there is a washing machine, a refrigerator, two wall-mounted air conditioners, a cabinet air conditioner, and two televisions installed throughout the space of a household. These smart home appliances all have voice modules, and the voice modules in the smart home appliances can pick up voice commands issued by users and send the voice commands to the cloud platform. The voice module can also perform voice feedback under the control of the cloud platform, that is, inform users of the execution status of some devices by means of voice broadcast.

[0024] However, since there are no smart home appliances installed in areas such as balconies, entrance areas, and bathrooms, the voice pickup function in these areas will be relatively poor. Therefore, voice terminals can be installed in these areas. Refer to Figure 3a and 3b , voice terminals are installed in positions such as the entrance area, balcony, dining room, study, secondary bathroom, master bathroom, head of the bed in the master bedroom, and head of the bed in the children's room. The voice terminal can pick up the voice issued by the user and can also access the home local area network through WIFI. Since the volume of the voice terminal is very small and it is inconvenient to install an amplifying module, the voice terminal does not have the function of voice broadcast.

[0025] It can be understood that since it is difficult for the optimal voice pickup range of each smart home appliance to cover all corners within a household, there may sometimes be a situation where the voice commands of users cannot be responded to. Therefore, in the embodiments of the present invention, voice terminals are installed in areas within the household that are not covered by smart home appliances. In this way, the optimal voice pickup ranges of each smart home appliance and each voice terminal can cover the entire space within a household.

[0026] Of course, the voice terminal can also have the function of light indication. For example, when a voice terminal is awakened as a responding voice device, it can be prompted by means of a breathing light. When a voice terminal is used as a responding voice device and the cloud platform controls the corresponding target smart home appliance to successfully execute an instruction, it can control the voice terminal used as the responding voice device to flash a green light three times for prompt. When the cloud platform controls the corresponding target smart home appliance to fail to execute an instruction, it can control the voice terminal used as the responding voice device to flash a yellow light three times for prompt.

[0027] Among them, all voice devices within a household (including each voice terminal and each smart home appliance) are communicatively connected to the cloud platform, so that the cloud platform can control each voice device within the household. Of course, an application program can be installed on the user's mobile terminal, and through this application program, the control, configuration, etc. of each voice terminal within the household can also be performed.

[0028] Example 1: A user utters the wake-up word "Changhong Xiaobai" on the balcony, and the voice terminal on the balcony is awakened. The voice terminal prompts the user that it has been awakened by means of a breathing light. Subsequently, the user says "Turn off the TV in the master bedroom", and the voice terminal picks up this voice command and sends the voice command to the cloud platform. After the cloud platform parses the voice command, it controls the TV in the master bedroom to turn off.

[0029] In the above Example 1, the voice terminal on the balcony is the response voice device among the interactive voice devices to be selected in the embodiments of the present invention. The function of the response voice device is to pick up the voice command issued by the user after being awakened, and then send the voice command to the cloud platform, so that the cloud platform will parse the voice command and then send it to the execution device (i.e., the target smart home appliance in the following text) for corresponding processing.

[0030] In addition to the response voice device, the interactive voice device to be selected in the embodiments of the present invention further includes a feedback voice device. The so-called feedback voice device refers to feeding back the processing result of the execution device to the user in the form of voice broadcast after the execution device performs corresponding processing, so that the user can understand the situation.

[0031] In practice, the response voice device and the feedback voice device can be the same device or different devices, which depends on the specific situation and will be described in detail below.

[0032] In summary, in a scenario, at least two voice devices are distributed in the entire space of a household. The at least two voice devices include smart home appliances and voice terminals. The union of the optimal sound pickup ranges of the smart home appliances and the voice terminals can cover the entire space; the voice module in the smart home appliances has the functions of voice pickup and voice feedback, and the voice module of the voice terminal has the function of voice pickup; the at least two voice devices are all communicatively connected to a cloud platform for controlling voice devices in the entire space.

[0033] In addition to being applicable to the above scenario, the method provided by the embodiments of the present invention is also applicable to a scenario where only smart home appliances exist in a household, and the voice module of the smart home appliance has the functions of sound pickup and sound feedback.

[0034] It is understandable that if some optional embodiments of the present invention involve voice terminals, the applicable scenarios for such specific embodiments are as follows: Voice devices are distributed throughout the entire space of a household. The voice devices include smart home appliances and voice terminals. The union of the optimal voice pickup ranges of each smart home appliance and each voice terminal can cover the entire space; the voice module in the smart home appliance has voice pickup and voice feedback functions, and the voice module of the voice terminal has voice pickup function; all the voice devices are communicatively connected to a cloud platform for controlling voice devices throughout the space. For example, a household includes at least two smart home appliances and at least two voice terminals.

[0035] It is understandable that if some optional embodiments of the present invention do not involve voice terminals, the applicable scenarios for such specific embodiments can be the scenarios described in the previous paragraph, or of course, can also be the scenario: a scenario where only smart home appliances are included in a household, and the voice module in the smart home appliance has voice pickup and voice feedback functions.

[0036] The embodiments of the present invention provide a method for electing an interactive voice device. Among interactive voice devices, the more important one is the answering voice device. Refer to Figure 1 , this method may include the following steps S100 - S200 to elect the answering voice device. Of course, before executing S000 - S100 of this solution, it is necessary to determine the scoring value threshold through the following step S000:

[0037] S000. The cloud platform obtains the historical scoring values of each voice device in the entire space; according to the historical scoring values of each voice device, determines the regular data for the voice device to be selected as the answering voice device; according to the regular data, sets the corresponding scoring value threshold for the voice device; and sends the scoring value threshold of each voice device to the voice device.

[0038] Among them, the historical scoring value of a voice device is the scoring value of the voice device each time it picks up a wake-up word within a preset historical time period, and the scoring value is used to represent the probability that the user wakes up the voice device; the regular data of a voice device is the corresponding historical scoring value range when the voice device is elected as the answering voice device within the preset historical time period.

[0039] It is understandable that a voice device has a scoring value threshold. Therefore, the cloud platform needs to determine the corresponding regular data according to the historical scoring value of each voice device, and then set the scoring value threshold for the corresponding voice device according to the regular data.

[0040] Among them, the scoring value can reflect the probability that a user wakes up a voice device. The higher the scoring value of a voice device, the greater the probability that the user wakes up the voice device. The calculation of the scoring value can be considered from multiple perspectives. For example, the distance between the user and the voice device, the sound pickup angle, the sound intensity, etc. After each voice device picks up the wake-up word, it calculates its own scoring value based on various factors, and then can send the scoring value to the cloud platform for storage.

[0041] For example, the cloud platform obtains the scoring values of each voice device in the family every time the wake-up word is picked up within the past month. For example, the number of times the living room TV picks up the wake-up word is 100 times, so there will be 100 historical scoring values. Another example is that the number of times the wall-mounted air conditioner in the bedroom picks up the wake-up word is 80 times, and there will be 80 historical scoring values. For the living room TV, among the corresponding 100 historical scoring values, the historical scoring values when the living room TV is selected as the answering voice device are screened out. Based on these screened historical scoring values, the regular data when the living room TV is selected as the answering voice device is summarized, that is, the historical scoring value interval corresponding to when the living room TV is selected as the answering voice device. The same method can be used for the wall-mounted air conditioner in the bedroom to determine the corresponding historical scoring value interval.

[0042] It can be understood that when the scoring value of a voice device falls within the historical scoring value interval, the probability that the voice device is selected as the answering voice device is higher than when the scoring value of the voice device falls outside the historical scoring value interval. When the scoring value of a voice device falls within the historical scoring value interval, it does not mean that this voice device will definitely be selected as the answering voice device.

[0043] After calculating the regular data of the voice device, a corresponding scoring value threshold can be set for this voice device according to the regular data. The scoring value threshold can be lower than the lower limit value of the historical scoring value interval. For example, the historical scoring value interval of a voice device is [80, 100], and the scoring value threshold set for this voice device can be 75.

[0044] After calculating the scoring value threshold of a voice device, the scoring value threshold is sent to the voice device, and in this way, this voice device will save it locally.

[0045] After obtaining the scoring value threshold, the following steps S100 - 200 can be executed:

[0046] S100. When each voice device picks up the preset wake-up word issued by the user, calculate the corresponding scoring value, and determine whether the scoring value is higher than the scoring value threshold corresponding to the voice device; if so, generate the election participation request according to the scoring value of the voice device, and send the election participation request to the decision-making device;

[0047] Among them, the decision-making device is an intelligent appliance among the at least two voice devices.

[0048] That is to say, when a voice device picks up a wake-up word, it calculates a corresponding score value according to factors such as distance, sound intensity, and pickup angle, and then compares the score value with its own score value threshold. If the score value is higher than its own score value threshold, it means that this voice device may be selected as the answering voice device. At this time, an election participation request is generated and sent to the decision-making device.

[0049] Of course, if the score value is less than or equal to its own score value threshold, it means that the probability of this voice device being selected as the answering voice device is very low. At this time, the voice device does not generate an election participation request, that is, it does not participate in the subsequent election process, which can filter out low-probability voice devices and improve the working efficiency of the decision-making device.

[0050] It can be understood that the score value of this voice device is included in the election participation request of a voice device.

[0051] S200. The decision-making device elects a voice device from the voice devices that send the election participation requests as the answering voice device for this wake-up request according to the score values in each of the election participation requests;

[0052] Among them, the answering voice device is used to pick up the voice task sent by the user after the preset wake-up word and send the picked-up voice task to the cloud platform, so that the cloud platform parses the voice task and sends the task obtained after parsing to the corresponding target intelligent appliance for execution.

[0053] That is to say, when the decision-making device receives election participation requests sent by multiple voice devices, it selects a voice device from the voice devices that send the election participation requests as the answering voice device for this time. The voice terminal selected as the answering voice device will pick up the voice task sent by the user and send the voice task to the cloud platform. In this way, the cloud platform will parse the voice task, and then know the user's needs, so as to control the target intelligent appliance to perform corresponding operations.

[0054] For example, the user says "Changhong Xiaobai" in the living room. Based on this wake-up request, the voice devices that pick up the wake-up word will calculate their respective scores, compare the scores with their own score thresholds, and generate election participation requests when their own scores are higher than their own score thresholds, and send the election participation requests to the decision-making device. The decision-making device selects a voice device from the various voice devices that send the election participation request as the answering voice device, and then the decision-making device informs the voice device. For example, the TV in the living room is selected as the answering voice device and responds "Yes", and then the user says "I'm a little hot". The TV in the living room picks up this voice and sends it to the cloud platform. The cloud platform parses this voice and obtains the parsed content. According to the parsed content, it can be known that the user wants to lower the temperature in the living room, so the cloud platform controls the cabinet air conditioner in the living room to turn on and enter the cooling mode. In this example, the cabinet air conditioner in the living room is the target smart home appliance.

[0055] In practice, the voice device selected as the answering voice device can be a smart home appliance or a voice terminal. For example, if a user initiates a wake-up request on the balcony, the voice terminal on the balcony is likely to be selected as the answering voice device.

[0056] In a specific implementation, the selecting of a voice device as the answering voice device from the voice devices that send the election participation request in S200 may include: the decision-making device specifically selects the voice device with the highest score as the answering voice device.

[0057] That is to say, the decision-making device selects the voice device with the highest score from the various voice devices that send the election participation request as the answering voice device. This method is simple and easy to implement.

[0058] Of course, in addition to the above methods, the step of selecting a voice device as the answering voice device from the various voice devices that send the election participation request in S200 may also include: the decision-making device selects a voice device as the answering voice device from the various voice devices that send the election participation request based on the score value and the product attributes of the voice device.

[0059] That is to say, while considering the scoring value, the product attributes of the voice device are also taken into account. For example, when the scoring values of two voice devices are similar, the voice device with a higher configuration can be selected as the response voice device. For example, among all the voice devices participating in the election, the scoring values of the TV in the master bedroom and the voice terminal in the master bedroom are the highest, and the scoring value of the voice terminal is slightly higher than that of the TV. However, at this time, the TV in the master bedroom can be selected as the response voice device because the TV can not only provide voice feedback but also play videos, music, etc. compared with the voice terminal. The TV can perform more functions, that is, the TV has a higher configuration than the voice terminal.

[0060] For another example, the scoring values of the TV in the master bedroom and the wall-mounted air conditioner in the master bedroom are the highest, and the scoring values of these two voice devices are similar. The TV can play videos, and the controller of the TV can perform more complex logical calculations compared with the controller of the air conditioner. Therefore, the TV is used as the response voice device.

[0061] It can be seen that in addition to considering the factor of the scoring value, the product attributes of the voice device itself are also considered. A voice device that can perform more functions and has a higher computing power can be used as the response voice device even if its scoring value is not the highest.

[0062] In specific implementation, the process of a voice device calculating its own scoring value is described below.

[0063] When the pick-up angle is within the preset range, the first calculation formula is used to calculate the scoring value corresponding to each voice device. The first calculation formula includes:

[0064] When r is within the first range, P2 = a * s + b / |r - 90|

[0065] When r is within the second range, P2 = b * s - a * |r - 90| + c

[0066] In the formula, P2 is the scoring value; s is the pick-up sound intensity; r is the pick-up angle; the first range is: r is greater than or equal to 60 and less than 80, or r is greater than 100 and less than or equal to 120; the second range is: r is greater than or equal to 80 and less than or equal to 100; a and b are preset weights, and a > b, c = 10 * a + b / 10, and the preset range is the union of the first range and the second range.

[0067] Among them, when r is within the first range, the greater the pickup intensity, the greater P2; the closer the pickup angle is to 90, the greater P2. Therefore, the wake-up score of a voice device with a high pickup intensity and a pickup angle close to 90 is relatively high. Moreover, when r is within the first range, the weight of the pickup sound intensity is a, and a is greater than b, indicating that more attention is paid to the pickup sound intensity at this time, that is to say, the pickup sound intensity is more important in this case.

[0068] Among them, when r is within the second range, the greater the pickup intensity, the greater P2, and the closer the pickup angle is, the greater P2. Therefore, the score of a voice device with a high pickup intensity and a pickup angle close to 90 is relatively high. When r is within the second range, the weight of the pickup angle is a, and a is greater than b, indicating that more attention is paid to the pickup angle at this time, that is to say, the pickup angle is more important in this case.

[0069] Furthermore, when the pickup sound intensity is the same, the score when r is within the second range should be greater than the score when r is within the first range. To ensure this requirement, in the embodiment of the present invention, the parameter c is added to the calculation formula when r is within the second range, and c is set to 10*a + b / 10. This value can ensure that the score when r is within the second range is greater than the score when r is within the first range under the condition of the same pickup sound intensity.

[0070] Among them, c = 10*a + b / 10 is calculated to ensure that b*s - a*|r - 90| + c is greater than or equal to a*s + b / |r - 90| when r is 100 and the pickup sound intensity is 0. Based on this c value, when r is any value within the second range, it can be ensured that the wake-up score when r is within the second range is greater than the wake-up score when r is within the first range under the condition of the same pickup sound intensity.

[0071] In practice, when the pickup angle is outside the preset range, for example, when the pickup angle is less than 60 or greater than 120, it indicates that the pickup angle of the voice device at this time is not the optimal pickup angle, but the corresponding score value can also be calculated using P2 = a*s + b / |r - 90|.

[0072] In specific implementation, the method provided by the embodiment of the present invention may further include: the cloud platform pre-determines a corresponding optimal interaction device group for each position and each orientation of the user who issues a preset wake-up word.

[0073] Furthermore, the process of the cloud platform pre-determining the corresponding optimal interaction device group specifically includes:

[0074] a1. The cloud platform obtains the position and orientation of the user who issues a preset wake-up word in the full space in the historical wake-up task;

[0075] a2. Obtain the sound intensity of the preset wake-up word picked up by each voice device, and select a first voice device from each voice device according to the sound intensity; wherein, the sound intensity picked up by each of the first voice devices is higher than that picked up by other voice devices, and the maximum difference between the sound intensities picked up by each of the first voice devices is within a preset difference range;

[0076] a3. Obtain the sound pickup angles of each of the first voice devices, and select a second voice device from the first voice devices whose sound pickup angles fall within the optimal sound pickup angle range according to the sound pickup angles of each of the first voice devices; form an optimal interaction device group for the position and orientation of the user with each of the second voice devices.

[0077] For example, when the user is in the middle position between the living room and the dining room and facing the balcony and says "Changhong Xiaobai", the sound intensity picked up by the 5 voice devices in the entrance, living room and dining room is slightly higher than that picked up by the voice devices in the laundry room and the kitchen, and the sound intensity picked up by the 5 voice devices in the entrance, living room and dining room is much higher than that picked up by the voice devices in the study, bedroom and bathroom. The first voice devices are screened out according to the sound intensity picked up by each voice device. Since the user stands in the middle position between the living room and the dining room, at this time, the sound intensity picked up by the 5 voice devices in the entrance, living room and dining room is about the same, and these 5 voice devices are the voice devices with the largest sound intensity among all voice devices, so these 5 voice devices are used as the first voice devices.

[0078] Then, since the user is facing the balcony, among the 3 voice devices in the living room and the balcony, they are facing the sound direction of the user, while the 2 voice devices in the entrance and the dining room are facing away from the sound direction of the user. Therefore, the sound pickup angles of the 3 voice devices in the living room and the balcony are within the optimal sound pickup angle range, while the sound pickup angles of the 2 voice devices in the entrance and the dining room are not within the optimal sound pickup angle range. Therefore, the 3 voice devices in the living room and the balcony are used as the second voice devices, and these 3 second voice devices form an optimal interaction device group. Of course, if the user is facing the dining room direction, the 2 voice devices in the dining room and the entrance form an optimal interaction device group.

[0079] It can be seen that an optimal interaction device group can be corresponding to the position and orientation of the user. In fact, when the user is in a certain position, an optimal interaction device group can be corresponding. For example, when the user is sitting on the sofa in the living room watching TV, the optimal interaction device group corresponding at this time is the optimal interaction device group formed by the 3 voice devices in the living room and the balcony.

[0080] When the user is at different positions and orientations within the entire space of the home, multiple best interaction device groups can be formed for multiple wake-up requests. The multiple best interaction device groups are saved and can be directly used later.

[0081] It can be understood that the best interaction device group is a virtual space grouping. There are at least two voice devices in this virtual space grouping. If there is only one voice device, there is no need to divide it into a group.

[0082] Here, an embodiment of the present invention proposes a best interaction device group. The best interaction device group is a virtual space grouping automatically divided based on past experience. The best interaction device group is a device grouping determined according to the user's position and orientation. Each voice device within a best interaction device group can be located in the same physical space or in multiple physical spaces. For example, when the user stands in the middle of the living room and the dining room and issues a wake-up request towards the balcony, the cabinet air conditioner and TV in the living room and the voice terminal located on the balcony will be divided into a best interaction device group.

[0083] When the cloud platform determines the corresponding best interaction device group according to the user's position and orientation, when each voice device in S100 picks up the preset wake-up word issued by the user, it calculates the corresponding score value and determines whether the score value is higher than the score value threshold corresponding to the voice device. This can specifically include:

[0084] When each voice device in the best interaction device group corresponding to the current position and current orientation of the user who issues the preset wake-up word picks up the preset wake-up word, it calculates the corresponding score value and determines whether the score value is higher than the score value threshold corresponding to the voice device.

[0085] That is to say, it is not necessary for each voice device that picks up the wake-up word to calculate the score value and determine whether the score value is higher than its own score value threshold. Only the voice devices that pick up the wake-up word in the best interaction device group need to calculate their own score values and compare the score values with the score value threshold. Specifically, the cloud platform can control each voice device in the best interaction device group to calculate the score value. For example, when any voice device picks up the voice and sends it to the cloud platform, the cloud platform then determines the corresponding best interaction device group and notifies each voice device in this best interaction device group to calculate its own score value.

[0086] Because the best interaction device group is determined according to the user's position and orientation and is a plurality of voice devices near the user, the probability of these several voice devices being selected is higher than the probability of voice devices in other positions being selected. This can reduce unnecessary calculations and the probability of errors.

[0087] For example, when a user stands in the living room and utters a wake-up word, the optimal interaction device group corresponding to the user's current location includes the TV in the living room, the floor-standing air conditioner in the living room, the voice terminal on the balcony, the voice terminals in the dining room, and the voice terminal at the entrance. Therefore, it is only necessary for these voice terminals to calculate their respective score values. For voice devices at other locations, even if they pick up the wake-up word, there is no need to calculate the score values because the probability of these voice devices at other locations being selected as the answering voice devices relative to each voice device in the optimal interaction device group is very small. This can reduce the workload of the other voice devices.

[0088] Based on the above optimal interaction device group, in the embodiment of the present invention, the cloud platform parses the voice task and issues the task obtained after parsing to the corresponding target smart home appliances for execution. Specifically, it may include the following steps:

[0089] b1. Determine whether there are smart home appliances in the optimal interaction device group where the voice answering device is located that can execute the task;

[0090] b2. If there are, use the smart home appliances in the optimal interaction device group where the voice answering device is located that can execute the task as the target smart home appliances, and issue the task to the target smart home appliances for execution;

[0091] b3. If not, use the smart home appliances in the entire space that can execute the task as the target smart home appliances, and issue the task to the target smart home appliances for execution.

[0092] It can be understood that when determining the target smart home appliances, first look for smart home appliances in the optimal interaction device group that can execute the task. If there are no target smart home appliances nearby that can execute the task, then it is necessary to look for target smart home appliances in the entire space that can execute the task as the target smart home appliances. Since the voice answering device is located near the user, each voice device in the optimal interaction device group is also located near the user, that is, first look for suitable target smart home appliances near the user, which conforms to the principle of looking nearby and improves the user experience. If there are no smart home appliances near the user that can execute the task, then look for smart home appliances that can execute the task from other locations.

[0093] In specific implementation, after the decision-making device determines the answering voice device for the current wake-up request, it will inform the cloud platform. Then, the cloud platform can determine the corresponding feedback voice device based on the answering voice device and use the feedback voice device for situation feedback.

[0094] That is, the method provided in the embodiment of the present invention may further include the following steps:

[0095] c1. The decision-making device notifies the cloud platform of the voice response device for the current wake-up request.

[0096] c2. If the cloud platform learns that the voice response device is a voice terminal, the cloud platform selects an intelligent appliance from the best interaction device group where the voice response device is located as the feedback voice device; if the voice response device is an intelligent appliance, the voice response device is simultaneously used as the feedback voice device.

[0097] c3. After the target intelligent appliance that executes the task finishes executing the task, it sends the task execution status to the cloud platform; the cloud platform sends the task execution status to the feedback voice device, so that the feedback voice device feeds back the task execution status to the user through voice.

[0098] That is to say, if the voice response device is a voice terminal, since the voice terminal does not have the function of voice broadcasting, an intelligent appliance needs to be used for voice broadcasting. Therefore, at this time, an intelligent appliance is selected from the best interaction device group where the voice response device is located as the feedback voice device. If the voice response device is an intelligent appliance, since the intelligent appliance has the function of voice broadcasting, the voice response device can be simultaneously used as the feedback voice device. After the target intelligent appliance finishes processing, the cloud platform will control the feedback voice device to feed back the execution status to the user through voice broadcasting so that the user can understand the situation.

[0099] In specific implementation, the method provided by the embodiment of the present invention may further include the following steps:

[0100] During the continuous time period when the first target intelligent appliance processes through voice broadcasting, if the cloud platform receives a new voice task and determines that the intelligent appliance that executes the new voice task is a second target intelligent appliance different from the first target intelligent appliance, and the second target intelligent appliance needs to execute the new voice task through voice broadcasting, then before controlling the second target intelligent appliance to perform corresponding processing, the first target intelligent appliance is controlled to abort the processing process to achieve the unique feedback in the entire space.

[0101] That is to say, at most one intelligent appliance can perform voice broadcasting at a time point. If a new task needs to be performed by other intelligent appliances through voice broadcasting during the voice broadcasting of an intelligent appliance, the original intelligent appliance needs to abort the broadcasting.

[0102] For example, when a smart voice speaker is playing a song and it is required that a smart TV play music, the playing of the smart voice speaker needs to be aborted first before the smart TV can be controlled to start playing music, so as to achieve unique voice feedback in the entire space and avoid interference between the voices played by multiple smart home appliances.

[0103] In specific implementation, when a user initiates a wake-up request, the corresponding optimal interaction device group can be found based on the user's location first. Specifically, if the user's location is within the optimal sound pickup range of an optimal interaction device group, the user's current location is considered to correspond to this optimal interaction device group. Then, it is determined whether there is a corresponding preferred response device based on this optimal interaction device group. If there is, the preferred response device can be directly used, and there is no need to use the response voice device sent by the decision-making device, that is, the decision-making device does not need to determine the response voice device at this time.

[0104] That is to say, before the method provided by the embodiment of the present invention, according to the score values in each of the election participation requests, selects a voice device from among the voice devices that send the election participation requests as the response voice device for this wake-up request, the following steps may further be included:

[0105] d1. Determine the corresponding optimal interaction device group according to the user's location in the entire space;

[0106] d2. Determine whether the optimal interaction device group has a corresponding preferred response device; wherein, the preferred response device is a smart home appliance preset by the user on the application program for the optimal interaction device group;

[0107] d3. If there is a corresponding preferred response device, determine whether the score value corresponding to the preferred response device is higher than a preset score value; if it is higher than the preset score value, use the preferred response device as the response voice device; if it is lower than or equal to the preset score value, control the decision-making device to determine the response voice device;

[0108] d4. If there is no corresponding preferred response device, control the decision-making device to determine the response voice device.

[0109] That is to say, the user can set a preferred response device for each optimal interaction device group on the application of the mobile terminal. For each wake-up request, the cloud platform determines the corresponding optimal interaction device group according to the user's location, and then judges whether a preferred response device is set for this optimal interaction device group. If a preferred response device is set, then calculate the scoring value of this preferred response device, and compare this scoring value with the preset scoring value. If this scoring value is higher than the preset scoring value, it means that the sound intensity picked up by the preferred response device is not very low and can meet the sound pickup requirements. At this time, this preferred response device is used as the response voice device.

[0110] However, if the scoring value of this preferred response device is less than or equal to the preset scoring value, it means that the sound intensity picked up by the preferred response device is very low at this time and cannot meet the sound pickup requirements. Therefore, it is necessary to use the response voice device determined by the decision-making device. Of course, if there is no corresponding preferred response device set for this optimal interaction device group, then it is necessary to use the response voice device determined by the decision-making device.

[0111] It is understandable that the preferred response device of an optimal interaction device group is a voice device in this optimal interaction device group, preferably a smart home appliance.

[0112] The determination of the decision-making device is described below:

[0113] Each voice device is controlled by the same preset application on the user's mobile terminal in the home. Therefore, the decision-making device is pre-determined by the preset application. Of course, the decision-making device can also be pre-determined by the cloud platform; wherein, the determination process of the decision-making device includes:

[0114] e1. Obtain each voice device accessing the home network;

[0115] It is understandable that when each voice device accesses the home network, the relevant information of this voice device, such as device identification, device type, device name, etc., will be seen on the preset application. Therefore, the preset application can obtain a device list formed by the relevant information of each voice device accessing the home network.

[0116] e2. Obtain the charged state data, computing power data and user usage habit data of each voice device joining the home network;

[0117] It is understandable that after the voice device runs for a period of time, a lot of data will be generated, such as the user usage habit data of the voice device and the charged state data of the voice device. These data will be recorded in the memory inside the voice device. The preset application will obtain these data from each voice device. At the same time, the preset application will also obtain the computing power data of each voice device.

[0118] Among them, the usage habit data of the voice device, for example, the time period of the day when the user is accustomed to watching TV, the season when the user is accustomed to turning on the air conditioner, etc. The power-on state data of the voice device refers to whether the voice device is always powered on, or powered on during a certain time period of the day, or rarely powered on, etc. The computing power data of the voice device refers to the data that can reflect the computing speed and computing volume of the voice device. Since the decision-making device needs to perform wake-up decision-making processing while realizing its own functions, the computing power of the voice device needs to be considered here.

[0119] e3. Determine the decision-making ability score of each voice device according to the power-on state data, computing power data and user usage habit data of each voice device;

[0120] It can be understood that when calculating the decision-making ability score of each voice device, not only the user's usage habits and power-on state need to be considered, but also the computing power of the voice device needs to be considered, that is, not only the external factors of the voice device are considered, but also the internal factors of the voice device are considered. Finally, a score reflecting the comprehensive decision-making ability of the voice device can be calculated.

[0121] Specifically, the second calculation formula can be used to calculate the decision-making ability score, and the second calculation formula includes:

[0122] P1 = u * (d 2 - 1 / y)

[0123] In the formula, P1 is the decision-making ability score; d is the average daily power-on duration of the voice device in the past month; y is the CPU computing power of the voice device; u is the usage mark of the voice device by the household user in the current season; if the household user uses the voice device in the current season, the usage mark corresponding to the voice device is 1; if the household user does not use the voice device in the current season, the usage mark corresponding to the voice device is 0.

[0124] In the above second calculation formula, u is the user's usage habit data. If the household user does not use the voice device in the current season, the usage mark corresponding to the voice device is 0, and at this time P1 is 0. If the household user uses the voice device in the current season, the usage mark corresponding to the voice device is 1, and at this time P1 = d 2 - 1 / y. For example, for the voice air conditioner as a voice device, some families do not use it in winter and only use it in summer.

[0125] Among them, d is the average daily power-on duration of the voice device in the past month. This parameter takes into account the user's usage situation in the recent period and also reflects the average power-on situation per day. For example, if the user only turns on the voice TV at night in the past month, the average daily power-on duration of the voice TV in the past month is only a few hours. While the voice refrigerator is always powered on, at this time, the average daily power-on duration of the voice refrigerator in the past month is 24 hours. The parameter d is a key parameter. The longer the power-on duration of the voice device, the more time the voice device can perform wake-up decision processing, which can reduce the occurrence of missed wake-up requests. The larger d is, the larger P1 is.

[0126] Among them, y reflects the computing power of the voice device. For example, the computing power of the CPU. The computing power of different CPUs is calculated differently. For example, some CPUs measure the computing power by word length, and some CPUs measure the computing power by double-precision floating-point computing power, which can be determined according to the actual situation of the CPU. The larger y is, the larger P1 is, but the relationship between y and P1 is not a proportional relationship.

[0127] It can be seen that the above second calculation formula can very reasonably reflect the decision-making ability of a voice device.

[0128] e4. Use the voice device with the highest decision-making ability score as the decision-making device.

[0129] In specific implementation, however, if the decision-making device loses power, other voice devices need to be replaced as the decision-making device. Of course, there may also be a situation where the previously determined decision-making device is not powered on. At this time, other voice devices also need to be replaced as the decision-making device.

[0130] Since the above situations may occur in the actual scenario, the process of the preset application determining the decision-making device may further include: the preset application detects whether the current decision-making device is powered on at a preset time interval through a heartbeat instruction; if it is not powered on, select the voice device with the highest decision-making ability score among the powered-on voice devices as the current decision-making device.

[0131] That is to say, the preset application on the mobile terminal will detect whether the current decision-making device is powered on at a time interval, specifically by means of a heartbeat instruction. For example, the preset application on the mobile terminal will send a heartbeat instruction to the decision-making device every once in a while. If the mobile terminal can receive the feedback information of the decision-making device, it means that the decision-making device is powered on at this time. If the feedback information of the decision-making device cannot be received, it means that the decision-making device is not powered on at this time.

[0132] If it is detected that the preset application on the mobile terminal finds that the current decision-making device is not powered on and other voice devices need to be replaced, the voice device with the highest decision-making ability score will be selected from each powered-on voice device as the current decision-making device, which can avoid affecting the wake-up process due to the unpowered decision-making device.

[0133] It can be understood that the above steps e1 to e5 can also be implemented by the cloud platform, that is, the cloud platform calculates the decision-making ability score of each voice device using the second calculation formula, and uses the voice device with the highest decision-making ability score as the decision-making device.

[0134] It can be understood that in order to pick up the voice commands issued by the user in each corner within the entire space of a family, multiple voice terminals are set up so that the union of the best sound pickup ranges of the smart home appliances and the voice terminals can cover the entire space, which can avoid or greatly reduce the problem of not responding to the user's commands due to not picking up the user's commands. Moreover, each voice terminal is connected to the cloud platform, which can form the control of each voice terminal within the entire space of a family.

[0135] In the election method provided by the embodiment of the present invention, a voice device has a corresponding score value threshold. When the voice device picks up the wake-up word, it will calculate the score value, and then compare its score value with its score value threshold. Only when the score value is higher than the score value threshold will an election participation request be generated. Because when the score value is less than or equal to the score value threshold, the probability of this voice device being selected is very low, so it does not need to participate in the election. This can filter out low-probability voice devices, reduce the calculation pressure of the decision-making device, reduce the data transmission volume, and improve the working efficiency of the decision-making device. Finally, the decision-making device elects a voice device from each voice device that sends the election participation request as the response voice device for this wake-up request. After determining the response voice device, use this response voice device to pick up the user's voice command, and then send the voice command to the cloud platform. After the cloud platform parses the voice command, it determines the target smart home appliance according to the parsing content, and then uses this target smart home appliance to perform corresponding processing. The response voice device and the target smart home appliance may not be in the same space, and the user does not need to walk to the position of the target smart home appliance to control the target smart home appliance. For example, when the user issues a command to turn off the TV in the living room in the bathroom, the voice terminal in the bathroom picks up this command and sends it to the cloud platform, and the cloud platform then controls the TV in the living room to turn off. It can be seen that the embodiment of the present invention can make the control of smart home appliances in the family convenient and flexible, and can greatly improve the user experience.

[0136] In a second aspect, the embodiment of the present invention provides an election system for an interactive voice device, see Figure 4, the system includes at least two voice devices and a cloud platform distributed in the entire space of a household. The at least two voice devices include smart home appliances. The voice module in the smart home appliances has the functions of voice pickup and voice feedback. The at least two voice devices are all communicatively connected to the cloud platform; the cloud platform is used to control the voice devices in the entire space; wherein:

[0137] Each voice device is used to: when a preset wake-up word issued by the user is picked up, calculate a corresponding score value, and determine whether the score value is higher than the score value threshold corresponding to the voice device; if so, generate the election participation request according to the score value of the voice device, and send the election participation request to the decision-making device; wherein, the decision-making device is a smart home appliance among the at least two voice devices, and the score value is used to represent the probability that the user wakes up the voice device.

[0138] The decision-making device is used to: according to the score values in each of the election participation requests, elect one voice device from the voice devices that send the election participation requests as the response voice device for the current wake-up request; wherein, the response voice device is used to pick up the voice task issued by the user after the preset wake-up word, and send the picked-up voice task to the cloud platform, so that the cloud platform parses the voice task and sends the task obtained after parsing to the corresponding target smart home appliance for execution.

[0139] In one embodiment, the voice device is specifically used to: when the sound pickup angle is within a preset range, calculate the score value corresponding to each voice device by using a first calculation formula, and the first calculation formula includes:

[0140] When r is within the first range, P2 = a*s + b / |r - 90|

[0141] When r is within the second range, P2 = b*s - a*|r - 90| + c

[0142] In the formula, P2 is the score value; s is the sound pickup intensity; r is the sound pickup angle; the first range is: r is greater than or equal to 60 and less than 80, or r is greater than 100 and less than or equal to 120; the second range is: r is greater than or equal to 80 and less than or equal to 100; a and b are preset weights, and a > b, c is 10*a + b / 10, and the preset range is the union of the first range and the second range.

[0143] In one embodiment, the cloud platform is used to: calculate the decision-making ability score of each voice device in advance by using a second calculation formula, and use the voice device with the highest decision-making ability score as the decision-making device; the second calculation formula includes:

[0144] P1 = u*(d2 -1 / y)

[0145] In the formula, P1 is the decision-making ability score; d is the average daily power-on duration of the voice device in the past month; y is the CPU computing power of the voice device; u is the usage mark of the voice device by the household user in the current season; if the household user uses the voice device in the current season, the usage mark corresponding to the voice device is 1; if the household user does not use the voice device in the current season, the usage mark corresponding to the voice device is 0.

[0146] It can be understood that the system provided in the second aspect corresponds to the method provided in the first aspect. For the explanations, embodiments, beneficial effects, examples, etc. of the relevant content in the second aspect, reference can be made to the corresponding parts in the first aspect.

[0147] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0148] Those skilled in the art should be able to realize that in one or more of the above examples, the functions described in the present invention can be implemented by hardware, software, add-ons, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0149] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solution of the present invention shall be included in the protection scope of the present invention.

Claims

1. An election method for an interactive voice device, characterized in that, There are at least two voice devices distributed throughout the space of a household. The at least two voice devices include smart home appliances. The voice module in the smart home appliances has the functions of voice pickup and voice feedback. The at least two voice devices are all communicatively connected to a cloud platform for controlling voice devices throughout the space; The method includes: When each voice device picks up a preset wake-up word issued by a user, it calculates a corresponding score value and determines whether the score value is higher than the score value threshold corresponding to the voice device; If so, an election participation request is generated according to the score value of the voice device, and the election participation request is sent to a decision-making device; Wherein, the decision-making device is a smart home appliance among the at least two voice devices, and the score value is used to represent the probability that the user wakes up the voice device; The decision-making device elects a voice device from the voice devices that send the election participation requests as the response voice device for the current wake-up request according to the score values in each election participation request; Wherein, the response voice device is used to pick up the voice task issued by the user after the preset wake-up word and send the picked-up voice task to the cloud platform, so that the cloud platform parses the voice task and sends the task obtained after parsing to the corresponding target smart home appliance for execution; The process of pre-determining the score value threshold corresponding to each voice device includes: The cloud platform obtains the historical score values of each voice device in the entire space; determines the rule data for the voice device to be selected as the response voice device according to the historical score values of each voice device; sets the corresponding score value threshold for the voice device according to the rule data; sends the score value threshold of each voice device to the voice device; Wherein, the historical score value of a voice device is the score value of the voice device after picking up the wake-up word each time within a preset historical time period, and the rule data of a voice device is the historical score value interval corresponding to the voice device when it is elected as the response voice device within the preset historical time period; When each voice device picks up a preset wake-up word issued by a user, calculating the corresponding score value includes: when the sound pickup angle is within a preset range, calculating the score value corresponding to each voice device using a first calculation formula, and the first calculation formula includes: When r is within the first range, P2 = a*s + b / |r - 90| When r is within the second range, P2 = b*s - a*|r - 90| + c In the formula, P2 is the score value; s is the sound pickup intensity; r is the sound pickup angle; The first range is: r is greater than or equal to 60 and less than 80, or, r is greater than 100 and less than or equal to 120; The second range is: r is greater than or equal to 80 and less than or equal to 100; a and b are preset weights, and a > b, c = 10*a + b / 10, and the preset range is the union of the first range and the second range.

2. The method according to claim 1, wherein Electing one of the voice devices that sent the election participation request as the response voice device includes: specifically, the decision-making device takes the voice device with the highest score value as the response voice device.

3. The method according to claim 1, wherein Specifically, the decision-making device elects one of the voice devices that sent the election participation request as the response voice device according to the score value and the product attributes of the voice device.

4. The method according to claim 1, wherein The method further includes: the cloud platform pre-determines a corresponding optimal interaction device group for each position and each orientation of the user who uttered the preset wake-up word. Correspondingly, when each voice device picks up the preset wake-up word uttered by the user, it calculates the corresponding score value and determines whether the score value is higher than the score value threshold corresponding to the voice device, including: when each voice device in the optimal interaction device group corresponding to the current position and current orientation of the user who uttered the preset wake-up word picks up the preset wake-up word, it calculates the corresponding score value and determines whether the score value is higher than the score value threshold corresponding to the voice device.

5. The method according to claim 4, characterized in that, The cloud platform parses the voice task and sends the parsed task to the corresponding target smart home appliance for execution, including: Determining whether there is a smart home appliance capable of executing the task in the optimal interaction device group where the response voice device is located; If there is, the smart home appliance in the optimal interaction device group where the response voice device is located and capable of executing the task is taken as the target smart home appliance, and the task is sent to the target smart home appliance for execution; If not, the smart home appliance in the entire space capable of executing the task is taken as the target smart home appliance, and the task is sent to the target smart home appliance for execution.

6. The method according to claim 4, wherein The cloud platform pre-determines a corresponding optimal interaction device group for each position and each orientation of the user who uttered the preset wake-up word, specifically including: The cloud platform obtains the position and orientation of the user who uttered the preset wake-up word in the entire space from the historical wake-up tasks; obtains the sound intensity of each voice device picking up the preset wake-up word, and selects the first voice device from each voice device according to the sound intensity; wherein, the sound intensity picked up by each of the first voice devices is higher than that picked up by other voice devices, and the maximum difference between the sound intensities picked up by each of the first voice devices is within the preset difference range; obtains the sound pickup angle of each of the first voice devices, and selects the second voice device whose sound pickup angle falls within the optimal sound pickup angle range from the first voice devices; forms the optimal interaction device group for the position and the orientation of the user with each of the second voice devices.

7. The method according to claim 4, wherein The at least two voice devices further include a voice terminal, and the union of the optimal sound pickup ranges of each of the smart home appliances and each of the voice terminals can cover the entire space; the voice module of the voice terminal has the function of voice pickup. The method further includes: The decision-making device informs the cloud platform of the response voice device of the current wake-up request. If the cloud platform learns that the response voice device is a voice terminal, the cloud platform selects an intelligent appliance from the best interaction device group where the response voice device is located as the feedback voice device; if the response voice device is an intelligent appliance, the response voice device is simultaneously used as the feedback voice device. After the target intelligent appliance that executes a task finishes executing the task, it sends the task execution status to the cloud platform; the cloud platform sends the task execution status to the feedback voice device so that the feedback voice device feeds back the task execution status to the user by voice.

8. The method according to claim 1, characterized in that, The method further includes: During the continuous time period when the first target intelligent appliance processes by voice broadcast, if the cloud platform receives a new voice task and determines that the intelligent appliance that executes the new voice task is a second target intelligent appliance different from the first target intelligent appliance, and the second target intelligent appliance needs to execute the new voice task by voice broadcast, then before the second target intelligent appliance needs to be controlled to perform corresponding processing, the first target intelligent appliance is controlled to abort the processing process to achieve the unique feedback in the entire space.

9. The method according to claim 1, characterized in that The cloud platform pre-calculates the decision-making ability score of each voice device by using a second calculation formula, and uses the voice device with the highest decision-making ability score as the decision-making device; the second calculation formula includes: P1 = u * (d 2 - 1 / y) In the formula, P1 is the decision-making ability score; d is the average daily power-on duration of the voice device in the past month; y is the CPU computing power of the voice device; u is the usage mark of the voice device by the household user in the current season; if the household user uses the voice device in the current season, the usage mark corresponding to the voice device is 1; if the household user does not use the voice device in the current season, the usage mark corresponding to the voice device is 0.

10. An election system for an interactive voice device, characterized in that, It includes at least two voice devices and a cloud platform distributed in the entire space of a household. The at least two voice devices include intelligent appliances. The voice module in the intelligent appliances has the functions of voice pickup and voice feedback. The at least two voice devices are all communicatively connected to the cloud platform; the cloud platform is used to control the voice devices in the entire space; wherein: Each voice device is used to: when picking up a preset wake-up word issued by the user, calculate the corresponding score value, and determine whether the score value is higher than the score value threshold corresponding to the voice device; if so, generate an election participation request according to the score value of the voice device, and send the election participation request to the decision-making device; wherein, the decision-making device is an intelligent appliance among the at least two voice devices, and the score value is used to represent the probability that the user wakes up the voice device. The decision-making device is used to: select a voice device from each of the voice devices that send the election participation requests as the response voice device for the current wake-up request according to the scoring values in each of the election participation requests; wherein, the response voice device is used to pick up the voice task issued by the user after the preset wake-up word, and send the picked-up voice task to the cloud platform, so that the cloud platform parses the voice task and sends the task obtained after parsing to the corresponding target smart home appliance for execution; The process of pre-determining the scoring value threshold corresponding to each voice device includes: The cloud platform obtains the historical scoring values of each voice device in the entire space; determines the rule data of the voice device being selected as the response voice device according to the historical scoring values of each voice device; sets the corresponding scoring value threshold for the voice device according to the rule data; sends the scoring value threshold of each voice device to the voice device; wherein, the historical scoring value of a voice device is the scoring value of the voice device after picking up the wake-up word each time within a preset historical time period, and the rule data of a voice device is the historical scoring value interval corresponding to the voice device being elected as the response voice device within the preset historical time period; The voice device is specifically used to: when the sound pickup angle is within a preset range, calculate the scoring value corresponding to each voice device by using a first calculation formula, and the first calculation formula includes: When r is within a first range, P2 = a*s + b / |r - 90| When r is within a second range, P2 = b*s - a*|r - 90| + c In the formula, P2 is the scoring value; s is the sound pickup intensity; r is the sound pickup angle; the first range is: r is greater than or equal to 60 and less than 80, or r is greater than 100 and less than or equal to 120; the second range is: r is greater than or equal to 80 and less than or equal to 100; a and b are preset weights, and a > b, c is 10*a + b / 10, and the preset range is the union of the first range and the second range.

11. The system according to claim 10, wherein The cloud platform is used to: pre-calculate the decision-making ability scoring of each voice device by using a second calculation formula, and use the voice device with the highest decision-making ability scoring as the decision-making device; the second calculation formula includes: P1 = u * (d 2 - 1 / y) In the formula, P1 is the decision-making ability scoring; d is the average daily power-on duration of the voice device in the past month; y is the CPU operation ability of the voice device; u is the usage mark of the voice device by the household user in the current season; if the household user uses the voice device in the current season, the usage mark corresponding to the voice device is 1; if the household user does not use the voice device in the current season, the usage mark corresponding to the voice device is 0.

Images