CN116092226A - Voice unlocking method, device, equipment and storage medium - Google Patents
Voice unlocking method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116092226A CN116092226A CN202211551037.4A CN202211551037A CN116092226A CN 116092226 A CN116092226 A CN 116092226A CN 202211551037 A CN202211551037 A CN 202211551037A CN 116092226 A CN116092226 A CN 116092226A
- Authority
- CN
- China
- Prior art keywords
- unlocking
- voice
- content
- information
- instruction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000004044 response Effects 0.000 claims abstract description 25
- 230000008451 emotion Effects 0.000 claims description 65
- 230000015654 memory Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 abstract description 4
- 230000009471 action Effects 0.000 description 7
- 230000008909 emotion recognition Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 206010028813 Nausea Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008693 nausea Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Lock And Its Accessories (AREA)
Abstract
The disclosure relates to a voice unlocking method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring a voice instruction of a user; matching the first content of the voice command with the content of the pre-input unlocking command; responding to the matching of the first content and the content of the pre-input unlocking instruction, and then matching the first voiceprint feature of the voice instruction with the voiceprint feature of the pre-input unlocking instruction; and controlling the door lock to be opened in response to the first voiceprint feature being matched with the voiceprint feature of the unlocking instruction. According to the method and the device, the content and the voiceprint characteristics of the voice command input by the user are respectively matched with the content and the voiceprint characteristics of the pre-input unlocking command, and the door lock is controlled to be opened when the content and the voiceprint characteristics are matched with each other, so that double verification can be carried out on the command content and the user identity, and the safety of the door lock is ensured.
Description
Technical Field
The disclosure relates to the technical field of voice recognition, and in particular relates to a voice unlocking method, a voice unlocking device, voice unlocking equipment and a storage medium.
Background
With the continuous development of technology, the unlocking mode of the anti-theft lock is more and more, from the original mechanical anti-theft door lock to the intelligent anti-theft door lock at present, the selection of people is more and more diversified, wherein the voice door lock supporting voice recognition does not need to carry a key or an access card by a user, the password does not need to be manually input during unlocking, and the unlocking can be completed only by speaking out of the password, so that the anti-theft door lock is very convenient to use, and is favored by people. However, the existing voice door lock can be opened only by inputting a correct password, and if the password is stolen by other people, the safety of the door lock cannot be ensured. Therefore, how to improve the security of the voice door lock is a technical problem to be solved.
Disclosure of Invention
In order to solve the technical problems, the present disclosure provides a voice unlocking method, a device, equipment and a storage medium.
A first aspect of an embodiment of the present disclosure provides a voice unlocking method, including:
acquiring a voice instruction of a user;
matching the first content of the voice command with the content of the pre-input unlocking command;
responding to the matching of the first content and the content of the pre-input unlocking instruction, and then matching the first voiceprint feature of the voice instruction with the voiceprint feature of the pre-input unlocking instruction;
And controlling the door lock to be opened in response to the first voiceprint feature being matched with the voiceprint feature of the unlocking instruction.
A second aspect of the disclosed embodiments provides a voice unlocking apparatus, the apparatus comprising:
the acquisition module is used for acquiring a voice instruction of a user;
the first matching module is used for matching the first content of the voice command with the content of the pre-recorded unlocking command;
the second matching module is used for matching the first voiceprint features of the voice command with the voiceprint features of the pre-input unlocking command in response to the fact that the first content is matched with the content of the pre-input unlocking command;
and the control module is used for controlling the door lock to be opened in response to the fact that the first voiceprint characteristic is matched with the voiceprint characteristic of the unlocking instruction.
A third aspect of the embodiments of the present disclosure provides a computer device, including a memory and a processor, and a computer program, where the memory stores the computer program, and when the computer program is executed by the processor, implements the voice unlocking method as in the first aspect.
A fourth aspect of the embodiments of the present disclosure provides a computer-readable storage medium, in which a computer program is stored which, when executed by a processor, implements the method of voice unlocking as in the first aspect described above.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:
in the voice unlocking method, the voice unlocking device, the voice unlocking equipment and the storage medium provided by the embodiment of the disclosure, by acquiring the voice command of the user, matching the first content of the voice command with the content of the pre-input unlocking command, matching the first voiceprint characteristic of the voice command with the voiceprint characteristic of the pre-input unlocking command in response to the matching of the first content with the content of the pre-input unlocking command, controlling the unlocking of the door lock in response to the matching of the first voiceprint characteristic with the voiceprint characteristic of the unlocking command, and respectively matching the content of the voice command and the voiceprint characteristic with the content of the pre-input unlocking command and the voiceprint characteristic when the voice command is unlocked, controlling the unlocking of the door lock when the voice command and the voiceprint characteristic are matched, so that double verification of command content and user identity is realized, and safety of the door lock is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments of the present disclosure or the solutions in the prior art, the drawings that are required for the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
Fig. 1 is a flowchart of a voice unlocking method provided in an embodiment of the present disclosure;
FIG. 2 is a flow chart of a method of matching instruction content provided by an embodiment of the present disclosure;
FIG. 3 is a flow chart of a method of matching voiceprint features provided by an embodiment of the present disclosure;
FIG. 4 is a flow chart of a method of controlling door lock unlocking provided by an embodiment of the present disclosure;
FIG. 5 is a flow chart of a method of alerting a user provided in an embodiment of the present disclosure;
FIG. 6 is a flow chart of a method of sending alarm information provided by an embodiment of the present disclosure;
FIG. 7 is a flow chart of another method of controlling door lock unlocking provided by an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a voice unlocking device according to an embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of a computer device according to an embodiment of the present disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, a further description of aspects of the present disclosure will be provided below. It should be noted that, without conflict, the embodiments of the present disclosure and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced otherwise than as described herein; it will be apparent that the embodiments in the specification are only some, but not all, embodiments of the disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
Fig. 1 is a flowchart of a voice unlocking method provided in an embodiment of the present disclosure, which may be performed by a voice unlocking apparatus. As shown in fig. 1, the voice unlocking method provided in this embodiment includes the following steps:
s101, acquiring a voice instruction of a user.
The voice command in the embodiments of the present disclosure may be understood as a command conveyed by voice, and, for example, when unlocking by voice, the voice command may be a password in voice form.
In the embodiment of the disclosure, the voice unlocking device may collect, in real time, a voice instruction sent by a user through an audio collection device, such as a microphone, where the audio collection device may be installed on the voice unlocking device, and may also be installed at other positions other than the voice unlocking device, which is not limited herein.
S102, matching the first content of the voice command with the content of the pre-recorded unlocking command.
The first content in the embodiments of the present disclosure may be understood as content included in a voice instruction, and the first content may be in audio form, text form, or other forms, which are not limited herein.
The unlocking command in the embodiment of the present disclosure may be understood as a preset command capable of controlling unlocking of the door lock, and by way of example, the unlocking command may be a text or a series of numbers, which is not limited herein.
In this embodiment of the present disclosure, after obtaining a voice command input by a user, the voice unlocking device may extract a first content of the voice command from the voice command, obtain a content of an unlocking command that is input in advance in a storage system, and perform a matching process on the first content of the voice command and the content of the unlocking command to obtain a matching result, where the storage system may be a local database or a database that is set in a cloud, and is not limited herein.
In an exemplary implementation manner of the embodiment of the present disclosure, the voice unlocking device may input, based on a content matching model that is trained in advance, the first content of the voice instruction and the content of the unlocking instruction into the content matching model, so as to obtain a matching result of whether the first content of the voice instruction and the content of the unlocking instruction match.
And S103, responding to the fact that the first content is matched with the content of the pre-input unlocking command, and matching the first voiceprint feature of the voice command with the voiceprint feature of the pre-input unlocking command.
The voiceprint features in the embodiments of the present disclosure may be understood as information for characterizing a voice spectrum of a speaker, and have irreplaceability and stability, different speakers have different voiceprint features, and the voiceprint features of the same speaker remain unchanged, so that identity recognition may be implemented through the voiceprint features, where the first voiceprint feature is a voiceprint feature of a user who inputs a voice instruction.
In this embodiment of the present disclosure, after matching a first content of a voice command with a content of an unlocking command that is input in advance, when a matching result is that the first content matches with the content of the unlocking command, the voice unlocking device extracts a first voiceprint feature of the voice command, obtains the voiceprint feature of the unlocking command that is input in advance in a storage system, and performs matching processing on the first voiceprint feature of the voice command and the voiceprint feature of the unlocking command to obtain a matching result, where specific matching modes include, but are not limited to:
In an exemplary implementation manner of the disclosed embodiment, the voice unlocking device may input the first voice print feature of the voice command and the voice print feature of the unlocking command into the voice print matching model based on the voice print matching model trained in advance, so as to obtain a matching result of whether the first voice print feature of the voice command and the voice print feature of the unlocking command match.
In an exemplary implementation manner of the embodiment of the present disclosure, the voiceprint feature may be represented in a vector form, the voice unlocking device may calculate a cosine similarity or euclidean distance between the first voiceprint feature and the voiceprint feature of the unlocking instruction after extracting the first voiceprint feature from the voice instruction, determine a matching degree between the first voiceprint feature and the voiceprint feature of the unlocking instruction based on a calculation result, compare the matching degree with a preset threshold, and if the matching degree between the voiceprint feature of the unlocking instruction and the first voiceprint feature is greater than or equal to the preset threshold, determine that the first voiceprint feature of the voice instruction and the voiceprint feature of the unlocking instruction match, otherwise determine that the first voiceprint feature of the voice instruction and the voiceprint feature of the unlocking instruction do not match.
And S104, controlling the door lock to be opened in response to the fact that the first voiceprint features are matched with the voiceprint features of the unlocking instruction.
In the embodiment of the disclosure, after the voice unlocking device performs the matching processing on the first voiceprint feature and the voiceprint feature of the unlocking instruction, when the matching result is that the first voiceprint feature is matched with the voiceprint feature of the unlocking instruction, the door lock is controlled to execute the unlocking action.
In an exemplary implementation of the disclosed embodiment, the voice unlocking device may send a control instruction to the door lock when it is determined that the first voiceprint feature matches the voiceprint feature of the unlocking instruction, so that the door lock performs the unlocking action according to the control instruction.
According to the embodiment of the disclosure, by acquiring the voice command of the user, matching the first content of the voice command with the content of the pre-input unlocking command, matching the first voiceprint feature of the voice command with the voiceprint feature of the pre-input unlocking command in response to the matching of the first content with the content of the pre-input unlocking command, and controlling the door lock to be opened in response to the matching of the first voiceprint feature with the voiceprint feature of the unlocking command, the content of the voice command and the voiceprint feature can be respectively matched with the content of the pre-input unlocking command and the voiceprint feature when the voice command is unlocked, and the door lock is controlled to be opened when the voice command is matched with the content of the pre-input unlocking command, so that double verification of command content and user identity is realized, and safety of the door lock is improved.
Fig. 2 is a flowchart of a method for matching instruction contents according to an embodiment of the present disclosure, as shown in fig. 2, on the basis of the above embodiment, the instruction contents may be matched by the following method.
S201, converting the voice instruction into first text information.
The first text information in the embodiments of the present disclosure may be understood as information representing the contents of a voice instruction in a text form.
In the embodiment of the disclosure, the voice unlocking device may convert the voice command into the first text information after obtaining the voice command input by the user.
In an exemplary implementation manner of the disclosed embodiment, the voice unlocking device may input the acquired voice command into a pre-trained voice recognition model, and perform recognition processing on the voice command through the voice recognition model to obtain first text information corresponding to the voice command. Specifically, the obtained voice command may be preprocessed to eliminate a silence period included in the voice command, then framing is performed, sound features are extracted from the obtained voice, and text information is obtained through an acoustic model and a language model, which may be based on a recurrent neural network (Recurrent Neural Network, RNN), an acoustic model may be based on a deep neural network (Deep Neural Networks, DNN), or may be based on a Long Short-Term Memory (LSTM), which is not limited herein.
S202, matching the first text information with the text information corresponding to the unlocking instruction.
In the embodiment of the disclosure, after the first text information is obtained, the voice unlocking device may obtain the text information of the unlocking instruction input in advance in the storage system, and perform matching processing on the first text information of the voice instruction and the text information of the unlocking instruction to obtain a matching result.
In an exemplary implementation manner of the embodiment of the present disclosure, the voice unlocking device may first determine a length of the first text information, and find whether text information having a length identical to or similar to that of the first text information exists in the text information corresponding to the unlocking instruction, if so, further perform a matching process on the first text information and the found text information, otherwise, may directly determine that the first text information is not matched with the text information corresponding to the unlocking instruction.
In an exemplary implementation manner of the embodiment of the present disclosure, the voice unlocking device may perform word segmentation processing on the first text information, perform matching processing on words in the first text information and words in the text information corresponding to the unlocking instruction according to a sequence, screen text information corresponding to the unlocking instruction that is successfully matched from the words, and then match a next word, and if there is an unlocking instruction in which all words are matched with words in the first text information, determine that the first text information is matched with the text information corresponding to the unlocking instruction.
According to the embodiment of the disclosure, the voice instruction is converted into the first text information, the first text information is matched with the text information corresponding to the unlocking instruction, so that the contents of the voice instruction and the unlocking instruction can be matched in a text form, the accuracy of verifying the instruction contents is improved, and the safety of the door lock is further improved.
Fig. 3 is a flowchart of a method for matching voiceprint features according to an embodiment of the present disclosure, as shown in fig. 3, on the basis of the foregoing embodiment, the voiceprint features may be matched by the following method.
S301, determining a target voiceprint feature corresponding to the first content based on a first corresponding relation between the content of the unlocking instruction and the voiceprint feature.
The first correspondence in the embodiment of the disclosure may be understood as a correspondence between the content of the pre-stored unlocking instruction and the voiceprint feature, when the user inputs the unlocking instruction, the user speaks the self-set unlocking instruction, at this time, the content of the unlocking instruction and the voiceprint feature of the user may be obtained simultaneously, and when the content of the unlocking instruction and the voiceprint feature are stored, the first correspondence between the content of the unlocking instruction and the voiceprint feature may be stored simultaneously, so that the voice unlocking device may obtain the first correspondence when needed.
In the embodiment of the disclosure, after determining that the first content is matched with the content of the pre-input unlocking instruction, the voice unlocking device may acquire a first correspondence between the content of the unlocking instruction and the voiceprint feature, determine the voiceprint feature corresponding to the first content of the voice instruction input by the user according to the first correspondence, and determine the voiceprint feature as the target voiceprint feature.
S302, matching the first voiceprint feature with the target voiceprint feature.
In this embodiment of the present disclosure, after determining the target voiceprint feature corresponding to the first content of the voice command, the voice unlocking device may extract the first voiceprint feature of the voice command, and perform a matching process on the first voiceprint feature and the target voiceprint feature of the unlocking command to obtain a matching result, where a specific matching manner is similar to S103 and is not described herein.
According to the embodiment of the disclosure, the target voiceprint feature corresponding to the first content is determined based on the first corresponding relation between the content of the unlocking instruction and the voiceprint feature, the first voiceprint feature and the target voiceprint feature are subjected to matching processing, the consistency of the instruction content and the voiceprint feature can be ensured when the voiceprint feature is verified, the safety of the door lock can be further improved only when the content of the voice instruction input by the user is consistent with the same unlocking instruction which is input by the user, and meanwhile, the user experience is improved because only the voiceprint feature needs to be matched once, and the time is short.
Fig. 4 is a flowchart of a method for controlling unlocking of a door lock according to an embodiment of the present disclosure. As shown in fig. 4, on the basis of the above-described embodiment, the door lock opening can be controlled as follows.
S401, determining first user information corresponding to the first content based on a second corresponding relation between the content of the unlocking instruction and the user information.
User information in the embodiments of the present disclosure may be understood as information for characterizing the identity of a user, and by way of example, the user information may be a user name or a user number, which is not limited herein.
The second correspondence in the embodiment of the disclosure may be understood as a correspondence between the content of the pre-stored unlocking instruction and the user information, when the user inputs the unlocking instruction, the user name of the user may be determined at the same time, or a user number may be automatically generated, at this time, the content of the unlocking instruction and the user information may be obtained at the same time, and when the content of the unlocking instruction is stored, the second correspondence between the content of the unlocking instruction and the user information may be also stored at the same time, so that the voice unlocking device may obtain the second correspondence when needed.
In the embodiment of the disclosure, after determining that the first content is matched with the content of the pre-input unlocking instruction, the voice unlocking device may acquire a second corresponding relationship between the content of the unlocking instruction and the user information, and determine, according to the second corresponding relationship, first user information corresponding to the content of the unlocking instruction matched with the first content.
S402, determining second user information corresponding to the first voiceprint feature based on a third corresponding relation between the voiceprint feature of the unlocking instruction and the user information.
The third correspondence in the embodiment of the disclosure may be understood as a correspondence between a voiceprint feature of an unlocking instruction stored in advance and user information, when the user inputs the unlocking instruction, the voiceprint feature of the unlocking instruction and the user information may be simultaneously acquired, and when the voiceprint feature of the unlocking instruction is stored, the third correspondence between the voiceprint feature of the unlocking instruction and the user information may also be simultaneously stored, so that the voice unlocking device may acquire the third correspondence when needed.
In the embodiment of the disclosure, after determining that the first voiceprint feature is matched with the voiceprint feature of the pre-input unlocking instruction, the voice unlocking device may acquire a third corresponding relationship between the voiceprint feature of the unlocking instruction and the user information, and determine, according to the third corresponding relationship, second user information corresponding to the voiceprint feature of the unlocking instruction matched with the first voiceprint feature.
S403, controlling the door lock to be opened in response to the fact that the first user information is the same as the second user information.
In the embodiment of the present disclosure, after the voice unlocking device obtains the first user information and the second user information, the first user information and the second user information may be compared, and if the first user information and the second user information are the same, the door lock is controlled to execute the unlocking action, and the specific control method is similar to S104, which is not repeated herein.
According to the embodiment of the disclosure, the first user information corresponding to the first content is determined based on the second corresponding relation between the content of the unlocking instruction and the user information, the second user information corresponding to the first voiceprint feature is determined based on the third corresponding relation between the voiceprint feature of the unlocking instruction and the user information, and the door lock is controlled to be opened in response to the fact that the first user information is identical to the second user information, so that after the first content of the voice instruction and the first voiceprint feature are independently verified, whether the content and the voiceprint feature belong to the same user or not can be verified, and only when the user information corresponding to the first user information and the voiceprint feature are identical, the safety of the door lock can be further improved through verification.
Fig. 5 is a flowchart of a method for reminding a user according to an embodiment of the present disclosure, and as shown in fig. 5, on the basis of the above embodiment, the user may be reminded by the following method.
S501, if the first content is not matched with the content of the pre-input unlocking instruction, a first reminding message is sent out, and the first reminding message is used for reminding the user of the voice instruction error.
The first reminding information in the embodiment of the disclosure may be understood as reminding information of a user that the voice command content input by the user is wrong and the unlocking command of the content is not input, and by way of example, the first reminding information may be reminding information in a voice form or reminding information in a text form, and is not limited herein.
In the embodiment of the disclosure, after the first content of the voice command is matched with the content of the pre-input unlocking command, the voice unlocking device determines that the pre-input unlocking command does not contain the voice command input by the user when the matching result is that the first content is not matched with the content of the unlocking command, and can send out first reminding information to the user to remind the user of the error of the voice command input so that the user can modify the content of the voice command and re-input the modified voice command.
S502, responding to the fact that the first voiceprint features are not matched with the voiceprint features of the unlocking instruction, sending second reminding information, wherein the second reminding information is used for reminding the user that the user does not have unlocking authority.
The second reminding information in the embodiment of the disclosure may be understood as reminding information for reminding the user that the user does not have unlocking authority and does not enter the unlocking instruction with the voiceprint feature, and the second reminding information may be, for example, reminding information in a voice form or reminding information in a text form, and is not limited herein.
In the embodiment of the disclosure, after the voice unlocking device performs matching processing on the first voiceprint feature of the voice instruction and the voiceprint feature of the pre-input unlocking instruction, when the matching result is that the first voiceprint feature is not matched with the voiceprint feature of the unlocking instruction, the user is determined to have no input unlocking instruction before, and at the moment, second reminding information can be sent to the user to remind the user that the user has no unlocking authority, so that the user can input the unlocking instruction after obtaining permission, or other users with unlocking authority are notified to unlock.
According to the embodiment of the disclosure, the first reminding information is sent out by responding to the mismatch of the first content and the content of the pre-input unlocking instruction, the first reminding information is used for reminding a user of voice instruction errors, the second reminding information is sent out by responding to the mismatch of the first voiceprint characteristic and the voiceprint characteristic of the unlocking instruction, the second reminding information is used for reminding the user of not having unlocking authority, and when the content or the voiceprint characteristic of the voice instruction input by the user is not matched with the content or the voiceprint characteristic of the pre-input unlocking instruction, the user can inform the user of the reason that the user cannot unlock smoothly, the user is prevented from attempting to input the same voice instruction for many times when the user does not know the situation, the unlocking failure experience is repeated, and the user experience is improved while the safety of the door lock is ensured.
Fig. 6 is a flowchart of a method for transmitting alarm information according to an embodiment of the present disclosure, and as shown in fig. 6, on the basis of the above embodiment, alarm information may be transmitted as follows.
S601, recording the times of continuously sending the first reminding information and the second reminding information.
In the embodiment of the disclosure, the voice unlocking device may add one to the recorded total number of times of sending the first reminding information and the second reminding information after sending the first reminding information or the second reminding information each time, and reset the total number of times to zero after controlling the door lock to be opened, thereby recording the number of times of continuously sending the first reminding information and the second reminding information.
S602, when the times of continuously sending the first reminding information and the second reminding information reach the preset times, sending alarm information to the bound equipment.
The preset times in the embodiment of the disclosure can be understood as the preset upper limit of times capable of continuously inputting the voice command which is not input, the specific numerical value of the preset times can be freely set according to the actual safety requirement, and the higher the safety requirement, the less the preset times can be set.
The bound device in the embodiments of the present disclosure may be understood as a preset device that binds with the voice unlocking device, such as a mobile phone of a room owner, or a terminal inside a security system, etc., which is not limited herein.
Alarm information in the embodiments of the present disclosure may be understood as information for reminding a person concerned of safety of the door lock.
In the embodiment of the disclosure, the voice unlocking device can monitor the times of continuously sending the first reminding information and the second reminding information, and when the times reach the preset times, the voice unlocking device determines that the times are the same
The number of times of continuously inputting the voice command which is not input reaches the upper limit, and at the moment, alarm information can be sent to the bound 5 devices so as to remind relevant personnel of paying attention to the safety of the door lock.
According to the embodiment of the disclosure, the number of times of continuously sending the first reminding information and the second reminding information is recorded, when the number of times of continuously sending the first reminding information and the second reminding information reaches the preset number of times, the alarm information is sent to the bound equipment, and the voice finger which is not input can be continuously input
The number of times reaches the upper limit, the room owner or security personnel is timely reminded, the non-0 legal personnel is prevented from attempting to unlock the door lock in other modes, and the safety of the door lock is further improved.
Fig. 7 is a flowchart of a method for controlling unlocking of a door lock according to an embodiment of the present disclosure. As shown in fig. 7, on the basis of the above-described embodiment, the door lock opening can be controlled as follows.
S701, based on a pre-trained emotion recognition model, recognizing 5 first emotion information contained in the voice instruction.
The emotion recognition model in the embodiment of the disclosure can be understood as a model which is trained in advance and can recognize emotion information in voice, and the emotion recognition model can be built based on a support vector machine (Support Vector Machine, SVM) algorithm or can be
Established based on Mel-frequency cepstral coefficient (Mel-Frequency Ceptral Coefficients, MFCC) of 0, not limited herein.
The first emotion information in the embodiments of the present disclosure may be understood as information for characterizing emotion contained and transmitted by the voice of the speaker, and by way of example, the first emotion information may include happiness, difficulty, angry, nausea, fear, surprise, and the like, without limitation.
In the embodiment of the disclosure, the voice unlocking device may input the obtained voice command into the pre-trained emotion recognition model after obtaining the voice command 5 input by the user to obtain the input
And outputting first emotion information of the voice instruction.
S702, matching the first emotion information with the emotion information of the pre-input unlocking instruction.
In the embodiment of the disclosure, after obtaining the first emotion information, the voice unlocking device may obtain the emotion information of the unlocking instruction that is input in advance in the storage system, and perform matching processing on the first emotion information of the voice instruction and the emotion information of the unlocking instruction to obtain a matching result, where the specific matching method includes, but is not limited to, the following steps:
in an exemplary implementation manner of the embodiment of the present disclosure, when the first emotion information is a classification result, the voice unlocking device may compare the first emotion information with emotion information of a pre-entered unlocking instruction, and determine whether the first emotion information and the emotion information are matched.
In another exemplary implementation manner of the embodiment of the present disclosure, when the first emotion information is represented in the form of a feature vector, the voice unlocking device may calculate a similarity between the first emotion information and the emotion information of the unlocking instruction, and if the similarity is greater than or equal to a preset threshold, determine that the first emotion information and the emotion information are matched, otherwise determine that the first emotion information and the emotion information are not matched.
And S703, controlling the door lock to be opened in response to the fact that the first emotion information is matched with the emotion information of the unlocking instruction.
In the embodiment of the present disclosure, after the voice unlocking device performs the matching processing on the first emotion information and the emotion information of the unlocking instruction, when the matching result is that the first emotion information is matched with the emotion information of the unlocking instruction, the door lock is controlled to perform the unlocking action, and the specific control method is similar to S104 and will not be described herein.
And S704, responding to the fact that the first emotion information is not matched with the emotion information of the unlocking instruction, and sending third reminding information, wherein the third reminding information is used for reminding the user of adjusting emotion when the voice instruction is input.
The third reminding information in the embodiment of the disclosure may be understood as reminding information for reminding that the emotion when the voice command is input is inconsistent with the emotion when the unlocking command is input, and the emotion when the voice command is input needs to be adjusted.
In the embodiment of the disclosure, after determining that the first content and the first voiceprint feature of the voice command are respectively matched with the content and the voiceprint feature of the pre-input unlocking command, when the first emotion information is not matched with the emotion information of the unlocking command, the voice unlocking device sends third reminding information to the user to remind the user to adjust the emotion when the voice command is input, so that the user inputs the adjusted voice command again.
According to the embodiment of the disclosure, the first emotion information contained in the voice command is recognized based on the pre-trained emotion recognition model, the first emotion information is matched with the emotion information of the pre-input unlocking command, the door lock is controlled to be opened in response to the fact that the first emotion information is matched with the emotion information of the unlocking command, the third reminding information is sent out in response to the fact that the first emotion information is not matched with the emotion information of the unlocking command, the third reminding information is used for reminding a user to adjust the emotion when the voice command is input, and after the content and the voice feature of the voice command are verified, the emotion information is verified, so that the safety of the door lock is further improved.
Fig. 8 is a schematic structural diagram of a voice unlocking device according to an embodiment of the present disclosure. As shown in fig. 8, the voice unlocking apparatus 800 includes: the device comprises an acquisition module 810, a first matching module 820, a second matching module 830 and a control module 840, wherein the acquisition module 810 is used for acquiring a voice instruction of a user; a first matching module 820, configured to match the first content of the voice command with the content of the pre-entered unlocking command; a second matching module 830, configured to match, in response to the matching of the first content with the content of the pre-entered unlocking instruction, a first voiceprint feature of the voice instruction with a voiceprint feature of the pre-entered unlocking instruction; and the control module 840 is configured to control the door lock to be opened in response to the first voiceprint feature matching the voiceprint feature of the unlock instruction.
Optionally, the voice unlocking apparatus 800 further includes: the conversion module is used for converting the voice instruction into first text information; the first matching module 820 is specifically configured to perform matching processing on the first text information and the text information corresponding to the unlocking instruction.
Optionally, the second matching module 830 includes: the determining unit is used for determining target voiceprint features corresponding to the first content based on a first corresponding relation between the content of the unlocking instruction and the voiceprint features; and the matching unit is used for matching the first voiceprint feature with the target voiceprint feature.
Optionally, the voice unlocking apparatus 800 further includes: the first determining module is used for determining first user information corresponding to the first content based on a second corresponding relation between the content of the unlocking instruction and the user information; the second determining module is used for determining second user information corresponding to the first voiceprint feature based on a third corresponding relation between the voiceprint feature of the unlocking instruction and the user information; the control module 840 is specifically configured to control unlocking of the door lock in response to the first user information being the same as the second user information.
Optionally, the voice unlocking apparatus 800 further includes: the first reminding module is used for sending first reminding information in response to the fact that the first content is not matched with the content of the pre-input unlocking instruction, and the first reminding information is used for reminding the user of the voice instruction error; and/or: and the second reminding module is used for responding to the fact that the first voiceprint characteristics are not matched with the voiceprint characteristics of the unlocking instruction, and sending second reminding information which is used for reminding the user that the user does not have unlocking authority.
Optionally, the voice unlocking device 800 further includes: the recording module is used for recording the times of continuously sending the first reminding information and the second reminding information; and the alarm module is used for sending alarm information to the bound equipment when the times of continuously sending the first reminding information and the second reminding information reach the preset times.
Optionally, the voice unlocking apparatus 800 further includes: the recognition module is used for recognizing the first emotion information contained in the voice instruction based on the pre-trained emotion recognition model; the third matching module is used for matching the first emotion information with the emotion information of the pre-input unlocking instruction; the control module 840 includes: the control unit is used for controlling the door lock to be opened in response to the fact that the first emotion information is matched with the emotion information of the unlocking instruction; and the reminding unit is used for sending third reminding information in response to the fact that the first emotion information is not matched with the emotion information of the unlocking instruction, and the third reminding information is used for reminding the user of adjusting emotion when the voice instruction is input.
The voice unlocking device provided in this embodiment can execute the method described in any one of the above embodiments, and the execution mode and the beneficial effects thereof are similar, and are not described herein again.
Fig. 9 is a schematic structural diagram of a computer device according to an embodiment of the present disclosure.
As shown in fig. 9, the computer device may include a processor 910 and a memory 920 storing computer program instructions.
In particular, the processor 910 described above may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.
The processor 910 reads and executes the computer program instructions stored in the memory 920 to perform the steps of the voice unlocking method provided by the embodiments of the present disclosure.
In one example, the computer device may also include a transceiver 930 and a bus 940. As shown in fig. 9, the processor 910, the memory 920, and the transceiver 930 are connected and communicate with each other through a bus 940.
The present disclosure also provides a computer-readable storage medium, which may store a computer program that, when executed by a processor, causes the processor to implement the voice unlocking method provided by the embodiments of the present disclosure.
The storage medium may, for example, include a memory 920 of computer program instructions executable by the processor 910 of the voice unlocking apparatus to perform the voice unlocking method provided by the embodiments of the present disclosure. Alternatively, the storage medium may be a non-transitory computer readable storage medium, for example, a ROM, a random access memory (Random Access Memory, RAM), a Compact Disc ROM (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like. The computer programs described above may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is merely a specific embodiment of the disclosure to enable one skilled in the art to understand or practice the disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown and described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of voice unlocking comprising:
acquiring a voice instruction of a user;
matching the first content of the voice command with the content of the pre-input unlocking command;
responding to the matching of the first content and the content of the pre-input unlocking instruction, and then matching the first voiceprint feature of the voice instruction with the voiceprint feature of the pre-input unlocking instruction;
and controlling the door lock to be opened in response to the first voiceprint feature being matched with the voiceprint feature of the unlocking instruction.
2. The method of claim 1, wherein prior to matching the first content of the voice command with the content of the pre-entered unlock command, the method further comprises:
converting the voice instruction into first text information;
the matching processing of the first content of the voice command and the content of the pre-recorded unlocking command comprises the following steps:
and matching the first text information with the text information corresponding to the unlocking instruction.
3. The method of claim 1, wherein the matching the first voiceprint feature of the voice command with the voiceprint feature of the pre-entered unlock command comprises:
Determining a target voiceprint feature corresponding to the first content based on a first corresponding relation between the content of the unlocking instruction and the voiceprint feature;
and matching the first voiceprint feature with the target voiceprint feature.
4. The method of claim 1, wherein prior to the controlling the door lock to open, the method further comprises:
determining first user information corresponding to the first content based on a second corresponding relation between the content of the unlocking instruction and the user information;
determining second user information corresponding to the first voiceprint feature based on a third corresponding relation between the voiceprint feature of the unlocking instruction and the user information;
the control door lock is opened, including:
and controlling the door lock to be opened in response to the first user information being identical to the second user information.
5. The method according to claim 1, wherein the method further comprises:
responding to the fact that the first content is not matched with the content of the pre-input unlocking instruction, sending first reminding information, wherein the first reminding information is used for reminding the user of the voice instruction error;
and/or:
and responding to the fact that the first voiceprint features are not matched with the voiceprint features of the unlocking instruction, sending second reminding information, wherein the second reminding information is used for reminding the user that the user does not have unlocking authority.
6. The method of claim 5, wherein the method further comprises:
recording the times of continuously sending the first reminding information and the second reminding information;
and when the times of continuously sending the first reminding information and the second reminding information reach the preset times, sending alarm information to the bound equipment.
7. The method of claim 1, wherein prior to the controlling the door lock to open, the method further comprises:
identifying first emotion information contained in the voice instruction based on a pre-trained emotion identification model;
matching the first emotion information with emotion information of the pre-input unlocking instruction;
the control door lock is opened, including:
controlling the door lock to be opened in response to the fact that the first emotion information is matched with the emotion information of the unlocking instruction;
and responding to the fact that the first emotion information is not matched with the emotion information of the unlocking instruction, sending third reminding information, wherein the third reminding information is used for reminding the user of adjusting emotion when the voice instruction is input.
8. A voice unlocking device, comprising:
the acquisition module is used for acquiring a voice instruction of a user;
The first matching module is used for matching the first content of the voice command with the content of the pre-recorded unlocking command;
the second matching module is used for matching the first voiceprint features of the voice command with the voiceprint features of the pre-input unlocking command in response to the fact that the first content is matched with the content of the pre-input unlocking command;
and the control module is used for controlling the door lock to be opened in response to the fact that the first voiceprint characteristic is matched with the voiceprint characteristic of the unlocking instruction.
9. A computer device, comprising: a memory; a processor; a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any of claims 1-7.
10. A computer readable storage medium, characterized in that the storage medium has stored therein a computer program which, when executed by a processor, implements the method of voice unlocking according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211551037.4A CN116092226A (en) | 2022-12-05 | 2022-12-05 | Voice unlocking method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211551037.4A CN116092226A (en) | 2022-12-05 | 2022-12-05 | Voice unlocking method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116092226A true CN116092226A (en) | 2023-05-09 |
Family
ID=86209232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211551037.4A Pending CN116092226A (en) | 2022-12-05 | 2022-12-05 | Voice unlocking method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116092226A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7158776B1 (en) * | 2001-09-18 | 2007-01-02 | Cisco Technology, Inc. | Techniques for voice-based user authentication for mobile access to network services |
| CN106022053A (en) * | 2016-05-26 | 2016-10-12 | 深圳市金立通信设备有限公司 | Unlocking method and device |
| CN107331400A (en) * | 2017-08-25 | 2017-11-07 | 百度在线网络技术（北京）有限公司 | A kind of Application on Voiceprint Recognition performance improvement method, device, terminal and storage medium |
| CN107798004A (en) * | 2016-08-29 | 2018-03-13 | 南京中兴新软件有限责任公司 | Keyword lookup method, apparatus and terminal |
| CN108806700A (en) * | 2018-06-08 | 2018-11-13 | 英业达科技有限公司 | The system and method for status is judged by vocal print and speech cipher |
| CN109118626A (en) * | 2018-08-08 | 2019-01-01 | 腾讯科技（深圳）有限公司 | Control method, device, storage medium and the electronic device of lockset |
| CN109273009A (en) * | 2018-08-02 | 2019-01-25 | 平安科技（深圳）有限公司 | Access control method, device, computer equipment and storage medium |
| CN110675880A (en) * | 2019-10-21 | 2020-01-10 | 北京声智科技有限公司 | Identity verification method and device and electronic equipment |
| CN111599074A (en) * | 2020-06-09 | 2020-08-28 | 苏州思必驰信息科技有限公司 | Building entrance guard registration method, use method and device |
| CN111768789A (en) * | 2020-08-03 | 2020-10-13 | 上海依图信息技术有限公司 | Electronic equipment and method, device and medium for determining identity of voice sender thereof |
| CN113536763A (en) * | 2021-07-20 | 2021-10-22 | 北京中科闻歌科技股份有限公司 | Information processing method, device, equipment and storage medium |
-
2022
- 2022-12-05 CN CN202211551037.4A patent/CN116092226A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7158776B1 (en) * | 2001-09-18 | 2007-01-02 | Cisco Technology, Inc. | Techniques for voice-based user authentication for mobile access to network services |
| CN106022053A (en) * | 2016-05-26 | 2016-10-12 | 深圳市金立通信设备有限公司 | Unlocking method and device |
| CN107798004A (en) * | 2016-08-29 | 2018-03-13 | 南京中兴新软件有限责任公司 | Keyword lookup method, apparatus and terminal |
| CN107331400A (en) * | 2017-08-25 | 2017-11-07 | 百度在线网络技术（北京）有限公司 | A kind of Application on Voiceprint Recognition performance improvement method, device, terminal and storage medium |
| CN108806700A (en) * | 2018-06-08 | 2018-11-13 | 英业达科技有限公司 | The system and method for status is judged by vocal print and speech cipher |
| CN109273009A (en) * | 2018-08-02 | 2019-01-25 | 平安科技（深圳）有限公司 | Access control method, device, computer equipment and storage medium |
| CN109118626A (en) * | 2018-08-08 | 2019-01-01 | 腾讯科技（深圳）有限公司 | Control method, device, storage medium and the electronic device of lockset |
| CN110675880A (en) * | 2019-10-21 | 2020-01-10 | 北京声智科技有限公司 | Identity verification method and device and electronic equipment |
| CN111599074A (en) * | 2020-06-09 | 2020-08-28 | 苏州思必驰信息科技有限公司 | Building entrance guard registration method, use method and device |
| CN111768789A (en) * | 2020-08-03 | 2020-10-13 | 上海依图信息技术有限公司 | Electronic equipment and method, device and medium for determining identity of voice sender thereof |
| CN113536763A (en) * | 2021-07-20 | 2021-10-22 | 北京中科闻歌科技股份有限公司 | Information processing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3345181B1 (en) | Speaker verification | |
| EP3327720B1 (en) | User voiceprint model construction method and apparatus | |
| JP6394709B2 (en) | SPEAKER IDENTIFYING DEVICE AND FEATURE REGISTRATION METHOD FOR REGISTERED SPEECH | |
| EP3518232B1 (en) | Verification of user identity for voice enabled devices | |
| CN108074310B (en) | Voice interaction method based on voice recognition module and intelligent lock management system | |
| CN109671185B (en) | Access control method and device | |
| US10476872B2 (en) | Joint speaker authentication and key phrase identification | |
| JP6096333B2 (en) | Method, apparatus and system for verifying payment | |
| WO2017197953A1 (en) | Voiceprint-based identity recognition method and device | |
| JP4588069B2 (en) | Operator recognition device, operator recognition method, and operator recognition program | |
| JP7123871B2 (en) | Identity authentication method, identity authentication device, electronic device and computer-readable storage medium | |
| CN106920303A (en) | A kind of method for unlocking and its intelligent door lock system based on speech recognition | |
| CN107240397A (en) | A kind of smart lock and its audio recognition method and system based on Application on Voiceprint Recognition | |
| CN108062464A (en) | Terminal control method and system based on Application on Voiceprint Recognition | |
| CN101772015A (en) | Method for starting up mobile terminal through voice password | |
| CN111883140A (en) | Authentication method, device, equipment and medium based on knowledge graph and voiceprint recognition | |
| CN109493494A (en) | Method for unlocking, device, equipment and medium based on smart lock | |
| CN104104664A (en) | Method, server, client and system for verifying verification code | |
| CN104462912B (en) | Improved biometric password security | |
| CN111684444A (en) | Identity authentication method, terminal equipment and storage medium | |
| CN110164455A (en) | Device, method and the storage medium of user identity identification | |
| CN112309406A (en) | Voiceprint registration method, voiceprint registration device and computer-readable storage medium | |
| CN110539721A (en) | vehicle control method and device | |
| Orken et al. | Development of security systems using DNN and i & x-vector classifiers | |
| CN111179945A (en) | Voiceprint recognition-based safety door control method and device |
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 |