Smart device voice wake-up method, device, electronic device and storage medium

Abstract

The present invention provides a method, apparatus, electronic device and storage medium for voice wake-up of smart devices. The method determines a target response device for responding to a voice signal based on distance information between each smart device and a user, usage information of each smart device and voice interaction information of the user, and controls the target response device to respond to the voice signal. This method can reduce the possibility that the response device determined by considering distance information alone in the prior art cannot meet the actual needs of the user, so that the target response device is more in line with the actual needs of the user, thereby improving not only the accuracy of the target response device but also the user experience.

Description

Technical Field

[0001] The present invention relates to the field of home appliance control technology, and in particular to a method and device for voice wake-up of an intelligent device, an electronic device, and a storage medium. Background Art

[0002] With the popularity of smart homes, a large number of smart devices that support voice control have emerged. These smart devices generally have integrated voice modules. When in standby mode, the voice recognition module can pick up and recognize surrounding voice signals. When it determines that the voice signal matches its preset wake-up signal, it wakes up from standby mode and responds to the user's voice signal as a responsive device.

[0003] Because smart devices may have the same wake-up signal, multiple smart devices may respond after the user wakes up. Currently, a common technical solution to this problem is to use distributed wake-up technology to calculate the smart device closest to the user and prioritize its wake-up. The prioritized smart device will then be used as the responding device to respond to the user's voice signal.

[0004] This distance-based priority wakeup method prioritizes the smart device closest to the user as the responding device, which may not be the desired device and therefore does not meet their actual needs. Furthermore, in confined spaces, or when the user is closest to two smart devices at the same time, it is difficult to guarantee the accuracy of the responding device. Summary of the Invention

[0005] The present invention provides a method and apparatus for waking up an intelligent device by voice, an electronic device and a storage medium, for resolving the defects in the prior art.

[0006] The present invention provides a method for waking up an intelligent device, comprising:

[0007] Determine each smart device corresponding to the wake-up information in the user's voice signal;

[0008] If it is determined that the smart devices do not include a preset response device, obtaining distance information between the smart devices and the user, usage information of the smart devices, and voice interaction information of the user within a first preset time period before and near the current moment;

[0009] Based on the distance information, the usage information, and the voice interaction information, a target response device among the smart devices is determined, and the target response device is controlled to respond to the voice signal.

[0010] According to a smart device wake-up method provided by the present invention, determining a target response device among the smart devices based on the distance information, the usage information, and the voice interaction information specifically includes:

[0011] For any of the smart devices, determining whether the distance information of the smart device and the usage information of the smart device meet corresponding information determination conditions, and obtaining a first determination result corresponding to the distance information of the smart device and a second determination result corresponding to the usage information of the smart device;

[0012] Recognize the voice interaction information, determine a recognition result, and based on the recognition result, determine whether any of the smart devices is the responding device, thereby obtaining a third determination result corresponding to the any of the smart devices;

[0013] Determining score information of any one of the smart devices based on the first judgment result, the second judgment result, and the third judgment result;

[0014] The target response device is selected from the smart devices based on the score information of the smart devices.

[0015] According to a smart device wake-up method provided by the present invention, determining the score information of any smart device based on the first judgment result, the second judgment result, and the third judgment result specifically includes:

[0016] Determining influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result respectively;

[0017] The influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result are added together to obtain score information of any smart device.

[0018] According to a smart device wake-up method provided by the present invention, determining the influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result, respectively, specifically includes:

[0019] For any judgment result corresponding to any smart device, if any judgment result is a positive judgment result, determining an influence score corresponding to any judgment result based on a preset score of the positive judgment result;

[0020] If any of the judgment results is a negative judgment result, the influence score corresponding to the any of the judgment results is determined based on the preset score of the negative judgment result.

[0021] According to a smart device wake-up method provided by the present invention, the usage information includes at least any one of the following:

[0022] Status information of each smart device at the current moment;

[0023] Usage information of each smart device within a second preset time period before and close to the current moment.

[0024] According to a smart device wake-up method provided by the present invention, the preset score of the positive judgment result corresponding to the distance information, the preset score of the positive judgment result corresponding to the status information, the preset score of the positive judgment result corresponding to the usage information, and the preset score of the positive judgment result corresponding to the voice interaction information decrease in sequence.

[0025] A smart device wake-up method provided by the present invention further includes:

[0026] If it is determined that the smart devices include the preset response device and the smart devices are in the same device group, the preset response device is controlled to respond to the voice signal.

[0027] The present invention also provides a smart device wake-up device, comprising:

[0028] A device determination module is used to determine each smart device corresponding to the wake-up information in the user's voice signal;

[0029] an information acquisition module, configured to, if it is determined that the smart devices do not include a preset response device, acquire distance information between the smart devices and the user, usage information of the smart devices, and voice interaction information of the user within a first preset time period before and near the current moment;

[0030] A control response module is used to determine a target response device among the smart devices based on the distance information, the usage information and the voice interaction information, and control the target response device to respond to the voice signal.

[0031] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-described smart device wake-up methods are implemented.

[0032] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described smart device wake-up methods.

[0033] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any of the above-mentioned smart device wake-up methods are implemented.

[0034] The present invention provides a method, apparatus, electronic device, and storage medium for voice wake-up of smart devices. First, the method determines the smart devices corresponding to the wake-up information in the user's voice signal. When the smart devices do not contain a preset response device, the method obtains the distance information between the smart devices and the user, the usage information of the smart devices, and the voice interaction information of the user in a first preset time period before and close to the current moment. Finally, based on the distance information, usage information, and voice interaction information, the method determines the target response device in each smart device, and controls the target response device to respond to the voice signal. This method determines the target response device for responding to the voice signal by using the distance information between the smart devices and the user, the usage information of the smart devices, and the voice interaction information of the user, and controls the target response device to respond to the voice signal. This method can reduce the possibility that the response device determined by considering the distance information alone in the prior art cannot meet the actual needs of the user, making the target response device more in line with the actual needs of the user, thereby not only improving the accuracy of the target response device, but also improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 This is a flow chart of the voice wake-up method for an intelligent device provided by the present invention;

[0037] Figure 2 This is a schematic diagram of the structure of the voice wake-up device for smart devices provided by the present invention;

[0038] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0039] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0040] At present, in order to solve the problem that all smart devices with the same wake-up signal may not respond to the user's voice control commands, a common technical solution is to use distributed wake-up technology to calculate the smart device closest to the user and wake it up first, and use the smart device that is woken up first as the responding device to respond to the voice signal issued by the user.

[0041] This approach of prioritizing wakeup based on distance selects the smart device closest to the user as the responding device, which may not be the responding device the user actually desires. For example, a user may be cooking in the kitchen, standing near the refrigerator, and want to voice-control the oven, which is slightly further away. However, they may find that only the refrigerator, which is closer, responds to their voice control commands. If they want to control the oven, they must move closer to the oven. Furthermore, distributed algorithms may not necessarily be able to accurately determine distances in a small kitchen space. Therefore, this approach cannot meet the actual needs of users. Moreover, in a small space, or when the user is simultaneously closest to two smart devices, it is difficult to guarantee the accuracy of the responding device. To this end, an embodiment of the present invention provides a smart device response method for determining the responding device that will ultimately respond to the user's voice signal from among the smart devices corresponding to the user's voice signal.

[0042] Figure 1 A flow chart of a smart device response method provided in an embodiment of the present invention is shown in FIG. Figure 1 As shown, the method includes:

[0043] S1, determining each smart device corresponding to the wake-up information in the user's voice signal;

[0044] S2: If it is determined that the smart devices do not include a preset response device, obtaining distance information between the smart devices and the user, usage information of the smart devices, and voice interaction information of the user within a first preset time period before and near the current moment;

[0045] S3: Determine a target response device among the smart devices based on the distance information, the usage information, and the voice interaction information, and control the target response device to respond to the voice signal.

[0046] Specifically, the smart device wake-up method provided in the embodiment of the present invention is executed by a server, which can be a local server or a cloud server. The local server can specifically be a computer, a tablet computer, a smart phone, etc., and this is not specifically limited in the embodiment of the present invention.

[0047] First, step S1 is performed to determine the smart devices corresponding to the wake-up information in the user's voice signal. The user's voice signal is a voice signal of a wake-up event triggered by the user, and the voice signal may contain wake-up information, which may correspond to multiple smart devices.

[0048] Each smart device corresponding to the wake-up information can be a smart device configured in the room where the user is located. In the room where the user is located, there can be multiple smart devices configured, and each smart device needs to be pre-configured with a voice module to receive and respond to the user's voice signal.

[0049] The smart device can be a smart home appliance, such as an oven, a refrigerator, a washing machine, a microwave oven, an air conditioner, and a sweeping robot, or can be other devices pre-configured with a voice module, which is not specifically limited in the embodiments of the present invention.

[0050] If all smart devices corresponding to the wake-up message are used to respond to the voice signal, confusion will arise, preventing the user from knowing which smart device they are communicating with, and thus reducing the user experience. Therefore, in this embodiment of the present invention, it is necessary to further determine a single responding device from among the smart devices corresponding to the wake-up message to respond to the user's voice signal. This is done by executing step S2.

[0051] In step S2, the server determines whether the smart devices corresponding to the wake-up information include a preset response device, where the preset response device refers to a smart device pre-specified by the user for responding to the voice signal.

[0052] If the smart devices corresponding to the wake-up information include a preset response device, the server can directly control the preset response device as a response device to respond to the user's voice signal.

[0053] If the preset response device is not included in the smart devices corresponding to the wake-up information, the server can obtain the distance information between each smart device and the user, the usage information of each smart device, and the user's voice interaction information within the first preset time period before and close to the current moment.

[0054] The server can first identify the source of the voice signal and determine the user's location. The server can also obtain and store the location information of each smart device when configuring the smart device for networking. Based on the user's location information and the location information of each smart device, the server can then determine the distance between each smart device and the user.

[0055] The usage information of each smart device is used to represent the usage-related information of each smart device, and may include, for example, the usage information of each smart device in the previous period and the current state information, etc., which is not specifically limited in the embodiments of the present invention.

[0056] Voice interaction information refers to the context of conversations between the user and the user during a first preset time period before and immediately before the current moment. This information can be used to determine whether any smart device responded within the first preset time period. The duration of the first preset time period can be set as needed, for example, to 10 minutes, 20 minutes, etc.

[0057] Finally, step S3 is executed to determine a target response device among the smart devices, combining the distance information, usage information, and voice interaction information. This target response device is the smart device that responds to the user's voice signal. In this embodiment of the present invention, a big data model can be used to determine a score for each smart device based on the distance information, usage information, and voice interaction information. The smart device with the highest score is then selected as the target response device. Furthermore, the server can control the target response device to respond to the user's voice signal.

[0058] The smart device wake-up method provided in an embodiment of the present invention first determines each smart device corresponding to the wake-up information in the user's voice signal. When each smart device does not contain a preset response device, the method obtains the distance information between each smart device and the user, the usage information of each smart device, and the user's voice interaction information in a first preset time period before and close to the current moment; finally, based on the distance information, usage information, and voice interaction information, the method determines the target response device in each smart device for responding to the voice signal and controls the target response device to respond to the voice signal through the distance information between each smart device and the user, the usage information of each smart device, and the user's voice interaction information. This method can reduce the possibility that the response device determined by considering distance information alone in the prior art cannot meet the user's actual needs, making the target response device more in line with the user's actual needs, not only improving the accuracy of the target response device, but also improving the user experience.

[0059] On the basis of the above embodiment, in the smart device wake-up method provided in the embodiment of the present invention, the usage information includes at least any one of the following:

[0060] Status information of each smart device at the current moment;

[0061] Usage information of each smart device within a second preset time period before and close to the current moment.

[0062] Specifically, in the embodiment of the present invention, the usage information of each smart device may include at least one of status information and usage information.

[0063] The status information is used to represent the current status of each smart device. The status information may include the shutdown status and the startup status. The startup status may include the standby status, the running status, the resource on-demand status, etc.

[0064] The usage information is used to indicate whether each smart device has been used within a second preset time period before and close to the current moment. The length of the second preset time period can be set as needed, for example, it can be set to 1 hour, 1.5 hours, etc.

[0065] In the embodiment of the present invention, the content of the usage information is enriched, which can further improve the accuracy of the target response device.

[0066] Based on the above embodiment, the smart device wake-up method provided in the embodiment of the present invention, wherein the target response device among the smart devices is determined based on the distance information, the usage information, and the voice interaction information, specifically includes:

[0067] For any of the smart devices, determining whether the distance information of the smart device and the usage information of the smart device meet corresponding information determination conditions, and obtaining a first determination result corresponding to the distance information of the smart device and a second determination result corresponding to the usage information of the smart device;

[0068] Recognize the voice interaction information, determine a recognition result, and based on the recognition result, determine whether any of the smart devices is the responding device, thereby obtaining a third determination result corresponding to the any of the smart devices;

[0069] Determining score information of any one of the smart devices based on the first judgment result, the second judgment result, and the third judgment result;

[0070] The target response device is selected from the smart devices based on the score information of the smart devices.

[0071] Specifically, in an embodiment of the present invention, when determining the target response device, for any smart device among the smart devices awakened by the user's voice, it is possible to determine whether the distance information and usage information of any smart device meet the corresponding information judgment conditions, and obtain a first judgment result corresponding to the distance information of any smart device and a second judgment result corresponding to the usage information of any smart device, respectively.

[0072] An information determination condition refers to a condition under which a smart device can be selected as a target response device, considering only the information corresponding to the condition. An information determination condition for distance information can be: the distance between the smart device and the user is the shortest. An information determination condition for usage information in usage information can be: the smart device has been used within the last second preset time period. An information determination condition for status information in usage information can be: the smart device is in a powered-on state.

[0073] The judgment process can be:

[0074] 1) Determine whether each smart device is the smart device closest to the user.

[0075] 2) Determine whether each smart device was last used, with a validity period of one hour. If the user last used the device more than one hour ago, the smart device wakeup process does not actually involve usage information for each smart device. The aforementioned "being used" includes voice control, manual local control, and remote control via the app; all of these fall within the scope of "being used."

[0076] 3) Determine whether each smart device is in a non-off state. For example, the smart devices include an oven, a refrigerator, and a gas water heater. However, if the gas water heater is off, the refrigerator is playing music, and the oven is running, then the user's wake-up event is likely intended to control the refrigerator or oven, not the gas water heater. Therefore, the second judgment result corresponding to the status information in the refrigerator and oven usage information is a positive judgment result, while the second judgment result corresponding to the status information in the gas water heater usage information is a negative judgment result.

[0077] The execution of the above steps 1), 2) and 3) are independent of each other, and can be executed simultaneously or given as needed, which is not specifically limited in the embodiment of the present invention.

[0078] Then, if the acquired voice interaction information is not empty, the voice interaction information is recognized to determine a recognition result. The recognition process may include determining the user intent in the voice interaction information and determining whether the user intent requires multiple rounds of dialogue, such as querying a recipe, which requires the user to switch to the next step. In this case, the recognition process also includes determining the responding device corresponding to the voice interaction information. The responding device is the last smart device to respond to the user's voice signal within a first preset time period.

[0079] Furthermore, the identification result can be used to determine whether any smart device is a responding device. Each smart device can carry identification information, and the identification information of any smart device can be compared with the identification information of the responding device to determine whether it is the same.

[0080] In the case that the acquired voice interaction information is empty, no processing is performed. In this case, the process of the smart device wake-up method does not actually involve voice interaction information.

[0081] The first and second judgment results may each include a positive judgment result or a negative judgment result. A positive judgment result indicates that a certain type of information meets the corresponding information judgment condition, while a negative judgment result indicates that a certain type of information does not meet the corresponding information judgment condition. The third judgment result may also include a positive judgment result or a negative judgment result. A positive judgment result indicates that any smart device is a responding device, while a negative judgment result indicates that any smart device is not a responding device.

[0082] Then, based on the first judgment result, the second judgment result, and the third judgment result, the score information of each smart device is determined. In the embodiment of the present invention, each positive judgment result corresponding to each type of information is assigned a preset score, and each negative judgment result corresponding to each type of information is also assigned a preset score. The value of the preset score can be set as needed and is not specifically limited here.

[0083] Generally, the preset score configured for a positive judgment result is usually greater than 0, and the preset score configured for a negative judgment result is usually equal to 0. The score information of any smart device can be determined based on the judgment result corresponding to the distance information and usage information of the smart device, combined with the preset scores configured for each judgment result.

[0084] Finally, based on the score information of each smart device corresponding to the wake-up information, a target response device is selected from each smart device. The smart device with the highest score can be selected from each smart device as the target response device.

[0085] In an embodiment of the present invention, when determining the target response device among each smart device based on distance information and usage information, information judgment conditions corresponding to each type of information and the recognition results of voice interaction information are introduced, and the score information of each smart device is determined based on the three judgment results, so that the obtained target response device can be more accurate.

[0086] Based on the above embodiment, the smart device wake-up method provided in the embodiment of the present invention, wherein the determining the score information of any smart device based on the first judgment result, the second judgment result, and the third judgment result specifically includes:

[0087] Determining influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result respectively;

[0088] The influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result are added together to obtain score information of any smart device.

[0089] Specifically, in an embodiment of the present invention, when determining the score information of any smart device, the first judgment result corresponding to the distance information of any smart device, the second judgment result corresponding to the usage information of any smart device, and the third judgment result corresponding to any smart device can be used first, combined with the preset scores configured for the judgment results corresponding to each type of information, to determine the influence scores corresponding to the first judgment result, second judgment result, and third judgment result of any smart device.

[0090] Then, the impact scores corresponding to the various judgment results are added together to obtain the score information of any smart device.

[0091] In an embodiment of the present invention, when determining the score information of any smart device, the influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result are introduced, which can simplify the process of determining the score information and improve the efficiency of determining the score information of any smart device.

[0092] Based on the above embodiment, the smart device wake-up method provided in the embodiment of the present invention, wherein determining the influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result respectively includes:

[0093] For any judgment result corresponding to any smart device, if any judgment result is a positive judgment result, determining an influence score corresponding to any judgment result based on a preset score of the positive judgment result;

[0094] If any of the judgment results is a negative judgment result, the influence score corresponding to the any of the judgment results is determined based on the preset score of the negative judgment result.

[0095] Specifically, in an embodiment of the present invention, when determining the influence score corresponding to each judgment result, for any of the first, second, and third judgment results, it is determined whether the judgment result is a positive judgment result or a negative judgment result. If it is a positive judgment result, the influence score corresponding to the judgment result is determined based on the preset score of the positive judgment result. If it is a negative judgment result, the image score corresponding to the judgment result is determined based on the preset score of the negative judgment result. The preset scores of the positive judgment result and the preset scores of the negative judgment result can be set as needed, and are not specifically limited in the embodiment of the present invention.

[0096] On the basis of the above embodiments, in the smart device wake-up method provided in the embodiments of the present invention, the preset score of the positive judgment result corresponding to the distance information, the preset score of the positive judgment result corresponding to the status information, the preset score of the positive judgment result corresponding to the usage information, and the preset score of the positive judgment result corresponding to the dialogue interaction context information are reduced in sequence.

[0097] Specifically, in embodiments of the present invention, the preset scores for positive judgment results corresponding to various types of information may be in the following order: preset score for positive judgment results corresponding to distance information > preset score for positive judgment results corresponding to state information > preset score for positive judgment results corresponding to usage information > preset score for positive judgment results corresponding to voice interaction information, in descending order. It should be noted that the judgment result corresponding to voice interaction information is the judgment result of whether any smart device is a responding device, and the positive judgment result corresponding to voice interaction information corresponds to the case where the third judgment result is a positive judgment result.

[0098] On the basis of the above embodiment, the smart device wake-up method provided in the embodiment of the present invention further includes:

[0099] If it is determined that the smart devices include the preset response device and the smart devices are in the same device group, the preset response device is controlled to respond to the voice signal.

[0100] Specifically, in embodiments of the present invention, when the smart devices corresponding to the wake-up information in the user's voice signal include a preset response device, and the smart devices are in the same device group, the preset response device can be controlled to respond to the voice signal. A device group is a user-defined group containing multiple smart devices. Within the device group, there is only one user-specified response device, the preset response device, and all other smart devices are in a non-responsive state.

[0101] For example, a user is in a kitchen with an oven next to the refrigerator and a gas water heater above it. Using existing distributed wakeup methods, every time the user wants to view a recipe on the refrigerator's large screen, they'll also wake up the water heater. However, users generally don't interact directly with the oven and water heater. Therefore, the user can group these three devices together and designate the refrigerator as the only responding device within the group. This way, whenever the user wakes up a device in this group, the refrigerator will respond.

[0102] In summary, in order to effectively solve the problems of the prior art, an embodiment of the present invention provides a processing method based on multiple judgment criteria such as device spatial relationship, functional relationship, and group relationship. When the server detects the user's wake-up event, it will comprehensively consider multiple factors such as device distance, the most recently used device, device status, group relationship, etc., and use the big data model to infer the final response device. The method provided in the embodiment of the present invention does not rely on a single condition for judgment, but makes a comprehensive judgment based on all the information perceived by the smart devices in the current environment to infer the user's expected response device. If the user wants to specify a fixed smart device for voice interaction in some specific environments, all voice devices in the current space can be pulled into the same group through custom device grouping, and a unique device can be specified to respond.

[0103] like Figure 2 As shown, based on the above embodiment, an embodiment of the present invention provides a smart device wake-up device, including:

[0104] A device determination module 21 is used to determine each smart device corresponding to the wake-up information in the user's voice signal;

[0105] an information acquisition module 22 configured to, if it is determined that the smart devices do not include a preset response device, acquire distance information between the smart devices and the user, usage information of the smart devices, and voice interaction information of the user within a first preset time period before and near the current moment;

[0106] The control response module 23 is configured to determine a target response device among the smart devices based on the distance information, the usage information, and the voice interaction information, and control the target response device to respond to the voice signal.

[0107] On the basis of the above embodiments, in the smart device wake-up apparatus provided in the embodiments of the present invention, the control response module is specifically configured to:

[0108] For any of the smart devices, determining whether the distance information of the smart device and the usage information of the smart device meet corresponding information determination conditions, and obtaining a first determination result corresponding to the distance information of the smart device and a second determination result corresponding to the usage information of the smart device;

[0109] Recognize the voice interaction information, determine a recognition result, and based on the recognition result, determine whether any of the smart devices is the responding device, thereby obtaining a third determination result corresponding to the any of the smart devices;

[0110] Determining score information of any one of the smart devices based on the first judgment result, the second judgment result, and the third judgment result;

[0111] The target response device is selected from the smart devices based on the score information of the smart devices.

[0112] On the basis of the above embodiments, in the smart device wake-up apparatus provided in the embodiments of the present invention, the control response module is specifically configured to:

[0113] Determining influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result respectively;

[0114] The influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result are added together to obtain score information of any smart device.

[0115] On the basis of the above embodiments, in the smart device wake-up apparatus provided in the embodiments of the present invention, the control response module is specifically configured to:

[0116] For any judgment result corresponding to any smart device, if any judgment result is a positive judgment result, determining an influence score corresponding to any judgment result based on a preset score of the positive judgment result;

[0117] If any of the judgment results is a negative judgment result, the influence score corresponding to the any of the judgment results is determined based on the preset score of the negative judgment result.

[0118] On the basis of the above embodiment, in the smart device wake-up apparatus provided in the embodiment of the present invention, the usage information includes at least any one of the following:

[0119] Status information of each smart device at the current moment;

[0120] Usage information of each smart device within a second preset time period before and close to the current moment.

[0121] On the basis of the above embodiments, in the smart device wake-up device provided in the embodiments of the present invention, the preset score of the positive judgment result corresponding to the distance information, the preset score of the positive judgment result corresponding to the status information, the preset score of the positive judgment result corresponding to the usage information, and the preset score of the positive judgment result corresponding to the voice interaction information are reduced in sequence.

[0122] On the basis of the above embodiment, in the smart device wake-up apparatus provided in the embodiment of the present invention, the control response module is further configured to:

[0123] If it is determined that the smart devices include the preset response device and the smart devices are in the same device group, the preset response device is controlled to respond to the voice signal.

[0124] Specifically, the functions of each module in the smart device wake-up device provided in the embodiment of the present invention correspond one-to-one to the operation process of each step in the above method embodiment, and the effects achieved are also consistent. Please refer to the above embodiment for details, and no further details will be given in the embodiment of the present invention.

[0125] Figure 3 An example of a physical structure diagram of an electronic device is shown below. Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the smart device wake-up method provided in the above embodiments, which includes: determining each smart device corresponding to the wake-up information in the user's voice signal; if it is determined that the smart devices do not include a preset response device, obtaining the distance information between the smart devices and the user, the usage information of the smart devices, and the voice interaction information of the user in a first preset time period before and near the current moment; based on the distance information, the usage information, and the voice interaction information, determining the target response device among the smart devices, and controlling the target response device to respond to the voice signal.

[0126] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0127] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the smart device wake-up method provided in the above-mentioned embodiments, the method including: determining each smart device corresponding to the wake-up information in the user's voice signal; if it is determined that the smart devices do not include a preset response device, obtaining the distance information between the smart devices and the user, the usage information of the smart devices, and the voice interaction information of the user within a first preset time period before and close to the current moment; based on the distance information, the usage information and the voice interaction information, determining the target response device among the smart devices, and controlling the target response device to respond to the voice signal.

[0128] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the smart device wake-up method provided in the above-mentioned embodiments, the method comprising: determining each smart device corresponding to the wake-up information in the user's voice signal; if it is determined that the smart devices do not include a preset response device, obtaining the distance information between the smart devices and the user, the usage information of the smart devices, and the voice interaction information of the user within a first preset time period before and close to the current moment; based on the distance information, the usage information, and the voice interaction information, determining the target response device among the smart devices, and controlling the target response device to respond to the voice signal.

[0129] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0130] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for waking up a smart device, characterized in that: include: Determine each smart device corresponding to the wake-up information in the user's voice signal; If it is determined that the smart devices do not include a preset response device, obtaining distance information between the smart devices and the user, usage information of the smart devices, and voice interaction information of the user within a first preset time period before and near the current moment; The preset response device refers to a smart device pre-designated by the user for responding to the voice signal; Determining a target response device among the smart devices based on the distance information, the usage information, and the voice interaction information, and controlling the target response device to respond to the voice signal; If it is determined that the smart devices include the preset response device and the smart devices are in the same device group, controlling the preset response device to respond to the voice signal; The device group is a user-defined group containing multiple smart devices. There is only one preset response device in the device group, and the other smart devices are in a closed response state.

2. The smart device wake-up method according to claim 1, characterized in that: The determining, based on the distance information, the usage information, and the voice interaction information, a target response device among the smart devices specifically includes: For any of the smart devices, determining whether the distance information of the smart device and the usage information of the smart device meet corresponding information determination conditions, and obtaining a first determination result corresponding to the distance information of the smart device and a second determination result corresponding to the usage information of the smart device; Recognize the voice interaction information, determine a recognition result, and based on the recognition result, determine whether any of the smart devices is the responding device, thereby obtaining a third determination result corresponding to the any of the smart devices; Determining score information of any one of the smart devices based on the first judgment result, the second judgment result, and the third judgment result; The target response device is selected from the smart devices based on the score information of the smart devices.

3. The smart device wake-up method according to claim 2, characterized in that: The determining the score information of any one of the smart devices based on the first judgment result, the second judgment result, and the third judgment result specifically includes: Determining influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result respectively; The influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result are added together to obtain score information of any smart device.

4. The smart device wake-up method according to claim 3, characterized in that: The determining of the influence scores corresponding to the first judgment result, the second judgment result, and the third judgment result respectively includes: For any judgment result corresponding to any smart device, if any judgment result is a positive judgment result, determining an influence score corresponding to any judgment result based on a preset score of the positive judgment result; If any of the judgment results is a negative judgment result, the influence score corresponding to the any of the judgment results is determined based on the preset score of the negative judgment result.

5. The smart device wake-up method according to claim 4, characterized in that: The usage information includes at least any one of the following: Status information of each smart device at the current moment; Usage information of each smart device within a second preset time period before and close to the current moment.

6. The smart device wake-up method according to claim 5, characterized in that: The preset scores of the positive judgment results corresponding to the distance information, the preset scores of the positive judgment results corresponding to the status information, the preset scores of the positive judgment results corresponding to the usage information, and the preset scores of the positive judgment results corresponding to the voice interaction information decrease in sequence.

7. A smart device wake-up device, characterized in that: include: A device determination module is used to determine each smart device corresponding to the wake-up information in the user's voice signal; The preset response device refers to a smart device pre-designated by the user for responding to the voice signal; an information acquisition module, configured to, if it is determined that the smart devices do not include a preset response device, acquire distance information between the smart devices and the user, usage information of the smart devices, and voice interaction information of the user within a first preset time period before and near the current moment; a control response module, configured to determine a target response device among the smart devices based on the distance information, the usage information, and the voice interaction information, and control the target response device to respond to the voice signal; If it is determined that the smart devices include the preset response device and the smart devices are in the same device group, controlling the preset response device to respond to the voice signal; The device group is a user-defined group containing multiple smart devices. There is only one preset response device in the device group, and the other smart devices are in a closed response state.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the smart device wake-up method according to any one of claims 1 to 6 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the smart device wake-up method according to any one of claims 1 to 6 are implemented.

Images