Device wake-up method and apparatus, electronic device, and storage medium

Abstract

A device wake-up method and apparatus, an electronic device, and a storage medium, applied to a home gateway. The device wake-up method comprises: receiving a plurality of voiceprint features and a plurality of pieces of voice description information sent by a plurality of smart devices within a preset duration (101); selecting, by means of a pre-stored voiceprint feature library, from among the plurality of voiceprint features, target voiceprint features corresponding to a target user (102); selecting from among the plurality of pieces of voice description information a plurality of pieces of voice description information corresponding to the target voiceprint features (103); scoring the plurality of pieces of voice description information on the basis of a preset scoring rule to obtain respective response scores of the plurality of pieces of voice description information corresponding to the target voiceprint features (104); and determining a target device from among the plurality of smart devices on the basis of the response scores, and sending a wake-up instruction to the target device, so that the target device responds to wake-up voice information on the basis of the wake-up instruction (105). The process of data processing is transferred from smart devices to a home gateway side, which improves response efficiency.

Description

Device wake-up methods, devices, electronic equipment and storage media

[0001] Cross-references to related applications

[0002] This disclosure claims priority to Chinese Patent Application No. 202411905145.6, filed on December 23, 2024, entitled “Device Wake-up Method, Apparatus, Electronic Device and Storage Medium”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure pertains to the field of smart home technology, and particularly relates to a device wake-up method, apparatus, electronic device, and storage medium. Background Technology

[0004] Currently, voice recognition in home appliances typically combines local and cloud-based methods. Local recognition requires the appliance to store a large instruction model library, which is costly and consumes a lot of memory, affecting processing efficiency. When local recognition fails to match the data, the audio file is uploaded to the cloud. The cloud server converts the audio file into text information, extracts the corresponding control commands, and sends them to the device for control.

[0005] However, this approach is susceptible to network fluctuations, and response times to commands cannot be guaranteed. Therefore, reducing processing operations on the home appliance side to improve response efficiency has become a pressing issue. Summary of the Invention

[0006] This disclosure provides a device wake-up method, apparatus, electronic device, and storage medium to solve the technical problem of low response efficiency of home appliances.

[0007] In a first aspect, this disclosure provides a device wake-up method applied to a home console, the method comprising:

[0008] The system receives multiple voiceprint features and multiple sound description information sent by multiple smart devices within a preset time period. The multiple voiceprint features and multiple sound description information are obtained by the smart devices through feature extraction of wake-up voice information. The home host is connected to the multiple smart devices respectively.

[0009] The target voiceprint feature corresponding to the target user is selected from multiple voiceprint features using a pre-stored voiceprint feature library.

[0010] Select multiple sound description information corresponding to the target voiceprint feature from the multiple sound description information;

[0011] The multiple sound description information corresponding to the target voiceprint feature are scored according to the preset scoring rules to obtain the response score of each sound description information corresponding to the target voiceprint feature.

[0012] Based on the response score, a target device is determined from the plurality of smart devices, and a wake-up command is sent to the target device so that the target device responds to the wake-up voice information according to the wake-up command.

[0013] In some embodiments, the sound description information includes sound intensity, sound angle, reception time, and response mode. The step of scoring the plurality of sound description information corresponding to the target voiceprint feature according to a preset scoring rule to obtain a response score for each sound description information corresponding to the target voiceprint feature includes:

[0014] Each sound description information is sorted according to the sound intensity, the sound angle, the reception time, and the response mode to obtain multiple sorting results;

[0015] Based on each sorting result and the preset scoring rules, the response score for each sound description information is obtained.

[0016] In some embodiments, obtaining the response score for each sound description information based on each sorting result and a preset scoring rule includes:

[0017] Based on the preset correspondence between the order and the score, the sound intensity score, sound angle score, reception time score and response mode score of each sound description information are obtained;

[0018] The sound intensity score, the sound angle score, the reception time score, and the response mode score are summed to obtain the response score for each sound description information.

[0019] In some embodiments, the method further includes:

[0020] If no pre-stored voiceprint is identical to the first voiceprint feature in the voiceprint feature library, a correspondence between the first voiceprint feature and user information is generated, wherein the first voiceprint feature is any one of the plurality of voiceprint features.

[0021] The correspondence is stored in the voiceprint feature library.

[0022] In some embodiments, after determining the target device from the plurality of smart devices based on the response score and sending a wake-up command to the target device, the method further includes:

[0023] Receive target audio data sent by the target device, wherein the target audio data is audio data sent by the target user collected by the target device;

[0024] Feature extraction is performed on the target audio data to obtain target feature information;

[0025] The target feature information is compared with the instruction feature values ​​stored in the pre-stored feature database to determine the target instruction corresponding to the target feature information;

[0026] The target instruction is sent to the target device so that the target device executes the target instruction.

[0027] Secondly, this disclosure provides a device wake-up method applied to a smart device, the method comprising:

[0028] Obtain the wake-up voice information issued by the target user;

[0029] Feature extraction is performed on the wake-up voice information to obtain voiceprint features and sound description information, which includes: sound intensity, sound angle, reception time, and response mode.

[0030] The voiceprint feature and the voice description information are sent to the home host, so that the home host selects the target voiceprint feature corresponding to the target user from multiple voiceprint features according to the correspondence between user information and voiceprint features, selects multiple voice description information corresponding to the target voiceprint feature from multiple voice description information, scores the multiple voice description information corresponding to the target voiceprint feature according to a preset scoring rule, obtains a response score for each voice description information corresponding to the target voiceprint feature, determines the target device according to the response score, and sends a wake-up command to the target device;

[0031] Upon receiving a wake-up command from the home host, the system responds to the wake-up voice information according to the wake-up command.

[0032] In some embodiments, the wake-up voice information includes first voice information and second voice information emitted by the target user, and the step of extracting features from the wake-up voice information to obtain sound intensity and sound angle includes:

[0033] The first speech information and the second speech information are analyzed to obtain the first speech intensity corresponding to the first speech information and the second speech intensity corresponding to the second speech information;

[0034] The root mean square (RMS) processing is performed on the first speech intensity and the second speech intensity to obtain the sound intensity.

[0035] The sound angle is determined based on the first reception time of the first voice information, the second reception time of the second voice information, the first voice intensity, and the second voice intensity.

[0036] In some embodiments, after responding to the wake-up voice information, the method further includes:

[0037] Collect the target audio data emitted by the target user;

[0038] The target audio data is sent to the home host so that the home host can extract features from the target audio data to obtain target feature information. The target feature information is then compared with the instruction feature values ​​stored in the pre-stored feature database to determine the target instruction corresponding to the target feature information.

[0039] Receive the target instruction sent by the home host and execute the target instruction.

[0040] Thirdly, this disclosure provides a device wake-up device for use in a home console, the device comprising:

[0041] The first receiving module is used to receive multiple voiceprint features and multiple sound description information sent by multiple smart devices within a preset time period. The multiple voiceprint features and multiple sound description information are obtained by the smart devices by extracting features from the wake-up voice information. The home host is connected to the multiple smart devices respectively.

[0042] The feature matching module is used to select the target voiceprint feature corresponding to the target user from multiple voiceprint features using a pre-stored voiceprint feature library.

[0043] The information selection module is used to select multiple sound description information corresponding to the target voiceprint feature from the multiple sound description information;

[0044] The scoring module is used to score the multiple sound description information corresponding to the target voiceprint feature according to the preset scoring rules, so as to obtain the response score of each sound description information corresponding to the target voiceprint feature;

[0045] The first sending module is configured to determine a target device from the plurality of smart devices based on the response score, and send a wake-up command to the target device so that the target device responds to the user's command according to the wake-up command.

[0046] Fourthly, this disclosure provides a device wake-up device for use in smart devices, the device comprising:

[0047] The acquisition module is used to acquire the wake-up voice information issued by the target user;

[0048] The feature extraction module is used to extract features from the wake-up voice information to obtain voiceprint features and sound description information, wherein the sound description information includes: sound intensity, sound angle, reception time and response mode;

[0049] The second sending module is used to send the voiceprint feature and the sound description information to the home host, so that the home host selects the target voiceprint feature corresponding to the target user from multiple voiceprint features according to the correspondence between user information and voiceprint features, selects multiple sound description information corresponding to the target voiceprint feature from multiple sound description information, scores the multiple sound description information corresponding to the target voiceprint feature according to a preset scoring rule, obtains the response score of each sound description information corresponding to the target voiceprint feature, and selects the smart device with the higher response score as the target device;

[0050] The second receiving module is used to respond to the wake-up voice information according to the wake-up command when it receives a wake-up command sent by the home host.

[0051] Fifthly, embodiments of this disclosure provide an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described device wake-up method.

[0052] Sixthly, embodiments of this disclosure provide a readable storage medium that, when instructions in the readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the aforementioned device wake-up method.

[0053] In summary, in this embodiment, the home host receives multiple voiceprint features and multiple voice description information sent by multiple smart devices within a preset time period. These voiceprint features and voice description information are obtained by the smart devices from feature extraction of wake-up voice information. The home host is connected to each of the multiple smart devices. Using a pre-stored voiceprint feature library, a target voiceprint feature corresponding to the target user is selected from the multiple voiceprint features. Multiple voice description information corresponding to the target voiceprint feature is selected from the multiple voice description information. The multiple voice description information is scored according to a preset scoring rule to obtain a response score for each voice description information corresponding to the target voiceprint feature. Based on the response score, a target device is determined from the multiple smart devices, and a wake-up command is sent to the target device, causing the target device to respond to the wake-up voice information according to the wake-up command. With the above technical solution, when there are multiple smart devices, the home host analyzes the user's wake-up voice to determine the device that needs to be woken up. The smart device only needs to collect voice and send and receive information. Through the processing, analysis and calculation of voice on the home host side, the unique wake-up function of the smart device is realized. The data processing process is transferred from the smart device to the home host side, which can effectively shorten the device wake-up response time and improve response efficiency. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 is a flowchart of a device wake-up method provided in an embodiment of this disclosure;

[0056] Figure 2 is a flowchart of another device wake-up method provided in an embodiment of this disclosure;

[0057] Figure 3 is a flowchart of another device wake-up method provided in an embodiment of this disclosure;

[0058] Figure 4 is a flowchart of another device wake-up method provided in an embodiment of this disclosure;

[0059] Figure 5 is a structural diagram of a device wake-up device provided in an embodiment of this disclosure;

[0060] Figure 6 is a structural diagram of another device wake-up device provided in an embodiment of this disclosure;

[0061] Figure 7 is a structural diagram of an electronic device provided in an embodiment of this disclosure;

[0062] Figure 8 is a structural diagram of another electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0063] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the protection scope of this disclosure.

[0064] Currently, voice recognition for home appliances is a combination of online and offline methods. When offline words cannot be matched, the audio file is uploaded to the cloud for recognition, the audio file is converted into text information, and then into corresponding control commands to be sent to the device for control. This solution is greatly affected by network conditions, resulting in inconsistent response times and a poor user experience. If all home appliances use offline voice recognition and need to support free speech, it is necessary to integrate Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) locally. Each home appliance also needs to store a large model library for voice training, which is too costly and will consume device memory and affect response efficiency.

[0065] With the development of technology, smart devices are becoming increasingly common in people's lives. To control these smart devices, users can wake up and control them via touch screen or voice commands. However, if voice commands are used to call smart devices, multiple devices in the same space may respond simultaneously. Therefore, a home hub can be introduced to provide unified control over all smart devices.

[0066] It's important to note that the home hub can be understood as the core component of a smart home system, responsible for connecting and controlling various smart devices in the home. The home hub can connect multiple smart devices to the network via wired or wireless connections, enabling interconnection and intelligent control between devices. Home hubs typically possess powerful processing capabilities and a rich set of interfaces, supporting multiple communication protocols and device types. They can be remotely controlled via mobile applications (APPs), voice assistants, and other methods, enabling convenient operation of smart home devices. Furthermore, the smart home hub also features security and privacy protection functions to ensure the security and privacy of user data.

[0067] The home host and multiple smart devices are connected via a network, which can include wired networks and wireless networks. Wired networks can include wide area networks (WANs), metropolitan area networks (MANs), local area networks (LANs), etc., while wireless networks can include Wireless Fidelity (WIFI) technology, Bluetooth, etc.

[0068] In some embodiments, the home host includes related units for data synchronization, data forwarding, scene analysis, and protocol conversion, enabling unified control of smart devices with different protocols after protocol conversion is completed through the home host. This improves protocol compatibility between different manufacturers. The home host is responsible for protocol conversion and data processing, and forwards data to different types of gateways to enable devices to perform corresponding actions, thereby achieving interoperability between devices of different categories.

[0069] Smart devices can specifically include: smart air conditioners, smart range hoods, smart refrigerators, smart ovens, smart stoves, smart washing machines, smart water heaters, smart washing equipment, smart dishwashers, smart projectors, smart TVs, smart clothes racks, smart curtains, smart audio-visual equipment, smart sockets, smart speakers, smart speakers, smart fresh air systems, smart kitchen and bathroom equipment, smart bathroom fixtures, smart robot vacuum cleaners, smart window cleaning robots, smart mopping robots, smart air purifiers, smart steam ovens, smart microwave ovens, smart water heaters, smart air purifiers, smart water dispensers, smart cameras, etc.

[0070] The device wake-up method provided in the embodiments of this disclosure will be described in detail below.

[0071] Figure 1 is a flowchart of a device wake-up method provided in an embodiment of this disclosure. The execution subject of this device wake-up method can be a home host. Referring to Figure 1, the device wake-up method may include:

[0072] Step 101: Receive multiple voiceprint features and multiple sound description information sent by multiple smart devices within a preset time period.

[0073] In this embodiment, the home host and multiple smart devices are connected to each other. When the home host and smart devices interact with each other, there will be a certain time difference between sending and receiving. In addition, there may also be a time difference between each smart device sending information due to network or other reasons. Therefore, if multiple smart devices send information to the home host at the same time, the home host may not receive multiple messages at the same time. Therefore, a time period can be set and the messages sent by each smart device received within that time period can be processed. The preset time period can be a time period set by the home host itself, such as 1.5 seconds (s), 2s, 3s, etc. This embodiment does not make a specific limitation.

[0074] In some embodiments, the home host can start timing from the moment it receives the voiceprint feature and voice description information sent by the first smart device. After a preset duration, the timing stops and the reception of voiceprint feature and voice description information sent by the smart device stops. Subsequently, multiple voiceprint features and multiple voice description information sent by the smart device received within the preset duration can be processed, while multiple voiceprint features and multiple voice description information sent by the smart device received outside the preset duration are not processed.

[0075] It should be noted that the multiple voiceprint features and multiple sound descriptions received by the home host are obtained by the smart devices from the feature extraction of the wake-up voice information. It can be understood that when a user needs to wake up a smart device, he / she issues a wake-up voice message. Multiple smart devices receive this wake-up voice message and process it respectively. Each smart device obtains the corresponding voiceprint features and sound descriptions for the wake-up voice message and sends them to the home host. Thus, the home host can receive multiple voiceprint features and multiple sound descriptions sent by multiple smart devices. There is a one-to-one correspondence between the smart devices, voiceprint features, and sound descriptions. That is to say, a smart device sends one voiceprint feature and one sound description to the home host.

[0076] In some embodiments, a voiceprint is a sound wave spectrum carrying speech information displayed by electroacoustic instruments. It is a biometric feature composed of over a hundred feature dimensions, including wavelength, frequency, and intensity. It is the collective term for the speech features contained within speech that characterize and identify the speaker, as well as the speech model built upon these features (parameters). Each person's voiceprint map differs due to their unique vocal organs and vocalization methods, making the voiceprint a unique biometric feature. Therefore, the user speaking can be identified by analyzing voiceprint features. In this embodiment, since there may be more than one user in a room, the speech collected by multiple smart devices may not be from the same user; therefore, specific user information can be determined by analyzing voiceprint features.

[0077] In some embodiments, sound description information can indicate relevant information about the speech collected by the smart device, such as sound intensity, spectrum, angle, etc.

[0078] Step 102: Select the target voiceprint feature corresponding to the target user from multiple voiceprint features using the pre-stored voiceprint feature library.

[0079] It should be noted that the pre-stored voiceprint feature database can contain multiple voiceprint features. Since each user's voiceprint features are different, the voiceprint feature database can store voiceprint features and user information in correspondence. In other words, the user information corresponding to a certain voiceprint feature can be found in the voiceprint feature database.

[0080] In this embodiment of the disclosure, when a user issues a wake-up voice message in a room, multiple smart devices can collect the wake-up voice message, but they may not only collect the voice of one user, but may collect other voices issued by other users. Therefore, the voiceprint features can be used for filtering. That is, the target voiceprint feature corresponding to the target user is selected from multiple voiceprint features. It can also be understood as selecting the target voiceprint feature corresponding to the same user from multiple voiceprint features. In other words, multiple voiceprint features corresponding to the same user are determined as target voiceprint features. There can be multiple smart devices corresponding to the target voiceprint feature, that is, multiple smart devices have collected the wake-up voice message of the target user.

[0081] Step 103: Select multiple voice description information corresponding to the target voiceprint feature from multiple voice description information.

[0082] In this embodiment of the disclosure, since there is a one-to-one correspondence between voiceprint features and sound description information, after selecting the target voiceprint feature corresponding to the target user, multiple sound description information corresponding to the target voiceprint feature can be selected.

[0083] It should be noted that since there are multiple smart devices in the room, when the target user issues a wake-up voice message, multiple smart devices will definitely collect the wake-up voice message. As a result, multiple smart devices will detect the target user's target voiceprint features and corresponding sound description information. Therefore, there are multiple sound description information corresponding to the target voiceprint features. If there is only one sound description information, it is impossible to determine whether the voice collected by the smart device corresponding to that sound description information is the wake-up voice message issued by the target user.

[0084] Step 104: Score multiple sound description information according to preset scoring rules to obtain the response score of each sound description information corresponding to the target voiceprint feature.

[0085] In this embodiment of the disclosure, since multiple smart devices have collected the wake-up voice information issued by the target user, the home host needs to analyze which device the target user specifically wants to wake up. Therefore, it can score each voice description information. The specific scoring rule can be a pre-set preset scoring rule, which can be a rule customized by the home host, thereby obtaining the response score of each voice description information corresponding to the target voiceprint feature.

[0086] Step 105: Determine the target device from multiple smart devices based on the response score, and send a wake-up command to the target device so that the target device responds to the wake-up voice information according to the wake-up command.

[0087] In this embodiment of the disclosure, after determining the response score of each voice description information, since there is a one-to-one correspondence between the voice description information and the smart device, the response score of the voice description information can also be regarded as the response score of the smart device. Therefore, the target device can be determined from multiple smart devices based on the response score of each smart device. The target device can be regarded as the device that the target user wants to wake up, and a wake-up command is sent to the target device. The wake-up command can instruct the target device to wake up and respond to the user. After receiving the wake-up command, the target device can respond to the wake-up voice information according to the wake-up command.

[0088] In summary, in this embodiment of the present disclosure, when multiple smart devices exist, the home host analyzes the user's wake-up voice to determine the device that needs to be woken up. The smart devices only need to collect voice data and send and receive information. By processing, analyzing, and calculating the voice data on the home host side, the unique wake-up function of the smart devices is realized. The data processing process is transferred from the smart devices to the home host side, which can effectively shorten the device wake-up response time and improve response efficiency.

[0089] Figure 2 is a flowchart of another device wake-up method provided in this disclosure. The execution subject of this device wake-up method can be a home host. Referring to Figure 2, the method may include the following steps:

[0090] Step 201: Receive multiple voiceprint features and multiple sound description information sent by multiple smart devices within a preset time period.

[0091] The method for this step has been explained in step 101 above, and will not be repeated here.

[0092] Step 202: Select the target voiceprint feature corresponding to the target user from multiple voiceprint features using the pre-stored voiceprint feature library.

[0093] The method for this step has been explained in step 102 above, and will not be repeated here.

[0094] In this embodiment of the disclosure, when filtering multiple voiceprint features, each voiceprint feature can be matched with a pre-stored voiceprint feature library in turn. If a match is detected with a pre-stored voiceprint feature in the voiceprint feature library, then the user information corresponding to the pre-stored voiceprint feature can be determined as the user information of the voiceprint feature.

[0095] In some embodiments, the user information can be represented by a user identity document (ID). That is, the pre-stored voiceprint feature library stores multiple user IDs and the voiceprint features corresponding to each user ID. If a voiceprint feature is detected to match a certain voiceprint in the pre-stored voiceprint feature library, then the user ID corresponding to the matched voiceprint can be determined as the ID number of the voiceprint feature. In this way, after matching each voiceprint feature, the target voiceprint feature corresponding to the target user is multiple identical voiceprint features with the same ID number.

[0096] In some embodiments, there may be cases where no matching voiceprint is detected in the voiceprint feature library. Therefore, after selecting the target voiceprint feature corresponding to the target user from multiple voiceprint features using the pre-stored voiceprint feature library, step 202 may further include the following steps:

[0097] Sub-step 2021: If there is no pre-stored voiceprint in the voiceprint feature library that is the same as the first voiceprint feature, generate the correspondence between the first voiceprint feature and the user information. The first voiceprint feature is any one of the multiple voiceprint features.

[0098] Sub-step 2022: Store the corresponding relationship in the voiceprint feature database.

[0099] It should be noted that there is no pre-stored voiceprint in the voiceprint feature database that is identical to the first voiceprint feature. This can also be understood as the home host not having previously received the voiceprint feature corresponding to the user from the smart device. Therefore, a new correspondence between the user information and the first voiceprint feature can be created, that is, a corresponding user ID can be created for the first voiceprint feature, and this correspondence can be stored in the voiceprint feature database. In this way, if the user continues to wake up the smart device in the future, the home host can match the specific user ID after receiving the voiceprint feature sent by the smart device.

[0100] Step 203: Select multiple voice description information corresponding to the target voiceprint feature from multiple voice description information.

[0101] The method for this step has been explained in step 103 above, and will not be repeated here.

[0102] In some embodiments, after selecting multiple voice description information corresponding to the target voiceprint feature, the voice description information, voiceprint feature, and smart device are all corresponding to each other, so the target voiceprint feature, multiple voice description information, and multiple smart devices can be stored accordingly.

[0103] For example, the correspondence between voice description information, voiceprint features, and smart devices can be shown in Table 1.

[0104] Table 1

[0105] As shown in Table 1, for the same user ID number 0001, three identical voiceprint features were selected: Feature 1 corresponds to three input devices: rice cooker, air purifier, and air conditioner. The sound description information for the rice cooker includes: time: 15:47:30:30.301, sound intensity: 10, sound angle: 90 degrees, and response method: speaker. The sound description information for the air purifier includes: time: 15:47:30:50.7, sound intensity: 7, sound angle: 45 degrees, and response method: buzzer. The sound description information for the air conditioner includes: time: 15:47:31:10.7, sound intensity: 3, sound angle: 30 degrees, and response method: speaker.

[0106] Step 204: Sort each sound description information corresponding to the target voiceprint feature according to sound intensity, sound angle, reception time and response mode to obtain multiple sorting results.

[0107] It should be noted that the sound description information can specifically include sound intensity, sound angle, reception time, and response mode. In other words, the home host can score multiple sound description information from these four aspects: sound intensity, sound angle, reception time, and response mode.

[0108] In this embodiment of the disclosure, since the home host needs to select the device that the user wants to wake up from multiple smart devices, it can be understood that it needs to compare multiple smart devices. Therefore, the multiple sound description information can be sorted from the above four perspectives. In other words, four sorting results can be obtained, and each sound description information has four corresponding orders.

[0109] In some embodiments, the sound intensity can indicate the distance between the target user and the smart device. The closer the target user is to the smart device, the greater the sound intensity; the farther the target user is from the smart device, the smaller the sound intensity. The sound angle can indicate the angle between the target user and the smart device. The receiving time is the moment when the smart device collects the wake-up voice information of the target user. The response mode is the way the smart device responds to the wake-up of the target user, which may include: speaker, buzzer, light, vibration, etc.

[0110] In some embodiments, when sorting sound intensity, sound angle, reception time, and response mode, they can be sorted according to certain sorting rules. For example, sound intensity and sound angle can be sorted in numerical order, reception time can be sorted in chronological order, and response mode can be sorted according to custom rules.

[0111] Step 205: Based on each sorting result and the preset scoring calculation rules, obtain the response score for each sound description information corresponding to the target voiceprint feature.

[0112] In this embodiment of the disclosure, after multiple sorting results are obtained, a score can be assigned to each sorting result. The score can be assigned according to a preset scoring calculation rule, which can be understood as the correspondence between the pre-selected sorting order and the score. Therefore, the response score of each sound description information corresponding to the target voiceprint feature can be obtained.

[0113] In some embodiments, step 205 includes:

[0114] Sub-step 2051: Based on the preset correspondence between the order and the score, obtain the sound intensity score, sound angle score, reception time score and response mode score for each sound description information.

[0115] Sub-step 2052: Accumulate the sound intensity score, sound angle score, reception time score, and response mode score to obtain the response score for each sound description information corresponding to the target voiceprint feature.

[0116] It should be noted that since the sound description information includes four dimensions: sound intensity, sound angle, reception time, and response mode, when scoring each sound description information, we can obtain the corresponding sound intensity score, sound angle score, reception time score, and response mode score for each sound description information. After summing the sound intensity score, sound angle score, reception time score, and response mode score, we can obtain the response score of the sound description information.

[0117] In some embodiments, the scores for sound intensity can be sorted in ascending order. Sound intensity is a value between 1 and 10, so the score can be the same as the sound intensity. If the sound intensity is 1, the corresponding score is 1; if the sound intensity is 2, the corresponding score is 2; if the sound intensity is 3, the corresponding score is 3; if the sound intensity is 10, the corresponding score is 10, and so on, to obtain the sound intensity score for each sound description information.

[0118] In some embodiments, the scores for sound angles can be sorted in ascending order. Sound angles are values ​​between 0 and 90 degrees, so the scores can be the same as the sound angles. A sound angle of 0 degrees corresponds to a score of 0, a sound angle of 30 degrees corresponds to a score of 30, a sound angle of 45 degrees corresponds to a score of 45, a sound intensity of 90 degrees corresponds to a score of 90, and so on, to obtain the sound angle score for each sound description.

[0119] In some embodiments, the scores for the reception times can be sorted in chronological order, with the earliest reception time receiving a score of 0. For each subsequent reception time delayed by a certain number of milliseconds, the score increases; for example, every 100 milliseconds (ms) increases the score by 10. If the earliest reception time is 15:47:30 0 ms, its score is 0. Then, 15:47:30 100 ms receives a score of 10, 15:47:30 200 ms receives a score of 20, 15:47:30 300 ms receives a score of 30, and so on, to obtain the reception time score for each audio description.

[0120] In some embodiments, the scoring of response modes can be based on preset rules, such as: a score of 50 for speaker + LCD display, a score of 45 for speaker response, a score of 40 for buzzer response, a score of 35 for light response, a score of 30 for vibration response, etc. The score is obtained by scoring based on these rules, thus obtaining the response mode score for each sound description information.

[0121] Step 206: Determine the target device from multiple smart devices based on the response score, and send a wake-up command to the target device so that the target device responds to the wake-up voice information according to the wake-up command.

[0122] The method for this step has been explained in step 105 above, and will not be repeated here.

[0123] In this embodiment of the disclosure, when determining the target device from multiple smart devices, the selection can be based on the response score.

[0124] In some embodiments, the smart device corresponding to the sound description information with the highest response score can be identified as the target device.

[0125] In some embodiments, if there are multiple smart devices corresponding to the sound description information with the highest response score, the sound description information with the same response score can be compared again in the order of sound intensity score, sound angle score, reception time score and response mode score until a unique sound description information is obtained, and the smart device corresponding to the unique sound description information is determined as the target device.

[0126] In some embodiments, the smart device corresponding to the sound description information with a response score greater than a preset threshold can be identified as the target device.

[0127] In some embodiments, if the response score of the sound description information corresponding to only one smart device is greater than a preset threshold, then the smart device can be directly identified as the target device.

[0128] In some embodiments, if the response scores of the sound description information corresponding to multiple smart devices are greater than a preset threshold, the sound description information corresponding to the multiple smart devices can be compared again in the order of sound intensity score, sound angle score, reception time score and response mode score until a unique sound description information is obtained, and the smart device corresponding to the unique sound description information is determined as the target device.

[0129] In some embodiments, if the response scores of the voice description information corresponding to multiple smart devices are greater than a preset threshold, then multiple smart devices can be output to the user, who can then select the target device to be woken up. Specifically, multiple smart devices can be controlled to respond and receive the user's selection of the target device to determine the target device.

[0130] Step 207: Receive the target audio data sent by the target device.

[0131] In this embodiment of the disclosure, the target audio data is the audio data sent by the target user collected by the target device; after waking up the target device, the target user can perform voice command control on the target device, that is, the target device can collect the target audio data sent by the target user and send the target audio data to the home host for analysis.

[0132] Step 208: Extract features from the target audio data to obtain target feature information.

[0133] In this embodiment of the disclosure, since the target audio data may include instructions from the target user for the target device, the home host can extract features from the target audio data to obtain target feature information.

[0134] Step 209: Compare the target feature information with the instruction feature values ​​stored in the pre-stored feature database to determine the target instruction corresponding to the target feature information.

[0135] In this embodiment, a pre-stored feature database can store multiple instruction feature values, i.e., instruction feature values ​​of supported devices, such as air conditioners, fans, air purifiers, rice cookers, etc. The feature database contains features of all possible commands for each device, such as features of all voice commands like "turn on the air conditioner," "turn on the air conditioner," "air conditioner on," or "turn on the air purifier," "turn off the rice cooker," etc. The target feature information is compared with the pre-stored instruction feature values. If the same feature exists, the target instruction corresponding to the target feature information can be directly determined, i.e., the target instruction corresponding to the target audio data. For example, if the target feature information matches the instruction feature value of "turn on the air conditioner," then the home host can determine that the user's target audio data is an instruction to turn on the air conditioner.

[0136] Step 210: Send the target instruction to the target device so that the target device executes the target instruction.

[0137] In this embodiment of the disclosure, after the target instruction is determined, the target instruction can be sent to the target device so that the target device executes the target instruction.

[0138] In some embodiments, the home host can also generate text data corresponding to the target instruction and send the text data and the target instruction together to the target device so that when the target device executes the target instruction, it can convert the text data into audio data for playback. For example, the text data could be "OK, the air conditioner has been turned on for you", so when the air conditioner is turned on, it can also play the audio "OK, the air conditioner has been turned on for you".

[0139] In summary, in this embodiment of the present disclosure, when multiple smart devices exist, the home host analyzes the user's wake-up voice to determine the device that needs to be woken up. The smart device only needs to collect voice data and send and receive information. By processing, analyzing, and calculating parameters such as voiceprint features, sound intensity, sound angle, reception time, and response mode on the home host side, the unique wake-up function of the smart device is realized. The data processing process is transferred from the smart device to the home host side, which can effectively shorten the device wake-up response time and improve response efficiency and accuracy.

[0140] Figure 3 is a flowchart of another device wake-up method provided in this disclosure. The subject executing this device wake-up method can be a smart device. Referring to Figure 3, the method may include the following steps:

[0141] Step 301: Obtain the wake-up voice information issued by the target user.

[0142] In this embodiment of the disclosure, each smart device is equipped with a microphone that can collect the user's voice, and thus can collect the wake-up voice information issued by the target user.

[0143] Step 302: Extract features from the wake-up voice information to obtain voiceprint features and sound description information.

[0144] In this embodiment, the sound description information includes: sound intensity, sound angle, reception time, and response mode. Detailed descriptions of the voiceprint features and sound description information can be found in the above embodiments and will not be repeated here.

[0145] It should be noted that when extracting features from wake-up voice information, preprocessing such as filtering and noise reduction can be performed to improve the audio quality of the wake-up voice information and avoid extracting useless features.

[0146] Step 303: Send the voiceprint features and voice description information to the home host.

[0147] In this embodiment of the disclosure, the home host selects the target voiceprint feature corresponding to the target user from multiple voiceprint features based on the correspondence between user information and voiceprint features, selects multiple voice description information corresponding to the target voiceprint feature from multiple voice description information, scores the multiple voice description information according to a preset scoring rule, obtains the response score of each voice description information corresponding to the target voiceprint feature, determines the target device based on the response score, and sends a wake-up command to the target device.

[0148] In this embodiment of the disclosure, each smart device can send voiceprint features and sound description information to the home host, so that the home host can receive multiple voiceprint features and multiple sound description information sent by multiple smart devices, and determine the target device according to the steps described in the above method.

[0149] Step 304: Upon receiving a wake-up command from the home host, respond to the wake-up voice information according to the wake-up command.

[0150] In this embodiment of the disclosure, once the home host determines that the current smart device is the target device, the current smart device can receive the wake-up command sent by the home host and then respond to the wake-up voice information. The response can be in the form of a speaker, buzzer, light, vibration, etc., such as outputting the voice "I am here, please give instructions", or emitting a red flashing light.

[0151] In summary, in this embodiment, the smart device acquires the wake-up voice information issued by the target user; performs feature extraction on the wake-up voice information to obtain voiceprint features and sound description information, including sound intensity, sound angle, reception time, and response mode; sends the voiceprint features and sound description information to the home host, so that the home host selects the target voiceprint feature corresponding to the target user from multiple voiceprint features based on the correspondence between user information and voiceprint features, selects multiple sound description information corresponding to the target voiceprint feature from multiple sound description information, scores the multiple sound description information according to a preset scoring rule, obtains the response score of each sound description information corresponding to the target voiceprint feature, determines the target device based on the response score, and sends a wake-up command to the target device; upon receiving the wake-up command sent by the home host, responds to the wake-up voice information according to the wake-up command. The smart device can retain only voice acquisition, simple feature extraction, and data transmission and reception functions, while transferring the specific data analysis, processing, and calculation functions to the home host, strengthening the role of the home host, reducing the steps on the smart device side, and improving the efficiency and accuracy of device wake-up.

[0152] Figure 4 is a flowchart of another device wake-up method provided in this disclosure. The subject executing this device wake-up method can be a smart device. Referring to Figure 4, the method may include the following steps:

[0153] Step 401: Obtain the wake-up voice information issued by the target user.

[0154] The method for this step has been explained in step 301 above, and will not be repeated here.

[0155] Step 402: Extract features from the wake-up voice information to obtain voiceprint features and sound description information.

[0156] The method for this step has been explained in step 302 above, and will not be repeated here.

[0157] In this embodiment of the disclosure, the sound description information includes: sound intensity, sound angle, reception time, and response mode.

[0158] The method for this step has been explained in step 302 above, and will not be repeated here.

[0159] In some embodiments, step 402 includes:

[0160] Sub-step 4021: Analyze the first speech information and the second speech information to obtain the first speech intensity corresponding to the first speech information and the second speech intensity corresponding to the second speech information.

[0161] It should be noted that, since it is necessary to determine the angle of the target user toward the smart device, at least two sets of audio are needed for comparison to obtain the angle. Therefore, the smart device can be equipped with at least two microphones. The wake-up voice information collected by the smart device can include the first voice information and the second voice information emitted by the target user. When calculating the sound intensity, it can be obtained by combining the voice intensity of each voice information. When calculating the sound angle, it is also necessary to combine multiple voice intensities and multiple moments. Therefore, it is necessary to calculate the voice intensity for both the first and second voice information to obtain the first voice intensity and the second voice intensity respectively.

[0162] Sub-step 4022: Perform root mean square processing on the first speech intensity and the second speech intensity to obtain the sound intensity.

[0163] It should be noted that the root mean square is a common mathematical calculation method. It can be understood as first calculating the squares of the first and second speech intensities, then calculating the average of the two squares, and finally taking the square root of the average. The result obtained is the sound intensity.

[0164] Sub-step 4023: Determine the sound angle based on the first reception time of the first voice information, the second reception time of the second voice information, the first voice intensity, and the second voice intensity.

[0165] It should be noted that since the target user's position relative to the smart device is fixed, but the positions of the two microphones are different, the voice intensities of the two voice information collected are different. In addition, the times at which the two microphones collect the voice information are also different. Therefore, the sound angle can be calculated based on the first reception time of the first voice information, the second reception time of the second voice information, the first voice intensity, and the second voice intensity.

[0166] In some embodiments, the sound angle can be calculated using mathematical formulas commonly used in the prior art, which will not be elaborated here.

[0167] Step 403: Send the voiceprint features and voice description information to the home host.

[0168] The method for this step has been explained in step 303 above, and will not be repeated here.

[0169] In this embodiment of the disclosure, the home host selects the target voiceprint feature corresponding to the target user from multiple voiceprint features based on the correspondence between user information and voiceprint features, selects multiple voice description information corresponding to the target voiceprint feature from multiple voice description information, scores the multiple voice description information according to a preset scoring rule, obtains the response score of each voice description information corresponding to the target voiceprint feature, determines the target device based on the response score, and sends a wake-up command to the target device.

[0170] Step 404: Upon receiving a wake-up command from the home host, respond to the wake-up voice information according to the wake-up command.

[0171] The method for this step has been explained in step 304 above, and will not be repeated here.

[0172] For example, the device wake-up method provided in this disclosure is applied to a smart home scenario. The smart home scenario includes a home host, input device 1, input device 2, input device 3, and input device 4. Input device 1 has a speaker, input device 2 has a light, input device 3 has a buzzer, and input device 4 has a speaker. When the user utters the voice "xiaoge xiaoge", input device 1 receives the voice after time 1, input device 2 receives the voice after time 2, input device 3 receives the voice after time 3, and input device 4 receives the voice after time 4. Input devices 1, 2, 3, and 4 respectively send information to the home host. The home host calculates a score based on sound intensity, sound angle, time interval, and response mode, thereby determining that input device 1 should respond.

[0173] Step 405: Collect the target audio data sent by the target user.

[0174] In this embodiment of the disclosure, after determining that the current smart device is the target device, target audio data emitted by the target user can be collected.

[0175] Step 406: Send the target audio data to the home host so that the home host can extract features from the target audio data, obtain target feature information, compare the target feature information with the instruction feature values ​​stored in the pre-stored feature database, and determine the target instruction corresponding to the target feature information.

[0176] In this embodiment of the disclosure, since the target audio data sent by the target user may include the target user's instructions for the target device, the target audio data can be sent to the home host so that the home host can extract features from the target audio data and then perform feature comparison to obtain the target instructions.

[0177] Step 407: Receive the target instruction sent by the home host and execute the target instruction.

[0178] In some embodiments, in addition to receiving the target instruction sent by the home host, text data sent by the home host may also be received. Therefore, the text data can also be converted into audio data. When executing the target instruction, the audio data can also be played. For example, the text data could be "Okay, the air conditioner has been turned on for you". When the air conditioner is started, the audio "Okay, the air conditioner has been turned on for you" can also be played.

[0179] In summary, smart devices can retain only voice acquisition, simple feature extraction, and data transmission and reception functions, while transferring specific data analysis, processing, and calculation functions to the home host. This strengthens the role of the home host, reduces the steps on the smart device side, and improves the efficiency and accuracy of device wake-up.

[0180] Figure 5 is a schematic diagram of a device wake-up device provided in an embodiment of this disclosure. The device wake-up device 500 can be applied to a home computer, and the device wake-up device 500 may include:

[0181] The first receiving module 501 is used to receive multiple voiceprint features and multiple sound description information sent by multiple smart devices within a preset time period. The multiple voiceprint features and multiple sound description information are obtained by the smart devices extracting features from the wake-up voice information. The home host is connected to the multiple smart devices respectively.

[0182] The feature matching module 502 is used to select the target voiceprint feature corresponding to the target user from multiple voiceprint features through a pre-stored voiceprint feature library.

[0183] The information selection module 503 is used to select multiple sound description information corresponding to the target voiceprint feature from multiple sound description information;

[0184] The scoring module 504 is used to score multiple sound description information according to preset scoring rules, and obtain the response score of each sound description information corresponding to the target voiceprint feature.

[0185] The first sending module 505 is used to determine the target device from multiple smart devices based on the response score, and send a wake-up command to the target device so that the target device can respond to the user's command according to the wake-up command.

[0186] In some embodiments, the sound description information includes sound intensity, sound angle, reception time, and response mode, and the scoring module may specifically include:

[0187] The sorting submodule is used to sort each sound description information according to sound intensity, sound angle, reception time, and response mode, and obtain multiple sorting results.

[0188] The scoring calculation submodule is used to obtain the response score of each sound description information corresponding to the target voiceprint feature based on each sorting result and the preset scoring calculation rules.

[0189] In some embodiments, the scoring calculation submodule may specifically include:

[0190] The scoring unit is used to obtain the sound intensity score, sound angle score, reception time score, and response mode score for each sound description information according to the preset order and the correspondence between scores.

[0191] The score accumulation unit is used to accumulate the sound intensity score, sound angle score, reception time score, and response mode score to obtain the response score for each sound description information corresponding to the target voiceprint feature.

[0192] In some embodiments, the device wake-up device 500 may further include:

[0193] The correspondence generation module is used to generate a correspondence between the first voiceprint feature and user information when there is no pre-stored voiceprint feature in the voiceprint feature library that is the same as the first voiceprint feature. The first voiceprint feature is any one of multiple voiceprint features.

[0194] The correspondence storage module is used to store the correspondence into the voiceprint feature library.

[0195] In some embodiments, the device wake-up device 500 may further include:

[0196] The third receiving module is used to receive target audio data sent by the target device. The target audio data is the audio data sent by the target user collected by the target device.

[0197] The audio extraction module is used to extract features from the target audio data to obtain target feature information;

[0198] The instruction matching module is used to compare the target feature information with the instruction feature values ​​stored in the pre-stored feature database to determine the target instruction corresponding to the target feature information.

[0199] The third sending module is used to send the target instruction to the target device so that the target device can execute the target instruction.

[0200] Figure 6 is a schematic diagram of a device wake-up device provided in an embodiment of this disclosure. The device wake-up device 600 can be applied to smart devices and may include:

[0201] The acquisition module 601 is used to acquire the wake-up voice information issued by the target user;

[0202] The feature extraction module 602 is used to extract features from the wake-up voice information to obtain voiceprint features and sound description information. The sound description information includes: sound intensity, sound angle, reception time and response mode.

[0203] The second sending module 603 is used to send voiceprint features and sound description information to the home host, so that the home host can select the target voiceprint feature corresponding to the target user from multiple voiceprint features according to the correspondence between user information and voiceprint features, select multiple sound description information corresponding to the target voiceprint feature from multiple sound description information, score the multiple sound description information according to the preset scoring rules, obtain the response score of each sound description information corresponding to the target voiceprint feature, determine the target device according to the response score, and send a wake-up command to the target device;

[0204] The second receiving module 604 is used to respond to the wake-up voice information according to the wake-up command when it receives a wake-up command sent by the home host.

[0205] In some embodiments, the wake-up voice information includes first voice information and second voice information emitted by the target user, and the feature extraction module may specifically include:

[0206] The speech analysis submodule is used to analyze the first speech information and the second speech information to obtain the first speech intensity corresponding to the first speech information and the second speech intensity corresponding to the second speech information.

[0207] The sound intensity determination module is used to perform root mean square processing on the first speech intensity and the second speech intensity to obtain the sound intensity.

[0208] The sound angle determination module is used to determine the sound angle based on the first reception time of the first voice information, the second reception time of the second voice information, the first voice intensity, and the second voice intensity.

[0209] In some embodiments, the device wake-up device 600 may further include:

[0210] The audio acquisition module is used to acquire target audio data emitted by the target user.

[0211] The fourth sending module is used to send the target audio data to the home host, so that the home host can extract features from the target audio data, obtain target feature information, compare the target feature information with the instruction feature values ​​stored in the pre-stored feature database, and determine the target instruction corresponding to the target feature information.

[0212] The fourth receiving module is used to receive the target instructions sent by the home host and execute the target instructions.

[0213] Figure 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. Referring to Figure 7, the electronic device 700 may include one or more of the following components: a processing component 702, a memory 704, a power supply component 706, a multimedia component 708, an audio component 710, an input / output (I / O) interface 712, a sensor component 714, and a communication component 716.

[0214] Processing component 702 typically controls the overall operation of electronic device 700, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 702 may include one or more modules to facilitate interaction between processing component 702 and other components. For example, processing component 702 may include a multimedia module to facilitate interaction between multimedia component 708 and processing component 702.

[0215] Memory 704 is used to store various types of data to support the operation of electronic device 700. Examples of this data include instructions for any application or method operating on electronic device 700, contact data, phonebook data, messages, pictures, multimedia, etc. Memory 704 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0216] Power supply component 706 provides power to various components of electronic device 700. Power supply component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 700.

[0217] Multimedia component 708 includes an interface that provides an output interface between electronic device 700 and a user. In some embodiments, the interface may include a liquid crystal display (LCD) and a touch panel (TP). If the interface includes a touch panel, the interface may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 708 includes at least one of a front-facing camera and a rear-facing camera. When electronic device 700 is in an operating mode, such as a shooting mode or a multimedia mode, at least one of the front-facing camera and the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0218] Audio component 710 is used to execute at least one of output audio signals and input audio signals. For example, audio component 710 includes a microphone (MIC) for receiving external audio signals when electronic device 700 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 704 or transmitted via communication component 716. In some embodiments, audio component 710 also includes a speaker for outputting audio signals.

[0219] Input / output (I / O) interface 712 provides an interface between processing component 702 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0220] Sensor assembly 714 includes one or more sensors for providing state assessments of various aspects of electronic device 700. For example, sensor assembly 714 may detect the on / off state of electronic device 700, the relative positioning of components such as the display and keypad of electronic device 700, changes in position of electronic device 700 or a component of electronic device 700, the presence or absence of user contact with electronic device 700, orientation or acceleration / deceleration of electronic device 700, and temperature changes of electronic device 700. Sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 714 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 714 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0221] Communication component 716 facilitates wired or wireless communication between electronic device 700 and other devices. Electronic device 700 can access wireless networks based on communication standards, such as WiFi, carrier networks (such as 2G, 3G, 4G, or 5G), or combinations thereof. In one exemplary embodiment, communication component 716 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 716 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0222] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to implement a method for demonstrating a vehicle-road cooperative scenario provided in this disclosure embodiment.

[0223] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, which can be executed by a processor 720 of an electronic device 700 to perform the above-described method. For example, the non-transitory storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0224] Figure 8 is a block diagram of an electronic device 800 according to another embodiment of the present disclosure. For example, the electronic device 800 may be provided as a server. Referring to Figure 8, the electronic device 800 includes a processing component 822, which further includes one or more processors, and memory resources represented by memory 832 for storing instructions, such as applications, that can be executed by the processing component 822. The applications stored in memory 832 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 822 is configured to execute instructions to perform a demonstration method of a vehicle-road cooperative scenario provided by an embodiment of the present disclosure.

[0225] Electronic device 800 may also include a power supply component 826 configured to perform power management of electronic device 800, a wired or wireless network interface 850 configured to connect electronic device 800 to a network, and an input / output (I / O) interface 858. Electronic device 800 may operate on an operating system stored in memory 832, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or similar.

[0226] In embodiments of this disclosure, memory 832 can be used to store software programs and various data. Memory 832 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store an operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, memory 832 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 832 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0227] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly handles operations related to the operating system, user interface, and applications, while the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor.

[0228] This disclosure also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described device wake-up method embodiments and achieve the same technical effects. To avoid repetition, these will not be described again here.

[0229] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0230] This disclosure also provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the device wake-up method embodiments described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0231] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the applications disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0232] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A device wake-up method, characterized in that, Applied to home consoles, the device wake-up method includes: The system receives multiple voiceprint features and multiple sound description information sent by multiple smart devices within a preset time period. The multiple voiceprint features and multiple sound description information are obtained by the smart devices through feature extraction of wake-up voice information. The home host is connected to the multiple smart devices respectively. The target voiceprint feature corresponding to the target user is selected from multiple voiceprint features using a pre-stored voiceprint feature library. Select multiple sound description information corresponding to the target voiceprint feature from the multiple sound description information; The multiple sound description information corresponding to the target voiceprint feature are scored according to the preset scoring rules to obtain the response score of each sound description information corresponding to the target voiceprint feature. Based on the response score, a target device is determined from the plurality of smart devices, and a wake-up command is sent to the target device so that the target device responds to the wake-up voice information according to the wake-up command.

2. The method according to claim 1, characterized in that, The sound description information includes sound intensity, sound angle, reception time, and response mode. The step of scoring the multiple sound description information corresponding to the target voiceprint feature according to a preset scoring rule to obtain a response score for each sound description information corresponding to the target voiceprint feature includes: Each sound description information is sorted according to the sound intensity, the sound angle, the reception time, and the response mode to obtain multiple sorting results; Based on each sorting result and the preset scoring rules, the response score for each sound description information is obtained.

3. The method according to claim 2, characterized in that, The step of obtaining the response score for each sound description information based on each sorting result and a preset scoring rule includes: Based on the preset correspondence between the order and the score, the sound intensity score, sound angle score, reception time score and response mode score of each sound description information are obtained; The sound intensity score, the sound angle score, the reception time score, and the response mode score are summed to obtain the response score for each sound description information.

4. The method according to claim 1, characterized in that, The method further includes: If no pre-stored voiceprint is identical to the first voiceprint feature in the voiceprint feature library, a correspondence between the first voiceprint feature and user information is generated, wherein the first voiceprint feature is any one of the plurality of voiceprint features. The correspondence is stored in the voiceprint feature library.

5. The method according to claim 1, characterized in that, After determining the target device from the plurality of smart devices based on the response score and sending a wake-up command to the target device, the method further includes: Receive target audio data sent by the target device, wherein the target audio data is audio data sent by the target user collected by the target device; Feature extraction is performed on the target audio data to obtain target feature information; The target feature information is compared with the instruction feature values ​​stored in the pre-stored feature database to determine the target instruction corresponding to the target feature information; The target instruction is sent to the target device so that the target device executes the target instruction.

6. A device wake-up method, characterized in that, Applied to smart devices, the device wake-up method includes: Obtain the wake-up voice information issued by the target user; Feature extraction is performed on the wake-up voice information to obtain voiceprint features and sound description information, which includes: sound intensity, sound angle, reception time, and response mode. The voiceprint feature and the voice description information are sent to the home host, so that the home host selects the target voiceprint feature corresponding to the target user from multiple voiceprint features according to the correspondence between user information and voiceprint features, selects multiple voice description information corresponding to the target voiceprint feature from multiple voice description information, scores the multiple voice description information corresponding to the target voiceprint feature according to a preset scoring rule, obtains the response score of each voice description information corresponding to the target voiceprint feature, determines the target device according to the response score, and sends a wake-up command to the target device; Upon receiving a wake-up command from the home host, the system responds to the wake-up voice information according to the wake-up command.

7. The method according to claim 6, characterized in that, The wake-up voice information includes first voice information and second voice information emitted by the target user. The step of extracting features from the wake-up voice information to obtain sound intensity and sound angle includes: The first speech information and the second speech information are analyzed to obtain the first speech intensity corresponding to the first speech information and the second speech intensity corresponding to the second speech information; The root mean square (RMS) processing is performed on the first speech intensity and the second speech intensity to obtain the sound intensity. The sound angle is determined based on the first reception time of the first voice information, the second reception time of the second voice information, the first voice intensity, and the second voice intensity.

8. The method according to claim 6, characterized in that, After responding to the wake-up voice information, the method further includes: Collect the target audio data emitted by the target user; The target audio data is sent to the home host so that the home host can extract features from the target audio data to obtain target feature information. The target feature information is then compared with the instruction feature values ​​stored in the pre-stored feature database to determine the target instruction corresponding to the target feature information. Receive the target instruction sent by the home host and execute the target instruction.

9. A device wake-up device, characterized in that, The device wake-up device, applicable to home consoles, includes: The first receiving module is used to receive multiple voiceprint features and multiple sound description information sent by multiple smart devices within a preset time period. The multiple voiceprint features and multiple sound description information are obtained by the smart devices by extracting features from the wake-up voice information. The home host is connected to the multiple smart devices respectively. The feature matching module is used to select the target voiceprint feature corresponding to the target user from multiple voiceprint features using a pre-stored voiceprint feature library. The information selection module is used to select multiple sound description information corresponding to the target voiceprint feature from the multiple sound description information; The scoring module is used to score the multiple sound description information corresponding to the target voiceprint feature according to the preset scoring rules, so as to obtain the response score of each sound description information corresponding to the target voiceprint feature; The first sending module is configured to determine a target device from the plurality of smart devices based on the response score, and send a wake-up command to the target device so that the target device responds to the user's command according to the wake-up command.

10. A device wake-up device, characterized in that, Applied to a target device, the device wake-up device includes: The acquisition module is used to acquire the wake-up voice information issued by the target user; The feature extraction module is used to extract features from the wake-up voice information to obtain voiceprint features and sound description information, wherein the sound description information includes: sound intensity, sound angle, reception time and response mode; The second sending module is used to send the voiceprint feature and the sound description information to the home host, so that the home host selects the target voiceprint feature corresponding to the target user from multiple voiceprint features according to the correspondence between user information and voiceprint features, selects multiple sound description information corresponding to the target voiceprint feature from multiple sound description information, scores the multiple sound description information corresponding to the target voiceprint feature according to a preset scoring rule, obtains a response score for each sound description information corresponding to the target voiceprint feature, determines the target device according to the response score, and sends a wake-up command to the target device; The second receiving module is used to respond to the wake-up voice information according to the wake-up command when it receives a wake-up command sent by the home host.

11. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the device wake-up method as described in any one of claims 1 to 5 or 6 to 8.

12. A readable storage medium, characterized in that, When the instructions in the readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the device wake-up method as described in any one of claims 1 to 5 or 6 to 8.

Images