Control method and device of intelligent device, intelligent device and readable storage medium

Abstract

The application provides a control method and device of a smart device, the smart device and a readable storage medium. The control method comprises the following steps: obtaining first voice information and a first wake-up threshold corresponding to a geographical position where the smart device is located; determining a first similarity between the first voice information and first preset wake-up information of the smart device; and controlling the smart device to enter a wake-up stage according to a comparison result of the first similarity and the first wake-up threshold. The wake-up condition of the smart device in different regions is more in line with the language habits of the region, the wake-up difficulty of the user in a dialect-speaking region for the smart device is effectively reduced on the basis of reducing the false wake-up probability, and the use experience of the user is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of smart device technology, and more specifically, to a control method for a smart device, a control device for a smart device, a smart device, and a readable storage medium. Background Technology

[0002] In related technologies, voice wake-up of smart devices leads to voice control. In current mainstream control methods, wake-up rate is generally controlled through a wake-up threshold. A common wake-up threshold is a constant, adjusted according to different device models and acoustic structures. If the wake-up threshold is too low, words similar to the wake word can wake the smart device, causing false wake-ups. If the wake-up threshold is too high, users will feel that the device is difficult to wake up. Due to China's vast territory, numerous dialects, and significant accent differences, in certain specific regions, the difference between accents and standard Mandarin, as well as the non-standard Mandarin spoken by some people, results in a poor device wake-up experience. Summary of the Invention

[0003] The present invention aims to at least solve or improve one of the technical problems existing in the prior art or related art.

[0004] Therefore, a first aspect of the present invention provides a control method for an intelligent device.

[0005] A second aspect of the present invention also provides a control device for a smart device.

[0006] A third aspect of the present invention also provides an intelligent device.

[0007] A fourth aspect of the present invention also provides an intelligent device.

[0008] A fifth aspect of the invention also provides a readable storage medium.

[0009] In view of this, a first aspect of the present invention provides a control method for a smart device, comprising: acquiring first voice information and a first wake-up threshold corresponding to the geographical location of the smart device; determining a first similarity between the first voice information and a first preset wake-up information of the smart device; and controlling the smart device to enter a wake-up phase based on a comparison result of the first similarity and the first wake-up threshold.

[0010] The intelligent device control method provided by this invention utilizes data statistics to pre-set a correspondence between regions and a first wake-up threshold. The first wake-up thresholds for different regions may be the same or different. When a user attempts to wake up the intelligent device using first voice information, the first voice information is compared with the wake-up word (first preset wake-up information) used to wake up the intelligent device, and a first similarity, i.e., the confidence level of the first voice information, is determined. A higher first similarity indicates a closer resemblance between the first voice information and the first preset wake-up information, resulting in a higher success rate in waking up the intelligent device. Simultaneously, the first wake-up threshold corresponding to the location of the intelligent device is queried using the correspondence between the smart device's location and the preset regions and first wake-up thresholds. Then, the first similarity is compared with the first wake-up threshold corresponding to the location, and the comparison result determines whether the user's voice meets the wake-up conditions. If the conditions are met, the intelligent device is woken up. By setting corresponding first wake-up thresholds for different regions instead of using fixed wake-up thresholds, the wake-up conditions of smart devices in different regions are made more in line with the language habits of that region. This reduces the probability of false wake-ups and effectively lowers the difficulty of waking up smart devices for users in dialect-speaking areas. Even elderly people and children with poor Mandarin can use smart devices normally, avoiding the problem of difficult wake-up and greatly improving the user experience.

[0011] Keyword spotting (KWS) refers to the real-time detection of specific segments in a user's voice within a continuous speech stream. The purpose of voice spotting is to activate a device from a sleep state to an active state.

[0012] Understandably, the geographical location corresponding to the first wake-up threshold can be a street, province, city, or even country, and can be reasonably set according to the regional differences in users' language habits.

[0013] The control method for an intelligent device provided by the present invention may further include the following additional technical features:

[0014] In the above technical solution, further, according to the comparison result of the first similarity and the first wake-up threshold, controlling the smart device to enter the wake-up stage includes: controlling the smart device to enter the wake-up stage based on the first similarity being greater than the first wake-up threshold; outputting a confirmation prompt message based on the first similarity being less than or equal to the first wake-up threshold; and controlling the smart device to enter the wake-up stage according to the confirmation instruction of the confirmation prompt message.

[0015] In this technical solution, after comparing the first similarity and the first wake-up threshold, if the first similarity is higher than (greater than) the first wake-up threshold, it means that the first voice information and the wake-up word used to wake up the smart device are highly similar, meeting the wake-up condition, and the smart device is then woken up to facilitate its operation. If the first similarity is not higher than (less than or equal to) the first wake-up threshold, that is, the first voice information and the wake-up word are less similar, and the wake-up condition is not met, a confirmation prompt is sent to the user to remind the user of the wake-up failure and to give the user a second chance to confirm. The user can confirm that they need to wake up the smart device using the first voice information by issuing a confirmation instruction. When the smart device receives the confirmation instruction, it can also be woken up.

[0016] The above technical solution addresses two main issues. First, by using a region-specific wake-up threshold as the basis for waking up smart devices, the wake-up conditions for smart devices in different regions are made more aligned with the local language habits. This reduces the probability of false wake-ups and effectively lowers the difficulty of waking up smart devices for users in dialect-speaking areas. Second, in the event of a wake-up failure, users can request a second confirmation, providing convenience for users in different regions to use smart devices.

[0017] Furthermore, the number of times the smart device is woken up based on confirmation instructions within a specified time period (e.g., one week or one month) is counted. If the number of wake-ups exceeds the preset number, it indicates that during recent use of the smart device, there have been frequent instances of initial wake-up recognition failure, requiring secondary confirmation to complete the wake-up operation. This may be because the pre-stored first wake-up threshold for the corresponding region does not match the user's language habits. In this case, the first wake-up threshold for the corresponding region is appropriately reduced by a preset offset and stored. This ensures that the smart device can be successfully woken up the next time the user triggers a wake-up event.

[0018] In any of the above technical solutions, the output of confirmation prompt information further includes: outputting confirmation prompt information based on the first similarity being greater than the second wake-up threshold of the smart device; wherein the second wake-up threshold is less than the first wake-up threshold.

[0019] In this technical solution, a confirmation prompt is only triggered when the similarity is greater than or slightly lower than a second wake-up threshold. This second wake-up threshold allows for further assessment of the user's wake-up request. This ensures successful wake-up of the smart device while avoiding frequent confirmation prompts that could disturb the user, thus improving the user experience.

[0020] Understandably, the difference between the first and second wake-up thresholds should not be too large or too small. If the difference is too large, meaning the second wake-up threshold is much smaller than the first, the smart device will frequently issue confirmation prompts if a wake-up failure occurs, disturbing the user. If the difference is too small, it will be impossible to distinguish the difference between the first and second wake-up thresholds, reducing the accuracy of judging the user's gliding needs.

[0021] In any of the above technical solutions, the control method of the smart device further includes: acquiring second voice information within a preset duration based on the output confirmation prompt information; determining a second similarity between the second voice information and the second preset wake-up information of the smart device; and generating a confirmation instruction based on the second similarity being greater than the preset similarity.

[0022] In this technical solution, after the smart device sends a confirmation prompt to the user, that is, after the first similarity is higher than the second wake-up threshold, the user can still confirm the wake-up event a second time by voice. Thus, in the case of wake-up failure, the user can confirm a second time by voice, which provides convenience for users in different regions to use smart devices.

[0023] Specifically, upon receiving a confirmation prompt, the smart device begins collecting second voice information. If the second voice information is collected within a preset time period, it is compared with second preset wake-up information used to determine the wake-up event. If the second similarity between the second voice information and the second preset wake-up information is greater than a preset similarity, it indicates successful voice matching, and a confirmation instruction is generated to wake up the smart device. If no second voice information is collected within the preset time period, or the second similarity is less than or equal to the preset similarity, it indicates that the secondary confirmation of this wake-up event has failed. In this case, the wake-up event triggered by the first voice information is ignored, and the smart device remains in sleep mode.

[0024] In any of the above technical solutions, the control method for the intelligent device further includes: obtaining input operation information of the intelligent device within a preset time period based on the output confirmation prompt information; and generating a confirmation instruction based on the fact that the input operation information is the same as the preset operation information.

[0025] In this technical solution, after the smart device sends a confirmation prompt to the user, that is, after the first similarity is higher than the second wake-up threshold, the user can also confirm the wake-up event a second time by inputting the smart device. Thus, in the event of wake-up failure, the user can make a second confirmation by voice, which provides convenience for users in different regions to use smart devices.

[0026] Specifically, based on the same principle as voice confirmation, when the smart device sends a confirmation prompt to the user, the device begins to collect input operation information. If the user's input operation information is collected within a preset time period, it is compared with preset operation information. If the preset operation information matches the input operation information, the operation information is considered successfully matched, and a confirmation instruction is generated to wake up the smart device. If no input operation information is collected within the preset time period, or if the preset operation information does not match the input operation information, it means that the secondary confirmation of this wake-up event has failed. In this case, the wake-up event triggered by the first voice information is ignored, and the smart device remains in sleep mode.

[0027] In any of the above technical solutions, the control method for the smart device further includes: determining the user information corresponding to the first voice information; and updating the first wake-up threshold according to the third wake-up threshold corresponding to the user information.

[0028] In this technical solution, before waking up the smart device by comparing a first wake-up threshold and a first voice message, the user information of the user who sent the first voice message is first identified. The first wake-up threshold is then corrected using a third wake-up threshold associated with that user, and the corrected first wake-up threshold is stored. Therefore, when the same user needs to wake up the smart device again, the first wake-up threshold matched by geographical location will be the first wake-up threshold corrected by the third wake-up threshold. This allows the smart device wake-up conditions to not only conform to the language habits of most people in a certain region, but also to be dynamically adjusted for individuals, further reducing the wake-up difficulty for different people in different regions and improving the reliability of the smart device.

[0029] In any of the above technical solutions, the control method of the smart device further includes: in response to the configuration command of the smart device, acquiring third voice information; determining user information based on the voiceprint features of the third voice information; determining the third similarity between the third voice information and the first preset wake-up information; and performing a weighted operation on the third similarity and the first wake-up threshold to obtain the third wake-up threshold corresponding to the user information.

[0030] In this technical solution, users can issue configuration commands to smart devices to set a third wake-up threshold that is linked to user information. These configuration commands, including wake-up instructions after the smart device's first startup or initialization, and control instructions for the smart device's configuration mode, are used to set the third wake-up threshold.

[0031] Specifically, upon receiving a configuration command, the smart device begins collecting third-party voice information. The user information of the user who issued the third-party voice information is matched using the voiceprint features of the third-party voice information. The third-party voice information is compared with a first preset wake-up information, and a third similarity is determined between the two. The product of the third similarity and its corresponding third weight is calculated, along with the product of the first wake-up threshold matched based on geographical location and its corresponding fourth weight. These two products are added together to obtain the third wake-up threshold, which is then bound to the user information to complete the configuration of the third wake-up threshold for each individual user. This allows for adjustments to the first wake-up threshold based on region, while simultaneously updating the first wake-up threshold based on the user's individual language habits. This helps reduce the wake-up difficulty for different groups of people in different regions, improving the reliability of the smart device.

[0032] Voiceprint features include rhythmic features, pitch features, and phoneme features.

[0033] In any of the above technical solutions, the control method for the smart device further includes: acquiring fourth voice information within a preset duration based on the smart device being in the wake-up phase; and controlling the operation of the smart device according to the control command corresponding to the fourth voice information.

[0034] In this technical solution, once the smart device is activated, the user can issue control commands to it via voice, causing the device to operate accordingly. This allows users to precisely control the air conditioner using voice commands, eliminating the need for manual adjustments and making the process more convenient and efficient.

[0035] Specifically, the system recognizes the text in the fourth voice message, such as "temperature," "cooling," or "increase the speed." Using the recognized text, it searches for the corresponding control command in a pre-stored list in memory. If found, the control command is determined. If not found, the fourth voice message is ignored, and a notification is output to inform the user of control failure.

[0036] In any of the above technical solutions, the control method for the smart device further includes: controlling the smart device to exit the wake-up phase based on the fact that no fourth voice information has been collected within a preset time period.

[0037] In this technical solution, if no fourth voice information is collected within a preset time after the smart device has been woken up, it means that the user no longer wants to run the smart device. In this case, the smart device is controlled to exit the wake-up phase and re-enter the sleep state, which helps to reduce the power consumption of the smart device and save the operating cost of the smart device.

[0038] In any of the above technical solutions, further, determining the first similarity between the first voice information and the first preset wake-up information of the smart device includes: identifying the first voice feature of the first voice information; comparing the first voice feature with the second voice feature in the first preset wake-up information to determine the first similarity.

[0039] In this technical solution, feature extraction processing is performed on the first voice information to obtain the first voice feature. By comparing the first voice feature contained in the first voice information with the second voice feature in the first preset wake-up information, the probability that the first voice feature corresponds to the second voice feature is the first similarity between the first voice information and the first preset wake-up information, so as to realize the voice wake-up function of the smart device through the first similarity.

[0040] Among them, speech features include syllable structure, pronunciation features, Mel frequency cepstrum coefficient (MFCC) features, etc.

[0041] According to a second aspect of the present invention, a control device for a smart device is also provided, comprising: an acquisition module for acquiring first voice information and a first wake-up threshold corresponding to the geographical location of the smart device; a determination module for determining a first similarity between the first voice information and first preset wake-up information of the smart device; and a wake-up module for controlling the smart device to enter a wake-up phase based on a comparison result between the first similarity and the first wake-up threshold.

[0042] In this technical solution, data statistics are used to pre-set a correspondence between regions and a first wake-up threshold. The first wake-up thresholds for different regions can be the same or different. When a user attempts to wake up a smart device using first voice information, the first voice information is compared with the wake-up word used to wake the smart device (first preset wake-up information), and a first similarity, i.e., the confidence level of the first voice information, is determined. A higher first similarity indicates a closer resemblance between the first voice information and the first preset wake-up information, resulting in a higher success rate in waking up the smart device. Simultaneously, the first wake-up threshold corresponding to the location of the smart device is queried using the correspondence between the smart device's location and the preset regions and first wake-up thresholds. Then, the first similarity is compared with the first wake-up threshold corresponding to the location, and the comparison result determines whether the user's voice meets the wake-up conditions. If the conditions are met, the smart device is woken up. By setting corresponding first wake-up thresholds for different regions instead of using fixed wake-up thresholds, the wake-up conditions of smart devices in different regions are made more in line with the language habits of that region. This reduces the probability of false wake-ups and effectively lowers the difficulty of waking up smart devices for users in dialect-speaking areas. Even elderly people and children with poor Mandarin can use smart devices normally, avoiding the problem of difficult wake-up and greatly improving the user experience.

[0043] According to a third aspect of the present invention, an intelligent device is also provided, comprising the control device for the intelligent device proposed in the second aspect. Therefore, this intelligent device possesses all the beneficial effects of the control device for the intelligent device proposed in the second aspect, and to avoid repetition, further details will not be provided.

[0044] According to a fourth aspect of the present invention, an intelligent device is also provided, comprising: a memory storing a program or instructions; and a processor connected to the memory, wherein the processor, when executing the program or instructions, implements the control method for the intelligent device proposed in the first aspect. Therefore, this intelligent device possesses all the beneficial effects of the control method for the intelligent device proposed in the first aspect, and to avoid repetition, further details are omitted.

[0045] Furthermore, smart devices include electrical appliances and terminal devices such as air conditioners, televisions, cooking appliances, refrigerators, and washing machines. Among them, terminal devices include mobile phones, tablets, computers, laptops, wearable devices, and in-vehicle terminals.

[0046] According to a fifth aspect of the present invention, a readable storage medium is provided on which a program or instructions are stored, which, when executed by a processor, perform the control method for the intelligent device proposed in the first aspect. Therefore, this readable storage medium possesses all the beneficial effects of the control method for the intelligent device proposed in the first aspect, and to avoid repetition, further details are omitted.

[0047] Additional aspects and advantages of the invention will become apparent in the following description or may be learned by practice of the invention. Attached Figure Description

[0048] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0049] Figure 1 One of the flowcharts of a control method for a smart device according to an embodiment of the present invention is shown;

[0050] Figure 2 A second schematic flowchart of a control method for an intelligent device according to an embodiment of the present invention is shown;

[0051] Figure 3 The third schematic flowchart illustrates a control method for an intelligent device according to an embodiment of the present invention;

[0052] Figure 4 The fourth schematic flowchart illustrates a control method for an intelligent device according to an embodiment of the present invention.

[0053] Figure 5 Fifth of the flowcharts illustrates a control method for an intelligent device according to an embodiment of the present invention;

[0054] Figure 6 A flowchart illustrating a control method for an intelligent device according to an embodiment of the present invention is shown in Figure 6.

[0055] Figure 7 The seventh illustration shows a flowchart of a control method for an intelligent device according to an embodiment of the present invention;

[0056] Figure 8 A flowchart illustrating a control method for a smart device according to a specific embodiment of the present invention is shown.

[0057] Figure 9 A structural block diagram of a control device for a smart device according to an embodiment of the present invention is shown;

[0058] Figure 10 A structural block diagram of a smart device according to an embodiment of the present invention is shown. Detailed Implementation

[0059] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0060] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0061] The following reference Figures 1 to 10 This invention describes a control method, apparatus, smart device, and readable storage medium for a smart device according to some embodiments of the present invention.

[0062] Example 1:

[0063] like Figure 1 As shown, according to one embodiment of the present invention, the present invention proposes a control method for a smart device, comprising:

[0064] Step 102: Obtain the first voice information and the first wake-up threshold corresponding to the geographical location of the smart device;

[0065] In this process, GPS (Global Positioning System) modules, WIFI (Wireless Fidelity) and / or base station positioning modules are pre-installed in smart devices to obtain the geographical location of the smart devices.

[0066] Step 104: Determine the first similarity between the first voice information and the first preset wake-up information of the smart device;

[0067] Step 106: Based on the comparison result of the first similarity and the first wake-up threshold, control the smart device to enter the wake-up stage.

[0068] Keyword spotting (KWS) refers to the real-time detection of specific segments in a user's voice within a continuous speech stream. The purpose of voice spotting is to activate a device from a sleep state to an active state.

[0069] In this embodiment, data statistics are used to pre-set a correspondence between regions and a first wake-up threshold. The first wake-up thresholds for different regions may be the same or different. When a user attempts to wake up a smart device using first voice information, the first voice information is compared with the wake-up word (first preset wake-up information) used to wake the smart device, and a first similarity, i.e., the confidence level of the first voice information, is determined. A higher first similarity indicates a closer resemblance between the first voice information and the first preset wake-up information, resulting in a higher success rate in waking up the smart device. Simultaneously, the first wake-up threshold corresponding to the location of the smart device is queried using the correspondence between the smart device's location and the preset regions and first wake-up thresholds. Then, the first similarity is compared with the first wake-up threshold corresponding to the location, and the comparison result determines whether the user's voice meets the wake-up conditions. If the conditions are met, the smart device is woken up. By setting corresponding first wake-up thresholds for different regions instead of using fixed wake-up thresholds, the wake-up conditions of smart devices in different regions are made more in line with the language habits of that region. This reduces the probability of false wake-ups and effectively lowers the difficulty of waking up smart devices for users in dialect-speaking areas. Even elderly people and children with poor Mandarin can use smart devices normally, avoiding the problem of difficult wake-up and greatly improving the user experience.

[0070] In some embodiments, the smart device includes a voice acquisition device (e.g., a microphone array), a speaker, a processor, and a memory. The first preset wake-up information required for activation is also pre-set; it can be a Chinese wake-up word, an English wake-up word, or a dialect wake-up word, such as "Open Sesame" or "Hello Xiaomei." During the configuration phase of the smart device, the user can record the first preset wake-up information through the microphone array and then save it to the memory. Similarly, when the user wants to turn on the smart device, the microphone array acquires the user's first voice message.

[0071] Understandably, the geographical location corresponding to the first wake-up threshold can be a street, province, city, or even country, and can be reasonably set according to the regional differences in users' language habits. For example, provinces and cities can be used as regional boundaries, and the first wake-up threshold for northern provinces can be set to 80%, while the first wake-up threshold for southern provinces can be set to 60%.

[0072] Furthermore, ambient noise information around the smart device is acquired; the first wake-up threshold is then adjusted based on this information. This allows for dynamic adjustment of the first wake-up threshold in the current wake-up process, depending on the environment in which the smart device is located. For example, if the ambient noise level is higher than the preset noise level, it indicates that the current environment is noisy, which is not conducive to voice information acquisition. In this case, the first wake-up threshold can be appropriately lowered. In quiet environments, however, there is no need to modify the first wake-up threshold, thereby improving the accuracy and reliability of wake-up word recognition.

[0073] It is worth mentioning that, in order to improve the recognition accuracy of the first speech information, noise reduction processing can be performed on the first speech information. Specifically, the location information of the sound source (coordinates, distance, angle, etc.) is first determined, and then a corresponding noise reduction algorithm is applied based on the location information of the sound source. This removes environmental noise and achieves noise and echo suppression.

[0074] Example 2:

[0075] like Figure 2 As shown, according to one embodiment of the present invention, the present invention proposes a control method for a smart device, comprising:

[0076] Step 202: Obtain the first voice information and the first wake-up threshold corresponding to the geographical location of the smart device;

[0077] Step 204: Determine the first similarity between the first voice information and the preset wake-up word;

[0078] Step 206: Is the first similarity greater than the first wake-up threshold? If yes, proceed to step 208; otherwise, proceed to step 210.

[0079] Step 208: Wake up the smart device;

[0080] Step 210: Output a confirmation message;

[0081] Step 212: Is a confirmation indication detected? If yes, proceed to step 210; otherwise, proceed to step 214.

[0082] Step 214: Ignore this wake-up event.

[0083] In this embodiment, a first similarity is determined by comparing the first voice information with a preset wake-up word (first preset wake-up information), and then the first similarity is compared with a first wake-up threshold. If the first similarity is higher than (greater than) the first wake-up threshold, it means that the first voice information and the wake-up word used to wake up the smart device are highly similar, meeting the wake-up condition, and the smart device is then woken up to allow it to operate. If the first similarity is not higher than (less than or equal to) the first wake-up threshold, that is, the first voice information and the wake-up word are less similar, not meeting the wake-up condition, a confirmation prompt is sent to the user to remind the user of the wake-up failure and give the user a second chance to confirm. The user can confirm that they need to wake up the smart device using the first voice information by issuing a confirmation instruction. When the smart device receives the confirmation instruction, it can also be woken up.

[0084] This embodiment addresses two main issues. First, by using a region-specific wake-up threshold as the basis for waking up smart devices, the wake-up conditions for smart devices in different regions are made more aligned with the language habits of those regions. This reduces the probability of false wake-ups and effectively lowers the difficulty of waking up smart devices for users in dialect-speaking areas. Second, in the event of a wake-up failure, users can request a second confirmation, providing convenience for users in different regions to use smart devices.

[0085] For example, for smart devices used in northern regions, where Mandarin is widely spoken, the corresponding first wake-up threshold is relatively high. However, if someone speaking a regional dialect tries to wake up the smart device in the northern region, wake-up failure is very likely. In this case, the person speaking the dialect can confirm the wake-up operation through other means, enabling the smart device to successfully wake up and operate, thus improving the practicality and reliability of the smart device.

[0086] Specifically, outputting confirmation prompts includes displaying or playing confirmation prompts. Confirmation prompts may include text, images, lights, etc., and this embodiment of the invention does not impose specific limitations.

[0087] Furthermore, the number of times the smart device is woken up based on confirmation instructions within a specified time period (e.g., one week or one month) is counted. If the number of wake-ups exceeds the preset number, it indicates that during recent use of the smart device, there have been frequent instances of initial wake-up recognition failure, requiring secondary confirmation to complete the wake-up operation. This may be because the pre-stored first wake-up threshold for the corresponding region does not match the user's language habits. In this case, the first wake-up threshold for the corresponding region is appropriately reduced by a preset offset and stored. This ensures that the smart device can be successfully woken up the next time the user triggers a wake-up event.

[0088] Specifically, the confirmation instructions for obtaining confirmation prompts include the following two methods.

[0089] Method 1: After the smart device sends a confirmation prompt to the user, that is, after the first similarity is higher than the second wake-up threshold, the second voice information within a preset time period is obtained. The wake-up event is then confirmed again through the second voice information. In the event of wake-up failure, the user can confirm again through voice, which provides convenience for users in different regions to use smart devices.

[0090] Upon receiving a confirmation prompt, the smart device begins collecting second voice information. If the second voice information is collected within a preset time period, it is compared with second preset wake-up information used to determine the wake-up event. If the second similarity between the second voice information and the second preset wake-up information is greater than a preset similarity, it indicates successful voice matching, and a confirmation instruction is generated to wake up the smart device. If no second voice information is collected within the preset time period, or the second similarity is less than or equal to the preset similarity, it indicates that the secondary confirmation of this wake-up event has failed. In this case, the wake-up event triggered by the first voice information is ignored, and the smart device remains in sleep mode.

[0091] It is worth mentioning that the first or second preset wake-up message can be a voiceprint feature, a word's textual structure feature, or a combination of both. The preset duration is the time required to respond to the second voice message. The first and second preset wake-up messages can be the same or different, and they can be bound to the user information of the smart device's owner. This means different users can set different wake-up words, thereby preventing unauthorized wake-up operations and improving the security of the smart device.

[0092] For example, a user sends a first voice message saying "Xiao Mei Xiao Mei." Because the user is using a dialect, the first voice message's similarity to a first preset wake-up message is lower than a first wake-up threshold, but higher than a second wake-up threshold. At this time, the indicator light on the air conditioner (smart device) starts flashing regularly to remind the user to confirm. The user then sends a second voice message saying "Confirm." The keyword "Confirm" is extracted from the second voice message. By comparing structural features, it can be determined that the second voice message is the same as the second preset wake-up message. The air conditioner is then activated.

[0093] Method 2: After the smart device sends a confirmation prompt to the user (i.e., the first similarity is higher than the second wake-up threshold), it acquires input operation information within a preset time period. This input operation information is used to perform a secondary confirmation of the wake-up event. Therefore, in the event of a failed wake-up, the user can confirm via voice, providing convenience for users in different regions using smart devices.

[0094] Based on the same principle as voice confirmation, when the smart device sends a confirmation prompt to the user, it begins collecting input operation information. If the user's input operation information is collected within a preset time period, it is compared with preset operation information. If the preset operation information matches the input operation information, the operation information is successfully matched, and a confirmation instruction is generated to wake up the smart device. If no input operation information is collected within the preset time period, or if the preset operation information does not match the input operation information, it means that the secondary confirmation of this wake-up event has failed. In this case, the wake-up event triggered by the first voice information is ignored, and the smart device remains in sleep mode.

[0095] For example, the input operation information includes input methods and input content. Input methods include click input, button input, fingerprint input, gesture input, etc. Input content includes: fingerprint, gesture, user information, specified commands, etc. Among them, button input includes, but is not limited to, single-click input, double-click input, long-press input, and combination key input of the power button, main menu button, and control buttons of the application used to control the smart device. Of course, the input operation information can also be other operation information of the user on the smart device. This application embodiment does not specifically limit the operation method and content, and can be any feasible method.

[0096] For example, if a user makes a "V" sign in the command detection area of ​​a smart device, the characteristics of this gesture are compared with preset gesture characteristics (preset operation information). If the "V" sign matches the preset operation information, a confirmation instruction is generated.

[0097] Example 3:

[0098] like Figure 3 As shown, according to one embodiment of the present invention, the present invention proposes a control method for a smart device, comprising:

[0099] Step 302: Obtain the first voice information and the first wake-up threshold corresponding to the geographical location of the smart device;

[0100] Step 304: Determine the first similarity between the first voice information and the preset wake-up word;

[0101] Step 306: Is the first similarity greater than the first wake-up threshold? If yes, proceed to step 308; otherwise, proceed to step 310.

[0102] Step 308: Wake up the smart device;

[0103] Step 310: Is the first similarity greater than the second wake-up threshold? If yes, proceed to step 312; otherwise, proceed to step 316.

[0104] Step 312: Output a confirmation message;

[0105] Step 314: Is a confirmation indication detected? If yes, proceed to step 308; otherwise, proceed to step 316.

[0106] Step 316: Ignore this wake-up event.

[0107] In this embodiment, a confirmation prompt is only triggered when the first similarity is greater than or slightly less than a second wake-up threshold. This second wake-up threshold allows for further assessment of the user's wake-up request. This ensures successful wake-up of the smart device while avoiding frequent confirmation prompts that could disturb the user, thus improving the user experience.

[0108] Understandably, the difference between the first and second wake-up thresholds should not be too large or too small. If the difference is too large, meaning the second wake-up threshold is much smaller than the first, the smart device will frequently issue confirmation prompts if a wake-up failure occurs, disturbing the user. If the difference is too small, it will be impossible to distinguish the difference between the first and second wake-up thresholds, reducing the accuracy of judging the user's gliding needs.

[0109] Example 4:

[0110] like Figure 4 As shown, according to one embodiment of the present invention, the present invention proposes a control method for a smart device, comprising:

[0111] Step 402: Obtain the first voice information and the first wake-up threshold corresponding to the geographical location of the smart device;

[0112] Step 404: Update the first wake-up threshold according to the third wake-up threshold corresponding to the user information associated with the first voice information;

[0113] Step 406: Determine the first similarity between the first voice information and the preset wake-up word;

[0114] Step 408: Is the first similarity greater than the first wake-up threshold? If yes, proceed to step 410; otherwise, proceed to step 412.

[0115] Step 410: Wake up the smart device;

[0116] Step 412: Ignore this wake-up event.

[0117] In this embodiment, before waking up the smart device by comparing a first wake-up threshold and a first voice message, the user information of the user who sent the first voice message is first identified. The first wake-up threshold is then corrected using a third wake-up threshold associated with that user, and the corrected first wake-up threshold is stored. Therefore, when the same user needs to wake up the smart device again, the first wake-up threshold matched by geographical location will be the first wake-up threshold corrected by the third wake-up threshold. This ensures that the smart device wake-up conditions not only conform to the language habits of most people in a certain region but can also be dynamically adjusted for individuals, further reducing the wake-up difficulty for different people in different regions and improving the reliability of the smart device.

[0118] Specifically, the product of the third wake-up threshold and its corresponding first weight is calculated, as is the product of the first wake-up threshold matched this time and its corresponding second weight. These two products are then added together, i.e., a weighted calculation is performed on the third and first wake-up thresholds. Finally, the value obtained from the weighted calculation is set as the new first wake-up threshold for this region and stored.

[0119] Example 5:

[0120] like Figure 5 As shown, according to one embodiment of the present invention, the present invention proposes a control method for a smart device, comprising:

[0121] Step 502: Receive configuration instructions for the smart device;

[0122] Step 504: In response to the configuration command, obtain third-party voice information;

[0123] Step 506: Compare the preset wake-up word with the third voice information to determine the third similarity;

[0124] Step 508: Perform a weighted operation on the third similarity and the first wake-up threshold to obtain the third wake-up threshold corresponding to the user information of the third voice information;

[0125] Step 510: Obtain the first voice information and the first wake-up threshold corresponding to the geographical location of the smart device;

[0126] Step 512: Adjust the first wake-up threshold according to the third wake-up threshold;

[0127] Step 514: Determine the first similarity between the first voice information and the preset wake-up word;

[0128] Step 516: Based on the comparison result of the first similarity and the first wake-up threshold, control the smart device to enter the wake-up stage.

[0129] In this embodiment, the user can issue configuration commands to the smart device to set a third wake-up threshold that is linked to the user's information. The configuration commands are used to set the third wake-up threshold and include wake-up instructions after the smart device's first startup or initialization, control instructions for the smart device's configuration mode, etc.

[0130] Specifically, upon receiving a configuration command, the smart device begins collecting third-party voice information. The user information of the user who issued the third-party voice information is matched using the voiceprint features of the third-party voice information. The third-party voice information is compared with a first preset wake-up information, and a third similarity is determined between the two. The product of the third similarity and its corresponding third weight is calculated, along with the product of the first wake-up threshold matched based on geographical location and its corresponding fourth weight. These two products are added together to obtain the third wake-up threshold, which is then bound to the user information to complete the configuration of the third wake-up threshold for each individual user. This allows for adjustments to the first wake-up threshold based on region, while simultaneously updating the first wake-up threshold based on the user's individual language habits. This helps reduce the wake-up difficulty for different groups of people in different regions, improving the reliability of the smart device.

[0131] Voiceprint features include rhythmic features, pitch features, and phoneme features.

[0132] Understandably, if a user configures the third wake-up threshold multiple times, resulting in multiple third wake-up thresholds, the first wake-up threshold can be adjusted based on the average of these multiple third wake-up thresholds. This will make the revised first wake-up threshold more closely reflect the user's actual language habits.

[0133] Example 6:

[0134] like Figure 6 As shown, according to one embodiment of the present invention, the present invention proposes a control method for a smart device, comprising:

[0135] Step 602: Obtain the first voice information and the first wake-up threshold corresponding to the location of the smart device;

[0136] Step 604: Determine the first similarity between the first voice information and the preset wake-up word;

[0137] Step 606: Wake up the smart device based on the first similarity.

[0138] Step 608: Whether the fourth voice information is collected within the preset time period. If yes, proceed to step 610; otherwise, proceed to step 612.

[0139] Step 610: Operate the smart device according to the control command corresponding to the fourth voice information;

[0140] Step 612: Control the smart device to exit the wake-up phase.

[0141] In this embodiment, once the smart device is activated, the user can issue control commands to it via fourth voice information, causing the device to operate according to those commands. This allows users to precisely control the air conditioner using voice commands, eliminating the need for manual adjustments and making the process more convenient and faster.

[0142] Specifically, the system recognizes the text in the fourth voice message, such as "temperature," "cooling," or "increase the speed." Using the recognized text, it searches for the corresponding control command in a pre-stored list in memory. If found, the control command is determined. If not found, the fourth voice message is ignored, and a notification is output to inform the user of control failure.

[0143] For example, when the air conditioner is in the wake-up phase and recognizes the content of the fourth voice message as "set the temperature to 18 degrees", it determines that the control command is to adjust the target temperature of the air conditioner to 18 degrees. At this time, in response to the control command, the air conditioner can directly set the temperature to 18 degrees.

[0144] Furthermore, if no fourth voice information is collected within a preset time period, it indicates that the user no longer wants to run the smart device. In this case, the smart device is controlled to exit the wake-up phase and re-enter the sleep state, which helps to reduce the power consumption of the smart device and save the operating cost of the smart device.

[0145] Example 7:

[0146] like Figure 7 As shown, according to one embodiment of the present invention, the present invention proposes a control method for a smart device, comprising:

[0147] Step 702: Obtain the first voice information and the first wake-up threshold corresponding to the geographical location of the smart device;

[0148] Step 704: Identify the first speech feature of the first speech information;

[0149] Step 706: Compare the first speech feature with the second speech feature in the first preset wake-up information to obtain the first similarity.

[0150] Step 708: Based on the comparison result of the first similarity and the first wake-up threshold, control the smart device to enter the wake-up stage.

[0151] In this embodiment, feature extraction processing is performed on the first voice information to obtain a first voice feature. By comparing the first voice feature contained in the first voice information with the second voice feature in the first preset wake-up information, the probability that the first voice feature corresponds to the second voice feature is the first similarity between the first voice information and the first preset wake-up information, so as to realize the voice wake-up function of the smart device through the first similarity.

[0152] Among them, speech features include syllable structure, pronunciation features, Mel frequency cepstrum coefficient (MFCC) features, etc.

[0153] Example 8:

[0154] like Figure 8 As shown, according to a specific embodiment of the present invention, the present invention proposes a control method for a smart device, comprising:

[0155] Step 802: Obtain the wake-up command word;

[0156] Step 804: Read the wake-up threshold for the current region;

[0157] Step 806: Is the confidence level of the wake-up command word higher than the first wake-up threshold? If yes, proceed to step 808; otherwise, proceed to step 814.

[0158] Step 808: Wake up the device and broadcast a message;

[0159] Step 810: Record the current confidence level and current region information, and calculate the user's average wake-up threshold based on the current confidence level;

[0160] Step 812: Take the weighted average of the pre-stored wake-up threshold and the average wake-up threshold on the local machine as the new first wake-up threshold for the current region.

[0161] Step 814: Is the confidence level close to the wake-up threshold? If yes, proceed to step 816; otherwise, proceed to step 818.

[0162] Step 816: Confirm again whether to wake up. If yes, proceed to step 808; if no, proceed to step 818.

[0163] Step 818: Ignore wake-up events.

[0164] In this embodiment, if the confidence level of the wake-up command word (first voice information) is higher than the wake-up threshold (first wake-up threshold), the device is woken up normally. If the confidence level of the wake-up command word is slightly lower than the wake-up threshold, secondary confirmation is required. This confirmation can be made with the user via an app or voice. If the user confirms that wake-up is needed, the confidence level and region information of this wake-up are recorded. If the user confirms that wake-up is not needed or the confidence level of the wake-up word is much lower than the wake-up threshold, the wake-up event is ignored. Furthermore, after waking up the device, the average wake-up threshold of users in the device's region (third wake-up threshold) is taken as one item in the weighted algorithm, and the other item is the wake-up threshold of the device itself. The wake-up threshold corresponding to the current region is then updated. This fully considers the different levels of Mandarin proficiency in each region, making the wake-up threshold more consistent with the common speaking habits of the region, and flexibly and conveniently implementing the device's voice wake-up function.

[0165] Example 9:

[0166] like Figure 9 As shown, according to an embodiment of the present invention, the present invention provides a control device 900 for a smart device, comprising: an acquisition module 902, a determination module 904, and a wake-up module 906.

[0167] Specifically, the acquisition module 902 is used to acquire the first voice information and the first wake-up threshold corresponding to the geographical location of the smart device; the determination module 904 is used to determine the first similarity between the first voice information and the first preset wake-up information of the smart device; and the wake-up module 906 is used to control the smart device to enter the wake-up stage based on the comparison result of the first similarity and the first wake-up threshold.

[0168] In this embodiment, data statistics are used to pre-set a correspondence between regions and a first wake-up threshold. The first wake-up thresholds for different regions may be the same or different. When a user attempts to wake up a smart device using first voice information, the first voice information is compared with the wake-up word (first preset wake-up information) used to wake the smart device, and a first similarity, i.e., the confidence level of the first voice information, is determined. A higher first similarity indicates a closer resemblance between the first voice information and the first preset wake-up information, resulting in a higher success rate in waking up the smart device. Simultaneously, the first wake-up threshold corresponding to the location of the smart device is queried using the correspondence between the smart device's location and the preset regions and first wake-up thresholds. Then, the first similarity is compared with the first wake-up threshold corresponding to the location, and the comparison result determines whether the user's voice meets the wake-up conditions. If the conditions are met, the smart device is woken up. By setting corresponding first wake-up thresholds for different regions instead of using fixed wake-up thresholds, the wake-up conditions of smart devices in different regions are made more in line with the language habits of that region. This reduces the probability of false wake-ups and effectively lowers the difficulty of waking up smart devices for users in dialect-speaking areas. Even elderly people and children with poor Mandarin can use smart devices normally, avoiding the problem of difficult wake-up and greatly improving the user experience.

[0169] Furthermore, the wake-up module 906 is also used to control the smart device to enter the wake-up stage based on the first similarity being greater than the first wake-up threshold; the control device 900 of the smart device also includes: an output module (not shown in the figure), the output module is used to output confirmation prompt information based on the first similarity being less than or equal to the first wake-up threshold; the wake-up module 906 is also used to control the smart device to enter the wake-up stage according to the confirmation indication of the confirmation prompt information.

[0170] Furthermore, the output module is also used to output a confirmation prompt message based on the first similarity being greater than the second wake-up threshold of the smart device; wherein the second wake-up threshold is less than the first wake-up threshold.

[0171] Furthermore, the acquisition module 902 is also used to acquire second voice information within a preset duration based on the output confirmation prompt information; the determination module 904 is also used to determine the second similarity between the second voice information and the second preset wake-up information of the smart device; and generate a confirmation instruction based on the second similarity being greater than the preset similarity.

[0172] Furthermore, the acquisition module 902 is also used to acquire the input operation information of the smart device within a preset time period based on the output confirmation prompt information; the determination module 904 is also used to generate a confirmation instruction based on the fact that the input operation information is the same as the preset operation information.

[0173] Furthermore, the determining module 904 is also used to determine the user information corresponding to the first voice information; the control device 900 of the smart device also includes: an updating module (not shown in the figure), which is used to update the first wake-up threshold according to the third wake-up threshold corresponding to the user information.

[0174] Furthermore, the acquisition module 902 is also used to acquire third voice information in response to the configuration command of the smart device; the determination module 904 is also used to determine user information based on the voiceprint features of the third voice information; determine the third similarity between the third voice information and the first preset wake-up information; and perform a weighted operation on the third similarity and the first wake-up threshold to obtain the third wake-up threshold corresponding to the user information.

[0175] Furthermore, the acquisition module 902 is also used to acquire the fourth voice information within a preset duration based on the smart device being in the wake-up phase; the control device 900 of the smart device also includes: a control module (not shown in the figure), which is used to control the operation of the smart device according to the control command corresponding to the fourth voice information.

[0176] Furthermore, the wake-up module 906 is also used to control the smart device to exit the wake-up phase if no fourth voice information is collected within a preset time period.

[0177] Furthermore, the control device 900 of the smart device also includes: an identification module (not shown in the figure), which is used to identify the first voice feature of the first voice information; the determination module 904 is also used to compare the first voice feature and the second voice feature in the first preset wake-up information to determine the first similarity.

[0178] In this embodiment, when each module of the control device 900 of the smart device performs its respective function, it implements the steps of the application icon display method in any embodiment of the first aspect. Therefore, the control device 900 of the smart device also includes all the beneficial effects of the control method of the smart device in any embodiment of the first aspect, which will not be repeated here.

[0179] Example 10:

[0180] According to one embodiment of the present invention, an intelligent device is provided, including the control device for the intelligent device proposed in the second aspect embodiment. Therefore, this intelligent device possesses all the beneficial effects of the control device for the intelligent device proposed in the second aspect embodiment, and to avoid repetition, further details are omitted.

[0181] For example, smart devices include electrical appliances and terminal devices such as air conditioners, televisions, cooking appliances, refrigerators, and washing machines. Terminal devices include mobile phones, tablets, computers, laptops, wearable devices, and in-vehicle terminals.

[0182] Example 11:

[0183] like Figure 10 As shown, according to one embodiment of the present invention, the present invention proposes a smart device 1000, including: a memory 1002 and a processor 1004.

[0184] Specifically, the memory 1002 stores programs or instructions. When the processor 1004 executes the programs or instructions, it implements the control method for the intelligent device proposed in the first aspect embodiment. Therefore, the intelligent device possesses all the beneficial effects of the control method for the intelligent device proposed in the first aspect embodiment, and to avoid repetition, further details will not be provided.

[0185] For example, smart devices include electrical appliances and terminal devices such as air conditioners, televisions, cooking appliances, refrigerators, and washing machines. Terminal devices include mobile phones, tablets, computers, laptops, wearable devices, and in-vehicle terminals.

[0186] Example 12:

[0187] According to one embodiment of the present invention, a readable storage medium is provided on which a program or instructions are stored, which, when executed by a processor, perform the control method of the intelligent device proposed in the first aspect embodiment. Therefore, this readable storage medium possesses all the beneficial effects of the control method of the intelligent device proposed in the first aspect embodiment, and to avoid repetition, further details are omitted.

[0188] In this invention, the term "multiple" refers to two or more unless otherwise explicitly defined. The terms "installed," "connected," "linked," and "fixed," etc., should be interpreted broadly. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; "linked" can be a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0189] In the description of this specification, the terms "one embodiment," "some embodiments," "specific embodiment," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0190] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A control method for an intelligent device, characterized in that, include: Obtain the first voice information and the first wake-up threshold corresponding to the geographical location of the smart device; Determine the first similarity between the first voice information and the first preset wake-up information of the smart device; Based on the comparison result of the first similarity and the first wake-up threshold, the smart device is controlled to enter the wake-up phase; The step of controlling the smart device to enter the wake-up phase based on the comparison result of the first similarity and the first wake-up threshold includes: Based on the fact that the first similarity is greater than the first wake-up threshold, the smart device is controlled to enter the wake-up phase; Based on the first similarity being less than or equal to the first wake-up threshold, output a confirmation prompt message; Based on the confirmation prompt, the smart device is controlled to enter the wake-up phase; The output confirmation prompt information includes displaying a confirmation prompt information or playing a confirmation prompt information; The control method for the intelligent device also includes: Obtain ambient noise information around the smart device; The first wake-up threshold is corrected based on the environmental noise information; The control method for the intelligent device also includes: In response to the configuration command of the smart device, third voice information is acquired; User information is determined based on the voiceprint features of the third voice information; Determine the third similarity between the third voice information and the first preset wake-up information; The third similarity and the first wake-up threshold are weighted and calculated to obtain the third wake-up threshold corresponding to the user information.

2. The control method for an intelligent device according to claim 1, characterized in that, The output confirmation message includes: Based on the fact that the first similarity is greater than the second wake-up threshold of the smart device, a confirmation prompt message is output; Wherein, the second wake-up threshold is less than the first wake-up threshold.

3. The control method for an intelligent device according to claim 1, characterized in that, Also includes: Based on the output confirmation prompt, obtain the second voice information within a preset duration; Determine the second similarity between the second voice information and the second preset wake-up information of the smart device; The confirmation instruction is generated based on the fact that the second similarity is greater than the preset similarity.

4. The control method for an intelligent device according to claim 1, characterized in that, Also includes: Based on the output confirmation prompt information, obtain the input operation information of the smart device within a preset time period; The confirmation instruction is generated based on the fact that the input operation information is the same as the preset operation information.

5. The control method for an intelligent device according to any one of claims 1 to 4, characterized in that, Also includes: Determine the user information corresponding to the first voice information; The first wake-up threshold is updated based on the third wake-up threshold corresponding to the user information.

6. The control method for an intelligent device according to any one of claims 1 to 4, characterized in that, Also includes: Based on the fact that the smart device is in the wake-up phase, the fourth voice information within a preset duration is obtained; The smart device is controlled to operate according to the control command corresponding to the fourth voice information.

7. The control method for an intelligent device according to claim 6, characterized in that, Also includes: If the fourth voice information is not collected within the preset time period, the smart device is controlled to exit the wake-up phase.

8. The control method for an intelligent device according to any one of claims 1 to 4, characterized in that, Determining the first similarity between the first voice information and the first preset wake-up information of the smart device includes: Identify the first speech feature of the first speech information; The first similarity is determined by comparing the first voice feature with the second voice feature in the first preset wake-up information.

9. A control device for an intelligent device, characterized in that, For performing a control method for a smart device as described in any one of claims 1 to 8, the control device for the smart device comprises: The acquisition module is used to acquire first voice information and a first wake-up threshold corresponding to the geographical location of the smart device; The determining module is used to determine the first similarity between the first voice information and the first preset wake-up information of the smart device; The wake-up module is used to control the smart device to enter the wake-up phase based on the comparison result between the first similarity and the first wake-up threshold.

10. A smart device, characterized in that, Includes the control device for the smart device as described in claim 9.

11. A smart device, characterized in that, include: A memory that stores programs or instructions; A processor, connected to the memory, implements the control method of the smart device as described in any one of claims 1 to 8 when executing the program or the instructions.

12. The intelligent device according to claim 11, characterized in that, The smart devices include: air conditioners, televisions, cooking appliances, refrigerators, washing machines, and terminal devices.

13. A readable storage medium having a program or instructions stored thereon, characterized in that, When the program or the instructions are executed by the processor, the control method of the smart device as described in any one of claims 1 to 8 is performed.

Images