Sound-based multi-appliance interaction method and device

Abstract

This invention discloses a voice-based method and apparatus for multi-device interaction. The method includes: acquiring multiple sound signals; determining the user's voice location information based on the sound signals and the receiving location information of the corresponding receivers; calculating the user's orientation information based on the voice location information, the receiver location information, and the intensity of the sound signal received by the receiver for each receiver location; determining the interaction weight of each appliance based on the voice location information and the orientation information; and identifying appliances with interaction weights exceeding a threshold as appliances requiring interaction. Applying this voice-based multi-device interaction method eliminates the need to set a wake-up word, allowing direct wake-up of the target appliance and convenient, natural voice control. Users simply need to issue commands to the target appliance, thus meeting consumer needs.

Description

Technical Field

[0001] This invention relates to the field of intelligent interaction of home appliances, and more particularly to a method and apparatus for interaction of multiple home appliances based on voice. Background Technology

[0002] With the increasing popularity of smart homes, most users have more and more smart appliances in their homes, and they also hope to control more devices through voice commands. However, the interaction process usually starts with waking up the device, and the current user experience is not good, specifically in the following ways:

[0003] 1. After setting up a large number of devices, it is quick, convenient and natural to determine which home appliance the user wants to wake up;

[0004] 2. To make the interaction look more natural, most manufacturers adopt the solution of custom wake words, which can set different wake words for different devices, making it more convenient and natural for users. However, setting wake words is not natural enough. Users need to remember each wake word, which does not achieve the naturalness of human-to-human interaction.

[0005] 2. If the wake word is canceled without proper handling, irrelevant content may also respond, or it may respond as if it were from another device, interfering with the user's life;

[0006] Therefore, there is currently no complete wake-up-free interaction solution, which cannot improve the naturalness of interaction between devices, users, and multiple electronic devices. Summary of the Invention

[0007] To address at least one of the aforementioned problems in the prior art, the present invention aims to provide a voice-based method and apparatus for interacting with multiple electronic devices that can determine the object requiring interaction without requiring wake-up. 。

[0008] To achieve the above-mentioned objective, one embodiment of the present invention provides a voice-based method for interaction among multiple electronic devices, comprising the following steps:

[0009] Acquire multiple audio signals, where each audio signal is a signal received by an independent audio receiving device;

[0010] Based on the sound signal and the reception location information of the corresponding audio receiver, the user's vocal position information is determined.

[0011] The user's orientation information is calculated based on the sound emission location information, the sound reception location information, and the intensity of the sound signal received by the sound receiving device corresponding to each sound reception location information;

[0012] The interaction weights of each home appliance are determined based on the sound source location information and the orientation information.

[0013] Home appliances whose interaction weight exceeds the threshold are identified as home appliances that require interaction.

[0014] As a further improvement of the present invention, in the step of acquiring multiple sound signals, at least three sound receiving devices are provided, and these sound receiving devices are not on the same straight line.

[0015] As a further improvement of the present invention, the step of determining the user's vocal location information includes:

[0016] Select two sound signals from all the stated sound signals;

[0017] In the two sound signals, the sound direction of the corresponding receiving device is determined based on each sound signal;

[0018] The intersection of the two sound directions is determined as the user's sound location information.

[0019] As a further improvement of the present invention, the step of selecting two sound signals from all the sound signals includes:

[0020] Of all the sound signals, select the two with the strongest sound signal intensity.

[0021] As a further improvement of the present invention, the step of calculating the user's orientation information includes:

[0022] Based on the sound emission location information, the sound reception location information, and the intensity of the sound signal received by the sound receiving device corresponding to each sound reception location information, calculate the reception angle weight of each sound receiving device;

[0023] Based on the reception angle weights of all radio devices, fit the user's orientation trend;

[0024] Based on the stated orientation trend, determine the user's orientation information.

[0025] As a further improvement of the present invention, the step of determining the interaction weights of each home appliance includes:

[0026] Based on the sound source location information and the orientation information, calculate the first distance between each home appliance and the user's orientation ray;

[0027] Calculate the intersection point of each appliance with the ray the user is facing, and the second distance from that intersection point to the user;

[0028] Determine the distance coefficient for each household appliance based on its first and second distances.

[0029] As a further improvement of the present invention, the step of determining the interaction weights of each home appliance includes:

[0030] Identify the sound signal;

[0031] Based on the degree of relationship between each home appliance and the sound signal, determine the relationship coefficient for each home appliance;

[0032] The interaction weight is determined based on the distance coefficient and the relationship coefficient.

[0033] As a further improvement of the present invention, the step of determining the relationship coefficient between each household appliance and the sound signal includes:

[0034] If the degree of relationship between the home appliance and the sound signal is greater than or equal to the threshold, then the relationship coefficient of the home appliance is 1;

[0035] If the degree of relationship between the home appliance and the sound signal is less than a threshold, then the relationship coefficient of the home appliance is 0.

[0036] To achieve one of the above-mentioned objectives, an embodiment of the present invention provides a voice-based multi-device interaction device, comprising:

[0037] The acquisition module is used to acquire multiple audio signals, where each audio signal is a signal received by an independent audio receiving device;

[0038] The location determination module is used to determine the user's voice location information based on the sound signal and the sound receiving location information of the corresponding sound receiving device;

[0039] The orientation determination module is used to calculate the user's orientation information based on the sound emission location information, the sound reception location information, and the intensity of the sound signal received by the sound receiving device corresponding to each sound reception location information;

[0040] An interaction weight calculation module is used to determine the interaction weight of each home appliance based on the sound emission location information and the orientation information.

[0041] The interaction object determination module is used to determine the home appliances whose interaction weight exceeds the threshold as the home appliances that need to be interacted with.

[0042] To achieve one of the above-mentioned objectives, an embodiment of the present invention provides an electronic device, characterized in that it comprises:

[0043] Storage module, used to store computer programs;

[0044] The processing module, when executing the computer program, can implement the steps in the above-described sound-based multi-device interaction method.

[0045] To achieve one of the above-mentioned objectives, one embodiment of the present invention provides a readable storage medium storing a computer program that, when executed by a processing module, can implement the steps in the above-described voice-based multi-device interaction method.

[0046] Compared with the prior art, the present invention has the following beneficial effects: by applying this voice-based multi-device interaction method, the target home appliance can be woken up directly without setting a wake word, making it convenient and natural to control the target home appliance with voice. Users only need to issue commands to the target device, making the interaction target clear and meeting the user needs of consumers. Attached Figure Description

[0047] Figure 1 This is a flowchart of a voice-based multi-device interaction method according to an embodiment of the present invention;

[0048] Figure 2 This is a schematic diagram of a structure for installing multiple radio receivers in a room according to an embodiment of the present invention;

[0049] Figure 3 This is a schematic diagram illustrating the principle of determining the user's vocal position according to an embodiment of the present invention;

[0050] Figure 4 This is a spatial schematic diagram illustrating the determination of a user's orientation according to an embodiment of the present invention;

[0051] Figure 5 This is a schematic diagram illustrating the principle of determining the user's orientation according to an embodiment of the present invention;

[0052] Figure 6 This is a schematic diagram illustrating the determination of the distance coefficient for each household appliance according to an embodiment of the present invention;

[0053] Figure 7 This is a schematic diagram of a multi-device interaction device based on sound according to an embodiment of the present invention. Detailed Implementation

[0054] The present invention will now be described in detail with reference to the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional modifications made by those skilled in the art based on these embodiments are included within the scope of protection of the present invention.

[0055] One embodiment of the present invention provides a method and apparatus for interacting with multiple home appliances based on sound. By applying this method, the target home appliance can be woken up directly without setting a wake word.

[0056] First, we will explain the user's usage scenarios.

[0057] This embodiment of the sound-based multi-device interaction method determines the device that the user needs to interact with based on the user's position and orientation angle and by using the logic of the regional sound field. Since it is difficult for the user to accurately face the target device when crossing rooms, and the probability of interaction is low when crossing rooms, this method is mainly based on the interaction of home appliances within a single room.

[0058] The room mainly contains two types of equipment: a radio for receiving voice signals and interactive home appliances. The radio itself can be an appliance, or it can be a device solely for receiving voice signals. Before using the methods described below, the room's dimensions need to be confirmed. Figure 2 For example, an XY-axis plan is created, and then the specific spatial coordinates of each home appliance and radio device are confirmed. This information can be entered manually by the user or by a camera device scanning the layout of the entire room to map out the specific spatial coordinates.

[0059] The following is combined Figures 1-6 This invention provides a voice-based method for interacting with multiple home appliances. The principle behind this method is that, in normal human interaction, one speaks to a target object when giving instructions. Based on the premise that the user speaks to the target object, this method can directly activate the target object without waking it up, making the interaction between the user and multiple home appliances more natural.

[0060] Although this application provides method operation steps as shown in the following embodiments or flowcharts, the execution order of these steps is not limited to the execution order provided in the embodiments of this application, where there is no necessary causal relationship in the steps of the method based on conventional or non-creative labor.

[0061] Specifically, this embodiment uses a voice-based method for interacting with multiple electronic devices, such as... Figure 1 As shown, it includes the following steps:

[0062] Step S10: Acquire multiple audio signals, where each audio signal is a signal received by an independent audio receiving device.

[0063] by Figure 2 For example, at least three audio receiving devices are set up, and these devices are not on the same straight line. This allows audio signals to be received from multiple directions, with each device receiving the signal from a different direction. Every three such devices can form a triangular area.

[0064] Step S20: Determine the user's vocal position information based on the sound signal and the reception position information of the corresponding radio device.

[0065] In step S20, the receiving devices can determine the user's location based on the sound source localization algorithm. Each current receiving device can obtain a ray representing the user's possible location. When multiple receiving devices receive the user's sound, multiple rays can be obtained, and the intersection of these rays represents the coordinates of the user's current location.

[0066] Step S20 further includes the following steps:

[0067] Step S21: Select two sound signals from all the sound signals;

[0068] Step S22: In the two sound signals, determine the sound direction of the corresponding receiving device based on each sound signal;

[0069] Step S23: The intersection of the two sound directions is determined as the user's voice location information.

[0070] like Figure 3 As shown, due to the existence of errors, the direction of the ray has a slight angular deviation. The further the extension direction, the greater the error. Therefore, the rays determined by different sound signals may have multiple intersection points. Here, only two are selected to determine the user's voice position information.

[0071] Furthermore, the two strongest sound signals are selected. They are then sorted according to intensity, and two rays corresponding to the strongest two signals are identified. This reduces error. Firstly, stronger sound intensity means closer distance, which means less deviation caused by angular errors. Secondly, louder sound generally results in higher accuracy. Therefore... Figure 3 Although two intersection points can be identified, only the intersection points determined by the two rays with the strongest sound are retained.

[0072] The confirmed location of the user can be denoted as (X0, Y0).

[0073] Step S30: Calculate the user's orientation information based on the sound emission location information, the sound reception location information, and the intensity of the sound signal received by the sound receiving device corresponding to each sound reception location information.

[0074] The direction the user is speaking can be determined by the intensity of the audio received by each receiving device after the user speaks. Based on the coordinates of the sound source location information calculated in step S20, the distance between the sound source location information and each receiving device can be determined. Combining this with the intensity and weighting coefficient of the sound signal received by the receiving devices, the direction the user is speaking can be determined.

[0075] In addition, step S30, which determines the user's orientation information, can also combine image recognition technology to determine the user's orientation.

[0076] Specifically, step S30 also includes the following steps:

[0077] Step S31: Calculate the reception angle weight of each receiving device based on the sound emission location information, the sound reception location information, and the intensity of the sound signal received by the receiving device corresponding to each sound reception location information;

[0078] Step S32: Fit the user's orientation trend based on the reception angle weights of all radio devices;

[0079] Step S33: Determine the user's orientation information based on the orientation trend.

[0080] In step S31, with Figure 4 For example, suppose there are 8 radio receivers in a room with spatial coordinates (X1, Y1), (X2, Y2)...(X8, Y8), and their distances from (X0, Y0) are d1, d2...d8, respectively. The sound intensities received by each receiver are D1, D2...D8, respectively. Then, the reception angle weight of each receiver can be calculated using the following formula:

[0081] Reception angle weight Where i ranges from 1 to 8, and K D and k d It is the weighting adjustment coefficient.

[0082] Step S32 Figure 5 As shown, the sound field distribution of the space is fitted on the graph by weighting each sound receiving angle. It can be seen that it roughly follows a normal distribution. The more sound receiving devices there are in the room, the more accurate the graph can be fitted, and the higher the measurement accuracy.

[0083] Step S33 Figure 5 For example, the position with the highest determined weight value is used to determine the user's orientation information. Figure 5 The user's orientation is roughly between the 4th and 5th radio receivers.

[0084] Step S40: Determine the interaction weight of each home appliance based on the sound source location information and the orientation information.

[0085] Based on the sound location information and orientation information obtained in steps S20 and S30, combined with the spatial coordinate information of each household appliance that has been determined, it can be determined which device the user is speaking to. If there is no device in the user's direction, a list of possible devices and their priorities can be calculated based on the vertical distance from the household appliance to the user's sound direction.

[0086] Step S40 also includes the following steps:

[0087] Step S41: Calculate the first distance between each home appliance and the user's orientation ray based on the sound source location information and the orientation information;

[0088] Step S42: Calculate the intersection point of each home appliance with the ray oriented towards the user, and the second distance from the intersection point to the user;

[0089] Step S43: Determine the distance coefficient for each household appliance based on the first and second distances.

[0090] by Figure 6 For example, the home appliances include s1, s2, and s3, and the user is located at position d0. d1, d2, and d3 are the intersections of the perpendicular lines from the three home appliances to the user's orientation.

[0091] In step S41, the first distance P1 of device s1 is the distance from s1 to d1, the first distance P2 of device s2 is the distance from s2 to d2, and the first distance P3 of device s3 is the distance from s3 to d3.

[0092] In step S42, the second distance D1 of device s1 is the distance from d1 to d0, the second distance D2 of device s2 is the distance from d2 to d0, and the second distance D3 of device s3 is the distance from d3 to d0.

[0093] In step S43, the formula for calculating the distance coefficient is: Where i ranges from 1 to 3, K D and K P This is the weighting adjustment coefficient. In this formula, the closer the device is to the user's orientation, the larger the calculated distance coefficient; the closer the intersection of the device and the perpendicular line from the user's orientation is to the user, the larger the distance coefficient.

[0094] Step S40 further includes the following steps:

[0095] Step S44: Identify the sound signal;

[0096] Step S45: Determine the relationship coefficient of each home appliance based on the degree of relationship between each home appliance and the sound signal;

[0097] Step S46: Determine the interaction weight based on the distance coefficient and the relationship coefficient.

[0098] In step S44, the specific instructions spoken by the user are obtained based on the results of natural language processing. Based on the specific content of the speech, the compatibility between the current instruction and a certain home appliance can be determined, and a relationship coefficient can be calculated.

[0099] In this embodiment, if the degree of relationship between the home appliance and the sound signal is greater than or equal to a threshold, then the relationship coefficient of the home appliance is 1.

[0100] If the degree of relationship between the home appliance and the sound signal is less than a threshold, then the relationship coefficient of the home appliance is 0.

[0101] In other words, the relationship coefficient can only take the value of 0 or 1. For example:

[0102] The user's instruction is to set the temperature to 10 degrees. For example, the functions of appliances such as water heaters, refrigerators, and air conditioners can be related to temperature, so the correlation coefficient for these appliances is 1. However, for devices such as televisions that do not support temperature settings, the correlation coefficient is 0.

[0103] In step S46, for unrelated devices, the interaction weight is 0; for related devices, the higher the interaction weight, the more likely the device is to need interaction.

[0104] Step S50: The home appliances whose interaction weight exceeds the threshold are identified as home appliances that need to be interacted with.

[0105] By applying a threshold to the interaction weight, it can be determined whether the home appliance needs to be woken up. If the threshold is exceeded, the interaction object is determined to be the home appliance. If the threshold is less than the threshold, the method is re-executed, ultimately enabling the user to interact directly without waking up the device.

[0106] Compared with the prior art, this embodiment has the following beneficial effects:

[0107] By applying this voice-based multi-device interaction method, the target home appliance can be woken up directly without setting a wake word, making it convenient and natural to control the target home appliance with voice. Users only need to issue commands to the target device, making the interaction targeted and meeting the user's needs.

[0108] In one embodiment, a voice-based multi-device interaction device is provided, such as... Figure 7 As shown. This voice-based multi-device interaction device includes the following modules, and the specific functions of each module are as follows:

[0109] The acquisition module is used to acquire multiple audio signals, where each audio signal is a signal received by an independent audio receiving device;

[0110] The location determination module is used to determine the user's voice location information based on the sound signal and the sound receiving location information of the corresponding sound receiving device;

[0111] The orientation determination module is used to calculate the user's orientation information based on the sound emission location information, the sound reception location information, and the intensity of the sound signal received by the sound receiving device corresponding to each sound reception location information;

[0112] An interaction weight calculation module is used to determine the interaction weight of each home appliance based on the sound emission location information and the orientation information.

[0113] The interaction object determination module is used to determine the home appliances whose interaction weight exceeds the threshold as the home appliances that need to be interacted with.

[0114] It should be noted that for details not disclosed in the voice-based multi-device interaction device of the present invention embodiments, please refer to the details disclosed in the voice-based multi-device interaction method of the present invention embodiments.

[0115] Those skilled in the art will understand that the schematic diagram is merely an example of a voice-based multi-device interaction device and does not constitute a limitation on the terminal device of the voice-based multi-device interaction device. It may include more or fewer components than shown in the diagram, or combine certain components, or different components. For example, the voice-based multi-device interaction device may also include input / output devices, network access devices, buses, etc.

[0116] The voice-based multi-device interaction device may further include computing devices such as computers, laptops, PDAs, and cloud servers, as well as, but not limited to, a processing module, a storage module, and a computer program stored in the storage module and executable on the processing module, such as the voice-based multi-device interaction method program described above. When the processing module executes the computer program, it implements the steps in the various voice-based multi-device interaction method embodiments described above, for example... Figure 1 The steps are shown.

[0117] Voice-based multi-device interaction devices may also include a signal transmission module and a communication bus. The signal transmission module is used to send data to the processing module or server. The radio, home appliances, and signal transmission module can transmit data wirelessly, such as via Bluetooth, Wi-Fi, or ZigBee. The communication bus is used to establish a connection between the signal transmission module, processing module, and storage module. The communication bus may include a path for transmitting information between the aforementioned signal transmission module, processing module, and storage module.

[0118] In addition, the present invention also proposes an electronic device, which includes a storage module and a processing module. When the processing module executes the computer program, it can implement the steps in the above-mentioned voice-based multi-device interaction method, that is, implement the steps in any of the above-mentioned technical solutions of the voice-based multi-device interaction method.

[0119] The electronic device may be integrated into a voice-based multi-device interaction device, a local terminal device, or part of a cloud server.

[0120] The processing module can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processing module serves as the control center for a voice-based multi-device interaction device, connecting all parts of the device via various interfaces and lines.

[0121] The storage module can be used to store the computer programs and / or modules. The processing module implements various functions of the voice-based multi-device interaction device by running or executing the computer programs and / or modules stored in the storage module and by calling the data stored in the storage module. The storage module may mainly include a program storage area and a data storage area, wherein the program storage area may store the operating system, at least one application program required for a function, etc. In addition, the storage module may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0122] For example, the computer program can be divided into one or more modules / units, which are stored in a storage module and executed by a processing module to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in a voice-based multi-device interaction device.

[0123] Furthermore, one embodiment of the present invention provides a readable storage medium storing a computer program that, when executed by a processing module, can implement the steps in the above-described voice-based multi-device interaction method, that is, implement the steps in any of the technical solutions of the above-described voice-based multi-device interaction method.

[0124] If the module integrated by the voice-based multi-device interaction method is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by the processing module, it can implement the steps of the various method embodiments described above.

[0125] The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying the computer program code, recording media, U disks, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0126] It should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This way of describing the specification is only for clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

[0127] The detailed descriptions listed above are merely specific descriptions of feasible embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. All equivalent embodiments or modifications made without departing from the spirit of the present invention should be included within the scope of protection of the present invention.

Claims

1. A voice-based method for multi-device interaction, characterized in that, Includes the following steps: Acquire multiple audio signals, where each audio signal is a signal received by an independent audio receiving device; Based on the sound signal and the reception location information of the corresponding audio receiver, the user's vocal position information is determined. The user's orientation information is calculated based on the sound emission location information, the sound reception location information, and the intensity of the sound signal received by the sound receiving device corresponding to each sound reception location information; The interaction weights of each home appliance are determined based on the sound source location information and the orientation information. Home appliances whose interaction weight exceeds the threshold are identified as home appliances that require interaction. The determination of the interaction weights of each home appliance includes: Based on the sound source location information and the orientation information, calculate the first distance between each home appliance and the user's orientation ray; Calculate the intersection point of each appliance with the ray the user is facing, and the second distance from that intersection point to the user; Determine the distance coefficient for each household appliance based on its first and second distances; Identify the sound signal; Based on the degree of relationship between each home appliance and the sound signal, determine the relationship coefficient for each home appliance; The interaction weight is determined based on the distance coefficient and the relationship coefficient.

2. The method for multi-device interaction based on sound according to claim 1, characterized in that, In the step of acquiring multiple sound signals, at least three audio receiving devices are set up, and these audio receiving devices are not on the same straight line.

3. The method for multi-device interaction based on sound according to claim 1, characterized in that, The step of determining the user's vocal location information includes: Select two sound signals from all the stated sound signals; In the two sound signals, the sound direction of the corresponding receiving device is determined based on each sound signal; The intersection of the two sound directions is determined as the user's sound location information.

4. The method for multi-device interaction based on sound according to claim 3, characterized in that, The step of selecting two sound signals from all the sound signals includes: Of all the sound signals, select the two with the strongest sound signal intensity.

5. The method for multi-device interaction based on sound according to claim 1, characterized in that, The step of calculating the user's orientation information includes: Based on the sound emission location information, the sound reception location information, and the intensity of the sound signal received by the sound receiving device corresponding to each sound reception location information, calculate the reception angle weight of each sound receiving device; Based on the reception angle weights of all radio devices, fit the user's orientation trend; Based on the stated orientation trend, determine the user's orientation information.

6. The method for multi-device interaction based on sound according to claim 1, characterized in that, The step of determining the relationship coefficient between each home appliance and the sound signal includes: If the degree of relationship between the home appliance and the sound signal is greater than or equal to the threshold, then the relationship coefficient of the home appliance is 1; If the degree of relationship between the home appliance and the sound signal is less than a threshold, then the relationship coefficient of the home appliance is 0.

7. A voice-based multi-device interaction device, characterized in that, include: The acquisition module is used to acquire multiple audio signals, where each audio signal is a signal received by an independent audio receiving device; The location determination module is used to determine the user's voice location information based on the sound signal and the sound receiving location information of the corresponding sound receiving device; The orientation determination module is used to calculate the user's orientation information based on the sound emission location information, the sound reception location information, and the intensity of the sound signal received by the sound receiving device corresponding to each sound reception location information; An interaction weight calculation module is used to determine the interaction weight of each home appliance based on the sound source location information and the orientation information; including: calculating a first distance between each home appliance and the user's orientation ray based on the sound source location information and the orientation information; calculating the intersection point of each home appliance and the user's orientation ray, and a second distance from the intersection point to the user; determining a distance coefficient for each home appliance based on the first and second distances; identifying the sound signal; determining a relationship coefficient for each home appliance based on the degree of relationship between each home appliance and the sound signal; and determining the interaction weight based on the distance coefficient and the relationship coefficient. The interaction object determination module is used to determine the home appliances whose interaction weight exceeds the threshold as the home appliances that need to be interacted with.

8. An electronic device, characterized in that, include: Storage module, used to store computer programs; The processing module, when executing the computer program, can implement the steps of the voice-based multi-device interaction method according to any one of claims 1 to 6.

9. A readable storage medium storing a computer program, characterized in that, When executed by the processing module, the computer program can implement the steps of the voice-based multi-device interaction method according to any one of claims 1 to 6.

Images