Voice control method and device for smart home, smart device and computer readable storage medium

Abstract

The invention relates to the technical field of smart families, and discloses a voice control method for a smart family, and the method comprises the steps: obtaining a first target region corresponding to a user position; analyzing the user voice to obtain a control instruction corresponding to the user voice; and determining a target device in the first target area according to the control instruction, and controlling the target device to perform voice feedback to the user according to the control instruction. According to the method, under the condition that a plurality of intelligent devices are arranged in a plurality of rooms, the intelligent device which performs voice interaction with the user is determined, and confusion during voice feedback of the intelligent device is avoided. The invention further discloses a voice control device for the smart home, intelligent equipment and a computer readable storage medium.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, for example, to a voice control method and apparatus for a smart home, an intelligent device, and a computer-readable storage medium. Background Art

[0002] At present, smart home has gradually become the new favorite of modern families, connecting various smart devices and systems to the Internet to achieve remote control and automatic operation. With the development of voice recognition technology, voice control has gradually been widely used in the field of smart home.

[0003] Related technologies disclose a method for controlling smart devices by voice, where users can initiate voice commands to control voice devices to perform corresponding operations, such as turning on and off the air conditioner. The entire process of voice interaction control includes several key links: voice wake-up, sending voice commands, device execution, device voice feedback, etc.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] Currently in smart homes, there are often multiple smart devices installed in multiple rooms. These smart devices often have voice interaction functions. When users issue commands, it is often impossible to determine which smart device will interact with the user by voice, resulting in confusion in the voice feedback of the smart devices.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] The embodiments of the present disclosure provide a voice control method and apparatus for a smart home, a smart device, and a computer-readable storage medium, so as to determine the smart device for voice interaction with a user when multiple smart devices are installed in multiple rooms, so as to avoid confusion in the voice feedback of the smart device.

[0009] In some embodiments, the method includes: obtaining a first target area corresponding to the user position; parsing the user voice to obtain a control instruction corresponding to the user voice; determining a target device in the first target area according to the control instruction, and controlling the target device to provide voice feedback to the user according to the control instruction.

[0010] Optionally, obtaining a first target area corresponding to the user's position includes: dividing the indoor space into multiple preset areas according to the user's current position, the equipment layout of the indoor space, the user's current voice and historical voice, and determining the first target area in the multiple preset areas according to the user's current position; wherein the preset areas include at least a responded area and a non-responsive area; and the first target area includes part or all of the responded area.

[0011] Optionally, the indoor space is divided into multiple preset areas according to the user's current position, the equipment layout of the indoor space, the user's current voice and historical voice, including: obtaining the user's movement trajectory, and determining the user's movement direction according to the movement trajectory and the current position; determining the target scene according to the movement trajectory, the movement direction, the current voice and the historical voice; dividing the indoor space into multiple preset areas according to the target scene, the current position, and the equipment layout of the indoor space.

[0012] Optionally, determining the user's moving direction according to the moving trajectory and the current position includes: determining the displacement of historical position points at adjacent moments in the moving trajectory as a moving vector; and determining a weighted average direction of multiple moving vectors as the user's moving direction.

[0013] Optionally, determining the target device in the first target area according to the control instruction includes: determining the target device in the first target area according to the control instruction includes:

[0014] Matching a response intelligent device corresponding to the control instruction in the first target area;

[0015] In the case where the answering intelligent device has voice feedback conditions, determining that the target device is the answering intelligent device; or,

[0016] When the answering smart device does not have the voice feedback condition, the target device is determined to be a smart device other than the answering smart device in the first target area.

[0017] Optionally, the voice feedback condition includes: the answering smart device is in operation and no audio is playing at the current moment.

[0018] In some embodiments, the device includes: an acquisition module, configured to obtain a first target area corresponding to the user position; an analysis module, configured to analyze the user voice and obtain a control instruction corresponding to the user voice; a voice feedback module, configured to determine a target device in the first target area according to the control instruction, and control the target device to provide voice feedback to the user according to the control instruction.

[0019] In some embodiments, the device includes a processor and a memory storing program instructions, and the processor is configured to execute the voice control method for a smart home when running the program instructions.

[0020] In some embodiments, the smart device includes: a smart device body; the voice control device for smart home is installed on the product body.

[0021] In some embodiments, the computer-readable storage medium stores program instructions, which, when executed, enable the computer to execute the voice control method for a smart home.

[0022] The voice control method and apparatus for smart home, smart device, and computer-readable storage medium provided by the embodiments of the present disclosure can achieve the following technical effects:

[0023] When multiple smart devices are set up in multiple rooms, the first target area corresponding to the user's position is first determined, and then the target device that provides voice feedback to the user is determined in the first target area based on the control instructions obtained by the user's voice analysis. In this way, the smart device that interacts with the user by voice is accurately determined, avoiding confusion when the smart device provides voice feedback, and improving the user experience.

[0024] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0026] Figure 1 is a schematic diagram of a voice control method for a smart home provided by an embodiment of the present disclosure;

[0027] Figure 2 is a schematic diagram of another voice control method for a smart home provided by an embodiment of the present disclosure;

[0028] Figure 3 is a schematic diagram of another voice control method for a smart home provided by an embodiment of the present disclosure;

[0029] Figure 4 is a schematic diagram of another voice control method for a smart home provided by an embodiment of the present disclosure;

[0030] Figure 5is a schematic diagram of a voice control device for a smart home provided by an embodiment of the present disclosure;

[0031] Figure 6 is a schematic diagram of another voice control device for a smart home provided by an embodiment of the present disclosure;

[0032] Figure 7 This is an application scenario diagram of a voice control method for a smart home provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0034] The terms "first", "second", etc. in the description of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so as to describe the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0035] Unless otherwise stated, the term "plurality" means two or more.

[0036] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0037] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0038] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0039] In the embodiments of the present disclosure, smart devices refer to household appliances and / or smart mobile devices formed by introducing microprocessors, sensor technology, and network communication technology into household appliances, and have the characteristics of smart control, smart perception, and smart application. The operation process of smart devices often relies on the application and processing of modern technologies such as the Internet of Things, the Internet, and electronic chips. Specifically, smart devices can communicate with servers by connecting to the Internet, or they can communicate with other smart devices directly through Bluetooth, Wi-Fi, etc. In some embodiments, smart devices are, for example, mobile devices, computers, or any combination thereof. It can also be a mobile phone, a smart home device, a wearable device, a smart mobile device, a virtual reality device, etc., or any combination thereof, wherein wearable devices include, for example: smart watches, smart bracelets, pedometers, etc. It can also be smart home appliances, such as smart refrigerators, smart TVs, smart washing machines, smart air conditioners, smart speakers, smart lights, and smart curtains, etc., or any combination thereof.

[0040] Figure 7 An application scenario diagram of the voice control method for a smart home provided by an embodiment of the present invention.

[0041] As shown in the figure, smart devices in multiple rooms communicate with the cloud server through the WiFi network. The cloud server is used to receive real-time status data of smart devices for subscription to the big data platform and application services. It also sends operating instructions from other business servers, big data platforms, application terminals, and smart terminals to smart devices.

[0042] Exemplarily, in the application scenario provided by this embodiment, if multiple smart devices are installed in multiple rooms, the smart device determined in the first target area to provide voice feedback to the user is controlled to perform voice interaction with the user, so as to avoid confusion during the voice feedback of the smart device and improve the user experience.

[0043] Combination Figure 1 As shown, the embodiment of the present disclosure provides a voice control method for a smart home, including:

[0044] S101: The smart device obtains a first target area corresponding to a user location.

[0045] S102, the smart device analyzes the user's voice and obtains a control instruction corresponding to the user's voice.

[0046] S103: The smart device determines a target device in the first target area according to the control instruction, and controls the target device to provide voice feedback to the user according to the control instruction.

[0047] By adopting the voice control method for smart home provided by the embodiment of the present disclosure, when multiple smart devices are set in multiple rooms, the first target area corresponding to the user's position is first determined, and then the target device that provides voice feedback to the user is determined in the first target area according to the control instruction obtained by the user's voice analysis. In this way, the smart device that interacts with the user by voice is accurately determined, and confusion is avoided when the smart device provides voice feedback, thereby improving the user experience.

[0048] Optionally, the smart device obtains a first target area corresponding to the user's location, including: the smart device divides the indoor space into multiple preset areas according to the user's current location, the device layout of the indoor space, the user's current voice and historical voice, and determines the first target area in the multiple preset areas according to the user's current location; wherein the preset areas at least include a responded area and a non-responded area; the first target area includes part or all of the area in the responded area

[0049] This helps to more accurately divide the preset area, thereby more accurately determining the first target area, and helps to accurately determine the smart device that interacts with the user by voice, avoid confusion when the smart device voice feedbacks, and improve the user experience.

[0050] Optionally, the smart device divides the indoor space into a plurality of preset areas according to the current location of the user, the device layout of the indoor space, the current voice and the historical voice of the user, including: the smart device obtains a movement trajectory composed of the historical locations of the user, and determines the movement direction of the user according to the movement trajectory and the current location. The smart device determines the target scene according to the movement trajectory, the movement direction, the current voice and the historical voice. The smart device divides the indoor space into a plurality of preset areas according to the target scene, the current location, and the device layout of the indoor space.

[0051] In this way, the moving direction is first determined according to the moving trajectory and the current position, which is conducive to more accurately predicting the user's movement. Then, the target scene is determined according to the moving trajectory, the moving direction, the current voice and the historical voice, which is conducive to more accurately determining the target scene according to the user's action intention and voice intention. Then, the indoor space is divided into multiple preset areas according to the target scene, the current position, and the equipment layout of the indoor space, which is conducive to more accurately dividing the preset areas according to the actual needs of the target scene, thereby more accurately determining the first target area.

[0052] Optionally, the smart device divides the indoor space into a plurality of preset areas according to the user's current location, the device layout of the indoor space, the user's current voice and historical voice, including: the smart device determines the user's current state according to the user's historical location and the historical state corresponding to the user's body posture when the user is at this location. The smart device determines the target scene according to the user's current location, current state, current voice and historical voice. The smart device divides the indoor space into a plurality of preset areas according to the target scene, the current location and the device layout of the indoor space.

[0053] In this way, first determine whether the user's current state has a tendency to move based on the user's historical position and the historical state corresponding to the user's body posture when in this position. If it is determined that the user has no tendency to move, it indicates that the user has no need to move in the short term. At this time, determining the target scene based on the current voice and the historical voice is conducive to more accurately determining the target scene according to the user's voice intention. Then, the indoor space is divided into multiple preset areas based on the target scene, the current position, and the equipment layout of the indoor space, which is conducive to more accurately dividing the preset areas according to the actual needs of the target scene, thereby more accurately determining the first target area.

[0054] Specifically, in the case where the controlled device can directly receive user interaction instructions in the target scene, the indoor space can be divided into multiple preset areas according to the clarity of the instructions received by the controlled device under the influence of the current position and the device layout of the indoor space. In the case where the controlled device cannot directly receive user interaction instructions in the target scene, the indoor space can be divided into multiple preset areas according to the convenience of interacting with each smart device under the influence of the device layout of the indoor space when the user is in the current position.

[0055] Optionally, the smart device obtains a movement trajectory composed of historical positions of the user, including: the smart device determines historical position data of the user at historical moments, and the smart device connects the historical position data on a two-dimensional plane according to the historical moments to obtain the movement trajectory.

[0056] Specifically, the smart device determines the historical location data of the user at the historical moment, including: the current location of the user at time t is L u (t) = (x u (t), y u (t)), and the historical position of the user at n historical moments before time t is: L u (tn), L u (t-n+1), ..., L u (t). The smart device connects the historical location data on a two-dimensional plane according to the historical moments to obtain the movement trajectory, including: the movement trajectory of the user from time tn to time t is T m (t) = {Lu (tn), L u (t-n+1), ..., L u (t)}.

[0057] In this way, the movement trajectory obtained by connecting the historical position data on a two-dimensional plane according to the historical moment is conducive to more accurately reflecting the user's action intention, thereby more accurately determining the target scene and dividing the preset area.

[0058] Optionally, the smart device determines the user's moving direction according to the moving trajectory and the current position, including: the smart device determines the displacement of the current position or the historical position at adjacent moments in the moving trajectory as a moving vector. The smart device determines the weighted average direction of multiple moving vectors as the user's moving direction.

[0059] Specifically, the smart device determines the displacement of the historical position points at adjacent moments in the movement trajectory as the movement vector, including: the smart device determines the user at the historical moment t i The coordinates L of the historical position on the two-dimensional plane u (t i )=(x u (t i ), y u (t i )). The smart device determines the movement vector

[0060] Specifically, the smart device determines the weighted average direction of multiple movement vectors as the movement direction of the user, including: in, is the user's moving direction, m is the number of moving vectors, ω i is the weight coefficient, is the movement vector. More specifically, ω i The value of can be 1.

[0061] In this way, the weighted average direction of the movement vector determined multiple times according to the displacement of the current position or the historical position at adjacent moments in the movement trajectory is used as the movement direction, which is conducive to more accurately reflecting the user's action intention, thereby more accurately determining the target scene and dividing the preset area.

[0062] Optionally, the smart device determines the target scene according to the moving track, moving direction, current voice and historical voice, including: the smart device determines the current scene feature vector according to the moving track, moving direction, current voice and historical voice. The smart device determines the target scene according to the current scene feature vector and the preset scene feature vector.

[0063] In this way, the current scene feature vector is first determined based on the movement trajectory, movement direction, current voice and historical voice, which is conducive to more accurately analyzing the current scene feature vector according to the user's action intention and voice intention. Then, the target scene is determined based on the current scene feature vector and the preset scene feature vector, which is conducive to more accurately determining the target scene according to the user's action intention and voice intention.

[0064] Optionally, the smart device determines the current scene feature vector according to the moving trajectory, the moving direction, the current voice and the historical voice, including: the smart device determines the current scene trajectory feature vector according to the moving trajectory. The smart device determines the current scene direction feature vector according to the moving direction. The smart device determines the current scene voice feature vector according to the current voice and the historical voice. The smart device combines the current scene trajectory feature vector, the current scene direction feature vector and the current scene voice feature vector into the current scene feature vector.

[0065] In this way, the current scene direction feature vector reflecting the user's action intention, the current scene trajectory feature vector and the current scene voice feature vector reflecting the user's voice intention are combined into a current scene feature vector, which is conducive to more accurately quantifying the user's action intention and voice intention, thereby more accurately matching the target scene corresponding to the user's action intention and voice intention.

[0066] Specifically, the smart device determines the current scene trajectory feature vector according to the mobile trajectory, including: extracting trajectory features from the mobile trajectory to obtain the current scene trajectory feature vector. The trajectory features include path patterns and / or area dwell time. More specifically, the smart device determines the current scene trajectory feature vector according to the mobile trajectory, including: the smart device extracts trajectory features from the mobile trajectory to obtain the current scene trajectory feature vector, which can be expressed as: in, is the current scene trajectory feature vector.

[0067] This helps to more accurately quantify the current scene direction feature vector that reflects the user's action intention, thereby more accurately matching the target scene corresponding to the user's action intention.

[0068] Specifically, the smart device determines the current scene direction feature vector according to the moving direction, including: the smart device extracts the direction feature from the moving direction to obtain the current scene direction feature vector. The direction feature includes the direction vector and / or the turning frequency. More specifically, the direction feature is extracted from the moving trajectory to obtain the current scene direction feature vector, which can be expressed as: in, is the current scene direction feature vector.

[0069] This is conducive to more accurately quantifying the current scene trajectory feature vector that reflects the user's action intention, thereby more accurately matching the target scene corresponding to the user's action intention.

[0070] Specifically, the smart device determines the current scene voice feature vector according to the current voice and the historical voice, including: the smart device extracts voice features from the current voice and the historical voice to obtain the current scene voice feature vector. The voice features include voice commands and / or the temporal relationship of commands. More specifically, the voice features are extracted from the current voice and the historical voice to obtain the current scene voice feature vector, which can be expressed as: in, is the speech feature vector of the current scene, V c is the current voice, H c (t) is the historical sound, H c (t) = {V c (tn), V c (t-n+1), ..., V c (t)},V c (t) is the speech uttered by the user at the current time t.

[0071] This helps to more accurately quantify the current scene speech feature vector that reflects the user's speech intention, thereby more accurately matching the target scene corresponding to the user's speech intention.

[0072] Specifically, the smart device combines the current scene trajectory feature vector, the current scene direction feature vector, and the current scene voice feature vector into a current scene feature vector, including: in, is the feature vector of the current scene.

[0073] This helps to more accurately quantify the user's action intention and voice intention, thereby more accurately matching the target scene corresponding to the user's action intention and voice intention.

[0074] Optionally, the smart device determines the target scene according to the current scene feature vector and the preset scene feature vector, including: the smart device determines the similarity between the current scene feature vector and each preset scene feature vector. The smart device determines the preset scene feature vector with the highest similarity to the current scene feature vector as the target scene feature vector, and determines the preset scene corresponding to the target scene feature vector as the target scene.

[0075] Specifically, the smart device determines the similarity between the current scene feature vector and each preset scene feature vector, including: Among them, S j is the jth preset scene, is the jth preset scene feature vector, j=1, 2, ..., k, k is the total number of preset scenes. The similarity is determined in the following manner: the similarity is determined by calculating the cosine similarity or the Euclidean distance.

[0076] Specifically, the smart device determines a preset scene feature vector having the highest similarity to the current scene feature vector as the target scene feature vector, and determines a preset scene corresponding to the target scene feature vector as the target scene, including: Where S is the target scene set, S = {S 1 , S 2 , ..., S k}.

[0077] This helps to more accurately match the target scene corresponding to the user's action intention and voice intention based on the user's action intention and voice intention.

[0078] In actual application, the user walks from the bedroom to the kitchen and issues a voice command of "start the coffee machine" at the same time. At this time, the trajectory features are extracted from the moving trajectory and the directional trajectory features are extracted from the moving direction to obtain the trajectory features and directional features of the user moving from the bedroom to the kitchen. The voice features are extracted from the current voice and the historical voice to obtain the voice pattern related to "morning preparation". The extracted trajectory features, directional features and voice features are matched with the preset scenes to calculate the similarity, and the preset scene with the highest similarity is selected as the "morning preparation" scene. When the user's scene confirmation command is received, the target scene is determined to be "morning preparation" and the smart device operations related to the target scene are started, such as starting the coffee machine and adjusting the lights.

[0079] Optionally, the number of preset areas is two or more, and the preset areas at least include: a responded area and a non-responded area. The smart device determines the first target area according to the user's current location, including: the smart device determines the area where the user's current location is located as the responded area, and the smart device determines the responded area as the first target area.

[0080] In this way, dividing the preset area into a responded area and a non-responded area is conducive to better determining the first target area where the smart device that performs voice feedback is located. In this way, it is conducive to more accurately dividing the preset area, thereby more accurately determining the first target area. It is conducive to accurately determining the smart device that performs voice interaction with the user, avoiding confusion when the smart device performs voice feedback, and improving the user experience.

[0081] Optionally, the smart device divides the indoor space into multiple preset areas according to the target scene, the current location, and the device layout of the indoor space, including: the smart device selects a subset of the smart device set whose function set completely covers the function set required for the target scene, minimizes the total distance from the current location, and all devices are in an available state and can be effectively controlled under the device layout of the indoor space, and determines it as the first smart device subset. The smart device optimizes the first smart device subset according to the greedy algorithm to obtain the second smart device subset. The smart device obtains the responded area and the non-responsive area based on the position connection of the smart devices in the second smart device subset and the architectural layout of the indoor space. Among them, the number of devices in the first smart device subset meets the device number constraint, and the function of the first smart device subset meets the function coverage priority constraint.

[0082] In this way, the smart device set is first optimized to obtain the first smart device subset through the optimization conditions that the function set completely covers the function set required for the target scene, the total distance from the current position is minimized, and all devices are in an available state and can be effectively controlled under the device layout of the indoor space, which is conducive to preliminarily obtaining the smart devices most relevant to the target scene, the current position, and the device layout of the indoor space. Then, the first smart device subset is optimized according to the greedy algorithm to obtain the second smart device subset, which is conducive to efficiently achieving the local optimum of the second smart device subset, so that the smart devices in the second smart device subset can better achieve the target scene. According to the location connection of the smart devices in the second smart device subset and the architectural layout of the indoor space, the responded area and the non-responded area are obtained, which is conducive to considering the impact of the architectural layout of the indoor space on the smoothness and accessibility of the preset area. In this way, it is conducive to more accurate division of the preset area.

[0083] Specifically, the function set completely covers the function set required by the target scenario, including: in, E * is the first smart device subset, E is the smart device set, E={e 1 , e 2 ,……,e n},e i represents the i-th device, for e i The function set, F s It is the set of functions required by the target scenario.

[0084] In this way, it is helpful to make the function set of the first smart device subset completely cover the function set required by the target scene, so as to match the target scene more accurately.

[0085] Specifically, the total distance from the current position is minimized, including: Among them, D u (ei ) is e i The distance from the current position, the coordinate of the current position is L u =(x u ,y u ),

[0086] In this way, it is helpful to minimize the total distance between the smart devices in the first smart device subset and the current location, which is helpful for users to interact with the smart devices in the target scene more conveniently, thereby matching the target scene more accurately.

[0087] Specifically, all devices are in an available state and can be effectively controlled under the device layout of the indoor space, including: Among them, A(e i ) means e i In available state. When A(e i ) is 1, indicating an available state. i ) value is 0, which means it is unavailable.

[0088] This helps ensure that all devices in the first smart device subset are available and can be effectively controlled under the device layout in the indoor space, avoiding the problem of no device interaction with the user due to unavailability or uncontrollable devices in the target scene, thereby more accurately matching the target scene and improving the user experience.

[0089] Specifically, the number of devices in the first smart device subset satisfies the device number constraint condition, including: * |≤k; wherein k is the number of devices in the first smart device subset, which is beneficial to improving the efficiency of dividing the preset area.

[0090] In this way, the number of devices in the first smart device subset meets the quantity constraint condition, thereby avoiding the problem of overly complex device control caused by an excessive number of devices in the first smart device subset.

[0091] Specifically, the functions of the first smart device subset meet the function coverage priority constraint condition, including: giving priority to selecting smart devices that cover the most functions

[0092] In this way, the functions of the first smart device subset meet the function coverage priority constraint condition, and the smart devices with the most functions covering the target scene are preferentially selected, which is conducive to improving the efficiency of dividing the preset area.

[0093] Specifically, the smart device optimizes the first smart device subset according to the greedy algorithm to obtain the second smart device subset, including:

[0094] The smart device initializes the first smart device subset.

[0095] The smart device calculates the distance between each smart device in the smart device set and the current location.

[0096] The smart device sorts the smart devices in the smart device set in ascending order according to the distance between the smart devices in the smart device set and the current location.

[0097] The smart device adds the smart devices in the smart device set to the first smart device subset one by one in the sorted order until the function set of the first smart device subset covers the function set required by the target scenario.

[0098] When the function set of the first smart device subset completely covers the function set required by the target scenario, the smart device uses the first smart device subset as the second smart device subset. Or,

[0099] When the function set of the first smart device subset cannot completely cover the function set required by the target scenario, the smart device selects the first smart device subset whose function set covers the most function sets required by the target scenario as the second smart device subset.

[0100] More specifically, the smart device initializes the first smart device subset, including: * = 0. The smart device adds the smart devices in the smart device set to the first smart device subset one by one in the sorted order until the function set of the first smart device subset covers the function set required by the target scenario, including:

[0101] In this way, optimizing the first smart device subset according to the greedy algorithm to obtain the second smart device subset is conducive to preferentially selecting the smart device closest to the current position as the smart device in the first smart device subset, thereby efficiently achieving the local optimum of the second smart device subset, so that the smart devices in the second smart device subset can better realize the target scenario.

[0102] Optionally, the smart device obtains the responded area and the non-responsive area according to the position connection of the smart devices in the second smart device subset and the architectural layout of the indoor space, including: the smart device connects the positions of the smart devices in the second smart device subset to obtain the first polygonal area. The smart device adjusts the boundary of the first polygonal area according to the architectural layout of the indoor space to avoid the boundary passing through the wall or furniture, and obtains the second polygonal area. The smart device adjusts the boundary of the second polygonal area in real time according to the movement trajectory and movement direction to obtain the responded area. The smart device determines that the area outside the boundary of the responded area is a non-responsive area.

[0103] In this way, by connecting the positions of the smart devices in the second smart device subset, the first polygonal area can be preliminarily obtained. The boundary of the first polygonal area is adjusted according to the architectural layout of the indoor space to avoid the boundary crossing the wall or furniture. Since the walls, partitions and furniture in the room are easy to constitute physical obstacles, if the preset area includes walls, partitions or furniture, it is impossible to ensure that users can enter and leave the preset area without obstacles. Therefore, it is necessary to consider the impact of the architectural layout of the indoor space on the smoothness and accessibility of the preset area. And then adjusting the boundary of the second polygonal area according to the real-time movement trajectory and movement direction and dividing the preset area accordingly is conducive to adjusting the boundary of the preset area again according to the user's action intention and dividing the preset area accordingly to obtain the responded area and the non-responsive area. In this way, it is conducive to more accurate division of the preset area.

[0104] Specifically, the smart device connects the positions of the smart devices in the second smart device subset to obtain a first polygonal area, including: Among them, Z p is the first polygonal area, is the location coordinate of the first smart device in the second smart device subset, is the location coordinate of the second smart device in the second smart device subset, is the position coordinate of the kth smart device in the second smart device subset, k is the total number of smart devices in the second smart device subset, and ConvexHull is a convex hull calculation formula.

[0105] This helps to more accurately determine the boundary of the first polygonal area.

[0106] Specifically, the smart device adjusts the boundary of the first polygonal area according to the architectural layout of the indoor space to avoid the boundary passing through the wall or furniture, and obtains the second polygonal area, including: Z p ′=Z p ∩Latout(S); where Z′ p is the second polygonal area, and Layout(S) is the architectural structure of the architectural layout of the indoor space.

[0107] This helps to more accurately determine the boundary of the second polygonal area.

[0108] Optionally, the smart device adjusts the boundary of the second polygonal area according to the moving trajectory and the moving direction to obtain the responded area, including:

[0109] The smart device determines the location of the target device based on the movement trajectory and movement direction.

[0110] When the target device is outside the boundary of the second polygonal area, the smart device adds the target device to the second smart device subset, and connects the positions of the smart devices in the second smart device subset to obtain a third polygonal area. The smart device uses the third polygonal area as the responded area. And / or,

[0111] When there is an excluded smart device in the second smart device subset, the excluded smart device is excluded from the second smart device subset, and the positions of the smart devices in the second smart device subset are connected to obtain a third polygonal area. The smart device uses the third polygonal area as the responded area.

[0112] The target location is determined based on the moving trajectory and the moving direction. The situations where the smart device is an excluded device include: the distance between the location of the smart device and the target location is greater than the distance threshold, and the function set of the smart device does not belong to the function set required by the target scene.

[0113] In this way, the boundary of the second polygonal area is adjusted in real time according to the moving trajectory and moving direction and the preset area is divided accordingly. If the target device is outside the boundary of the second polygonal area, the range of the preset area is expanded. If there is an excluded device in the second smart device subset, the range of the preset area is reduced. In this way, it is beneficial to expand or reduce the range of the preset area again according to the user's action intention, obtain the responded area and the non-responded area, and thus it is beneficial to divide the preset area more accurately.

[0114] Specifically, the smart device determines the location of the target device according to the moving trajectory and the moving direction, including: the smart device determines the target location according to the moving trajectory and the moving direction. The smart device determines the location of the smart device closest to the target location in the second smart device subset as the location of the target device. More specifically, the smart device determines the target location according to the moving trajectory and the moving direction, including: Among them, l′ u is the target location, is the moving trajectory, D t is the moving direction, "·" is the dot product operation, and λ is the predicted moving distance proportional coefficient. Specifically, the smart device adds the target device to the second smart device subset, and connects the positions of the smart devices in the second smart device subset to obtain a third polygonal area, including: Among them, Z″ p is the third polygonal area, The location of the target device.

[0115] In this way, it is helpful to determine the position of the target device according to the moving trajectory and moving direction in real time, so as to update the preset area matching the target scene in real time, which is helpful to better meet the needs of users in the target scene.

[0116] Specifically, the smart device excludes the smart devices that are excluded devices from the second smart device subset, and connects the positions of the smart devices in the second smart device subset to obtain a third polygonal area, including: in, is the location coordinate of the smart device in the second smart device subset, \ is the exclusion operation, is the distance between the location of the smart device and the target location, and δ is the distance threshold.

[0117] In this way, if there is a smart device in the second smart device subset that is an excluded device, the range of the preset area is reduced. In this way, it is beneficial to further expand or reduce the range of the preset area according to the user's action intention, obtain the responded area and the non-responsive area, and thus facilitate more accurate division of the preset area.

[0118] In actual application, if the smart devices in the second smart device subset are televisions and lamps, the positions of the televisions and lamps are connected to obtain the first polygonal area Z. p The boundary is adjusted according to the wall and furniture position in the living room (the architectural layout of the interior space) to avoid the boundary crossing the wall or furniture, and the second polygonal area Z′ is obtained p The moving track and moving direction are from the sofa to the coffee table. The second polygonal area Z′ is adjusted according to the moving track and moving direction. p The boundary of the response area Z″ is obtained p .

[0119] When the user is on the sofa, get the first polygon area Z p When the user moves toward the coffee table, the target position L′ is determined u . It is determined that the smart device closest to the target location is the audio device on the coffee table. At this time, the audio device is the target device. target If the audio equipment is in the second polygonal area Z' p If the boundary is beyond the boundary, the second polygonal area Z′ is extended p If the boundary of the second smart device subset is reached, the audio device is added to the second smart device subset, and the positions of the smart devices in the second smart device subset are connected to obtain a third polygonal area, and the third polygonal area is determined as the responded area Z″ p When the user reaches the coffee table, music is played through the audio equipment, and the user is confirmed whether the division of the responded area and the non-response area meets the user's needs.

[0120] Optionally, the smart device parses the user voice to obtain the control instruction corresponding to the user voice, including: the smart device determines the control instruction corresponding to the current voice according to the first target area, the historical control instructions corresponding to the historical voice, and the current voice. Specifically, the smart device determines the control instruction corresponding to the current voice according to the first target area, the historical control instructions corresponding to the historical voice, and the current voice, including: the smart device obtains the current voice in the first target area. The smart device combines the historical control instructions corresponding to the historical voice and the current voice to obtain the control instruction corresponding to the current voice through semantic analysis.

[0121] In this way, it is helpful to more accurately determine the current control instruction by combining the context and the first target area, thereby more accurately determining the target device that can achieve the target scenario.

[0122] Optionally, the smart device determines the target device in the first target area according to the control instruction, including: the smart device matches the answering smart device corresponding to the control instruction in the first target area. The smart device determines the target device as the answering smart device according to whether the answering smart device has a voice feedback condition.

[0123] In this way, the response intelligent device corresponding to the control instruction is matched in the first target area, and whether it is used as the target device for realizing the target scene still needs to be determined according to whether the response intelligent device has the voice feedback condition.

[0124] Optionally, the smart device determines the target device as the answering smart device according to whether the answering smart device has the voice feedback condition, including: the smart device determines the target device as the answering smart device when the answering smart device has the voice feedback condition. Or, the smart device determines the target device as a smart device other than the answering smart device in the first target area when the answering smart device does not have the voice feedback condition.

[0125] In this way, if the answering smart device meets the voice feedback condition, the target device is the answering smart device, and if the answering smart device does not meet the voice feedback condition, the target smart device is other smart devices in the first target area. This helps to accurately determine the smart device that interacts with the user by voice, avoid confusion when the smart device voice feedbacks, and improve the user experience.

[0126] Specifically, the number of voice feedback includes one or more times.

[0127] In this way, when the number of voice feedbacks is one, it is helpful to realize a simple voice interaction scenario between the user and the target home appliance. When the number of voice feedbacks is multiple times, it is helpful to realize a complex interaction scenario between the user and the target home appliance.

[0128] Specifically, the answering smart device has the voice feedback condition, including: the answering smart device is in operation and not playing audio at the current moment. The answering smart device does not have the voice feedback condition, including: the answering smart device is in shutdown state and / or is playing audio at the current moment.

[0129] This helps to avoid the problem of device downtime and unavailability, as well as the problem of interrupting the playing audio to answer the smart device, which ruins the user experience.

[0130] Optionally, after the smart device obtains the control instruction corresponding to the user's voice, the smart device further includes: when the execution result of the control instruction is perceptible to the user, the smart device does not control the target device to provide voice feedback to the user. Specifically, the execution result of the control instruction is a change in sound, light or air output parameters.

[0131] In this way, if the execution result of the control instruction is perceptible to the user, there is no need for voice feedback, thus avoiding the problem of too frequent voice feedback causing user disgust.

[0132] Combination Figure 2 As shown, the embodiment of the present disclosure provides another voice control method for a smart home, including:

[0133] S201, the smart device divides the indoor space into multiple preset areas according to the user's current location, the device layout of the indoor space, the user's current voice and historical voice, and determines a first target area according to the user's current location.

[0134] S202, the smart device analyzes the user's voice and obtains a control instruction corresponding to the user's voice.

[0135] S203: The smart device determines a target device in the first target area according to the control instruction, and controls the target device to provide voice feedback to the user according to the control instruction.

[0136] By adopting the voice control method for smart home provided by the embodiment of the present disclosure, when multiple smart devices are set in multiple rooms, the indoor space is first divided into multiple preset areas according to the user's current position, the device layout of the indoor space, the user's current voice and historical voice, and the first target area is determined according to the user's current position, which is conducive to more accurate division of the preset area, thereby more accurately determining the first target area. It is conducive to accurately determining the smart device that interacts with the user by voice, avoiding confusion when the smart device voice feedback, and improving the user experience. Then, according to the control instructions obtained by the user voice analysis, the target device that provides voice feedback to the user is determined in the first target area. In this way, the smart device that interacts with the user by voice is accurately determined, avoiding confusion when the smart device voice feedback, and improving the user experience.

[0137] Combination Figure 3 As shown, the embodiment of the present disclosure provides another voice control method for a smart home, including:

[0138] S301: The smart device obtains a first target area corresponding to a user location.

[0139] S302, the smart device analyzes the user's voice and obtains a control instruction corresponding to the user's voice.

[0140] S303: The smart device matches in the first target area to obtain a response smart device corresponding to the control instruction.

[0141] S304: When the answering smart device meets the voice feedback condition, the smart device determines that the target device is the answering smart device. Or,

[0142] S305: When the answering smart device does not meet the voice feedback condition, the smart device determines that the target device is a smart device other than the answering smart device in the first target area.

[0143] S306: The smart device controls the target device to provide voice feedback to the user according to the control instruction.

[0144] Using the voice control method for smart home provided by the embodiment of the present disclosure, when multiple smart devices are set up in multiple rooms, first determine the first target area corresponding to the user's position, and then obtain the control instructions based on the user's voice analysis. In the first target area, match the responding smart device corresponding to the control instruction. If the responding smart device meets the voice feedback condition, the target device is the responding smart device. If the responding smart device does not meet the voice feedback condition, the target smart device is another smart device in the first target area. In this way, it is helpful to accurately determine the smart device that interacts with the user by voice, avoid confusion when the smart device voice feedbacks, and improve the user experience.

[0145] Combination Figure 4 As shown, the embodiment of the present disclosure provides another voice control method for a smart home, including:

[0146] S401: The smart device obtains a first target area corresponding to a user location.

[0147] S402, the smart device analyzes the user's voice and obtains a control instruction corresponding to the user's voice.

[0148] S403: The smart device determines a target device in the first target area according to the control instruction.

[0149] S404: When the execution result of the control instruction is not perceptible to the user, the smart device controls the target device to provide voice feedback to the user according to the control instruction. Or,

[0150] S404: When the execution result of the control instruction is perceptible to the user, the smart device does not control the target device to provide voice feedback to the user.

[0151] By adopting the voice control method for smart home provided by the embodiment of the present disclosure, when multiple smart devices are set in multiple rooms, the first target area corresponding to the user's position is first determined, and then the target device that provides voice feedback to the user is determined in the first target area according to the control instruction obtained by the user's voice analysis. In this way, the smart device that interacts with the user by voice is accurately determined, and confusion is avoided when the smart device provides voice feedback, thereby improving the user experience. If the user can perceive the execution result of the control instruction, there is no need for voice feedback, so as to avoid the problem that the voice feedback is too frequent and causes user disgust.

[0152] Combination Figure 5 As shown, the embodiment of the present disclosure provides a voice control device 200 for a smart home, including an acquisition module 501, an analysis module 502 and a voice feedback module 503. The acquisition module 501 is configured to obtain a first target area corresponding to the user's position; the analysis module 502 is configured to analyze the user's voice and obtain a control instruction corresponding to the user's voice; the voice feedback module 503 is configured to determine a target device in the first target area according to the control instruction, and control the target device to provide voice feedback to the user according to the control instruction.

[0153] When multiple smart devices are installed in multiple rooms, the voice control device 200 for smart home provided by the embodiment of the present disclosure first determines the first target area corresponding to the user's position, and then determines the target device that provides voice feedback to the user in the first target area according to the control instruction obtained by the user's voice analysis. In this way, the smart device that interacts with the user by voice is accurately determined, which avoids confusion when the smart device provides voice feedback, and improves the user experience.

[0154] Combination Figure 6As shown, the embodiment of the present disclosure provides a voice control device 70 for a smart home, including a processor (processor) 700 and a memory (memory) 701. Optionally, the device 70 may also include a communication interface (Communication Interface) 702 and a bus 703. Among them, the processor 700, the communication interface 702, and the memory 701 can communicate with each other through the bus 703. The communication interface 702 can be used for information transmission. The processor 700 can call the logic instructions in the memory 701 to execute the voice control method for a smart home of the above embodiment.

[0155] In addition, the logic instructions in the memory 701 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0156] The memory 701 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 700 executes the functional application and data processing by running the program instructions / modules stored in the memory 701, that is, the voice control method for smart home in the above embodiment is implemented.

[0157] The memory 701 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 701 may include a high-speed random access memory and may also include a non-volatile memory.

[0158] The embodiments of the present disclosure provide a smart device, including: a smart device body, and the above-mentioned voice control device 200 (70) for smart home. The voice control device 200 (70) for smart home is installed on the smart device body. The installation relationship described here is not limited to placement inside the smart device body, but also includes installation connections with other components of the smart device 100, including but not limited to physical connections, electrical connections or signal transmission connections. It can be understood by those skilled in the art that the voice control device 200 (70) for smart home can be adapted to a feasible smart device body, thereby realizing other feasible embodiments.

[0159] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned voice control method for a smart home.

[0160] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0161] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent possible changes only. Unless explicitly required, individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments. As used in the description of the embodiments, unless the context clearly indicates otherwise, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this application, the term "comprise" and its variants "comprises" and / or including (comprising) refer to the existence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and / or these groups. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same or similar parts between the embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0162] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0163] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0164] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A voice control method for a smart home, characterized in that: include: Obtaining a first target area corresponding to the user's location; Analyze the user's voice and obtain the control instructions corresponding to the user's voice; A target device is determined in the first target area according to the control instruction, and the target device is controlled according to the control instruction to provide voice feedback to the user.

2. The method according to claim 1, characterized in that Obtaining a first target area corresponding to the user location includes: Divide the indoor space into multiple preset areas based on the user's current location, the device layout of the indoor space, the user's current voice and historical voice; Determine a first target area among a plurality of preset areas according to a current location of the user; The preset area includes at least a responded area and a non-responded area; and the first target area includes part or all of the responded area.

3. The method according to claim 2, characterized in that The indoor space is divided into multiple preset areas based on the user's current location, the device layout of the indoor space, the user's current voice and historical voice, including: Obtain the user's movement trajectory and determine the user's movement direction based on the movement trajectory and current location; Determine the target scene based on the movement trajectory, movement direction, current voice and historical voice; The indoor space is divided into multiple preset areas according to the target scene, current location, and equipment layout of the indoor space.

4. The method according to claim 3, characterized in that Determining the moving direction of the user according to the moving trajectory and the current position includes: The displacement of the historical position points at adjacent moments in the moving trajectory is determined as a moving vector; The weighted average direction of the multiple motion vectors is determined as the user's moving direction.

5. The method according to any one of claims 1 to 4, characterized in that: Determining a target device in a first target area according to the control instruction includes: Matching a response intelligent device corresponding to the control instruction in the first target area; In the case where the answering intelligent device has voice feedback conditions, determining that the target device is the answering intelligent device; or, When the answering smart device does not have the voice feedback condition, the target device is determined to be a smart device other than the answering smart device in the first target area.

6. The method according to claim 5, characterized in that The voice feedback conditions include: The answering smart device is currently in operation and no audio is playing.

7. A voice control device for a smart home, characterized in that: include: An acquisition module, configured to acquire a first target area corresponding to a user position; The parsing module is configured to parse the user's voice and obtain the control instruction corresponding to the user's voice; The voice feedback module is configured to determine a target device in the first target area according to the control instruction, and control the target device to provide voice feedback to the user according to the control instruction.

8. A voice control device for a smart home, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the voice control method for a smart home as described in any one of claims 1 to 6 when running the program instructions.

9. A smart device, characterized in that: include: Smart device body; The voice control device for a smart home as described in claim 7 or 8 is installed on the product body.

10. A computer-readable storage medium storing program instructions, characterized in that: When the program instructions are executed, the computer is used to execute the voice control method for a smart home as described in any one of claims 1 to 6.

Images