45results about How to "Improve wake-up efficiency" patented technology

The invention proposes a voice wakeup method and a voice wakeup device based on artificial intelligence. The voice wakeup method comprises the following steps: acquiring pronunciation information corresponding to a custom wakeup word; acquiring approximate pronunciation information corresponding to the pronunciation information; and building a wakeup word recognition network according to a preset spam word list, the pronunciation information and the approximate pronunciation information so as to recognize voice input by a user according to the wakeup word recognition network and determine whether or not need to perform a wakeup operation according to the recognition result. According to the embodiments of the invention, a wakeup word recognition network can be built dynamically for different custom wakeup, so that the accuracy of wakeup is enhanced effectively, the rate of false alarm is reduced, and the wakeup efficiency is improved. The device has smaller memory footprint and low power consumption.

The embodiment of the invention discloses a method for awakening a smart device for speech recognition. The method comprises the steps of entering the speech detection state after determining that a first portion of a user holding a first smart device faces a second smart device, and conducting speed recognition after detecting speech energy in the speech detection state. According to the scheme, the second smart device is awaken for speech recognition without using an awakening word, that is to say, the second smart device is awaken before a user speaks the awakening word, so that awakening time is shortened and awakening efficiency is improved. Furthermore, the second smart device is awaken for speech recognition only after the first portion of the user holding the first smart device faces the second smart device, and the situation that the second smart device is in a constantly awaken state is avoided, so that power consumption of the second smart device is reduced and user experience is improved.

The invention relates to a mobile terminal, in particular to a system awakening method and a system awakening device. The method includes: when a preset awakening event in a core layer is triggered, awakening a pre-registered initial awakening device; awakening a pre-registered first slow awakening device; during awakening of the first slow awakening device or after operation for awakening the first slow awakening device is finished, awakening a pre-registered second slow awakening device if receiving an awakening command of a user layer. According to the method, the first slow awakening device is awakened before the awakening command of the user layer is received, so that system awakening time is shortened, and system awakening efficiency is improved.

The invention provides a train control method, device and system. A vehicle on board controller (VOBC) is disposed at one end of a train. The train control method comprises the steps that the VOBC performs a train awakening process; after the train is successfully awakened, the VOBC acquires an operation plan sent by an automatic train supervision system (ATS); according to the direction indicatedby the operation plan, the VOBC sets the train running direction to be downlink or uplink; in the case of downlink, the VOBC takes the other end of the train without the VOBC as the head of the trainto position the train; in the case of uplink, the VOBC takes the end of the train with the VOBC as the head of the train to position the train; and according to the train positioning, the train is controlled to leave a parking garage. The train control method can simplify train configuration, reduces the train cost, shortens the length of time required for awakening the train, and improves the awakening efficiency of the train. Further, it is possible to realize that the train does not need end change to activate a cab in different running directions, the operation steps are simplified, and the running efficiency of the train is improved.

The invention provides a square wave detector for a wireless wake-up circuit. The frequency of the square wave detector can be configured within the range of 10-200 kHz. The square wave detector comprises a signal acquisition circuit and a square wave detection circuit, wherein the square wave detection circuit comprises a jitter detection module path, a frequency detection module path, a relevant detection module path and an AND circuit which are used for respectively detecting the duty factor, the frequency and the relevance of an input sampling signal; and when outputs of the three detection module paths are high levels respectively, the output of the AND circuit is also high level and the square wave detection circuit outputs a wake-up signal. By detecting the jitter, the frequency and the relevance of the input sampling signal, the accurate judgment and clutter reduction are realized, the mistaken wake-up probability is effectively reduced, the wake-up probability is increased and the wake-up time is remarkably shortened, thereby increasing the work efficiency of a wake-up receiver and reducing the power consumption of the system. The square wave detector provided by the invention is suitable for wake-up receiving circuits of an RFID (Radio Frequency Identification) system and an ETC (Electronic Toll Collection) system.

The invention discloses an intelligent sleep wake-up system and an intelligent sleep wake-up method. The intelligent sleep wake-up system comprises a computer and a photosensitive sensor, a gravity sensor, a speaker, a pillow vibrating mechanism, a curtain control mechanism and a lamp, which are connected with the computer respectively, wherein the photosensitive sensor is used for detecting brightness of outdoor light and transmitting the detected data to the computer; the gravity sensor is installed on a bed, and is used for detecting weight change of the bed and transmitting the detected data to the computer; the pillow vibrating mechanism is connected with a pillow; the curtain control mechanism is connected with a curtain; the curtain control mechanism is used for opening the curtain; and the computer respectively controls the curtain control mechanism, the lamp, the speaker and the pillow vibrating mechanism to be started according to the received data. The intelligent sleep wake-up system and the intelligent sleep wake-up method provided by the invention can detect an outdoor environment in real time and automatically start according to the environment, and a combination of multiple wakeup methods is adopted to wake up people in sleep, so that the wakeup efficiency is greatly improved.

The embodiments of the present invention disclose a screen state adjustment method and apparatus. The method comprises the following steps that: the current iris information of a user is obtained, and data matching is performed on the current iris information and pre-stored iris information; when a data matching result corresponding to the current iris information indicates that the matching is successful, and screen gaze information corresponding to the current iris information is obtained; and when it is detected that the screen gaze information satisfies a preset gaze condition, the state of a current screen is switched to an awake state from a sleep state. With the screen state adjustment method and apparatus of the invention adopted, a convenient screen wake-up mode can be provided, operation steps are simplified, and the wake-up efficiency of the screen can be improved.

The invention discloses a voice awakening method and device, electronic equipment and a storage medium, which are used for effectively improving the awakening efficiency of voice awakening and improving the use experience of a user. The method comprises the following steps of: obtaining a defect wake-up word for performing voice wake-up at present, wherein the defect wake-up words are wake-up words different from standard mandarin voice, acquiring rhythm feature information corresponding to the defect wake-up word, determining a standard wake-up word corresponding to the defect wake-up word according to the rhythm feature information and a pre-trained corpus recognition model, wherein the corpus recognition model is obtained by training a plurality of defect voice samples marked with standard voice, and finally performing voice waking according to the standard wake-up word.

The invention discloses a method for awakening a power line communication network by employing an expanded ISP (Inter-System Protocol) signal. The method comprises the steps as follows: current network equipment in the power line communication network detects whether the expanded ISP signal is received under a standby mode; if the expanded ISP signal is detected within a certain period of time, the current network equipment transfers the expanded ISP signal to a lower-level network equipment in the power line communication network to awaken the lower-level network equipment, and the current network equipment joins in the network to achieve awakening of the current network equipment. Correspondingly, the invention also discloses a system for awakening the power line communication network by employing the expanded ISP signal. According to the invention, the expanded ISP signal is used as an awakening signal of the power line network; the expanded ISP signal is simple in structure, and easy to detect, and supports simultaneous transmission to a certain extent, so that the power consumption under the standby mode can be reduced; the network can be rapidly awakened, and the awakening efficiency of the overall network is improved.

The invention relates to an equipment awakening method and device, electronic equipment and a storage medium. The wake-up method is applied to first electronic equipment, and the method comprises thefollowing steps: receiving a wake-up message from second electronic equipment, and acquiring locally acquired voice data when determining that the current state is a non-wake-up state; performing Mel-frequency cepstrum coefficient extraction on the voice data to obtain a first Mel-frequency cepstrum coefficient of the voice data; analyzing a second Mel-frequency cepstrum coefficient carried in thewake-up message from the wake-up message; matching the first Mel-frequency cepstrum coefficient with the second Mel-frequency cepstrum coefficient, and generating a wake-up instruction when determining that the difference between the first Mel-frequency cepstrum coefficient and the second Mel-frequency cepstrum coefficient is less than or equal to a set threshold; and in response to the wake-up instruction, waking up the first electronic equipment. The invention is suitable for differentiated multi-equipment pre-awakening scenes under multi-electronic-device networking.

Provided are an electronic device and a switching method for working modes thereof. The method comprises: respectively operating a first work system and a second work system on a first hardware core and a second hardware core of an electronic device; under a normal work mode, the first hardware core detecting a standby signal which indicates to enter a standby mode; the first hardware core sending an interrupt signal, and storing first reply data which is corresponding to the first operating state of the first work system to volatile memory of the electronic device, to respond to the standby signal; the second hardware core storing second reply data of the second operating state of the second work system to the volatile memory, to respond to the interrupt signal; entering the standby mode, and pausing power supply for the first hardware core and the second hardware core under the standby mode. Thus, awakening speed of the electronic device is improved.

The embodiment of the invention relates to the technical field of to-be-awakened equipment, in particular to an awakening method and electronic equipment. In the embodiment of the invention, the method comprises the following steps: receiving a first awakening instruction, and analyzing a media access control (MAC) address contained in the first awakening instruction; determining an equipment typeof awakening equipment according to the MAC address; wherein the awakening equipment is equipment for sending the first awakening instruction to the equipment to be awakened; and entering a working state indicated by the awakening mode corresponding to the awakening equipment according to a preset comparison relationship between the equipment type and the awakening mode.

The embodiment of the invention discloses a voice wake-up method, device and equipment. The method comprises the steps of for an acquired to-be-processed voice signal, acquiring to-be-processed voice features from the to-be-processed voice signal, and coding the to-be-processed voice features to obtain acoustic coding representations; after the acoustic coding representations corresponding to the to-be-processed voice signal are obtained, carrying out integration according to the acoustic coding representations and the weights corresponding to the acoustic coding representations, and then obtaining a character sequence included in the to-be-processed voice signal according to the integrated acoustic coding representations; and after the character sequence is obtained, determining whether to wake up the equipment or not according to the character sequence and the keyword. That is, possible characters are acquired from the to-be-processed voice signal, and then whether to wake up or not is judged based on the character level instead of a voice frame, so that the wake-up efficiency is improved.

The invention discloses a voice interaction method and system. The voice interaction method specifically includes the following operating steps that S1, environment mixed voice information including target user voice information is acquired; S2, the target voice information is identified and the target voice information is separated from the environment mixed voice information; S3, the target voice information is translated into a digital signal command, and a corresponding program is mobilized according to the digital signal command; and S4, response is output. According to the voice interaction method and system, the voice interactive system can be waken up by a human body or voice, the operation is simple, the situation that the voice interactive system can be waken up for use due to the failure to correctly identify a preset voice command can be avoided, and the wake-up efficiency of the system is improved; and the environmental sound before a target user voice period is simultaneously collected, accurate environmental sound reference data information can be provided when eliminating ground noise from mixed voice, the improvement of the accuracy of the target voice information acquisition is facilitated, and the accuracy and efficiency of human-computer interaction are improved.

The invention is applicable to the technical field of set-top boxes and provides a wake-up method and device for an intelligent set-top box, electronic equipment and a storage medium. The wake-up method for the intelligent set-top box comprises the following steps of when the set-top box is standby and enters a deep standby mode, sending an abnormal data packet to preset equipment so as to enablethe preset equipment to be disconnected with the set-top box; judging whether a broadcast packet sent by any key of preset equipment is received or not, wherein the broadcast packet carries a key value corresponding to the key; if the broadcast packet is received, waking up the set top box to enter a shallow standby mode; judging whether the key value is a power key value or not; and if the key value is the power key value, waking up the set top box to enter a normal operation mode. The method is advantaged in that wake-up efficiency of the set-top box can be improved, and diversification of wake-up modes of the set-top box is improved.

The invention discloses a method and a circuit for waking up an I2C (Inter-Integrated Circuit) device. The method comprises the following steps of: judging whether a starting signal is received or not; when determining that the starting signal is received, judging whether a next signal received after the starting signal is a matched address signal or not when determining that the next signal is amatched address signal, generating a wake-up instruction to wake up the I2C device; otherwise, clearing the starting signal received before the next signal, and returning to the step of judging whether the starting signal is received or not. By means of a mode, the efficiency of the awakening process of the I2C device can be improved, and timely awakening and normal use of the I2C device are guaranteed.

The invention relates to an energy storage control device, an energy storage charging method and an energy storage box. The energy storage control device comprises the components of an energy storage module which is connected with external charging equipment through a relay; a battery management module which is connected with the energy storage module and is used for acquiring an electric signal of the energy storage module; and a switching control switch which is connected with the battery management module, wherein when the battery management module detects a fact that the energy storage module requires shutdown according to the acquired electric signal of the energy storage module, the battery management module switches off the relay and makes the switching control switch perform switching so that the battery management module is connected with external charging equipment. When the battery management module detects a fact that the external charging equipment can charge the energy storage module, the battery management module switches on the relay and makes the switching control switch perform switching so that the battery management module is connected with the energy storage module. After the energy storage module is shut down, the external charging equipment can automatically charge the energy storage module, thereby preventing manual operation and improving arousing efficiency to the energy storage module.

The invention provides an intelligent sound equipment control method and device, and a storage medium. The method comprises the steps of: obtaining the current signal intensity of a target wireless earphone corresponding to a target user, and determining a target distance between the target user and intelligent sound equipment based on the current signal intensity; and when the target distance isnot greater than a first distance threshold, controlling the intelligent sound equipment to switch from a screensaver mode to a working mode. According to the invention, the target distance between the target user and the intelligent sound equipment is determined based on the signal intensity of the target wireless earphone, and when the target distance between the target user and the intelligentsound box is detected to be very short, namely, the target distance is not greater than the first distance threshold, the intelligent sound equipment is controlled to quit from the screensaver mode and enter the working mode, so that the user can perform related operations conveniently, wakeup errors caused by wakeup instruction abnormality are avoided while the user experience is improved, the wakeup efficiency of the intelligent sound equipment is improved, and the technical problem of low wakeup efficiency of the current intelligent sound equipment wakeup mode is solved.

The invention discloses a graphic code recognition method and device and electronic equipment, and belongs to the technical field of communication. The graphic code recognition method comprises the steps: obtaining an application identifier set corresponding to a target graphic code, wherein the target graphic code comprises at least one graphic code; determining a target application identifier from the application identifier set, and determining a to-be-identified graphic code from the at least one graphic code; identifying the to-be-identified graphic code by utilizing an application programcorresponding to the target application identifier, wherein the application identifier set comprises at least two application identifiers, and the application programs corresponding to the application identifiers can identify the graphic codes. According to the scheme, the problem that an existing graphic code recognition scheme is tedious in operation is well solved.

The invention belongs to the technical field of sensors, and particularly relates to a wireless sensor network node awakening system and method based on a way-finding algorithm, and the system comprises an active awakening center, wireless sensor nodes, and a sensor network. The wireless sensor nodes are irregularly distributed in a sensor network; each wireless sensor node comprises a central control unit, an active wake-up control unit, a passive wake-up control unit and a sensor. The active awakening control unit responds to an awakening command of the active awakening center and awakens the sensor node; and the passive awakening control unit awakens the sensor node under the control of a preset triggering condition of the central control unit. Through the combination of a passive awakening mode and an active awakening mode, the power consumption of the sensor network is reduced, and the service life of the sensor network is prolonged; meanwhile, the path finding method based on thegenetic algorithm enables the sensor awakening efficiency to be higher, and reduces the probability of false awakening.

The invention provides a voice wake-up method for terminal equipment, which comprises the following steps that: when a user voice reported by a woken terminal is received, confirming the historical wake-up record data of the woken terminal , and when the woken terminal does not confirm that the user voice is a terminal wake-up voice, reporting the user voice; determining whether the user voice is the terminal awakening voice of the awakened terminal or not through the historical awakening record data; and if the user voice is confirmed to be the terminal awakening voice, issuing a starting instruction to the awakened terminal. The invention further provides a device and a computer readable storage medium. According to the invention, the historical wake-up voice data of the voice terminal device is recorded and reported to the server when the voice terminal device fails to recognize the wake-up voice, and the voice recognition effect of the voice terminal device is improved by recognizing the user voice according to the historical wake-up voice data.

The present invention proposes an artificial intelligence-based voice wake-up method and device, wherein the voice wake-up method includes: acquiring pronunciation information corresponding to a custom wake-up word; acquiring approximate pronunciation information corresponding to the pronunciation information; The word list, the pronunciation information and the approximate pronunciation information construct a wake-up word recognition network to recognize the voice input by the user according to the wake-up word recognition network, and determine whether to perform a wake-up operation according to the recognition result. The embodiment of the present invention can dynamically construct a wake-up word recognition network for different custom wake-ups, effectively improve the correct rate of wake-ups, reduce false alarm rates, improve wake-up efficiency, occupy less memory, and consume less power.

The present application discloses a voice wake-up method, device, electronic equipment and storage medium, which are used to effectively improve the wake-up efficiency of voice wake-up and enhance user experience. The method includes: acquiring the flawed wake-up word currently undergoing voice wake-up, the flawed wake-up word is a wake-up word different from standard Mandarin speech, and then acquiring the prosodic feature information corresponding to the flawed wake-up word, and according to the prosody feature information and the pre-trained corpus The recognition model determines the standard wake-up word corresponding to the flawed wake-up word. The corpus recognition model is trained based on multiple flawed sound samples marked with standard voices, and finally wakes up the voice according to the standard wake-up word.

The invention discloses a multifunctional key communication method, and belongs to the technical field of communication methods. The method comprises the following steps of: enabling a single chip and a reception chip to be located in a sleep time period and waiting for awakening; after the sleep time is over, awakening the single chip and the reception chip external interruption, receiving a signal by the reception signal, sending the signal to the single chip, and detecting whether the received signal has a guidance code or not by the single chip; when the single chip detects that the received signal has the guidance code, detecting a pulse number of the guidance code; when the single chip detects that the pulse number of the guidance code in the received signal is greater than or equal to 3, judging whether the received signal has a synchronous code or not by the single chip; when the single chip judges that the signal has the synchronous code, receiving a data instruction code by the single chip, and judging whether a data bit pulse width length meets a requirement or not; and when the data bit pulse width length meets the requirement, judging whether the data is completely received or not by the single chip. The invention aims at providing the multifunctional key communication method which is convenient to use and good in effect; and the method is used for data communication.

The invention discloses a sound awakening method and device, a storage medium and electrical equipment. The method comprises the following steps: acquiring environmental sound parameters of an environment to which the electrical equipment belongs; determining whether the environmental sound parameter of the environment to which the electrical equipment belongs is greater than a set sound parameter; if the environment sound parameter of the environment to which the electrical equipment belongs is greater than the set sound parameter, determining whether a sound wake-up action exists in the environment to which the electrical equipment belongs; and if the sound wake-up action exists in the environment to which the electrical equipment belongs, reducing the sound broadcast volume in the environment to which the electrical equipment belongs so as to perform sound wake-up on the electrical equipment based on the sound wake-up action in the environment to which the electrical equipment belongs under the condition of reducing the sound broadcast volume in the environment to which the electrical equipment belongs. According to the scheme, the problem of low sound awakening rate in a noisyenvironment can be solved, and the effect of improving the sound awakening rate in the noisy environment is achieved.

The embodiment of the invention discloses a method for awakening a smart device for speech recognition. The method comprises the steps of entering the speech detection state after determining that a first portion of a user holding a first smart device faces a second smart device, and conducting speed recognition after detecting speech energy in the speech detection state. According to the scheme, the second smart device is awaken for speech recognition without using an awakening word, that is to say, the second smart device is awaken before a user speaks the awakening word, so that awakening time is shortened and awakening efficiency is improved. Furthermore, the second smart device is awaken for speech recognition only after the first portion of the user holding the first smart device faces the second smart device, and the situation that the second smart device is in a constantly awaken state is avoided, so that power consumption of the second smart device is reduced and user experience is improved.