CN111620011A - Voice processing method, intelligent container and computer readable storage medium - Google Patents
Voice processing method, intelligent container and computer readable storage medium Download PDFInfo
- Publication number
- CN111620011A CN111620011A CN202010354480.7A CN202010354480A CN111620011A CN 111620011 A CN111620011 A CN 111620011A CN 202010354480 A CN202010354480 A CN 202010354480A CN 111620011 A CN111620011 A CN 111620011A
- Authority
- CN
- China
- Prior art keywords
- audio signal
- task
- barrel cover
- execute
- awakening
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/14—Other constructional features; Accessories
- B65F1/16—Lids or covers
- B65F1/1623—Lids or covers with means for assisting the opening or closing thereof, e.g. springs
- B65F1/1638—Electromechanically operated lids
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/14—Other constructional features; Accessories
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/138—Identification means
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Reverberation, Karaoke And Other Acoustics (AREA)
Abstract
The invention discloses a voice processing method, an intelligent container and a computer readable storage medium, wherein the method comprises the following steps: collecting audio signals in a designated area through a sound collection device; determining whether the audio signal is used to indicate that a wake-up operation is performed; and when the audio signal is determined to be used for indicating to execute the awakening operation, determining a task instruction corresponding to the audio signal according to the audio signal, wherein the task instruction is used for indicating to execute the preset operation corresponding to the audio signal. The intelligent container provided by the method has the characteristic of low power consumption, and when the intelligent container is a garbage can, the requirements of reducing direct contact between people and between people and public facilities are met, the advocated requirements of energy conservation and emission reduction are also met, the requirement of people on clean environment is met, and the environment is better.
Description
Technical Field
The present invention relates to the field of speech processing technologies, and in particular, to a speech processing method, an intelligent container, and a computer-readable storage medium.
Background
With the development of society, the health consciousness of people is gradually increased, when people are in public places or use public facilities, people are easy to contact and interact with the public places and/or the public facilities, and the contact behaviors are easy to bring the risk of cross infection. For example, the garbage bin can be seen in the street and alley as a general public facility, people almost have the demand of losing rubbish every day, and in order to prevent that rubbish in the garbage bin from falling out, present garbage bin all has the lid, and people need open the lid and lose rubbish into again when losing rubbish to this will contact with the garbage bin, and rubbish itself is just unhygienic, and the sanitary risk that arouses is great.
Disclosure of Invention
The embodiment of the invention provides a voice processing method, an intelligent container and a computer readable storage medium, which have the effect of controlling the intelligent container to be awakened and controlled without contact.
An embodiment of the present invention provides a speech processing method applied to an intelligent container, where the method includes: collecting audio signals in a designated area through a sound collection device; determining whether the audio signal is used to indicate that a wake-up operation is performed; and when the audio signal is determined to be used for indicating to execute the awakening operation, determining a task instruction corresponding to the audio signal according to the audio signal, wherein the task instruction is used for indicating to execute the preset operation corresponding to the audio signal.
In an embodiment, the determining whether the audio signal is used to indicate that a wake-up operation is performed includes: identifying the audio signal through a low-power consumption awakening model to obtain an identification result, wherein the identification result is used for determining whether the audio signal is used for indicating to execute awakening operation; the low-power wake-up model is obtained through training of a training set, and the training set comprises audio samples corresponding to instructions for executing the preset operation.
In an embodiment, when it is determined that the audio signal is used to instruct to perform a wake-up operation, determining, according to the audio signal, a task instruction corresponding to the audio signal includes: when the audio signal is determined to be used for indicating to execute the awakening operation, performing text conversion on the audio signal to obtain a task text; matching the task text with a task list to obtain a matching result; and generating a task instruction corresponding to the task text based on the matching result.
In an embodiment, the preset operation includes at least one of: the method comprises the following steps of performing first preset operation for controlling the barrel cover to be opened, performing second preset operation for controlling the barrel cover to be closed, and performing third preset operation for controlling the barrel cover to be normally opened; correspondingly, the audio signal comprises at least one of the following: the first audio signal is used for representing that the barrel cover is opened, the second audio signal is used for representing that the barrel cover is closed, and the third audio signal is used for representing that the barrel cover is normally opened.
In an embodiment, after determining the task instruction corresponding to the audio signal according to the audio signal, the method further includes: acquiring a level signal which is generated by a digital signal processing module and corresponds to the task instruction; and executing preset operation corresponding to the task instruction according to the level signal.
Another aspect of an embodiment of the present invention provides an intelligent container, including: the acquisition module is used for acquiring audio signals in the designated area through the sound acquisition device; a first determining module, configured to determine whether the audio signal is used to instruct a wake-up operation to be performed; and the second determining module is used for determining a task instruction corresponding to the audio signal according to the audio signal when the audio signal is determined to be used for instructing to execute the awakening operation, wherein the task instruction is used for instructing to execute the preset operation corresponding to the audio signal.
In an embodiment, the first determining module includes: identifying the audio signal through a low-power consumption awakening model to obtain an identification result, wherein the identification result is used for determining whether the audio signal is used for indicating to execute awakening operation; the low-power wake-up model is obtained through training of a training set, and the training set comprises audio samples corresponding to instructions for executing the preset operation.
In an embodiment, the second determining module includes: the conversion sub-module is used for performing text conversion on the audio signal to obtain a task text when the audio signal is determined to be used for indicating to execute the awakening operation; the matching submodule is used for matching with a task list based on the task text to obtain a matching result; and the generation submodule is used for generating a task instruction corresponding to the task text based on the matching result.
In an embodiment, the preset operation includes at least one of: the method comprises the following steps of performing first preset operation for controlling the barrel cover to be opened, performing second preset operation for controlling the barrel cover to be closed, and performing third preset operation for controlling the barrel cover to be normally opened; correspondingly, the audio signal comprises at least one of the following: the first audio signal is used for representing that the barrel cover is opened, the second audio signal is used for representing that the barrel cover is closed, and the third audio signal is used for representing that the barrel cover is normally opened.
In an embodiment, the smart container further comprises: the acquisition module is used for acquiring a level signal which is generated by the digital signal processing module and corresponds to the task instruction; and the execution module is used for executing preset operation corresponding to the task instruction according to the level signal.
Another aspect of the embodiments of the present invention provides a computer-readable storage medium, which includes a set of computer-executable instructions, and when the instructions are executed, the storage medium is configured to perform any one of the above-mentioned speech processing methods.
The voice processing method, the intelligent container and the computer readable storage medium provided by the embodiment of the invention are particularly suitable for intelligent containers which are required by multiple people, such as an intelligent garbage can, an intelligent storage box, an intelligent recycling box, an intelligent collection box and the like. The intelligent container executes the awakening operation according to the audio signal by applying the method, after awakening, the preset operation related to the audio signal is determined according to the audio signal, and the awakening and control of the intelligent container are realized by acquiring the audio signal once without manually controlling the intelligent container to contact the surface of the intelligent container, so that the risk of cross infection caused by the contact of the intelligent container and the intelligent container is avoided.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Fig. 1 is a schematic flow chart illustrating an implementation of a speech processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a flow chart of implementing task matching of a voice processing method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating an implementation flow of a voice processing method for executing a predetermined operation according to an embodiment of the present invention;
fig. 4 is a schematic block diagram of an intelligent container according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart illustrating an implementation of a speech processing method according to an embodiment of the present invention.
Referring to fig. 1, in one aspect, an embodiment of the present invention provides a speech processing method applied to an intelligent container, where the method includes: an operation 101 of acquiring an audio signal in a designated area through a sound acquisition device; an operation 102 of determining whether an audio signal is used to indicate to perform a wake-up operation; and operation 103, when it is determined that the audio signal is used for instructing to execute the wake-up operation, determining a task instruction corresponding to the audio signal according to the audio signal, where the task instruction is used for instructing to execute a preset operation corresponding to the audio signal.
The voice processing method provided by the embodiment of the invention is applied to the intelligent container with the function of accommodating articles, and is further particularly suitable for the intelligent container with the function of accommodating articles required by multiple users, such as an intelligent garbage can, an intelligent storage box, an intelligent recycling box, an intelligent collecting box and the like. The intelligent garbage can executes the awakening operation according to the audio signal, determines the preset operation related to the audio signal according to the audio signal after awakening, and awakens and controls the intelligent container by acquiring the audio signal once without manually controlling the intelligent container to contact the surface of the intelligent container, so that the risk of cross infection caused by contact with the intelligent container is avoided.
In operation 101, a sound collection apparatus is an apparatus for collecting a sound signal, such as a microphone, a sound pickup, and the like. The sound collection device may be mounted at or near the center of the designated area to facilitate collection of sound within the designated area. The specified area is the distance of intelligent container circumference within the specific range, and is specific, when sound collection system installs on intelligent container, but the specified area can be with sound collection system's collection distance coincidence. The audio signal may include an ambient signal unrelated to the user's intention and/or a speech signal related to the user's intention.
After the audio signal is acquired, the intelligent container needs to perform operation 102, and the intelligent container analyzes and processes the audio signal to determine whether the audio signal is used to instruct a wake-up operation to be performed. The analysis processing mode of the intelligent container can be different based on different awakening modes. In one case, the smart container may recognize the audio signal through a voice wakeup model to determine whether the audio signal is used to indicate that a wakeup operation is performed; in another case, the smart container may also match the list of wakeup words through an audio signal to determine whether a wakeup operation needs to be performed. In the embodiment of the invention, the intelligent container identifies the audio signal through the voice wake-up model, and determines whether the audio signal is used for indicating to execute the wake-up operation according to the identification result. The intelligent container determines whether the audio signal corresponds to a wake-up instruction through analysis, and the wake-up instruction is used for indicating to execute wake-up operation. And when the audio signal is determined to correspond to the awakening instruction, executing awakening operation corresponding to the awakening instruction.
When the intelligent container is determined to be the audio signal and used for indicating to execute the awakening operation, namely the user has the intention of awakening the intelligent container, the intelligent container executes the awakening operation of the intelligent container, the awakened intelligent container analyzes and processes the audio signal to determine a task instruction corresponding to the audio signal, and the task instruction is used for indicating to execute the preset operation. The method comprises the steps of receiving a task instruction, and determining the mode of the audio signal according to the task instruction, wherein the mode of the awakened intelligent container for analyzing and processing the audio signal can be different according to different task instruction determination modes. In one case, the intelligent container can recognize the audio signal through a voice processing model to determine a task instruction corresponding to the audio signal, wherein the voice processing model is used for determining and outputting the task instruction corresponding to the audio signal; further, the input data of the speech processing model is correspondingly different according to the difference between the model architecture of the speech processing model and the training set, for example, when the training samples of the training set are character data, the method needs to perform text transcription on the audio signal to obtain the character data for inputting the speech processing model, and when the training samples of the training set are audio data, the method can directly input the audio signal into the speech processing model for recognition.
Based on the above description, the following provides an embodiment of a specific scenario, in which the intelligent container is an intelligent trash can located under a building of a community, and a microphone is mounted on a cover of the trash can and used for collecting audio signals. When the user needs to throw away rubbish, the user sends out voice information within the range that the microphone can collect the audio signal, and the microphone collects the audio signal containing the voice information of the user, namely the cover is opened. The dustbin carries out analysis processing on the audio signal to determine whether the audio signal meets the condition for generating the awakening instruction, and when the audio signal meets the condition for generating the awakening instruction, the awakening instruction is generated and used for indicating awakening operation. The dustbin awakens the dustbin, the awakened dustbin analyzes and processes the audio signal to determine a task instruction of opening a cover corresponding to the audio signal, and controls the power mechanism to start according to the task instruction to execute mechanical action corresponding to opening the cover. In one case, the user can dispose of the trash into the trash receptacle after the trash receptacle lid is opened. At this point, the user may speak a voice message and the microphone picks up an audio signal "close the lid" containing the user's voice message. The dustbin carries out analysis processing on the audio signals to determine a task instruction of closing the cover corresponding to the audio signals, and controls the power mechanism to start according to the task instruction to execute mechanical action corresponding to closing the cover. The dustbin awakens up the back, can be in the running state in the settlement time, and the settlement time can be predetermine according to the demand, and after exceeding the settlement time, the dustbin switches into standby state. In another case, the user discards the trash in the trash bin after the trash bin cover is opened. At this point, the user may speak a voice message and the microphone picks up an audio signal "close the lid" containing the user's voice message. The dustbin carries out analysis processing on the audio signal to determine whether the audio signal meets the condition for generating the awakening instruction, and when the audio signal meets the condition for generating the awakening instruction, the awakening instruction is generated and used for indicating awakening operation. The dustbin awakens the dustbin, the awakened dustbin analyzes and processes the audio signal to determine a task instruction of closing the cover corresponding to the audio signal, and controls the power mechanism to start according to the task instruction to execute mechanical action corresponding to closing the cover. That is, after the dustbin is awakened, after the dustbin executes the preset operation, the dustbin is switched to the standby state, and at this time, the dustbin needs to be awakened again so as to execute the next preset operation. According to different requirements of users, the voice message sent by the user can also comprise 'closing the cover', 'opening the cover' and the like.
Further, it can be supplemented that the preset operation corresponding to the same audio signal can be adjusted according to the actual situation of the product, for example, in one case, when the method is applied to a trash can, the lid needs to be closed in consideration of the fact that the user loses the trash, in order to facilitate the user operation, the operation content can be preset to automatically close the lid for the set condition after the lid is opened, and the set condition can be set time, such as: 5s, 10s, 20s or other time, and the setting time can be realized by a timer. After the garbage can is opened according to a user instruction and preset uncovering operation is executed, a timer counts time, and after set time is met, the uncovering operation is executed. Further, the setting condition may be a setting action, for example, a photoelectric sensor or an infrared sensor is provided at an opening position of the trash can, and when the sensor is triggered, it is considered that there is trash thrown into the trash can, and the trash can performs a lid closing operation.
In an embodiment of the present invention, the determining whether the audio signal is used to instruct to perform the wake-up operation in operation 102 includes: identifying the audio signal through the low-power consumption awakening model to obtain an identification result, wherein the identification result is used for determining whether the audio signal is used for indicating to execute awakening operation; the low-power consumption awakening model is obtained through training of a training set, and the training set comprises audio samples corresponding to instructions for executing preset operations.
In the embodiment of the invention, the audio signal is awakened and identified through the low-power-consumption awakening model. The low power consumption of the model can be realized by a low power consumption chip, and the model comprises a General-purpose input/output port control Unit (General-purpose-output/output, GPIO) of a General Micro Control Unit (MCU) so as to be used for controlling various power mechanisms to operate by an intelligent container and realize mechanical operations such as opening a cover and closing the cover, and the chip further comprises a Digital Signal Processing module (DSP) so as to be used for voice awakening and voice recognition Processing. Furthermore, the low-power chip can be selected as a DSP chip with an M4F architecture, and when the intelligent container is in a standby state without being awakened, the power consumption can be lower than 1mA, so that the intelligent container can be continuously standby for approximately 3 months under the support of 4 batteries, thereby achieving the purposes of long-term use and reducing frequent battery replacement. A further low-power chip can be selected as a cotex-m 4f high-performance processor, the sleep power consumption of the processor can reach the uA level, and the wakeup signal is triggered in a way of supporting always on.
In order to realize that one language information of the user can be used for indicating to execute the awakening operation and the preset operation, the training set comprises an audio sample corresponding to the instruction to execute the preset operation. For example, when the smart container is a multi-compartment storage box with a lid, the training samples of the training set may include "open all boxes", "close all boxes", "open left box", "open first box", "close third box", "keep second box half open", and other audio samples for directly or indirectly indicating the lid action.
Fig. 2 is a schematic flow chart illustrating an implementation process of task matching in a speech processing method according to an embodiment of the present invention.
Referring to fig. 2, in the embodiment of the present invention, in operation 103, when it is determined that the audio signal is used to instruct to perform the wake-up operation, determining a task instruction corresponding to the audio signal according to the audio signal includes: operation 1031, when it is determined that the audio signal is used for instructing to perform a wake-up operation, performing text conversion on the audio signal to obtain a task text; operation 1032, matching is performed on the task text and the task list to obtain a matching result; at operation 1033, a task instruction corresponding to the task text is generated based on the matching result.
In the embodiment of the invention, the task instruction is determined in a task list matching mode. Specifically, the method comprises the steps of firstly performing text conversion on an audio signal to determine a task text corresponding to the audio signal, then matching the task text with a preset task list, wherein the task list comprises task instructions which can be generated and/or executed by the intelligent container and is used for associating the task text with the task instructions, determining a matching result matched with the task text in the task list, and generating the task instructions based on the matching result. Further, after the audio signal is subjected to text conversion, in order to improve matching efficiency and accuracy, keyword extraction can be performed on the task text to remove irrelevant voice content in the user voice signal. For example, when the voice signal of the user is "open the lid of the trash bin", the voice signal is converted into a task text, keywords are extracted to obtain keywords of "lid" and "open", and the keywords are matched with the task list to obtain a task instruction corresponding to "lid open". It can be understood that when the intelligent container has a plurality of accommodating cavities, the task list and the keywords also include task object information. For example, when the smart container is a container with 3 accommodating cavities, after the user sends out a voice signal, the container acquires an audio signal as "close the right cover". After the audio signal text is converted, keywords are extracted to obtain keywords of 'close', 'right' and 'cover', matching is carried out through a task list, a task object is determined to be a cover of the right accommodating cavity, a task instruction corresponding to 'close the right cover' is obtained, and the instruction is executed to close the right cover. Further, the task matching can be performed through a task matching list, and can also be identified through a matching model. When recognition is performed by a matching model, training of the matching model may be performed with keywords, task text samples, task lists, and the like as training samples and parameters.
In an embodiment of the present invention, when the smart container is a smart container for accommodating an article, the preset operation includes at least one of: the method comprises the following steps of performing first preset operation for controlling the barrel cover to be opened, performing second preset operation for controlling the barrel cover to be closed, and performing third preset operation for controlling the barrel cover to be normally opened; accordingly, the audio signal comprises at least one of: the first audio signal is used for representing that the barrel cover is opened, the second audio signal is used for representing that the barrel cover is closed, and the third audio signal is used for representing that the barrel cover is normally opened.
It is to be added that the difference between the first preset operation and the third preset operation is the time difference, in one case, the opening of the barrel cover can correspond to the opening action of the barrel cover with a short preset time, and the opening of the barrel cover with a long time can correspond to the opening action of the barrel cover with a long preset time. Under another condition, the opening of the barrel cover can correspond to the opening action of the barrel cover without preset time, and the barrel cover is normally opened and corresponds to the opening base of the barrel cover with preset time. The preset time is the time for executing the closing action of the barrel cover after the barrel cover is opened.
It is understood that when the smart container has a plurality of housing chambers, the number of task instructions acquired based on the audio signal is at least one. In addition to the first preset operation, the second preset operation, and the third preset operation, the third preset operation may further include a fourth preset operation for controlling opening of a plurality of barrel covers, a fifth preset operation for controlling closing of a plurality of barrel covers, a sixth preset operation for controlling opening of a part of barrel covers, and a seventh preset operation for controlling closing of a part of barrel covers, which is not described in detail below. It will be appreciated that the audio signal that can be used to match the preset operation can also be used for the wake-up operation. For example, in an implementation scenario, when the trash can is a trash can capable of having a trash classification function, the trash can includes three accommodating cavities respectively corresponding to harmful trash, recyclable trash, and non-recyclable trash. The corresponding preset operation may be to open a cover corresponding to the harmful garbage, close a cover corresponding to the harmful garbage, keep a cover corresponding to the harmful garbage normally open, open a cover corresponding to the recyclable garbage, close a cover corresponding to the recyclable garbage, keep a cover corresponding to the recyclable garbage normally open, open a cover corresponding to the unrecoverable garbage, close a cover corresponding to the unrecoverable garbage, keep a cover corresponding to the unrecoverable garbage normally open, open a cover corresponding to the harmful garbage and the recyclable garbage and the unrecoverable garbage, open a cover corresponding to the harmful garbage and the unrecoverable garbage, close a cover corresponding to the harmful garbage and the recyclable garbage, keep a cover corresponding to the recyclable garbage and the unrecoverable garbage, and the like.
Fig. 3 is a schematic flow chart illustrating an implementation process of executing a predetermined operation by a voice processing method according to an embodiment of the present invention.
Referring to fig. 3, in an embodiment of the present invention, after determining a task instruction corresponding to an audio signal according to the audio signal, the method further includes: 301, obtaining a level signal corresponding to a task instruction generated by a digital signal processing module; and step 302, executing a preset operation corresponding to the task instruction according to the level signal.
In the method, the opening and closing of the container lid is effected by means of an electric motor. After the task instruction is obtained, controlling a GPIO port of the DSP chip to output a corresponding level signal; and after receiving the level signal, the motor control module of the intelligent container controls a power mechanism of the intelligent container to perform other operations such as opening a cover, closing the cover and the like.
A specific implementation scenario is provided below, in which the smart container is a trash can, and a microphone is mounted on the trash can.
When a user needs to throw garbage, the user sends out voice, the garbage can picks up the voice through the microphone and then wakes up and recognizes the voice signal corresponding to the voice of the user through the voice wake-up model, after the recognition result is that wake-up operation is executed, the garbage can wakes up and converts the voice signal to obtain a character result corresponding to the voice signal, such as a json character result, the json character result is subjected to task matching, a corresponding task instruction is determined, and a level signal corresponding to the task instruction is output. And after receiving the level signal, the motor control module of the garbage can controls the motor to operate according to a preset action so as to open and close the cover.
Another specific implementation scenario is provided below, in which the intelligent container is a trash can with a sorting function, and includes a first accommodating cavity for accommodating recyclable trash and a second accommodating cavity for accommodating non-recyclable trash, and a microphone is mounted on the trash can.
When a user needs to throw the recyclable garbage, the user sends out voice, the garbage can picks up the voice through the microphone and then turns on the cover of the recyclable garbage according to the voice signal of the user, the voice awakening model is used for awakening and recognizing, after the garbage can is awakened, the voice signal is subjected to character conversion, a character result corresponding to the voice signal is subjected to task matching, a corresponding task instruction is determined, and a level signal corresponding to the 'turn on the cover of the recyclable garbage' is output. And after receiving the level signal, the motor control module of the garbage can controls the motor to open the cover corresponding to the recyclable garbage and keep the cover of the unrecoverable garbage closed. And after the cover opening time of the cover corresponding to the recyclable garbage reaches the preset time, controlling the motor to close the cover corresponding to the recyclable garbage. It can be understood that, in this technical solution, the operation of controlling the motor to close the cover corresponding to the recyclable waste can be directly performed by outputting a level signal of "opening the cover capable of recycling waste, closing the cover capable of recycling waste after reaching the set time" to instruct the motor control module to perform the above operation after receiving the level signal. The operation of controlling the motor to close the cover corresponding to the recyclable garbage may also be that after the set time is reached, the garbage bin generates a level signal of "closing the cover corresponding to the recyclable garbage" to the motor control module to instruct the motor control module to perform the corresponding operation.
The intelligent container provided by the method has the characteristic of low power consumption, and when the intelligent container is a garbage can, the requirement for reducing direct contact between people and between people and public facilities is favorably met, the advocated requirement for energy conservation and emission reduction is also met, the requirement for cleanness of the environment by people is also favorably met, and the environment is better.
Fig. 4 is a schematic block diagram of an intelligent container according to an embodiment of the present invention.
Another aspect of an embodiment of the present invention provides an intelligent container, including: the acquisition module 401 is configured to acquire an audio signal in a designated area through a sound acquisition device; a first determining module 402, configured to determine whether an audio signal is used to indicate to perform a wake-up operation; a second determining module 403, configured to determine, according to the audio signal, a task instruction corresponding to the audio signal when it is determined that the audio signal is used to instruct to perform a wake-up operation, where the task instruction is used to instruct to perform a preset operation corresponding to the audio signal.
In this embodiment of the present invention, the first determining module 402 includes: identifying the audio signal through the low-power consumption awakening model to obtain an identification result, wherein the identification result is used for determining whether the audio signal is used for indicating to execute awakening operation; the low-power consumption awakening model is obtained through training of a training set, and the training set comprises audio samples corresponding to instructions for executing preset operations.
In this embodiment of the present invention, the second determining module 403 includes: a conversion submodule 4031, configured to perform text conversion on the audio signal to obtain a task text when it is determined that the audio signal is used to indicate that the wake-up operation is performed; the matching sub-module 4032 is used for matching the task text with the task list to obtain a matching result; and the generating sub-module 4033 is used for generating a task instruction corresponding to the task text based on the matching result.
In the embodiment of the invention, the preset operations comprise a first preset operation for controlling the opening of the barrel cover, a second preset operation for controlling the closing of the barrel cover and a third preset operation for controlling the normal opening of the barrel cover; correspondingly, the audio signals comprise a first audio signal for indicating that the barrel cover is opened, a second audio signal for indicating that the barrel cover is closed and a third audio signal for indicating that the barrel cover is normally opened.
In an embodiment of the present invention, the smart container further includes: an obtaining module 404, configured to obtain a level signal corresponding to the task instruction generated by the digital signal processing module; and the execution module 405 is configured to execute a preset operation corresponding to the task instruction according to the level signal.
Another aspect of embodiments of the present invention provides a computer-readable storage medium comprising a set of computer-executable instructions, which when executed, perform any one of the above-described speech processing methods.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A speech processing method, applied to an intelligent container, the method comprising:
collecting audio signals in a designated area through a sound collection device;
determining whether the audio signal is used to indicate that a wake-up operation is performed;
and when the audio signal is determined to be used for indicating to execute the awakening operation, determining a task instruction corresponding to the audio signal according to the audio signal, wherein the task instruction is used for indicating to execute the preset operation corresponding to the audio signal.
2. The method of claim 1, wherein the determining whether the audio signal is indicative of performing a wake-up operation comprises:
identifying the audio signal through a low-power consumption awakening model to obtain an identification result, wherein the identification result is used for determining whether the audio signal is used for indicating to execute awakening operation;
the low-power wake-up model is obtained through training of a training set, and the training set comprises audio samples corresponding to instructions for executing the preset operation.
3. The method of claim 1, wherein when it is determined that the audio signal is used to indicate to perform a wake-up operation, determining a task instruction corresponding to the audio signal according to the audio signal comprises:
when the audio signal is determined to be used for indicating to execute the awakening operation, performing text conversion on the audio signal to obtain a task text;
matching the task text with a task list to obtain a matching result;
and generating a task instruction corresponding to the task text based on the matching result.
4. The method according to any of claims 1-3, wherein the pre-set operation comprises at least one of: the method comprises the following steps of performing first preset operation for controlling the barrel cover to be opened, performing second preset operation for controlling the barrel cover to be closed, and performing third preset operation for controlling the barrel cover to be normally opened;
correspondingly, the audio signal comprises at least one of the following: the first audio signal is used for representing that the barrel cover is opened, the second audio signal is used for representing that the barrel cover is closed, and the third audio signal is used for representing that the barrel cover is normally opened.
5. The method of claim 4, wherein after determining task instructions corresponding to the audio signal from the audio signal, the method further comprises:
acquiring a level signal which is generated by a digital signal processing module and corresponds to the task instruction;
and executing preset operation corresponding to the task instruction according to the level signal.
6. A smart container, characterized in that the smart container comprises:
the acquisition module is used for acquiring audio signals in the designated area through the sound acquisition device;
a first determining module, configured to determine whether the audio signal is used to instruct a wake-up operation to be performed;
and the second determining module is used for determining a task instruction corresponding to the audio signal according to the audio signal when the audio signal is determined to be used for instructing to execute the awakening operation, wherein the task instruction is used for instructing to execute the preset operation corresponding to the audio signal.
7. The smart container of claim 6 wherein the first determining module comprises: identifying the audio signal through a low-power consumption awakening model to obtain an identification result, wherein the identification result is used for determining whether the audio signal is used for indicating to execute awakening operation; the low-power wake-up model is obtained through training of a training set, and the training set comprises audio samples corresponding to instructions for executing the preset operation.
8. The smart container of claim 6 wherein the second determining module comprises:
the conversion sub-module is used for performing text conversion on the audio signal to obtain a task text when the audio signal is determined to be used for indicating to execute the awakening operation;
the matching submodule is used for matching with a task list based on the task text to obtain a matching result;
and the generation submodule is used for generating a task instruction corresponding to the task text based on the matching result.
9. The smart container of any one of claims 6 to 8 wherein the preset operations include at least one of: the method comprises the following steps of performing first preset operation for controlling the barrel cover to be opened, performing second preset operation for controlling the barrel cover to be closed, and performing third preset operation for controlling the barrel cover to be normally opened;
correspondingly, the audio signal comprises at least one of the following: the first audio signal is used for representing that the barrel cover is opened, the second audio signal is used for representing that the barrel cover is closed, and the third audio signal is used for representing that the barrel cover is normally opened.
10. A computer-readable storage medium comprising a set of computer-executable instructions that, when executed, perform the speech processing method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010354480.7A CN111620011A (en) | 2020-04-29 | 2020-04-29 | Voice processing method, intelligent container and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010354480.7A CN111620011A (en) | 2020-04-29 | 2020-04-29 | Voice processing method, intelligent container and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111620011A true CN111620011A (en) | 2020-09-04 |
Family
ID=72268200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010354480.7A Pending CN111620011A (en) | 2020-04-29 | 2020-04-29 | Voice processing method, intelligent container and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111620011A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113816038A (en) * | 2021-09-29 | 2021-12-21 | 夏日阳光智能科技(苏州)有限公司 | Intelligent voice garbage can sound pickup and low-power-consumption control method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180178978A1 (en) * | 2014-03-14 | 2018-06-28 | Simplehuman, Llc | Containers with multiple sensors |
| CN109509470A (en) * | 2018-12-11 | 2019-03-22 | 平安科技（深圳）有限公司 | Voice interactive method, device, computer readable storage medium and terminal device |
| CN110473544A (en) * | 2019-10-09 | 2019-11-19 | 杭州微纳科技股份有限公司 | A kind of low-power consumption voice awakening method and device |
| CN111048095A (en) * | 2019-12-24 | 2020-04-21 | 苏州思必驰信息科技有限公司 | Voice transcription method, equipment and computer readable storage medium |
| CN111081254A (en) * | 2019-12-26 | 2020-04-28 | 苏州思必驰信息科技有限公司 | Voice recognition method and device |
-
2020
- 2020-04-29 CN CN202010354480.7A patent/CN111620011A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180178978A1 (en) * | 2014-03-14 | 2018-06-28 | Simplehuman, Llc | Containers with multiple sensors |
| CN109509470A (en) * | 2018-12-11 | 2019-03-22 | 平安科技（深圳）有限公司 | Voice interactive method, device, computer readable storage medium and terminal device |
| CN110473544A (en) * | 2019-10-09 | 2019-11-19 | 杭州微纳科技股份有限公司 | A kind of low-power consumption voice awakening method and device |
| CN111048095A (en) * | 2019-12-24 | 2020-04-21 | 苏州思必驰信息科技有限公司 | Voice transcription method, equipment and computer readable storage medium |
| CN111081254A (en) * | 2019-12-26 | 2020-04-28 | 苏州思必驰信息科技有限公司 | Voice recognition method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113816038A (en) * | 2021-09-29 | 2021-12-21 | 夏日阳光智能科技(苏州)有限公司 | Intelligent voice garbage can sound pickup and low-power-consumption control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109720752A (en) | A kind of sort-type automatic shutter dustbin and its control method based on speech recognition | |
| CN204938038U (en) | A kind of refuse classification equipment | |
| CN111268302A (en) | Garbage classifier based on voice recognition and working method thereof | |
| CN110570856A (en) | intelligent garbage can based on voice interaction auxiliary classification putting and auxiliary putting method | |
| CN210593595U (en) | Intelligent garbage bin based on pronunciation waste classification | |
| CN205441599U (en) | Garbage bin is removed in acoustic control based on mike's array | |
| CN109573403A (en) | Novel and multifunctional intelligent dustbin and application method | |
| CN111959995A (en) | Garbage classification voice interaction system based on ROS | |
| CN112158486A (en) | Intelligent garbage classification device and classification method | |
| CN212830602U (en) | Domestic automatic intelligent classification garbage bin | |
| CN111620011A (en) | Voice processing method, intelligent container and computer readable storage medium | |
| CN112320138A (en) | Indoor movable garbage classification device | |
| CN211077233U (en) | Interactive intelligent classification garbage bin | |
| CN103482275A (en) | Intelligent-classification garbage can | |
| CN214297580U (en) | Intelligent garbage recognition and classification device based on internet | |
| CN209922092U (en) | Material recycling bin capable of automatically identifying human face and garbage types | |
| CN210681937U (en) | Intelligent garbage can | |
| Tu et al. | Design and implementation of intelligent control garbage bin | |
| CN213504143U (en) | Intelligent garbage can based on garbage classification | |
| CN110902211A (en) | Intelligent classification garbage can based on infrared sensor and control method thereof | |
| CN112389897A (en) | Intelligent garbage can based on voice garbage classification and working method thereof | |
| CN107973030A (en) | Intelligent garbage bin | |
| CN214932722U (en) | Intelligence speech classification garbage bin | |
| CN110282288A (en) | A kind of intelligent sound garbage classification device and classification method | |
| CN113378627B (en) | Automatic garbage classification method and device based on DSP chip and single chip microcomputer control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 215024 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Jiangsu Province Applicant after: Sipic Technology Co.,Ltd. Address before: 215024 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Jiangsu Province Applicant before: AI SPEECH Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200904 |