A device control method and apparatus, an electronic device, and a storage medium

Abstract

The application discloses a device control method and device, an electronic device and a storage medium, and is used for quickly and simply controlling a device. According to the application, a keyword carried in a received voice instruction is determined, and a candidate device corresponding to the keyword is determined. If the number of the candidate devices is at least two, first time information of the received voice instruction is recognized. Based on the first time information and previously saved use time information of each device, a target device is selected from each candidate device. Based on the voice instruction, the target device is controlled, and therefore, the purpose of quickly and simply controlling the device can be achieved.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and in particular to a device control method, apparatus, electronic device and storage medium. Background Technology

[0002] Smart voice-activated devices (hereinafter referred to as devices for ease of description) have brought great convenience to users' lives. For example, users can control devices such as air conditioners simply by saying "turn on the air conditioner" or even "it's a bit hot in the room." This interaction method works fine when there is only one device fulfilling the user's needs. However, when multiple devices are involved, the user usually needs to clarify which device they want to control. For instance, if a user says "turn on the air conditioner," and the corresponding device includes both the bedroom and living room air conditioners, the user typically needs to clarify whether they want the bedroom or living room air conditioner turned on before control can be achieved. This interaction process is cumbersome, inefficient, and negatively impacts the user experience.

[0003] Therefore, there is an urgent need for a technical solution that can quickly and easily control the equipment. Summary of the Invention

[0004] This application provides a device control method, apparatus, electronic device, and storage medium for quick and easy control of devices.

[0005] In a first aspect, this application provides a device control method, the method comprising:

[0006] Based on the keywords carried in the received voice command, determine the candidate device corresponding to the keyword;

[0007] If the number of candidate devices is at least two, then the first-time information of receiving the voice command is identified;

[0008] Based on the first time information and the pre-saved usage time information of each device, a target device is selected from each candidate device; the target device is controlled based on the voice command.

[0009] Secondly, this application provides a device control apparatus, the apparatus comprising:

[0010] The determination module is used to determine the candidate device corresponding to the keywords carried in the received voice command;

[0011] The recognition module is used to recognize the first-time information of receiving the voice command if the number of candidate devices is at least two.

[0012] The control module is used to select a target device from candidate devices based on the first time information and the pre-saved usage time information of each device; and to control the target device based on the voice command.

[0013] Thirdly, this application provides an electronic device, including: a processor and a memory;

[0014] The memory stores computer instructions;

[0015] The processor is configured to read the computer instructions and execute the method described in any of the preceding descriptions.

[0016] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions for causing the computer to perform the method described in any of the preceding claims.

[0017] Fifthly, this application also provides a computer program product that, when invoked by a computer, causes the computer to perform the method described in any of the preceding claims.

[0018] Since this application can determine the candidate device corresponding to the keyword carried in the received voice command; if the number of candidate devices is at least two, the first time information of the received voice command is identified; based on the first time information and the usage time information of each device in advance, the target device is selected from each candidate device; based on the voice command, the target device is controlled, thereby achieving the purpose of quick and convenient control of the device. Attached Figure Description

[0019] To more clearly illustrate the implementation methods in the embodiments of this application or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0020] Figure 1 A schematic diagram of a first type of device control process provided in some embodiments is shown;

[0021] Figure 2 A schematic diagram of a second device control process provided in some embodiments is shown;

[0022] Figure 3 A schematic diagram of a third device control process provided in some embodiments is shown;

[0023] Figure 4A schematic diagram of a fourth device control process provided in some embodiments is shown;

[0024] Figure 5 A schematic diagram of a fifth device control process provided in some embodiments is shown;

[0025] Figure 6 A schematic diagram of a sixth device control process provided in some embodiments is shown;

[0026] Figure 7 The diagram illustrates a process for determining a set of associated devices according to some embodiments;

[0027] Figure 8 This diagram illustrates another process for determining the set of associated devices provided by some embodiments;

[0028] Figure 9 A schematic diagram of a device control apparatus provided in some embodiments is shown;

[0029] Figure 10 A schematic diagram of an electronic device structure provided by some embodiments is shown. Detailed Implementation

[0030] To make the objectives and implementation methods of this application clearer, exemplary embodiments of this application will be clearly and completely described below with reference to the accompanying drawings of the exemplary embodiments. Obviously, the described exemplary embodiments are only a part of the embodiments of this application, and not all of the embodiments. The terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms can be used interchangeably where appropriate.

[0031] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0032] Figure 1 The diagram illustrates a first type of device control process provided in some embodiments, such as... Figure 1 As shown, the process includes the following steps:

[0033] S101: Based on the keywords carried in the received voice command, determine the candidate device corresponding to the keywords.

[0034] The device control method provided in this application is applied to electronic devices, such as PCs, mobile terminals, servers, and smart voice devices such as smart speakers.

[0035] In one possible implementation, when a user wants to control a smart voice device, they can input a voice command into the electronic device. Upon receiving the voice command, the electronic device can perform text conversion and intent understanding to identify keywords carried in the voice command. Then, based on these keywords, it determines candidate devices corresponding to the keywords (for ease of description, the devices corresponding to the keywords are referred to as candidate devices). Optionally, the keywords can include noun-like device keywords such as air conditioner, curtains, and lights, as well as verb-like control keywords such as open and close. Devices containing these device keywords in the user's saved device list can be considered as candidate devices. For example, if the user's input voice command is "turn on the air conditioner," and the user's device list includes both a living room air conditioner and a bedroom air conditioner, then both the living room air conditioner and the bedroom air conditioner can be identified as candidate devices.

[0036] S102: If the number of candidate devices is at least two, then identify the first time information of receiving the voice command.

[0037] In one possible implementation, when the number of candidate devices is empty, it can be assumed that the user's device list does not yet contain a device that satisfies the user's voice command. The user can then be prompted to purchase the relevant device or bind the relevant device to the electronic device, so that the device list stored on the electronic device includes the relevant device. Optionally, when the number of candidate devices is 1, this candidate device can be directly designated as the target device, and the target device can be controlled based on voice commands. The control of the target device based on voice commands can employ existing technologies, which will not be elaborated upon here.

[0038] In one possible implementation, if the number of candidate devices is at least two, that is, if the number of candidate devices is multiple, in order to quickly and accurately determine the target device from the candidate devices, the time information of receiving the voice command can be identified first (for ease of description, the time when the voice command is received is called the first time information), and the target device can be determined by the following S103 steps.

[0039] S103: Based on the first time information and the pre-saved usage time information of each device, select a target device from each candidate device; control the target device based on the voice command.

[0040] In one possible implementation, after recognizing the first time information when a voice command is received, the target device can be selected from the candidate devices based on the first time information and the pre-saved user usage time information of each device.

[0041] In one possible implementation, to quickly and accurately identify the target device from candidate devices, the user's usage patterns and habits can be analyzed based on the time and frequency of device usage. This allows for the discovery of relationships between devices, and devices with strong correlations that the user frequently uses can be saved into a single set of associated devices. For example, if a user typically performs a series of control operations around 6:00 PM, such as turning on the living room porch light, turning on the living room air conditioner, and closing the living room window, then these actions can be considered strongly correlated and saved into a set of associated devices. The method for establishing these associated device sets will be described in subsequent embodiments and will not be elaborated upon here.

[0042] In one possible implementation, when selecting a target device from candidate devices based on first time information and pre-saved usage time information of each device, it can be first determined whether any other device (referred to as the first other device for convenience) has been controlled (referred to as the first control for convenience). If any first other device has been controlled within the pre-saved time period before the first time information, then the first other device can be regarded as the operated device; and according to the pre-saved set of the user's associated devices, it can be determined whether any candidate device and the operated device are located in the same set of associated devices (referred to as the first associated device set for convenience), and in the first associated device set, the control performed on any candidate device is the second control carried by voice command, and the control performed on the operated device is the aforementioned first control. If so, it can be considered that the user is very likely to want to control the candidate device located in the first associated device set, and the candidate device can be determined as the target device.

[0043] For example, taking the set of associated devices that includes "turn on the living room porch light, turn on the living room air conditioner, and close the living room window" as an example, assuming the user's voice command is to turn on the air conditioner, both the living room air conditioner and the bedroom air conditioner can be considered as candidate devices. Assuming the set duration is half an hour, if the system detects that the living room porch light was turned on within half an hour before the first time information, then the living room porch light can be considered an operated device. Since both turning on the living room air conditioner and turning on the living room porch light (operated devices) are located in the same first associated device set of "turn on the living room porch light, turn on the living room air conditioner, and close the living room window," the living room air conditioner can be identified as the target device, and the target device can be controlled based on the second control carried in the voice command, namely "turn on."

[0044] In one possible implementation, the associated device set may also carry specific operating parameters for the devices. When controlling the target device based on voice commands, the control can also be based on the specific operating parameters carried in the first associated device set, etc. For example, assuming the specific operating parameters for the living room air conditioner carried in the first associated device set are "the air conditioner temperature is 26°C, and the mode is cooling," then when controlling the living room air conditioner as a target device based on voice commands, the operating temperature of the living room air conditioner can be intelligently set to 26°C, and the operating mode can be set to cooling.

[0045] In one possible implementation, considering that devices located in the same set of associated devices are usually those that the user wants to control together, to improve the user experience, when controlling the target device based on voice commands, other devices in the first set of associated devices besides the target device and the already operated device (referred to as second other devices for convenience) can also be controlled according to the control of the second other devices carried in the first set of associated devices (referred to as third control for convenience). For example, taking the first set of associated devices as "turn on the living room porch light, turn on the living room air conditioner, and close the living room window," the voice command is to turn on the air conditioner. After recognizing the already operated device as the living room porch light and identifying the target device as the living room air conditioner, the user can turn on the living room air conditioner and close the living room window.

[0046] To facilitate understanding, the device control process provided in this application will be illustrated below with a specific embodiment. (See reference...) Figure 2 , Figure 2 A schematic diagram of a second device control process provided in some embodiments is shown, which includes the following steps:

[0047] S201: Based on the keywords carried in the received voice command, determine the candidate device corresponding to the keywords.

[0048] S202: If the number of candidate devices is at least two, then identify the first-time information received by the voice command.

[0049] S203: If any first control has been performed on any first other device within a set time period prior to the first time information, then the first other device is regarded as the operated device; according to the pre-saved set of each associated device of the user, it is determined whether any candidate device and the operated device are located in the same first associated device set, and if the control performed on any candidate device in the first associated device set is the second control carried by the voice command, and the control performed on the operated device is the first control, then the candidate device is determined as the target device.

[0050] S204: Control the target device based on voice commands.

[0051] To facilitate understanding, a specific embodiment will be used to illustrate the device control process provided in this application. (See attached document.) Figure 3 , Figure 3 A schematic diagram of a third device control process provided in some embodiments is shown, which includes the following steps:

[0052] S301: Based on the keywords carried in the received voice command, determine the candidate device corresponding to the keywords.

[0053] S302: If the number of candidate devices is at least two, then identify the first-time information received by the voice command.

[0054] S303: If any first control has been performed on any first other device within a set time period prior to the first time information, then the first other device is regarded as the operated device; according to the pre-saved set of each associated device of the user, it is determined whether any candidate device and the operated device are located in the same first associated device set, and if the control performed on any candidate device in the first associated device set is the second control carried by the voice command, and the control performed on the operated device is the first control, then the candidate device is determined as the target device.

[0055] S304: Based on voice commands, control the target device, and for the second other device in the first associated device set, excluding the target device and the operated device, control the second other device according to the third control of the second other device carried in the first associated device set.

[0056] In one possible implementation, considering that users may tend to perform the same control operations on the device within the same time period each day—for example, a user might habitually open the window around 7:00 AM and turn on the living room porch light around 6:00 PM—to facilitate quick and convenient device control, when selecting the target device from candidate devices based on the first time information and pre-saved usage time information of each device, it can also be determined whether any candidate device has been controlled via a second voice command within a historical time period corresponding to the first time information. If so, that candidate device is identified as the target device. For example, assuming the first time information for receiving the voice command is 9:30 AM, the historical time period can be defined as 9:00 AM to 10:00 AM of the previous day or several days prior. If the control to turn on the living room air conditioner was performed within this historical time period, the living room air conditioner can be identified as the target device. In another possible implementation, the candidate device that has been controlled the most times within multiple historical time periods—that is, the candidate device most frequently used by the user—can also be identified as the target device.

[0057] To facilitate understanding, a specific embodiment will be used to illustrate the device control process provided in this application. (See attached document.) Figure 4 , Figure 4 A schematic diagram of a fourth device control process provided in some embodiments is shown, which includes the following steps:

[0058] S401: Based on the keywords carried in the received voice command, determine the candidate device corresponding to the keywords.

[0059] S402: If the number of candidate devices is at least two, then identify the first-time information received by the voice command.

[0060] S403: Determine whether any candidate device has been subjected to second control via voice command within the historical time period corresponding to the first time information; if so, determine the candidate device as the target device.

[0061] S404: Controls the target device based on voice commands.

[0062] In one possible implementation, the associated device set may carry time information for controlling the device (referred to as second time information for convenience). Taking the associated device set as "turn on the living room porch light, turn on the living room air conditioner, close the living room window" as an example, the associated device set carrying the second time information could be "turn on the living room porch light at time t1, turn on the living room air conditioner at time t2, close the living room window at time t3," etc. In another possible implementation, to improve user experience by controlling other devices in the associated device set while controlling the target device, optionally, the associated device set where the target device is located during a historical time period can be determined based on the second time information carried by each associated device set of the user (referred to as the second associated device set for convenience). Then, other devices in the second associated device set besides the target device (referred to as the third other devices for convenience) can be controlled according to the control information carried in the second associated device set (referred to as the fourth control for convenience). It is understood that the control of the target device in the second associated device set is the second control carried by the voice command. For example, taking the second set of associated devices as "turn on the living room porch light at 18:00, turn on the living room air conditioner at 18:01, and close the living room window at 18:02", the voice command received is to turn on the air conditioner. The first time information of the voice command received is 18:01. While the target device is determined to be the living room air conditioner and the living room air conditioner is turned on, the living room porch light in the second set of associated devices where the target device is located can also be turned on and the living room window closed.

[0063] To facilitate understanding, a specific embodiment will be used to illustrate the device control process provided in this application. (See attached document.) Figure 5 , Figure 5 A schematic diagram of a fifth device control process provided in some embodiments is shown, which includes the following steps:

[0064] S501: Based on the keywords carried in the received voice command, determine the candidate device corresponding to the keywords.

[0065] S502: If the number of candidate devices is at least two, then identify the first-time information received by the voice command.

[0066] S503: Determine whether any candidate device has been subjected to second control via voice command within the historical time period corresponding to the first time information; if so, determine the candidate device as the target device.

[0067] S504: Based on voice commands, control the target device, and if, according to the second time information carried by each set of associated devices of the user that is stored in advance, it is determined that the target device is located in the second set of associated devices within the historical time period corresponding to the first time information, and the control of the target device in the second set of associated devices is the second control carried by the voice command, then for the third other device in the second set of associated devices other than the target device, control the third other device according to the fourth control carried by the second set of associated devices.

[0068] In one possible implementation, in order to accurately determine the target device, before determining whether the second control carried by the voice command has been performed on any candidate device within the historical time period corresponding to the first time information, it can be further determined whether the first control has been performed on other devices within a set time period before the first time information. If the first control has been performed on any other device (the first other device), then the first other device can be designated as the operated device as provided in the above embodiment. Based on the pre-saved set of each associated device of the user, it is determined whether any candidate device and the operated device are located in the same first associated device set, and in the first associated device set, the control performed on any candidate device is the second control carried by the voice command, and the control performed on the operated device is the first control. If so, then the candidate device is determined as the target device.

[0069] Optionally, if no first control has been performed on other devices within a set time period prior to determining the first time information, then determine whether any candidate device has been subject to second control via voice command within the historical time period corresponding to the first time information. If so, then determine the candidate device as the target device.

[0070] To facilitate understanding, a specific embodiment will be used to illustrate the device control process provided in this application. (See attached document.) Figure 6 , Figure 6 A schematic diagram of a sixth device control process provided in some embodiments is shown, which includes the following steps:

[0071] S601: Based on the keywords carried in the received voice command, determine the candidate device corresponding to the keywords.

[0072] S602: If the number of candidate devices is at least two, then identify the first-time information received by the voice command.

[0073] S603: Determine whether other devices have been controlled within the set time period prior to the first time information. If yes, proceed to S604; otherwise, proceed to S605.

[0074] S604: If any first control has been performed on any first other device within the set time period prior to the first time information, then the first other device is regarded as the operated device; according to the pre-saved set of each associated device of the user, it is determined whether any candidate device and the operated device are located in the same first associated device set, and in the first associated device set, the control performed on any candidate device is the second control carried by the voice command, and the control performed on the operated device is the first control; if so, then the candidate device is determined as the target device, and S606 is performed.

[0075] S605: Determine whether any candidate device has been subjected to second control via voice command within the historical time period corresponding to the first time information; if so, determine the candidate device as the target device.

[0076] S606: Controls target devices based on voice commands.

[0077] Optionally, if the target device cannot be determined based on the methods in S604 and S605, further interaction with the user can be conducted to inquire about the device the user wants to control, etc., which will not be elaborated here.

[0078] The following describes the process of determining the set of associated devices.

[0079] In one possible implementation, when determining the sets of associated devices, the steps can be based on historical user data on device usage stored in a database, i.e., information about each control device. For ease of description, information such as turning on the living room air conditioner or closing the living room window included in the set of associated devices is referred to as control device information. Optionally, considering that adding devices with low user frequency to the set of associated devices might reduce the accuracy of identifying target devices, to improve the accuracy of identifying target devices, the usage weight (represented by w(d) for ease of understanding) of each device (control device information) can be determined first. Devices (control device information) with w(d) greater than a set usage weight threshold (represented by α for ease of understanding) are retained in the database (e.g., a frequent usage database), while devices (control device information) with w(d) less than the set usage weight threshold α are deleted.

[0080] Optionally, when determining the usage weight w(d) of each device (information of the control device), the number of days each control device's information appears within a set statistical period can be determined first (represented by f(d) for ease of understanding). The statistical period can be flexibly set according to needs; for example, it can be 3 days, 1 week, 15 weeks, 1 month, 6 months, etc. Assuming the information of the living room air conditioner control device appears several times on the first and second days respectively, then the number of days the information of this control device appears, f(d), is 2. Optionally, the usage weight w(d) of each control device's information can be determined based on the number of days f(d) each control device's information appears and the preset weight coefficient corresponding to each control device's information (represented by a for ease of understanding). For example, for each control device's information, the product of the number of days f(d) the information of that control device appears and the preset weight coefficient a corresponding to that control device's information can be used as the usage weight w(d) of that control device's information, i.e., w(d) = a * f(d). The preset weight coefficient 'a' and the weight threshold 'α' can be flexibly set according to requirements, and this application does not impose specific limitations on them.

[0081] In one possible implementation, after retaining the information of control devices whose usage weight w(d) is greater than the set usage weight threshold α, the information of control devices whose usage weight w(d) is greater than the set usage weight threshold α can be used as devices frequently used by the user (frequent items). The retained frequent items are stored in a frequent database, and the subsequent process of determining each set of associated devices (also known as a frequent sequence) is performed based on each frequent item in the frequent database.

[0082] In one possible implementation, when determining the sets of associated devices, the following operations may be performed separately for each control device in the database:

[0083] First, identify the information of the control devices that appear simultaneously with the information of one of the control devices within at least two days within a set statistical period (for ease of description, this is referred to as the information of the control-associated devices). This process can be accomplished using the Prefix-Projected Pattern Growth (PrefixSpan) algorithm, a type of association rule mining algorithm used to discover frequent sequences.

[0084] After identifying the information of a control-related device that appears simultaneously with the information of one of the control devices within at least two days, the information can be used as a basis for determining the time (t) of the appearance of that control device's information. iThe time (t) when the information of the control-associated device appears on the same day. i-1 The time interval (t) i -t i-1 The device sequence weight (represented by W(s)) is determined by taking the information of the control device and the information of the associated control device as a set of related devices, and the number of days they appear simultaneously (w(s)).

[0085] In one possible implementation, considering that the more days the information from two control devices appears simultaneously, the higher the correlation between their information. Simultaneously, the shorter the time interval between the appearance of information from two control devices, the higher the correlation between their information. Therefore, when determining the device sequence weight W(s), the number of days w(s) during which the information from one control device and its corresponding associated control device appear simultaneously can be used as the numerator, and the time interval (t) during which the information from that control device and its corresponding associated control device appear on the same day can be used as the numerator. i -t i-1 The device sequence weight W(s) is calculated using the denominator. Optionally, when calculating the device sequence weight W(s) of an associated device set, it can be based on the time interval between the information of every two control devices in the associated device set. Where n is the total number of control devices included in the associated device set, and t i -t i-1 Let τ be the time interval between the occurrence of information from any two control devices. τ is a coefficient greater than 0 to prevent the denominator from being zero. For example, taking the associated device set as "turn on the living room porch light, turn on the living room air conditioner, close the living room window," and assuming that the number of days when turning on the living room porch light, turning on the living room air conditioner, and closing the living room window occur simultaneously is 3 days, then the time interval t between turning on the living room porch light and turning on the living room air conditioner... i -t i-1 The time interval t is 1 minute between turning on the living room porch light and closing the living room window. i -t i-1 The time interval t is 2 minutes between turning on the living room air conditioner and closing the living room window. i -t i-1 If the time interval is 1 minute, then the device sequence weight of this associated device set is...

[0086] In one possible implementation, after determining the device sequence weight W(s) for each associated device set, it can be determined whether the device sequence weight W(s) of the associated device set is greater than a set device sequence weight threshold (denoted by β for ease of understanding). If the device sequence weight W(s) of a certain associated device set is greater than the set device sequence weight threshold β, it can be considered that the correlation between the devices in the associated device set is relatively strong, and the associated device set can be saved; the subsequent process of determining the target device is based on the saved associated device set.

[0087] Understandably, if the device sequence weight W(s) of a certain associated device set is not greater than the set device sequence weight threshold β, it can be considered that the correlation between the devices in the associated device set is relatively weak, and the associated device set can be deleted, without using the associated device set as the basis for subsequent determination of target devices.

[0088] For ease of understanding, the process of determining the set of associated devices provided in this application will be described below through a specific embodiment. (See reference...) Figure 7 , Figure 7 The diagram illustrates a process for determining a set of associated devices according to some embodiments, the process including the following steps:

[0089] S701: For each control device in the database, determine the information of control-related devices that appear simultaneously with the information of that control device within a set statistical period of at least two days.

[0090] S702: Based on the time interval between the occurrence of information from the control device and information from the control-related device on the same day, and the number of days they occur simultaneously, determine the device sequence weight of the set of related devices composed of the information from the control device and the information from the control-related device.

[0091] S703: If the device sequence weight of the associated device set is greater than the set device sequence weight threshold, then the associated device set is saved; otherwise, the associated device set is deleted.

[0092] For ease of understanding, the process of determining the set of associated devices provided in this application will be described below through a specific embodiment. (See reference...) Figure 8 , Figure 8 The diagram illustrates another process for determining the associated device set according to some embodiments, which includes the following steps:

[0093] S801: Determine the number of days that information from each control device appears within a set statistical period; based on the number of days that information from each control device appears and the preset weight coefficient corresponding to the information from each control device, determine the usage weight of information from each control device; retain information from control devices whose usage weight is greater than the set usage weight threshold, and delete information from control devices whose usage weight is not greater than the set usage weight threshold.

[0094] S802: For each control device information stored in the database, determine the information of control-related devices that appear simultaneously with the information of that control device for at least two days within a set statistical period.

[0095] S803: Based on the time interval between the occurrence of information from the control device and information from the control-related device on the same day, and the number of days they occur simultaneously, determine the device sequence weight of the set of related devices composed of the information from the control device and the information from the control-related device.

[0096] S804: If the device sequence weight of the associated device set is greater than the set device sequence weight threshold, then the associated device set is saved; otherwise, the associated device set is deleted.

[0097] This application can intelligently determine the target device based on the user's usage habits, thereby not only improving the speed and convenience of device control and reducing the cumbersome process of interaction with the user, thus improving efficiency, but also improving the accuracy of device control and enhancing the user experience.

[0098] In one possible implementation, considering that when a user first uses the voice device (i.e., during the cold start phase), historical data on the user's device usage may not be available or may be limited, and the set of associated devices cannot be determined based on the methods provided in the above embodiments, the system's default set of associated devices applicable to most users (device sequence mode) can be used as the user's associated device set. In other words, the system's default usage habits of most users can be used as the user's usage habits, and the target device can be determined based on the system's default set of associated devices. For example, the system's default device sequence mode (associated device set) could be: "Turn on the living room air conditioner at time t, turn on the living room air conditioner at time t1, close the living room window at time t2," "The washing machine on the balcony finishes washing at time t, the clothes rack on the balcony lowers at time t1, and rises at time t2," "Turn on the stove at time t, turn on the range hood at time t1, adjust the range hood's airflow at time t2," "Open the oven door at time t, close the oven door at time t1, and start the oven at time t2," etc., and can be flexibly set according to needs. This application does not specifically limit this.

[0099] Based on the same technical concept, this application provides a device control apparatus. Figure 9 The diagram illustrates a device control apparatus according to some embodiments, such as... Figure 9 As shown, the device includes:

[0100] The determining module 91 is used to determine the candidate device corresponding to the keyword carried in the received voice command;

[0101] The recognition module 92 is used to recognize the first-time information of receiving the voice command if the number of candidate devices is at least two.

[0102] The control module 93 is used to select a target device from the candidate devices based on the first time information and the pre-saved usage time information of each device; and to control the target device based on the voice command.

[0103] In one possible implementation, the control module 93 is specifically used for:

[0104] If any first control has been performed on any first other device within a set time period prior to the first time information, then the first other device is regarded as the operated device.

[0105] Based on the pre-saved set of associated devices for each user, determine whether any candidate device and the already operated device are in the same first set of associated devices, and in the first set of associated devices, the control performed on any candidate device is the second control carried by the voice command, and the control performed on the already operated device is the first control. If so, then the candidate device is determined as the target device.

[0106] In one possible implementation, the control module 93 is further configured to:

[0107] For the second other device in the first set of associated devices, other than the target device and the operated device, control is performed on the second other device according to the third control carried in the first set of associated devices.

[0108] In one possible implementation, the control module 93 is specifically used for:

[0109] If the second control carried by the voice command was performed on any candidate device within the historical time period corresponding to the first time information, then the candidate device is determined as the target device.

[0110] In one possible implementation, the control module 93 is further configured to:

[0111] If, based on the second time information carried by each set of associated devices of a user that is saved in advance, it is determined that the target device is located in the second set of associated devices during the historical time period, and the control performed on the target device in the second set of associated devices is the second control carried by the voice command, then for the third other device in the second set of associated devices other than the target device, the fourth control carried by the second set of associated devices is used to control the third other device.

[0112] In one possible implementation, the control module 93 is further configured to:

[0113] Determine whether other devices have been controlled within a set time period prior to the first time information. If not, proceed with the next steps.

[0114] In one possible implementation, the control module 93 is specifically used for:

[0115] Perform the following operations on the information of each control device in the database:

[0116] Identify information about control-related devices that appears simultaneously with information about a control device for at least two days within a set statistical period.

[0117] Based on the time interval and the number of days that the information of the one control device and the information of the control associated device appear on the same day, determine the device sequence weight of the associated device set composed of the information of the one control device and the information of the control associated device;

[0118] If the weight of the device sequence is greater than the set threshold for device sequence weight, the associated device set is saved; otherwise, the associated device set is deleted.

[0119] In one possible implementation, the control module 93 is further configured to:

[0120] Determine the number of days each control device's information appears within the set statistical period;

[0121] Based on the number of days that information from each control device appears and the preset weight coefficient corresponding to the information from each control device, the usage weight of information from each control device is determined.

[0122] Information on control devices whose weights are greater than the set weight threshold is retained, and subsequent steps are performed based on the retained information of each control device.

[0123] Based on the same technical concept and the above embodiments, this application also provides an electronic device. Figure 10The diagram illustrates a schematic representation of an electronic device structure provided in some embodiments, such as... Figure 10 As shown, it includes: processor 101, communication interface 102, memory 103 and communication bus 104, wherein processor 101, communication interface 102 and memory 103 communicate with each other through communication bus 104.

[0124] The memory 103 stores a computer program, which, when executed by the processor 101, causes the processor 101 to complete the steps of the above-described device control method.

[0125] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0126] The communication interface 102 is used for communication between the above-mentioned electronic device and other devices.

[0127] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0128] The processors mentioned above can be general-purpose processors, including central processing units, network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits, field-programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0129] Based on the same technical concept and the above embodiments, this application provides a computer-readable storage medium storing a computer program executable by an electronic device, wherein computer-executable instructions are used to cause a computer to execute the process executed by the aforementioned device control method.

[0130] The aforementioned computer-readable storage medium can be any available medium or data storage device that can be accessed by the processor in an electronic device, including but not limited to magnetic storage such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), optical storage such as CDs, DVDs, BDs, HVDs, etc., and semiconductor storage such as ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs), etc.

[0131] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0133] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0135] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A device control method, characterized in that, The method includes: Based on the keywords carried in the received voice command, determine the candidate device corresponding to the keyword; If the number of candidate devices is at least two, then the first-time information of receiving the voice command is identified; Based on the first time information and the pre-saved usage time information of each device, a target device is selected from each candidate device; the target device is controlled based on the voice command. The step of selecting a target device from candidate devices based on the first time information and pre-saved usage time information of each device includes: If any first control has been performed on any first other device within a set time period prior to the first time information, then the first other device is regarded as the operated device. Based on the pre-saved set of each user's associated devices, determine whether any candidate device and the already operated device are in the same first set of associated devices, and in the first set of associated devices, the control performed on any candidate device is the second control carried by the voice command, and the control performed on the already operated device is the first control. If so, then the candidate device is determined as the target device. The process of determining the sets of associated devices includes: Perform the following operations on the information of each control device in the database: Identify information about control-related devices that appears simultaneously with information about a control device for at least two days within a set statistical period. Based on the time interval and the number of days that the information of the one control device and the information of the control associated device appear on the same day, determine the device sequence weight of the associated device set composed of the information of the one control device and the information of the control associated device; If the weight of the device sequence is greater than the set threshold for device sequence weight, the associated device set is saved; otherwise, the associated device set is deleted.

2. The method according to claim 1, characterized in that, The method further includes: For the second other device in the first set of associated devices, other than the target device and the operated device, control is performed on the second other device according to the third control carried in the first set of associated devices.

3. The method according to claim 1, characterized in that, The step of selecting a target device from candidate devices based on the first time information and pre-saved usage time information of each device includes: If the second control carried by the voice command was performed on any candidate device within the historical time period corresponding to the first time information, then the candidate device is determined as the target device.

4. The method according to claim 3, characterized in that, The method further includes: If, based on the second time information carried by each set of associated devices of a user that is saved in advance, it is determined that the target device is located in the second set of associated devices during the historical time period, and the control performed on the target device in the second set of associated devices is the second control carried by the voice command, then for the third other device in the second set of associated devices other than the target device, the fourth control carried by the second set of associated devices is used to control the third other device.

5. The method according to claim 3, characterized in that, Before determining whether any candidate device has undergone the second control carried by the voice command within the historical time period corresponding to the first time information, the method further includes: Determine whether other devices have been controlled within a set time period prior to the first time information. If not, proceed with the next steps.

6. The method according to claim 1, characterized in that, Before performing the operations on the information of each control device in the database, the method further includes: Determine the number of days each control device's information appears within the set statistical period; Based on the number of days that information from each control device appears and the preset weight coefficient corresponding to the information from each control device, the usage weight of information from each control device is determined. Information on control devices whose weights are greater than the set weight threshold is retained, and subsequent steps are performed based on the retained information of each control device.

7. A device control apparatus, characterized in that, The device includes: The determination module is used to determine the candidate device corresponding to the keywords carried in the received voice command; The recognition module is used to recognize the first-time information of receiving the voice command if the number of candidate devices is at least two. The control module is used to select a target device from candidate devices based on the first time information and the pre-saved usage time information of each device; and to control the target device based on the voice command. Specifically, the control module is configured to: if any first other device has been controlled within a set time period prior to the first time information, then designate the first other device as an operated device; determine, based on a pre-saved set of associated devices for the user, whether any candidate device and the operated device are located in the same first associated device set, and in the first associated device set, the control performed on any candidate device is the second control carried by the voice command, and the control performed on the operated device is the first control; if so, then determine the candidate device as the target device. The control module is specifically configured to perform the following operations on the information of each control device in the database: determine the information of control-related devices that appear simultaneously with the information of a control device within a set statistical period for at least two days; determine the device sequence weight of the associated device set composed of the information of the control device and the information of the control-related device based on the time interval between their appearance on the same day and the number of days they appear simultaneously; if the device sequence weight is greater than a set device sequence weight threshold, then the associated device set is saved; otherwise, the associated device set is deleted.

8. An electronic device, characterized in that, The electronic device includes at least a processor and a memory, the processor being configured to implement the steps of the method as described in any one of claims 1-6 when executing a computer program stored in the memory.

Images