Intelligent device control method and device, storage medium and electronic device

Abstract

The present invention discloses a control method and device for smart devices, a storage medium and an electronic device. Relating to the field of smart home technology, the method comprises: obtaining a set of historical audio segments, and extracting the voiceprint features of each historical audio segment in the set of historical audio segments respectively, to obtain a voiceprint feature vector of each historical audio segment; determining similar parameters of the voiceprint feature vectors of every two historical audio segments in the set of historical audio segments, and clustering the historical audio segments according to the similar parameters of the voiceprint feature vectors of every two historical audio segments, to obtain a plurality of audio groups; in the case of receiving a target voice command, determining a target audio group that matches the target voice command from a plurality of audio groups; obtaining target device parameters corresponding to the target audio group and the target operation, and controlling the target device to perform the target operation according to the target device parameters. The present invention solves the technical problem that the need for personalized settings leads to poor user experience.

Description

Technical Field

[0001] The present invention relates to the field of smart homes, and in particular to a control method and device for smart devices, a storage medium and an electronic device. Background Art

[0002] Smart home devices are becoming more and more popular in households. In order to facilitate interaction with smart devices, many families usually use voice to control smart home devices, such as turning on the air conditioner through voice commands.

[0003] However, each family member has different habits in using smart devices, and usually needs to adjust the smart device according to their own habits after it is started. The need to adjust each time makes the operation repetitive and cumbersome, which is not a good user experience.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a control method and device for a smart device, a storage medium, and an electronic device, so as to at least solve the technical problem that the need for personalized settings leads to poor user experience.

[0006] According to one aspect of an embodiment of the present invention, a control method for a smart device is provided, comprising: obtaining a set of historical audio segments, and respectively extracting voiceprint features of each historical audio segment in the set of historical audio segments to obtain a voiceprint feature vector of each historical audio segment, wherein the set of historical audio segments includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected; determining similarity parameters of the voiceprint feature vectors of every two historical audio segments in the set of historical audio segments, and clustering the historical audio segments according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, wherein each of the audio groups corresponds to For an object, a similarity parameter between a voiceprint feature vector of each historical audio segment in each of the above audio groups and a voiceprint feature vector of at least one historical audio segment in the same audio group is greater than a preset similarity threshold; when a target voice command is received, a target audio group matching the target voice command is determined from the above multiple audio groups, wherein the target voice command is used to instruct a target device to perform a target operation; a target device parameter corresponding to the target audio group and the target operation is obtained, and the target device is controlled to perform the target operation according to the target device parameter, wherein the target device parameter is used to indicate an operating parameter of the target device.

[0007] According to another aspect of an embodiment of the present invention, a control device for a smart device is also provided, comprising: an acquisition unit, used to acquire a set of historical audio segments, and respectively extract voiceprint features of each historical audio segment in the set of historical audio segments to obtain a voiceprint feature vector of each historical audio segment, wherein the set of historical audio segments includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected; a clustering unit, used to determine similarity parameters of the voiceprint feature vectors of every two historical audio segments in the set of historical audio segments, and cluster the historical audio segments according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, wherein each of the audio groups has a similarity parameter for each of the historical audio segments. For an object, a similarity parameter between a voiceprint feature vector of each historical audio segment in each of the above audio groups and a voiceprint feature vector of at least one historical audio segment in the same audio group is greater than a preset similarity threshold; a determination unit is used to determine, when receiving a target voice instruction, a target audio group that matches the target voice instruction from the above multiple audio groups, wherein the target voice instruction is used to instruct the control of a target device to perform a target operation; a control unit is used to obtain target device parameters corresponding to the target audio group and the target operation, and control the target device to perform the target operation according to the target device parameters, wherein the target device parameters are used to indicate the operating parameters of the target device.

[0008] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the control method of the above-mentioned smart device when running.

[0009] According to another aspect of an embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the control method of the smart device through the computer program.

[0010] In an embodiment of the present invention, a historical audio segment set is obtained, and voiceprint features of each historical audio segment in the historical audio segment set are respectively extracted to obtain a voiceprint feature vector of each historical audio segment, wherein the historical audio segment set includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected, similarity parameters of voiceprint feature vectors of every two historical audio segments in the historical audio segment set are determined, and the historical audio segments are clustered according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, wherein each audio group corresponds to an object, and the similarity parameter of the voiceprint feature vector of each historical audio segment in each audio group and the voiceprint feature vector of at least one historical audio segment in the same audio group is greater than a preset similarity threshold, and when a target voice command is received, a target audio group matching the target voice command is determined from the multiple audio groups, wherein , the target voice instruction is used to instruct the target device to perform the target operation; the target device parameters corresponding to the target audio group and the target operation are obtained, and the target device is controlled to perform the target operation according to the target device parameters, wherein the target device parameters are used to indicate the operating parameters of the target device, by obtaining a set of historical audio segments and clustering the historical audio segments to form audio groups, and by determining the target audio group that matches the target voice instruction, the target device parameters corresponding to the target audio group are used to control the operation of the target device, thereby achieving the purpose of object matching for voice instructions based on clustering of historical audio data without the need for personalized settings, thereby controlling the operation of the device based on the device parameters corresponding to the object, thereby achieving the technical effect of realizing personalized operation control without the need for personalized settings, thereby solving the technical problem of poor user experience caused by the need for personalized settings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0012] Figure 1 is a schematic diagram of an application environment of an optional control method for a smart device according to an embodiment of the present invention;

[0013] Figure 2 is a flow chart of an optional control method of an intelligent device according to an embodiment of the present invention;

[0014] Figure 3 is a flow chart of an optional control method of an intelligent device according to an embodiment of the present invention;

[0015] Figure 4is a flow chart of an optional control method of an intelligent device according to an embodiment of the present invention;

[0016] Figure 5 is a flow chart of an optional control method of an intelligent device according to an embodiment of the present invention;

[0017] Figure 6 is a flow chart of an optional control method of an intelligent device according to an embodiment of the present invention;

[0018] Figure 7 is a schematic structural diagram of an optional control device for an intelligent device according to an embodiment of the present invention;

[0019] Figure 8 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] According to one aspect of an embodiment of the present invention, a control method for a smart device is provided, and the control method for a smart device is widely used in smart home (Smart Home), smart home, smart home device ecology, smart residential (Intelligence House) ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the control method for the smart device can be applied to Figure 1 In the hardware environment composed of the terminal device 102 and the server 104 shown in FIG. Figure 1 As shown, the server 104 is connected to the terminal device 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0023] The terminal device 102 is not limited to sending the voice command to the server 104 through the network, so as to determine the operating parameters for operating the terminal device 102 through the server 104, and return the operating parameters to the terminal device 102 through the network to control the terminal device 102 to operate according to the operating parameters. The server 104 determines the operating parameters corresponding to the voice command and is not limited to executing S102 to S108 in sequence. S102, obtain a voiceprint feature vector. Obtain a historical audio segment set, and extract the voiceprint features of each historical audio segment in the historical audio segment set respectively, to obtain a voiceprint feature vector of each historical audio segment, wherein the historical audio segment set includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected. S104, obtain multiple audio groups. Determine the similarity parameters of the voiceprint feature vectors of every two historical audio segments in the historical audio segment set, and cluster the historical audio segments according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, wherein each audio group corresponds to an object, and the similarity parameters of the voiceprint feature vector of each historical audio segment in each audio group and the voiceprint feature vector of at least one historical audio segment in the same audio group are greater than a preset similarity threshold. S106, determine the target audio group. In the case of receiving a target voice instruction, determine a target audio group that matches the target voice instruction from multiple audio groups, wherein the target voice instruction is used to instruct the control of the target device to perform a target operation. S108, perform the target operation. Obtain the target device parameters corresponding to the target audio group and the target operation, and control the target device to perform the target operation according to the target device parameters, wherein the target device parameters are used to indicate the operating parameters of the target device.

[0024] The server may be a single server, or a server cluster consisting of multiple servers, or a cloud server. The network may include but is not limited to at least one of the following: a wired network, a wireless network. The wired network may include but is not limited to at least one of the following: a wide area network, a metropolitan area network, a local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart speaker, a smart fresh air device, a smart kitchen and bathroom device, a smart bathroom device, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc. The above is only an example, and no limitation is made in this embodiment.

[0025] As an optional implementation, Figure 2 As shown, the control method of the above-mentioned smart device includes:

[0026] S202, obtaining a historical audio segment set, and extracting voiceprint features of each historical audio segment in the historical audio segment set respectively, to obtain a voiceprint feature vector of each historical audio segment, wherein the historical audio segment set includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected;

[0027] S204, determining similarity parameters of voiceprint feature vectors of every two historical audio segments in the historical audio segment set, and clustering the historical audio segments according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, wherein each audio group corresponds to an object, and a similarity parameter of a voiceprint feature vector of each historical audio segment in each audio group and a voiceprint feature vector of at least one historical audio segment in the same audio group is greater than a preset similarity threshold;

[0028] S206, when receiving a target voice instruction, determining a target audio group matching the target voice instruction from multiple audio groups, wherein the target voice instruction is used to instruct to control the target device to perform a target operation;

[0029] S208, obtaining target device parameters corresponding to the target audio group and the target operation, and controlling the target device to perform the target operation according to the target device parameters, wherein the target device parameters are used to indicate operating parameters of the target device.

[0030] The historical audio data is not limited to the historical voice commands collected or received for the target device or the device network where the target device is located. The device network where the target device is located is not limited to including at least one terminal device with voice collection and voice control functions, which is used to collect or receive voice commands to implement the voice control function of the terminal device in the device network.

[0031] Acquiring historical audio data is not limited to starting to cluster the historical audio data to determine at least one audio group when the amount of historical audio data accumulates to a preset amount. When the amount of historical audio data reaches a preset amount, each historical audio data is not limited to being segmented according to an audio segmentation rule.

[0032] The segmentation of each historical audio data is not limited to segmenting the audio according to a preset length or a preset audio volume or other arbitrary standards, so that each historical audio data is divided into at least two audio segments. Thus, at least two historical audio segments corresponding to all the historical audio data are obtained, and the historical audio segment set includes the historical audio segments corresponding to all the historical audio data.

[0033] When extracting voiceprint features of audio data, the voiceprint features of each historical audio segment in the historical audio segment set are extracted separately, and are not limited to representing the voiceprint features of each historical audio segment in the form of a vector. Therefore, based on the voiceprint feature vector of each historical audio segment, audio segments are clustered in the historical audio segment set, and multiple audio groups are constructed through audio segment clustering.

[0034] Clustering the historical audio segments according to the voiceprint feature vectors is not limited to calculating the similarity parameters of the voiceprint feature vectors of every two historical audio segments, and clustering the audio segments based on the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups. Specifically, clustering the audio segments based on the similarity parameters of the voiceprint feature vectors of every two historical audio segments is not limited to clustering the historical audio segments corresponding to the two voiceprint feature vectors when the similarity parameters of the two voiceprint feature vectors are greater than the preset similarity threshold, thereby continuing to perform audio segment clustering based on the voiceprint feature vectors after the two historical audio segments are clustered. It is not limited to calculating the class voiceprint feature vector of the current class obtained after clustering the two historical audio segments, thereby continuing to perform clustering based on the similarity parameters of the class voiceprint feature vectors of every two current classes. It can also be based on the similarity parameters of every two voiceprint feature vectors, clustering multiple historical audio segments whose similarity parameters are greater than the preset similarity threshold. In this method, it is also not limited to the existence of multiple clusterings, thereby obtaining multiple audio groups.

[0035] In the multiple audio groups formed by clustering historical audio, each audio group corresponds to an object, but the object corresponding to the audio group is a virtual object determined by performing audio clustering, and the probability that the audio data in an audio group is the same virtual object is greater than a preset probability. The virtual object corresponds to the real object corresponding to the historical audio data. However, it should be noted that the target audio group is not a group of audio data divided according to the object after the object is determined, but an audio group formed by clustering historical audio data based on multiple objects.

[0036] The number of objects included in a group of objects corresponding to the historical audio data is not limited here, and is not limited to one or more objects using the target device or the target device network. The target voice instruction is used to instruct the target device to perform the target operation through voice. When multiple audio groups are obtained, it is not limited to updating the target audio group using the target voice instruction under preset conditions. For example, after a preset time has passed, the audio group is updated using the voice instructions corresponding to each audio group.

[0037] Each audio group is not limited to corresponding to its own device parameters, and is not limited to including device parameters corresponding to each operation, so that the device parameters corresponding to the audio group are determined based on the audio group. As an optional implementation, if Figure 3 As shown, obtaining the target device parameters corresponding to the target audio group and the target operation includes:

[0038] S302, obtaining a target parameter group corresponding to a target audio group;

[0039] S304: Search the target parameter group for a target device parameter corresponding to the target operation.

[0040] Each audio group is not limited to corresponding to its own parameter group, and the parameter group includes device parameters of each device operation corresponding to the audio group. From the target parameter group corresponding to the target audio group, the target device parameter corresponding to the target operation is searched.

[0041] The device parameters in the parameter group corresponding to the audio group are not limited to those determined based on historical audio data. They are not limited to device operations extracted from historical audio data and historical device parameters corresponding to the device operations. When each audio group is determined based on historical audio data, the parameter group corresponding to the audio group is determined by each historical audio data included in the audio group.

[0042] As an optional implementation, after receiving the target voice instruction, the method further includes:

[0043] S1, when a target audio group is not determined from a plurality of audio groups, obtaining a reference device parameter corresponding to a target operation, wherein the reference device parameter is used to indicate a historical operating parameter of the target device performing the target operation;

[0044] S2, controlling the target device to perform the target operation according to the reference device parameters.

[0045] When the target audio group is not determined from the multiple audio groups, it is determined that the target voice command does not correspond to any of the current audio groups, thereby obtaining reference device parameters corresponding to the target operation, and controlling the target device to perform the target operation according to the reference device parameters. The reference device parameters are not limited to historical operating parameters of the target device, or operating parameters preset for the target device.

[0046] In an embodiment of the present application, a historical audio segment set is obtained, and the voiceprint features of each historical audio segment in the historical audio segment set are respectively extracted to obtain a voiceprint feature vector of each historical audio segment, wherein the historical audio segment set includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected, and similarity parameters of the voiceprint feature vectors of every two historical audio segments in the historical audio segment set are determined, and the historical audio segments are clustered according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, wherein each audio group corresponds to an object, and the similarity parameter of the voiceprint feature vector of each historical audio segment in each audio group and the voiceprint feature vector of at least one historical audio segment in the same audio group is greater than a preset similarity threshold, and when a target voice command is received, a target audio group matching the target voice command is determined from the multiple audio groups, wherein , the target voice instruction is used to instruct the target device to perform the target operation; the target device parameters corresponding to the target audio group and the target operation are obtained, and the target device is controlled to perform the target operation according to the target device parameters, wherein the target device parameters are used to indicate the operating parameters of the target device, by obtaining a set of historical audio segments and clustering the historical audio segments to form audio groups, and by determining the target audio group that matches the target voice instruction, the target device parameters corresponding to the target audio group are used to control the operation of the target device, thereby achieving the purpose of object matching for voice instructions based on clustering of historical audio data without the need for personalized settings, thereby controlling the operation of the device based on the device parameters corresponding to the object, thereby achieving the technical effect of realizing personalized operation control without the need for personalized settings, thereby solving the technical problem of poor user experience caused by the need for personalized settings.

[0047] As an optional implementation, historical audio segments are clustered according to similar parameters of voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, including: when the target clustering condition includes the target number of groups, when the number of candidate audio groups obtained by clustering the historical audio segments is consistent with the target number of groups, it is determined that multiple audio groups are obtained, wherein the target number of groups is used to indicate the number of a group of objects associated with a target device network, and the target device network includes the target device.

[0048] The target number of groups is not limited to the number of groups obtained before clustering and used to indicate the formation of clusters. For example, the number of objects input by the device network, taking the device network as a home network as an example, the number of objects is not limited to the number of family members input. The number of audio groups obtained by clustering the audio segments is limited by the target number of groups. When multiple audio groups of the target number of groups are obtained by clustering, the clustering of the audio segments is stopped, so that the multiple audio groups obtained by clustering are regarded as groups corresponding to multiple family members respectively, and parameter groups are obtained according to the audio groups.

[0049] As an optional implementation, historical audio segments are clustered according to similar parameters of voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, including: when the target clustering condition does not include the target number of groups, when the Bayesian parameters of the candidate audio groups reach the target extreme value conditions, it is determined that multiple audio groups are obtained.

[0050] In the case where the target number of groups is not included in the target clustering condition, it is not limited to determining whether to stop clustering based on the Bayesian parameters of the audio group. The condition that the Bayesian parameters reach the target extreme value is not limited to minimizing the Bayesian error rate of the audio group. In the case where the Bayesian error rate of the current audio group is less than that of any round of audio groups, it is not limited to determining the current audio group as the audio group obtained by clustering. The audio group of any round can be an audio group of the historical round of the current audio group, or it can be the next or next few audio groups of the current audio group.

[0051] As an optional implementation, Figure 4 As shown, the above-mentioned audio set is clustered according to the voiceprint feature of each audio in the audio set to obtain multiple audio groups, and then it also includes:

[0052] S402, performing audio sampling on the historical audio segments included in each audio group, and determining redundant audio data in the historical audio segments, wherein the redundant audio data is audio data in the historical audio segments whose audio features do not meet preset audio requirements;

[0053] S404, removing redundant audio data in the historical audio segment to obtain a reference audio segment;

[0054] S406, calculating the audio group feature of the audio group based on the reference voiceprint feature vector of the reference audio segment in the audio group.

[0055] In the case of clustering to obtain multiple audio groups, audio sampling is performed again on each historical audio segment included in the audio group to determine whether each historical audio segment includes redundant audio data. Redundant audio data is data in the historical audio segment where the audio features do not meet the preset audio requirements, and the preset audio requirements are not limited to indicating the number of objects in the audio. When the number of objects in the audio is 1, that is, the voice of a clear object, it is determined that the audio in the historical audio segment meets the preset audio requirements. When the number of objects in the audio is greater than 1, that is, there is an overlap of object voices, the audio is determined to be redundant audio data, and the redundant audio data is removed from the historical audio segment.

[0056] When redundant audio data in the historical audio segment is removed to obtain a reference audio segment, the audio group features of each audio group are determined based on the reference audio segment. Determining the audio group based on the reference audio segment is not limited to re-extracting the voiceprint feature vector based on the reference audio segment, thereby determining the audio group features of the audio group by the voiceprint feature vectors of each reference audio segment in the audio group. It can also be based on the reference audio segment to re-cluster the audio segments to obtain multiple audio groups.

[0057] As an optional implementation, Figure 5 As shown, the above-mentioned determination of the target audio group matching the target voice command from the multiple audio groups includes:

[0058] S502, segmenting the target voice command to obtain a set of target audio segments corresponding to the target voice command;

[0059] S504, respectively extracting the voiceprint features of each target audio segment in the target audio segment set to obtain a target voiceprint feature vector of each target audio segment;

[0060] S506: Determine a target audio group that matches the target voice command based on the target voiceprint feature vector of each target audio segment and the audio group features of each of the multiple audio groups.

[0061] When determining the target audio group that matches the target voice command, it is not limited to segmenting the target voice command to obtain a set of target audio segments, extracting the voiceprint features of each target audio segment, and obtaining a target voiceprint feature vector for each target audio segment, thereby determining the target audio group based on each target voiceprint feature vector and multiple voice group features.

[0062] As an optional implementation, Figure 6As shown, the target audio group matching the target voice command determined based on the target voiceprint feature vector of each target audio segment and the respective audio group features of the multiple audio groups includes:

[0063] S602, calculating a reference similarity parameter between a target voiceprint feature vector of each target audio segment and each audio group feature, wherein the reference similarity parameter is used to indicate a similarity between the target voiceprint feature vector and the audio group feature;

[0064] S604, determining a reference parameter of each audio group feature based on the reference similarity parameter, wherein the reference parameter is used to indicate the similarity between the audio group feature and the voiceprint feature of the target voice command;

[0065] S606: Determine a target audio group from the multiple audio groups according to the reference parameters corresponding to the multiple audio groups.

[0066] The target voiceprint feature vector of each target audio segment obtained by segmenting the target voice command and the reference similarity parameters of each audio group feature are calculated respectively, so as to determine the reference parameters of each target voice command and each audio group feature, and determine the target audio group from the audio group based on multiple reference parameters. The reference parameters of each target voice command and each audio group feature are not limited to statistical parameters of multiple reference similarity parameters, and are not limited to arbitrary statistical parameters, such as mean, variance, mean square error, etc.

[0067] As an optional implementation, determining a target audio group from multiple audio groups based on reference parameters corresponding to each of the multiple audio groups includes: when there is a target reference parameter greater than a target threshold among the reference parameters, determining the audio group corresponding to the target reference parameter as the target audio group; when multiple reference parameters are all less than the target threshold, determining that the target audio group has not been determined from the multiple audio groups.

[0068] In the case where there is a target reference parameter among multiple reference parameters, it is not limited to determining the audio group corresponding to the target reference parameter with the largest parameter value among the reference parameters as the target audio group. If multiple reference parameters are all less than the target threshold, it is determined that the target audio group has not been determined from the multiple audio groups, so that the reference operation parameters are used to control the operation of the target device.

[0069] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0070] According to another aspect of the embodiments of the present invention, there is also provided a control device for an intelligent device for implementing the control method of the intelligent device. Figure 7 As shown, the device comprises:

[0071] An acquisition unit 702 is used to acquire a historical audio segment set, and respectively extract voiceprint features of each historical audio segment in the historical audio segment set to obtain a voiceprint feature vector of each historical audio segment, wherein the historical audio segment set includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected;

[0072] The clustering unit 704 is used to determine similar parameters of the voiceprint feature vectors of every two historical audio segments in the historical audio segment set, and cluster the historical audio segments according to the similar parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, wherein each audio group corresponds to an object, and the similarity parameter of the voiceprint feature vector of each historical audio segment in each audio group and the voiceprint feature vector of at least one historical audio segment in the same audio group is greater than a preset similarity threshold;

[0073] A determination unit 706 is used to determine a target audio group matching the target voice instruction from multiple audio groups when receiving the target voice instruction, wherein the target voice instruction is used to instruct the target device to perform a target operation;

[0074] The control unit 708 is used to obtain target device parameters corresponding to the target audio group and the target operation, and control the target device to perform the target operation according to the target device parameters, wherein the target device parameters are used to indicate the operating parameters of the target device.

[0075] Optionally, the above-mentioned clustering unit clusters the historical audio segments according to similar parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, including: when the target clustering condition includes the target number of groups, when the number of candidate audio groups obtained by clustering the historical audio segments is consistent with the target number of groups, it is determined that multiple audio groups are obtained, wherein the target number of groups is used to indicate the number of a group of objects associated with the target device network, and the target device network includes the target device.

[0076] Optionally, the above-mentioned extraction unit clusters the historical audio segments according to the similar parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, including: when the target clustering condition does not include the target number of groups, when the Bayesian parameters of the candidate audio groups reach the target extreme value conditions, it is determined that multiple audio groups are obtained.

[0077] Optionally, the control device of the above-mentioned smart device also includes a sampling unit, which is used to perform audio sampling on the historical audio segments included in each audio group after clustering the historical audio segments according to similar parameters of the voiceprint feature vectors of every two historical audio segments, and determine redundant audio data in the historical audio segments, wherein the redundant audio data is audio data in the historical audio segments whose audio features do not meet preset audio requirements; remove the redundant audio data in the historical audio segments to obtain a reference audio segment; and calculate the audio group features of the audio group based on the reference voiceprint feature vector of the reference audio segment in the audio group.

[0078] Optionally, the above-mentioned determination unit 706 is also used to segment the target voice command to obtain a target audio segment set corresponding to the target voice command; respectively extract the voiceprint features of each target audio segment in the target audio segment set to obtain a target voiceprint feature vector for each target audio segment; based on the target voiceprint feature vector of each target audio segment and the audio group features of each of the multiple audio groups, determine the target audio group that matches the target voice command.

[0079] Optionally, the above-mentioned determination unit 706 determines the target audio group that matches the target voice command based on the target voiceprint feature vector of each target audio segment and the audio group features of each of the multiple audio groups, including: calculating the reference similarity parameters of the target voiceprint feature vector of each target audio segment and the features of each audio group, wherein the reference similarity parameters are used to indicate the similarity between the target voiceprint feature vector and the audio group features; determining the reference parameters of each audio group feature based on the reference similarity parameters, wherein the reference parameters are used to indicate the similarity between the audio group features and the voiceprint features of the target voice command; and determining the target audio group from the multiple audio groups according to the reference parameters corresponding to each of the multiple audio groups.

[0080] Optionally, the above-mentioned determination unit 706 determines the target audio group from the multiple audio groups according to the reference parameters corresponding to each of the multiple audio groups, including: when there is a target reference parameter greater than a target threshold value in the reference parameters, determining the audio group corresponding to the target reference parameter as the target audio group; when multiple reference parameters are all less than the target threshold value, determining that the target audio group has not been determined from the multiple audio groups.

[0081] Optionally, the control unit 708 is further configured to obtain a target parameter group corresponding to the target audio group; and search the target device parameters corresponding to the target operation in the target parameter group.

[0082] Optionally, the control device of the above-mentioned smart device also includes a reference unit, which is used to obtain reference device parameters corresponding to the target operation when the target audio group is not determined from multiple audio groups, wherein the reference device parameters are used to indicate the historical operating parameters of the target device to perform the target operation; and control the target device to perform the target operation according to the reference device parameters.

[0083] In an embodiment of the present application, a historical audio segment set is obtained, and the voiceprint features of each historical audio segment in the historical audio segment set are respectively extracted to obtain a voiceprint feature vector of each historical audio segment, wherein the historical audio segment set includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected, and similarity parameters of the voiceprint feature vectors of every two historical audio segments in the historical audio segment set are determined, and the historical audio segments are clustered according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, wherein each audio group corresponds to an object, and the similarity parameter of the voiceprint feature vector of each historical audio segment in each audio group and the voiceprint feature vector of at least one historical audio segment in the same audio group is greater than a preset similarity threshold, and when a target voice command is received, a target audio group matching the target voice command is determined from the multiple audio groups, wherein , the target voice instruction is used to instruct the target device to perform the target operation; the target device parameters corresponding to the target audio group and the target operation are obtained, and the target device is controlled to perform the target operation according to the target device parameters, wherein the target device parameters are used to indicate the operating parameters of the target device, by obtaining a set of historical audio segments and clustering the historical audio segments to form audio groups, and by determining the target audio group that matches the target voice instruction, the target device parameters corresponding to the target audio group are used to control the operation of the target device, thereby achieving the purpose of object matching for voice instructions based on clustering of historical audio data without the need for personalized settings, thereby controlling the operation of the device based on the device parameters corresponding to the object, thereby achieving the technical effect of realizing personalized operation control without the need for personalized settings, thereby solving the technical problem of poor user experience caused by the need for personalized settings.

[0084] According to another aspect of the embodiments of the present invention, an electronic device for implementing the control method of the above-mentioned smart device is also provided. The electronic device may be Figure 1 The terminal device or server shown in the figure. This embodiment is described by taking the electronic device as a server as an example. Figure 8 As shown, the electronic device includes a memory 802 and a processor 804. The memory 802 stores a computer program, and the processor 804 is configured to execute the steps in any of the above method embodiments through the computer program.

[0085] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0086] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0087] S1, obtaining a historical audio segment set, and extracting voiceprint features of each historical audio segment in the historical audio segment set respectively, to obtain a voiceprint feature vector of each historical audio segment, wherein the historical audio segment set includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected;

[0088] S2, determining similarity parameters of voiceprint feature vectors of every two historical audio segments in the historical audio segment set, and clustering the historical audio segments according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, wherein each audio group corresponds to an object, and a similarity parameter of a voiceprint feature vector of each historical audio segment in each audio group and a voiceprint feature vector of at least one historical audio segment in the same audio group is greater than a preset similarity threshold;

[0089] S3, upon receiving a target voice instruction, determining a target audio group matching the target voice instruction from multiple audio groups, wherein the target voice instruction is used to instruct a target device to perform a target operation;

[0090] S4, obtaining target device parameters corresponding to the target audio group and the target operation, and controlling the target device to perform the target operation according to the target device parameters, wherein the target device parameters are used to indicate operating parameters of the target device.

[0091] Alternatively, a person skilled in the art may understand that: Figure 8 The structure shown is for illustration only, and the electronic device may also be any terminal device. Figure 8 The structure of the electronic device is not limited. Figure 8 More or fewer components (such as network interfaces, etc.) as shown in, or with Figure 8 Different configurations shown.

[0092] Among them, the memory 802 can be used to store software programs and modules, such as the program instructions / modules corresponding to the control method and device of the smart device in the embodiment of the present invention. The processor 804 executes various functional applications and data processing by running the software programs and modules stored in the memory 802, that is, realizing the control method of the above-mentioned smart device. The memory 802 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 802 may further include a memory remotely arranged relative to the processor 804, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 802 can be specifically, but not limited to, used to store information such as a collection of historical audio segments, target voice instructions, multiple audio groups, target device parameters, etc. As an example, if Figure 8 As shown, the memory 802 may include, but is not limited to, the acquisition unit 702, clustering unit 704, determination unit 706, and control unit 708 in the control device of the smart device. In addition, it may also include, but is not limited to, other module units in the control device of the smart device, which will not be repeated in this example.

[0093] Optionally, the transmission device 806 is used to receive or send data via a network. Specific examples of the network may include wired networks and wireless networks. In one example, the transmission device 806 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 806 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0094] In addition, the electronic device further comprises: a display 808 for displaying the target device parameters; and a connection bus 810 for connecting various module components in the electronic device.

[0095] In other embodiments, the terminal device or server may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes through network communication. Among them, the nodes may form a peer-to-peer (P2P, Peer To Peer) network, and any form of computing device, such as a server, terminal and other electronic devices, may become a node in the blockchain system by joining the peer-to-peer network.

[0096] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in various optional implementations of the control aspect of the above-mentioned intelligent device. The computer program is configured to execute the steps of any of the above-mentioned method embodiments when it is run.

[0097] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0098] S1, obtaining a historical audio segment set, and extracting voiceprint features of each historical audio segment in the historical audio segment set respectively, to obtain a voiceprint feature vector of each historical audio segment, wherein the historical audio segment set includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected;

[0099] S2, determining similarity parameters of voiceprint feature vectors of every two historical audio segments in the historical audio segment set, and clustering the historical audio segments according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, wherein each audio group corresponds to an object, and a similarity parameter of a voiceprint feature vector of each historical audio segment in each audio group and a voiceprint feature vector of at least one historical audio segment in the same audio group is greater than a preset similarity threshold;

[0100] S3, upon receiving a target voice instruction, determining a target audio group matching the target voice instruction from multiple audio groups, wherein the target voice instruction is used to instruct a target device to perform a target operation;

[0101] S4, obtaining target device parameters corresponding to the target audio group and the target operation, and controlling the target device to perform the target operation according to the target device parameters, wherein the target device parameters are used to indicate operating parameters of the target device.

[0102] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0103] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0104] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which can be personal computers, servers or network devices, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.

[0105] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0106] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0107] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0109] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A control method for an intelligent device, characterized in that: include: Acquire a historical audio segment set, and respectively extract voiceprint features of each historical audio segment in the historical audio segment set to obtain a voiceprint feature vector of each historical audio segment, wherein the historical audio segment set includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected, and the objects are family members in a home network; Determine similarity parameters of voiceprint feature vectors of every two historical audio segments in the historical audio segment set, and cluster the historical audio segments according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, wherein each audio group corresponds to one of the objects, and a similarity parameter between the voiceprint feature vector of each historical audio segment in each audio group and the voiceprint feature vector of at least one historical audio segment in the same audio group is greater than a preset similarity threshold; Performing audio sampling on the historical audio segments included in each of the audio groups to determine redundant audio data in the historical audio segments, wherein the redundant audio data is audio data in which the number of the objects in the historical audio segments is greater than 1; removing the redundant audio data in the historical audio segment; In the case of receiving a target voice instruction, determining a target audio group matching the target voice instruction from the multiple audio groups, wherein the target voice instruction is used to instruct to control the target device to perform a target operation; The target device parameters corresponding to the target audio group and the target operation are obtained, and the target device is controlled to perform the target operation according to the target device parameters, wherein the target device parameters are used to indicate the operating parameters of the target device.

2. The method according to claim 1, characterized in that The historical audio segments are clustered according to similar parameters of the voiceprint feature vectors of every two historical audio segments to obtain multiple audio groups, including: In a case where the target clustering condition includes the target number of groups, when the number of candidate audio groups obtained by clustering the historical audio segments is consistent with the target number of groups, the multiple audio groups are determined to be obtained, wherein the target number of groups is used to indicate the number of the group of objects associated with the target device network, and the target device network includes the target device.

3. The method according to claim 2, characterized in that The clustering of the historical audio segments according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain the multiple audio groups includes: In a case where the target clustering condition does not include a target number of groups, when the Bayesian parameter of the candidate audio group reaches a target extreme value condition, it is determined that the multiple audio groups are obtained.

4. The method according to claim 1, characterized in that: After performing audio sampling on the historical audio segments included in each of the audio groups and determining redundant audio data in the historical audio segments, the method further includes: Removing the redundant audio data from the historical audio segment to obtain a reference audio segment; An audio group feature of the audio group is calculated based on a reference voiceprint feature vector of the reference audio segment in the audio group.

5. The method according to claim 1, characterized in that The step of determining a target audio group matching the target voice command from the plurality of audio groups comprises: Segmenting the target voice command to obtain a set of target audio segments corresponding to the target voice command; Extracting the voiceprint features of each target audio segment in the target audio segment set respectively to obtain a target voiceprint feature vector of each target audio segment; Based on the target voiceprint feature vector of each target audio segment and the audio group features of each of the multiple audio groups, the target audio group matching the target voice command is determined.

6. The method according to claim 5, characterized in that The determining the target audio group matching the target voice command based on the target voiceprint feature vector of each target audio segment and the audio group features of each of the multiple audio groups comprises: Calculating a reference similarity parameter between the target voiceprint feature vector of each target audio segment and each of the audio group features, wherein the reference similarity parameter is used to indicate the similarity between the target voiceprint feature vector and the audio group feature; Determining a reference parameter of each of the audio group features based on the reference similarity parameter, wherein the reference parameter is used to indicate the similarity between the audio group feature and the voiceprint feature of the target voice command; The target audio group is determined from the multiple audio groups according to the reference parameters corresponding to each of the multiple audio groups.

7. The method according to claim 6, characterized in that Determining the target audio group from the multiple audio groups according to the reference parameters corresponding to the multiple audio groups respectively includes: When there is a target reference parameter greater than a target threshold value among the reference parameters, determining the audio group corresponding to the target reference parameter as the target audio group; When the plurality of reference parameters are all smaller than the target threshold, it is determined that the target audio group is not determined from the plurality of audio groups.

8. The method according to claim 1, characterized in that: The step of obtaining the target device parameters corresponding to the target audio group and the target operation includes: Obtaining a target parameter group corresponding to the target audio group; The target device parameter corresponding to the target operation is searched in the target parameter group.

9. The method according to claim 1, characterized in that: In a case where the target audio group is not determined from the multiple audio groups, obtaining a reference device parameter corresponding to the target operation, wherein the reference device parameter is used to indicate a historical operating parameter of the target device performing the target operation; The target device is controlled to perform the target operation according to the reference device parameters.

10. A control device for an intelligent device, characterized in that: include: an acquisition unit, configured to acquire a historical audio segment set, and respectively extract voiceprint features of each historical audio segment in the historical audio segment set to obtain a voiceprint feature vector of each historical audio segment, wherein the historical audio segment set includes audio segment data obtained by segmenting historical audio data generated by a group of objects collected, and the objects are family members in a home network; a clustering unit, configured to determine similarity parameters of voiceprint feature vectors of every two historical audio segments in the historical audio segment set, and cluster the historical audio segments according to the similarity parameters of the voiceprint feature vectors of every two historical audio segments to obtain a plurality of audio groups, wherein each of the audio groups corresponds to one of the objects, and a similarity parameter between the voiceprint feature vector of each historical audio segment in each of the audio groups and the voiceprint feature vector of at least one historical audio segment in the same audio group is greater than a preset similarity threshold; The device is further configured to perform audio sampling on the historical audio segments included in each of the audio groups, determine redundant audio data in the historical audio segments, wherein the redundant audio data is audio data in which the number of the objects in the historical audio segments is greater than 1; remove the redundant audio data in the historical audio segments; a determination unit is configured to determine, when receiving a target voice instruction, a target audio group that matches the target voice instruction from the multiple audio groups, wherein the target voice instruction is used to instruct a target device to be controlled to perform a target operation; A control unit is used to obtain target device parameters corresponding to the target audio group and the target operation, and control the target device to perform the target operation according to the target device parameters, wherein the target device parameters are used to indicate operating parameters of the target device.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 9 when executed.

12. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 9 through the computer program.

Images