CN109036438A - Storage cabinet control, device, computer equipment and storage medium - Google Patents

Storage cabinet control, device, computer equipment and storage medium Download PDF

Info

Publication number
CN109036438A
CN109036438A CN201810947490.4A CN201810947490A CN109036438A CN 109036438 A CN109036438 A CN 109036438A CN 201810947490 A CN201810947490 A CN 201810947490A CN 109036438 A CN109036438 A CN 109036438A
Authority
CN
China
Prior art keywords
locker
vocal print
print feature
default
target
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.)
Granted
Application number
CN201810947490.4A
Other languages
Chinese (zh)
Other versions
CN109036438B (en
Inventor
潘燕飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN201810947490.4A priority Critical patent/CN109036438B/en
Publication of CN109036438A publication Critical patent/CN109036438A/en
Application granted granted Critical
Publication of CN109036438B publication Critical patent/CN109036438B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/06—Decision making techniques; Pattern matching strategies
    • G10L17/14—Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
    • 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
    • G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
    • G07C9/00571—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys operated by interacting with a central unit
    • 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
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • 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
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/22—Interactive procedures; Man-machine interfaces
    • 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
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Game Theory and Decision Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Lock And Its Accessories (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

This application involves data processing technique, a kind of storage cabinet control, device, computer equipment and storage medium are provided.The described method includes: obtaining the voice messaging that speech detector detects；Target voice content is extracted from the voice messaging by speech recognition modeling, and target vocal print feature is extracted from the voice messaging by Application on Voiceprint Recognition model；The default voice content that inquiry matches with the target voice content, and the default vocal print feature to match with the target vocal print feature；When inquiring the default voice content and the default vocal print feature, inquiry locker mark corresponding with the default vocal print feature；Corresponding electromagnetic lock, which is identified, to the locker sends enabling control instruction；The enabling control instruction is used to indicate the electromagnetic lock and opens the corresponding locker of the locker mark.It is capable of the safety of locker using this method.

Description

Storage cabinet control, device, computer equipment and storage medium
Technical field
This application involves field of intelligent control technology, set more particularly to a kind of storage cabinet control, device, computer Standby and storage medium.
Background technique
With the development of intelligent control technology, each emporium and supermarket are designed with the self-service locker for accessing article, with Article is temporarily stored convenient for people, it is many convenient to bring to people's lives.Currently, locker is all to pass through bar codes technique It is managed and controls, is i.e. the voucher of unlatching locker cabinet door is the code-bar with bar code, by scanning code-bar Bar code opens locker cabinet door.
However, papery code-bar uses inconvenience, and is easily lost in this kind of storage cabinet control, to deposit In the lower problem of locker safety.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of locker control that can be improved locker safety Method, apparatus, computer equipment and storage medium processed.
A kind of storage cabinet control, which comprises
Obtain the voice messaging that speech detector detects；
Extract target voice content from the voice messaging by speech recognition modeling, and by Application on Voiceprint Recognition model from Target vocal print feature is extracted in the voice messaging；
The default voice content that inquiry matches with the target voice content, and with the target vocal print feature phase The default vocal print feature matched；
When inquiring the default voice content and the default vocal print feature, inquiry and the default vocal print feature phase Corresponding locker mark；
Corresponding electromagnetic lock, which is identified, to the locker sends enabling control instruction；The enabling control instruction is used to indicate The electromagnetic lock opens the locker and identifies corresponding locker.
Before the voice messaging that the acquisition speech detector detects in one of the embodiments, the method is also Include:
Obtain pickup instruction；
It is instructed according to the pickup and generates pickup code and shown by display；The pickup code is used as and target language The default voice content that sound content matches；
The voice messaging for obtaining speech detector and detecting, comprising:
Obtain the speech detector voice messaging detected according to pickup instruction；The voice messaging carries State pickup code.
The default voice content that the inquiry matches with the target voice content in one of the embodiments, with And the default vocal print feature to match with the target vocal print feature, comprising:
For pre-stored each candidate speech content, calculate separately in the candidate speech content and the target voice The first matching rate between appearance；
The candidate speech content that first matching rate is met to the first preset matching condition, be determined as in the target voice Hold the default voice content to match；
For each of pre-stored candidate vocal print feature, calculates separately the candidate vocal print feature and the target vocal print is special The second matching rate between sign；
The candidate vocal print feature that second matching rate is met to the second preset matching condition is determined as special with the target vocal print Levy the default vocal print feature to match.
In one of the embodiments, the method also includes:
When the electromagnetic lock, which opens the locker according to the enabling control instruction, identifies corresponding locker, delete Corresponding relationship between the locker mark and the default vocal print feature.
In one of the embodiments, it is described to the locker identify corresponding electromagnetic lock send enabling control instruction it Before, the method also includes:
It receives the locker and identifies the Item Information that corresponding article detection apparatus is detected and sent；
It is selected to put question to data from pre-stored problem set according to the Item Information；
According to the enquirement data generate it is corresponding put question to voice messaging, and described in the enquirements voice messaging is sent to Speech detector；
Obtain answer voice messaging corresponding with the enquirement voice messaging detected by the speech detector；
Corresponding answer data are extracted from the answer voice messaging by the speech recognition modeling；
Correct option corresponding with the enquirement data is determined according to the Item Information；
It is corresponding to generate enabling control instruction when the answer data and the correct option match.
In one of the embodiments, the method also includes:
Obtain speech detector according to deposit part instruction detected by deposit part voice messaging；
By Application on Voiceprint Recognition model from it is described deposit to extract in part voice messaging deposit part vocal print feature accordingly；
Selection locker identifies from candidate locker mark, and part vocal print feature is deposited described in foundation and the locker identifies Between corresponding relationship；
Part vocal print feature and locker mark are deposited by described, and the corresponding storage of the corresponding relationship established；Institute It states and deposits part vocal print spy as pre-stored default vocal print feature.
A kind of locker control device, described device include:
Obtain module, the voice messaging detected for obtaining speech detector；
Extraction module for extracting target voice content from the voice messaging by speech recognition modeling, and passes through Application on Voiceprint Recognition model extracts target vocal print feature from the voice messaging；
Matching module, for inquiring the default voice content to match with the target voice content, and with the mesh The default vocal print feature that mark vocal print feature matches；
Enquiry module, for when inquiring the default voice content and the default vocal print feature, inquiry with it is described Preset the corresponding locker mark of vocal print feature；
Sending module sends enabling control instruction for identifying corresponding electromagnetic lock to the locker；The enabling control System instruction is used to indicate the electromagnetic lock and opens the corresponding locker of the locker mark.
Described device in one of the embodiments, further include: removing module；
Removing module, it is corresponding according to the enabling control instruction unlatching locker mark for working as the electromagnetic lock When locker, the corresponding relationship between the locker mark and the default vocal print feature is deleted.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing Device performs the steps of when executing the computer program
Obtain the voice messaging that speech detector detects；
Extract target voice content from the voice messaging by speech recognition modeling, and by Application on Voiceprint Recognition model from Target vocal print feature is extracted in the voice messaging；
The default voice content that inquiry matches with the target voice content, and with the target vocal print feature phase The default vocal print feature matched；
When inquiring the default voice content and the default vocal print feature, inquiry and the default vocal print feature phase Corresponding locker mark；
Corresponding electromagnetic lock, which is identified, to the locker sends enabling control instruction；The enabling control instruction is used to indicate The electromagnetic lock opens the locker and identifies corresponding locker.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor It is performed the steps of when row
Obtain the voice messaging that speech detector detects；
Extract target voice content from the voice messaging by speech recognition modeling, and by Application on Voiceprint Recognition model from Target vocal print feature is extracted in the voice messaging；
The default voice content that inquiry matches with the target voice content, and with the target vocal print feature phase The default vocal print feature matched；
When inquiring the default voice content and the default vocal print feature, inquiry and the default vocal print feature phase Corresponding locker mark；
Corresponding electromagnetic lock, which is identified, to the locker sends enabling control instruction；The enabling control instruction is used to indicate The electromagnetic lock opens the locker and identifies corresponding locker.
Above-mentioned storage cabinet control, device, computer equipment and storage medium obtain the language that speech detector detects When message ceases, target voice content and target vocal print feature are extracted from accessed voice messaging respectively, to extracted Target voice content and target vocal print feature carry out double authentication and open corresponding locker when double authentication passes through.When looking into It askes the default voice content to match with target voice content and inquires the default sound that Speech Object vocal print feature matches When line feature, determine that double authentication passes through, inquire corresponding with default vocal print feature locker mark, and to the locker mark Know corresponding electromagnetic lock and send enabling control instruction, to open locker.This kind carries out double authentication based on voice messaging to control The method of locker processed can effectively improve locker safety.
Detailed description of the invention
Fig. 1 is the application scenario diagram of storage cabinet control in one embodiment；
Fig. 2 is the flow diagram of storage cabinet control in one embodiment；
Fig. 3 is the flow diagram of storage cabinet control in another embodiment；
Fig. 4 is the structural block diagram of locker control device in one embodiment；
Fig. 5 is the structural block diagram of locker control device in another embodiment；
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not For limiting the application.
Storage cabinet control provided by the present application can be applied in application environment as shown in Figure 1.Wherein, storing Cabinet controlling terminal 120 is electrically connected with electromagnetic lock 140, and locker controlling terminal 120 is led to by electric signal with electromagnetic lock 140 Letter.Locker controlling terminal 120 obtains the voice messaging that speech detector detects, respectively from the voice messaging more got Extract corresponding target voice content and target vocal print feature.When inquiring in the default voice to match with target voice content When holding and inquiring the default vocal print feature to match with target vocal print feature, the inquiry of locker controlling terminal 120 and default sound The corresponding locker mark of line feature, and identify corresponding electromagnetic lock 140 to the locker inquired and send control of opening the door Instruction, to open corresponding locker.Wherein, electromagnetic lock 140 is more than one, such as electromagnetic lock 1, electromagnetic lock 2,,, electromagnetic lock n. The locker of the corresponding control of locker controlling terminal 120 is more than one, such as locker 1, locker 2,,, locker n.Storage Object cabinet is corresponding with electromagnetic lock 140, i.e., each locker is corresponding with corresponding electromagnetic lock, for example, electromagnetic lock 1 and locker 1 it is right It answers, locker controlling terminal 120 controls corresponding locker by electromagnetic lock 140.
In one embodiment, as shown in Fig. 2, providing a kind of storage cabinet control, it is applied in Fig. 1 in this way Locker controlling terminal for be illustrated, comprising the following steps:
S202 obtains the voice messaging that speech detector detects.
Wherein, voice messaging is the speech detector audio-frequency information detected when user speaks.Voice messaging is to take Audio-frequency information with target voice content and target vocal print feature.Target voice content refers to the text transmitted when user speaks Perhaps information in word.Target vocal print feature is the tamber parameter for characterizing user voice feature.
Specifically, locker controlling terminal obtains voice messaging by speech detector.Locker controlling terminal is built-in with Speech detector, locker controlling terminal detect the voice messaging in specified range by built-in speech detector.Voice inspection It surveys device and is also possible to the individual components with locker controlling terminal point-to-point connection.Speech detector detects the language in specified range Message breath, and detected voice messaging is sent to locker controlling terminal.Wherein, specified range is preassigned area Domain range.
In one embodiment, speech detector can be microphone, specifically can be directional microphone.Directive property wheat Gram wind can detecte the voice messaging in assigned direction specified range.Acquiring voice messaging by directional microphone can be effective Reduce influence of the ambient noise to target voice content and target vocal print feature is extracted.
In one embodiment, it when locker controlling terminal gets pickup instruction, is instructed according to accessed pickup Speech detector is opened, voice messaging is detected by speech detector.Pickup instruction is to be triggered according to detected by user Specified pickup operation triggering generate.Trigger action of the specified pickup operation such as user to specified pickup control.
In one embodiment, locker controlling terminal is detected in specified range by infrared sensor or heat sensor There are when target user, the speech prompt information for indicating input pickup password, such as mesh are pushed to target user by loudspeaker Mark the speech prompt information that voice content is " please say pickup password ".Further, locker controlling terminal is examined by voice It surveys device detection target user and is directed to the voice messaging that speech prompt information is fed back.In the present embodiment, the step that loudspeaker is realized Suddenly it can also be realized by speech detector.
S204 extracts target voice content by speech recognition modeling from voice messaging, and passes through Application on Voiceprint Recognition model Target vocal print feature is extracted from voice messaging.
Wherein, speech recognition modeling is to carry out model training acquisition, Neng Gouyong according to the training sample set obtained in advance In the model for extracting corresponding target voice content from acquired voice messaging.It includes multiple targets that the training sample, which is concentrated, Target voice content corresponding to voice messaging and each target voice information.Application on Voiceprint Recognition model is according to the instruction obtained in advance Practice sample set carry out model training acquisition, can be used in from acquired voice messaging extracting corresponding target vocal print feature Model.It includes that target vocal print corresponding to multiple target voice information and each target voice information is special that the training sample, which is concentrated, Sign.Multiple target voice information that training sample for training speech recognition modeling is concentrated, and for training Application on Voiceprint Recognition mould Multiple target voice information that the training sample of type is concentrated can be the same or different.
Specifically, locker controlling terminal passes through preparatory trained speech recognition modeling from accessed voice messaging It is middle to extract corresponding target voice content, and extracted from the voice messaging accordingly by preparatory trained Application on Voiceprint Recognition model Target vocal print feature.
In one embodiment, locker controlling terminal obtains multiple target voice information, and determines each target respectively Target voice content and target vocal print feature in voice messaging.Locker controlling terminal is special using target voice information as input Sign is trained acquisition to the speech recognition modeling of initialization using corresponding target voice content as the output feature expected The speech recognition modeling that training is completed.Similarly, locker controlling terminal is using target voice information as input feature vector, accordingly Target vocal print feature is trained the sound for obtaining training and completing to the Application on Voiceprint Recognition model of initialization as desired output feature Line identification model.Wherein, sound-groove model such as artificial neural network (ANN), hidden Markov model (HMM) and Gaussian Mixture mould Type (GMM) etc..
In one embodiment, speech recognition modeling and vocal print identification model can be trained in advance by other computer equipments It is good, then it is transplanted to locker controlling terminal.Alternatively, will be via other computer equipments trained speech recognition modeling in advance And/or Application on Voiceprint Recognition model, it is burnt in the processor built in locker controlling terminal.
S206, the default voice content that inquiry matches with target voice content, and match with target vocal print feature Default vocal print feature.
Wherein, default voice content is preset voice content.Default voice content specifically can be in advance from pre- If the voice content for extracting and being pre-stored in voice messaging.Similarly, default vocal print feature is preset vocal print feature, tool Body can be the vocal print feature extracted and be pre-stored from default voice messaging in advance.Default voice messaging is preset language Message breath specifically can be and deposit voice messaging acquired, corresponding with part user is deposited during part.
Specifically, locker controlling terminal is according to the target voice content extracted from voice messaging, inquiry and the target The default voice content that voice content matches.Locker controlling terminal is special according to the target vocal print extracted from voice messaging Sign, the default vocal print feature that inquiry matches with the target vocal print feature.
In one embodiment, locker controlling terminal is by the target voice content extracted and pre-stored candidate language Sound content is matched respectively, and the candidate speech content of successful match is determined as matching with extracted target voice content Default voice content.Similarly, locker controlling terminal is by extracted target vocal print feature and pre-stored candidate vocal print Feature is matched respectively, and the candidate vocal print feature of successful match is determined as matching with extracted target vocal print feature Default vocal print feature.
In one embodiment, locker controlling terminal is pre-stored between candidate speech content and candidate vocal print feature Corresponding relationship.Locker controlling terminal successively carries out extracted target voice content with pre-stored candidate speech content Match.When successful match, locker controlling terminal stops between currently performed target voice content and candidate speech content Matching operation inquires candidate vocal print feature corresponding with the candidate speech content according to the candidate speech content of successful match, and The candidate vocal print feature inquired is matched with the target vocal print feature extracted.When candidate's vocal print feature and mesh When marking vocal print feature successful match, locker controlling terminal stop currently performed candidate vocal print feature and target vocal print feature it Between matching operation, and the candidate speech content of successful match is determined as default voice content, and by the time of successful match Vocal print feature is selected to be determined as default vocal print feature.
Further, when it fails to match for candidate's vocal print feature and target vocal print feature, locker controlling terminal continues Matching operation between performance objective voice content and candidate speech content.In currently performed target voice content and candidate language When matching result corresponding to matching operation between sound content is that it fails to match, locker controlling terminal continues to execute target language Matching operation between sound content and candidate speech content.Between currently performed target voice content and candidate speech content Matching operation corresponding to matching result be successful match when, locker controlling terminal execute it is above-mentioned according to candidate speech content The correlation step of query candidate vocal print feature.
In one embodiment, locker control equipment extracts target voice content and target vocal print from voice messaging When feature, pre-stored candidate speech content and candidate vocal print feature are read.Locker controlling terminal is from read candidate language The determining default voice content to match with target voice content in sound content, and determined from read candidate vocal print feature The default vocal print feature to match with target vocal print feature.
In one embodiment, locker controlling terminal is inquired in memory presets with what target voice content matched Voice content, and the default vocal print feature to match with target vocal print feature.Memory can be built in locker control eventually End, is also possible to the individual components with locker controlling terminal point-to-point connection.
S208 is inquired corresponding with default vocal print feature when inquiring default voice content and default vocal print feature Locker mark.
Wherein, locker mark is used for unique identification locker.Locker mark specifically can be by number, letter and symbol The character string of at least one of characters such as conjunction composition.Locker mark is corresponding with candidate vocal print feature, and locker control is eventually End is pre-stored with the corresponding relationship between locker mark and candidate vocal print feature.
Specifically, when locker controlling terminal inquires in the default voice to match with extracted target voice content When holding and inquiring the default vocal print feature to match with extracted target vocal print feature, locker controlling terminal is according to institute The default vocal print feature inquired, inquiry locker mark corresponding with the default vocal print feature.
In one embodiment, locker controlling terminal is pre-stored with candidate speech content, candidate vocal print feature and storing Corresponding relationship between cabinet mark.When inquired from pre-stored candidate speech content match with target voice content it is pre- If voice content and inquiring the default vocal print feature to match with target vocal print feature from pre-stored candidate vocal print feature When, locker is identified according to the default voice content and default vocal print feature inquired, is looked into according to corresponding corresponding relationship Ask corresponding locker mark.
In one embodiment, locker controlling terminal is pre-stored with candidate speech content, candidate vocal print feature and user Corresponding relationship between corresponding relationship and user identifier between mark and locker mark.Locker controlling terminal according to The default voice content inquired and default vocal print feature inquire corresponding user identifier, and then according to the user inquired Mark inquires corresponding locker mark.
In one embodiment, the corresponding relationship being stored in memory between default vocal print feature and locker mark. When inquiring default voice content and default vocal print feature, locker controlling terminal is according to default vocal print feature, in memory Middle inquiry locker mark corresponding with the default vocal print feature.
S210 identifies corresponding electromagnetic lock to locker and sends enabling control instruction；Enabling control instruction is used to indicate electricity Magnetic padlock opens locker and identifies corresponding locker.
Wherein, enabling control instruction is to open the corresponding electromagnetic lock of locker, for triggering to open corresponding locker Instruction.Enabling control instruction specifically can be low and high level.
Specifically, when inquire locker corresponding with default vocal print feature mark when, locker controlling terminal according to The locker mark inquired inquires electromagnetic lock mark corresponding with locker mark.When inquire and locker mark pair When the electromagnetic lock mark answered, locker controlling terminal identifies corresponding electromagnetic lock to the electromagnetic lock and sends enabling control instruction.Electricity Enabling control instruction opens corresponding locker to magnetic padlock based on the received, i.e. electromagnetic lock executes unlocking according to enabling control instruction Operation, to open corresponding locker.
In one embodiment, when inquiring default voice content and default vocal print feature, locker controlling terminal pair Enabling control instruction should be generated.Locker controlling terminal can also be when inquiring locker mark, according to the storage inquired Object cabinet mark generates corresponding enabling control instruction.Locker controlling terminal can also inquire it is corresponding with locker mark When electromagnetic lock identifies, corresponding enabling control instruction is generated according to the electromagnetic lock mark inquired.
In one embodiment, the corresponding relationship being stored in memory between locker mark and electromagnetic lock mark.Storage Object cabinet controlling terminal inquires corresponding corresponding relationship according to locker mark in memory.
Above-mentioned storage cabinet control, when obtaining the voice messaging that speech detector detects, respectively from accessed Target voice content and target vocal print feature are extracted in voice messaging, to extracted target voice content and target vocal print feature It carries out double authentication and opens corresponding locker when double authentication passes through.Match when inquiring with target voice content When presetting voice content and inquiring the default vocal print feature that Speech Object vocal print feature matches, determine that double authentication passes through, Locker mark corresponding with default vocal print feature is inquired, and identifies corresponding electromagnetic lock to the locker and sends control of opening the door Instruction, to open locker.This kind carries out double authentication based on voice messaging come the method for controlling locker, can effectively improve Locker safety.
In one embodiment, before step S202, above-mentioned storage cabinet control further include: obtain pickup instruction；Root It is instructed according to pickup and generates pickup code and shown by display；Pickup code is used as to be preset with what target voice content matched Voice content；Step S202 includes: to obtain the speech detector voice messaging detected according to pickup instruction；Voice messaging is taken With pickup code.
Wherein, pickup instruction is the instruction by specifying pickup to operate triggering.Pickup is instructed for triggering correlation when pickup Authentication operation.Specified pickup operation such as user is to the click or cunning on the pressing operation or touch screen of specified pickup button Dynamic operation.Pickup instruction is used to indicate locker controlling terminal and authenticates to the user for triggering specified pickup operation, and is recognizing Card opens corresponding locker when passing through.Pickup code can be the character string being made of number and/or letter, such as 1357.
Specifically, when detecting the specified pickup operation of user's triggering, locker controlling terminal is according to detected Specified pickup operation generates corresponding pickup instruction.Locker controlling terminal instructs random generate accordingly according to pickup generated Pickup code, and pickup code generated is shown by display.Locker controlling terminal is by pickup code generated It is stored in local as candidate speech content, in order to from pre-stored candidate speech content, look into locker controlling terminal When inquiry is with the default voice content that extracted target voice content matches from voice messaging, locker controlling terminal should Pickup code is as the default voice content to match with target voice content inquired.
Further, when locker controlling terminal shows pickup code generated by display, pickup is instructed and is sent To speech detector.When speech detector receives pickup instruction, real-time detection carries the voice messaging of pickup code, and by institute The voice messaging detected is sent to locker controlling terminal.
In one embodiment, locker controlling terminal is instructed according to pickup and is generated accordingly according to specified pickup code format Pickup code, and pickup code generated is sent to display, it is shown by display.Wherein, pickup code format ratio is specified Such as 6 bit digitals.In one embodiment, display can be built in locker controlling terminal, be also possible to control with locker The individual components of terminal point-to-point connection.In one embodiment, locker controlling terminal is logical according to predetermined period dynamic refresh Cross pickup code shown by display.
In one embodiment, speech detector is built-in in locker controlling terminal.Locker controlling terminal is according to taking Speech detector is opened in part instruction, to detect voice messaging by speech detector.
For example, the generation of locker controlling terminal takes accordingly when detecting the specified pickup operation of user's triggering Part instruction, instructs according to pickup and generates pickup code, and pickup code is shown to user by display.User is according to display institute The pickup code triggering of display carries the voice messaging of the pickup code, in order to which locker controlling terminal is according to the voice messaging pair The identity of the user authenticates.
In above-described embodiment, is instructed according to pickup and generate pickup code and be shown to user, in case user forgets default pickup Password and lead to not pickup, pickup efficiency is improved, to improve locker control efficiency.
In one embodiment, step S206 includes: to calculate separately candidate for pre-stored each candidate speech content The first matching rate between voice content and target voice content；First matching rate is met to the candidate of the first preset matching condition Voice content is determined as the default voice content to match with target voice content；It is special for each of pre-stored candidate vocal print Sign, calculates separately the second matching rate between candidate vocal print feature and target vocal print feature；It is pre- that second matching rate is met second If the candidate vocal print feature of matching condition is determined as the default vocal print feature to match with target vocal print feature.
Wherein, candidate speech content is to be pre-stored during depositing part, may be confirmed as default language by matching operation The voice content of sound content.First matching rate refers to the matching degree between candidate speech content and target voice content.First Preset matching condition is for the default voice content to match with target voice content determining from multiple candidate speech contents Constraint condition, for example the first matching rate reaches the first matching rate threshold value.
Similarly, candidate vocal print feature is to be pre-stored during depositing part, may be confirmed as presetting by matching operation The vocal print feature of vocal print feature.Second matching rate refers to the matching degree between candidate vocal print feature and target vocal print feature.The Two preset matching conditions are for the default vocal print spy to match with target vocal print feature determining from multiple candidate vocal print features The constraint condition of sign, such as the second matching rate reach the second matching rate threshold value.
In one embodiment, locker controlling terminal calculates separately pre-stored each candidate speech content and is extracted Target voice content between the first matching rate, each first matching rate is compared with the first matching rate threshold value respectively, The candidate speech content that first matching rate is reached to the first matching rate threshold value is determined as matching with target voice content default Voice content.In one embodiment, locker controlling terminal obtains the first matching rate corresponding to each candidate speech content When, maximum first matching rate of numerical value is screened from multiple first matching rate, by the first matching rate filtered out and first It is compared with rate threshold value.When first matching rate filtered out reaches the first matching rate threshold value, locker controlling terminal will The corresponding candidate speech content of the first matching rate filtered out is determined as default voice content.Similarly, locker control is whole End determining default vocal print feature to match with target vocal print feature from multiple candidate vocal print features according to above-mentioned processing logic.
In one embodiment, multiple candidate speech contents and multiple candidate vocal print features are stored in memory.Storing Cabinet controlling terminal is out of determining in the candidate speech content that memory is pre-stored the default voice to match with target voice content Hold, and the determining default vocal print to match with target vocal print feature is special from the candidate vocal print feature being pre-stored in memory Sign.
In above-described embodiment, according to the first matching rate and the second matching rate of calculating, respectively from multiple candidate speech contents Default voice content and default vocal print feature are determined in multiple candidate vocal print features, improve default voice content and default sound The accuracy rate and efficiency that line feature determines, to improve locker control efficiency, and improve the safety of locker.
In one embodiment, above-mentioned storage cabinet control further include: when electromagnetic lock is opened according to enabling control instruction When locker identifies corresponding locker, the corresponding relationship between locker mark and default vocal print feature is deleted.
Specifically, when electromagnetic lock, which opens locker according to enabling control instruction, identifies corresponding locker, locker control Terminal processed is identified according to locker, is inquired the corresponding relationship between locker mark and corresponding default vocal print feature, that is, is inquired Corresponding relationship between locker mark and the candidate vocal print feature as default vocal print feature.When inquiring corresponding relationship When, locker controlling terminal deletes inquired corresponding relationship.
In one embodiment, when deleting the corresponding relationship between locker mark and default vocal print feature, locker Controlling terminal deletes candidate vocal print feature corresponding with locker mark, and candidate corresponding with candidate's vocal print feature Voice content, and delete the candidate vocal print feature and candidate speech content inquired.In one embodiment, locker controls Terminal deletion instructs the pickup code for generating and storing according to pickup.
In one embodiment, when opening locker, locker controlling terminal deletes the locker pair in memory The corresponding corresponding relationship of the locker mark answered.
In one embodiment, when electromagnetic lock opens corresponding locker according to enabling control instruction, locker control is eventually The corresponding relationship delete operation of end detection user's triggering.When detecting corresponding relationship delete operation, locker control instruction pair The corresponding relationship between corresponding locker mark and default vocal print feature should be deleted.The such as user's pickup of corresponding relationship delete operation And when closing locker, to the pressing operation of designated button, or in the sliding of touch screen or the click of designated position.Such energy Enough user is facilitated to reuse locker, effectively prevents needing the problem of re-replacing locker when the pickup of midway.
In above-described embodiment, when opening locker according to enabling control instruction, correspondence corresponding to the locker is deleted Relationship in order to which the locker is recycled, and can be avoided and pass through because of historical user according to the corresponding relationship of historical storage The article of active user is authenticated and stolen, locker safety is improved.
In one embodiment, before identifying corresponding electromagnetic lock transmission enabling control instruction to locker, method is also wrapped It includes: receiving locker and identify the Item Information that corresponding article detection apparatus is detected and sent；According to Item Information from pre-stored The problem of set in selection put question to data；Voice messaging is putd question to accordingly according to puing question to data to generate, and will put question to voice messaging It is sent to speech detector；Obtain answer voice messaging corresponding with voice messaging is putd question to detected by speech detector；It is logical It crosses speech recognition modeling and extracts corresponding answer data from answer voice messaging；It is determined according to Item Information and puts question to data pair The correct option answered；It is corresponding to generate enabling control instruction when answer data and correct option match.
Wherein, article detection apparatus is the device for acquiring Item Information in locker, for example camera or X-ray are swept Retouch instrument etc..Item Information is the information of the article for describing to be stored in locker.Item Information can specifically include article Title, color, type or number of packages etc..Item Information specifically can be it is shooting and send by camera, comprising locker The pictorial information of middle stored article is also possible to the scanned picture information for scanning and sending by x-ray scanning instrument.
The set that problem set is made of multiple enquirement data.Data are putd question to refer to the problem of puing question to accordingly topic number According to, such as " please at least saying a kind of article that you are stored ".Put question to taking according to enquirement data corresponding generation when voice messaging Voice messaging with the enquirement data.Answer data refer to user for the corresponding feedback of enquirement data putd question in voice messaging Voice messaging, user is carried in the voice messaging for the answer data for puing question to data, the i.e. answer of user.
Specifically, when inquiring locker mark, locker controlling terminal identifies corresponding Articles detecting to locker Device sends Articles detecting instruction, so that the article detection apparatus corresponding storing of Articles detecting command detection based on the received The Item Information of cabinet, and detected Item Information is sent to locker controlling terminal.Locker controlling terminal is according to institute The Item Information received is randomly choosed from pre-stored problem set puts question to data, is generated according to selected enquirement data It is corresponding to put question to voice messaging, and enquirement voice messaging generated is pushed into user by speech detector.Locker control Terminal processed obtains user for the answer voice messaging for the enquirement data feedback putd question in voice messaging by speech detector, and Corresponding answer data are extracted from acquired answer voice messaging by preparatory trained speech recognition modeling.
Further, when locker controlling terminal selects to put question to data from problem set, according to accessed article Information determines correct option corresponding to selected enquirement data, and by identified correct option and from answer voice messaging Extracted answer data are matched.When successful match, the triggering of locker controlling terminal generates enabling control instruction, and will Enabling control instruction generated is sent to electromagnetic lock.
In one embodiment, locker controlling terminal determines the matching rate between correct option and answer data, when this When matching rate reaches preset matching rate threshold value, triggering generates corresponding enabling control instruction.
In one embodiment, problem set is pre-stored in memory.Locker controlling terminal is based on the received Data are putd question in Item Information selection from the problem set that memory is pre-stored.
In above-described embodiment, when the certification based on voice messaging passes through, based on the Item Information in locker to corresponding User puts question to, and further to verify the identity of user, passes through identity in a manner of imitation or recorded speech information to avoid other people The problem of authenticating and article is caused to be lost improves locker safety.
In one embodiment, above-mentioned storage cabinet control further include: obtain speech detector according to part is deposited and instruct institute What is detected deposits part voice messaging；Part vocal print feature is deposited accordingly from extraction in part voice messaging is deposited by Application on Voiceprint Recognition model； The selection locker mark from candidate locker mark, establishes the corresponding relationship deposited between part vocal print feature and locker mark； Part vocal print feature and locker mark will be deposited, and the corresponding storage of the corresponding relationship established；Deposit part vocal print spy be used as it is pre-stored Default vocal print feature.
Wherein, depositing part instruction is by the specified instruction deposited part and operate triggering.Specifying and depositing part operation is preassigned user Deposit trigger action when part, for example, user to the specified pressing operation for depositing part button or user to designated position on touch screen The click at place or slide.Depositing part instruction and being used to indicate locker controlling terminal is the specified user's distribution for depositing part operation of triggering Locker, and open distributed locker.Candidate locker mark, which refers to, may be selected as and deposit the foundation of part vocal print feature The locker of corresponding relationship identifies.It is the locker for being currently at idle state that candidate locker, which identifies corresponding locker,.
Specifically, locker controlling terminal detect user triggering it is specified deposit part operation when, according to detected finger Surely deposit part operation generate accordingly deposit part instruction, and by it is generated deposit part instruction be sent to speech detector.Speech detector That deposits part command detection relative users based on the received deposits part voice messaging, and part voice messaging detected of depositing is sent To locker controlling terminal.Locker controlling terminal passes through preparatory trained Application on Voiceprint Recognition model and deposits part language from received It is extracted in message breath and deposits part vocal print feature accordingly.Locker controlling terminal query candidate locker mark, when inquiring candidate When locker identifies, the selection locker mark from the candidate locker mark inquired, and establish selected locker Mark and the extracted corresponding relationship deposited between part vocal print feature.
Further, locker controlling terminal deposits part vocal print feature as candidate vocal print feature storage to originally for extracted Ground, in order to which in the pickup verification process for relative users, which is determined as by locker controlling terminal The default vocal print feature to match with the vocal print feature of the user.Locker controlling terminal by established deposit part vocal print feature with Corresponding relationship between locker mark is pre-stored.
In one embodiment, locker controlling terminal establishes the corresponding pass deposited between part vocal print feature and locker mark After system, part vocal print feature and locker mark and corresponding relationship storage will be deposited in memory.
In one embodiment, when get deposit part instruction when, locker controlling terminal pass through built-in speech detector Part voice messaging is deposited in detection accordingly.
In one embodiment, locker controlling terminal correspondence determines whether there is the storing for being currently at idle state Cabinet, when there is the locker for being currently at idle state, by the corresponding locker of the locker for being currently at idle state Mark is determined as candidate locker mark.
In one embodiment, locker controlling terminal inquiry pre-stored locker mark and corresponding candidate vocal print feature Between corresponding relationship, candidate locker mark is determined according to the corresponding relationship inquired and default locker identification list. Specifically, each locker preset in locker identification list is identified, the inquiry of locker controlling terminal and the locker Identify corresponding corresponding relationship.When not inquiring corresponding relationship, locker controlling terminal identifies corresponding locker true It is set to candidate locker mark.Default locker identification list locker corresponding to each locker identifies the collection formed It closes.
In one embodiment, locker controlling terminal passes through preparatory trained speech recognition modeling and believes from part voice is deposited Breath, which extracts, deposits part voice content accordingly, and deposits part voice content using extracted as candidate speech content and be stored in local. In one embodiment, locker controlling terminal part vocal print feature and deposits part voice from depositing to extract to deposit respectively in part voice messaging Corresponding relationship when content, established and deposit part vocal print feature, deposit part voice content between selected locker mark, and by institute The corresponding relationship of foundation is stored to local.In one embodiment, locker controlling terminal establish respectively deposit part vocal print feature and Corresponding relationship between locker mark, and deposit part vocal print feature and deposit the corresponding relationship between part voice content.
In above-described embodiment, get deposit part instruction when, based on detected part voice messaging of depositing to depositing accordingly Part vocal print feature is registered, in order to be authenticated based on the part vocal print feature of depositing registered to user during pickup, Locker control efficiency is improved, ensure that locker safety.
As shown in figure 3, in one embodiment, providing a kind of storage cabinet control, this method specifically includes following Step:
S302 obtains pickup instruction.
S304 is instructed according to pickup and is generated pickup code and shown by display；Pickup code is used as and target voice The default voice content that content matches.
S306 obtains the speech detector voice messaging detected according to pickup instruction；Voice messaging carries pickup Code.
S308 extracts target voice content by speech recognition modeling from voice messaging, and passes through Application on Voiceprint Recognition model Target vocal print feature is extracted from voice messaging.
S310 calculates separately candidate speech content and target voice content for pre-stored each candidate speech content Between the first matching rate.
First matching rate is met the candidate speech content of the first preset matching condition by S312, is determined as and target voice The default voice content that content matches.
S314 calculates separately candidate vocal print feature and target vocal print feature for each of pre-stored candidate vocal print feature Between the second matching rate.
Second matching rate is met the candidate vocal print feature of the second preset matching condition by S316, is determined as and target vocal print The default vocal print feature that feature matches.
S318 is inquired corresponding with default vocal print feature when inquiring default voice content and default vocal print feature Locker mark.
S320 receives locker and identifies the Item Information that corresponding article detection apparatus is detected and sent.
S322 selects to put question to data from pre-stored problem set according to Item Information.
S324 puts question to voice messaging according to puing question to data to generate accordingly, and voice messaging will be putd question to be sent to voice inspection Survey device.
S326 obtains answer voice messaging corresponding with voice messaging is putd question to detected by speech detector.
S328 extracts corresponding answer data by speech recognition modeling from answer voice messaging.
S330 determines correct option corresponding with data are putd question to according to Item Information.
S332, it is corresponding to generate enabling control instruction when answer data match with correct option.
S334 identifies corresponding electromagnetic lock to locker and sends enabling control instruction；Enabling control instruction is used to indicate electricity Magnetic padlock opens locker and identifies corresponding locker.
S336 deletes locker when electromagnetic lock, which opens locker according to enabling control instruction, identifies corresponding locker Corresponding relationship between mark and default vocal print feature.
In above-described embodiment, pickup code is generated according to accessed pickup instruction, and detect the language for carrying pickup code Message breath, and then based in the voice messaging target voice content and target vocal print feature user identity is authenticated, when Certification verifies user identity based on Item Information corresponding to corresponding locker when passing through again, opens when being verified Corresponding locker is opened, and deletes corresponding corresponding relationship.In this way, repeatedly being authenticated, being mentioned to user identity during pickup High locker safety.
In one embodiment, in above-mentioned each embodiment, locker controlling terminal execute the step of specifically can be by built-in It is executed in the processor of the locker controlling terminal.
It should be understood that although each step in the flow chart of Fig. 2 and Fig. 3 is successively shown according to the instruction of arrow, But these steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these There is no stringent sequences to limit for the execution of step, these steps can execute in other order.Moreover, in Fig. 2 and Fig. 3 At least part step may include that perhaps these sub-steps of multiple stages or stage are not necessarily same to multiple sub-steps One moment executed completion, but can execute at different times, and the execution in these sub-steps or stage sequence is also not necessarily Be successively carry out, but can at least part of the sub-step or stage of other steps or other steps in turn or Alternately execute.
In one embodiment, as shown in figure 4, providing a kind of locker control device 400, comprising: obtain module 402, extraction module 404, matching module 406, enquiry module 408 and sending module 410, in which:
Obtain module 402, the voice messaging detected for obtaining speech detector.
Extraction module 404 for extracting target voice content from voice messaging by speech recognition modeling, and passes through sound Line identification model extracts target vocal print feature from voice messaging.
Matching module 406, for inquiring the default voice content to match with target voice content, and with target vocal print The default vocal print feature that feature matches.
Enquiry module 408, for when inquiring default voice content and default vocal print feature, inquiry to be special with default vocal print Levy corresponding locker mark.
Sending module 410 sends enabling control instruction for identifying corresponding electromagnetic lock to locker；Enabling control instruction It is used to indicate electromagnetic lock and opens the corresponding locker of locker mark.
In one embodiment, module 402 is obtained, is also used to obtain pickup instruction；It is instructed according to pickup and generates pickup code And it is shown by display；Pickup code is used as the default voice content to match with target voice content；It is also used to obtain The speech detector voice messaging detected according to pickup instruction；Voice messaging carries pickup code.
In one embodiment, matching module 406 are also used to count pre-stored each candidate speech content respectively Calculate the first matching rate between candidate speech content and target voice content；First matching rate is met into the first preset matching condition Candidate speech content, be determined as the default voice content to match with target voice content；For pre-stored each candidate Vocal print feature calculates separately the second matching rate between candidate vocal print feature and target vocal print feature；Second matching rate is met The candidate vocal print feature of second preset matching condition is determined as the default vocal print feature to match with target vocal print feature.
As shown in figure 5, in one embodiment, locker control device 400 further include: removing module 412；
Removing module 412 is used for when electromagnetic lock opens locker according to enabling control instruction and identifies corresponding locker, Delete the corresponding relationship between locker mark and default vocal print feature.
In one embodiment, locker control device 400 further include: question and answer module 414；
Question and answer module 414 identifies the Item Information that corresponding article detection apparatus is detected and sent for receiving locker； It is selected to put question to data from pre-stored problem set according to Item Information；Believe according to puing question to data to generate corresponding enquirement voice Breath, and voice messaging will be putd question to be sent to speech detector；Obtain speech detector detected by with put question to voice messaging pair The answer voice messaging answered；Corresponding answer data are extracted from answer voice messaging by speech recognition modeling；According to article Information determines correct option corresponding with data are putd question to；It is corresponding to generate control of opening the door when answer data and correct option match System instruction.
In one embodiment, locker control device 400 further include: deposit part registration module 416；
Deposit part registration module 416, for obtain speech detector according to deposit part instruction it is detected deposit part voice messaging； Part vocal print feature is deposited accordingly from extraction in part voice messaging is deposited by Application on Voiceprint Recognition model；It is selected from candidate locker mark Locker mark establishes the corresponding relationship deposited between part vocal print feature and locker mark；Part vocal print feature and locker will be deposited Mark, and the corresponding storage of corresponding relationship established；It deposits part vocal print spy and is used as pre-stored default vocal print feature.
Specific about locker control device limits the restriction that may refer to above for storage cabinet control, This is repeated no more.Modules in above-mentioned locker control device can come fully or partially through software, hardware and combinations thereof It realizes.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with software Form is stored in the memory in computer equipment, executes the corresponding operation of the above modules in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be locker controlling terminal, Its internal structure chart can be as shown in Figure 6.The computer equipment includes the processor connected by system bus, memory, leads to Believe interface, speech detector and display.Wherein, the processor of the computer equipment is for providing calculating and control ability.It should The memory of computer equipment includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operation System, computer program and database.The built-in storage is operating system and computer program in non-volatile memory medium Operation provide environment.The database of the computer equipment is used to store the candidate vocal print feature and time being pre-stored in registration process Select the corresponding relationship between voice content, and candidate vocal print feature and locker mark.The network interface of the computer equipment For being communicated with external terminal by network connection.To realize a kind of locker control when the computer program is executed by processor Method processed.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with Computer program, which performs the steps of when executing computer program obtains the voice letter that speech detector detects Breath；Target voice content is extracted from voice messaging by speech recognition modeling, and passes through Application on Voiceprint Recognition model from voice messaging Middle extraction target vocal print feature；The default voice content that inquiry matches with target voice content, and with target vocal print feature The default vocal print feature to match；When inquiring default voice content and default vocal print feature, inquiry and default vocal print feature Corresponding locker mark；Corresponding electromagnetic lock, which is identified, to locker sends enabling control instruction；Enabling control instruction is used for Indicate that electromagnetic lock opens locker and identifies corresponding locker.
In one embodiment, it is realized when processor executes computer program and obtains the voice letter that speech detector detects Before the step of breath, also performs the steps of and obtain pickup instruction；According to pickup instruct generate pickup code and by display into Row display；Pickup code is used as the default voice content to match with target voice content；Obtain the language that speech detector detects Message breath, comprising: obtain the speech detector voice messaging detected according to pickup instruction；Voice messaging carries pickup Code.
In one embodiment, inquire the default voice content to match with target voice content, and with target vocal print The default vocal print feature that feature matches, comprising: for pre-stored each candidate speech content, calculate separately in candidate speech Hold the first matching rate between target voice content；In the candidate speech that first matching rate is met to the first preset matching condition Hold, is determined as the default voice content to match with target voice content；For each of pre-stored candidate vocal print feature, respectively Calculate the second matching rate between candidate vocal print feature and target vocal print feature；Second matching rate is met into the second preset matching item The candidate vocal print feature of part is determined as the default vocal print feature to match with target vocal print feature.
In one embodiment, it also performs the steps of when processor executes computer program when electromagnetic lock is according to enabling When control instruction opens locker mark corresponding locker, locker mark pass corresponding between default vocal print feature is deleted System.
In one embodiment, realize that identifying corresponding electromagnetic lock to locker sends when processor executes computer program Before the step of enabling control instruction, also performs the steps of and receive the corresponding article detection apparatus detection of locker mark simultaneously The Item Information of transmission；It is selected to put question to data from pre-stored problem set according to Item Information；It is generated according to enquirement data It is corresponding to put question to voice messaging, and voice messaging will be putd question to be sent to speech detector；It obtains detected by speech detector Answer voice messaging corresponding with voice messaging is putd question to；It is extracted from answer voice messaging by speech recognition modeling and is answered accordingly Inscribe data；Correct option corresponding with data are putd question to is determined according to Item Information；When answer data and correct option match, It is corresponding to generate enabling control instruction.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains speech detector root Part voice messaging is deposited detected by part instruction according to depositing；It is deposited accordingly by Application on Voiceprint Recognition model from extraction in part voice messaging is deposited Part vocal print feature；The selection locker mark from candidate locker mark, foundation are deposited between part vocal print feature and locker mark Corresponding relationship；Part vocal print feature and locker mark will be deposited, and the corresponding storage of the corresponding relationship established；Deposit part vocal print spy use Make pre-stored default vocal print feature.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated Machine program performs the steps of when being executed by processor obtains the voice messaging that speech detector detects；Pass through speech recognition Model extracts target voice content from voice messaging, and target vocal print spy is extracted from voice messaging by Application on Voiceprint Recognition model Sign；The default voice content that inquiry matches with target voice content, and the default vocal print to match with target vocal print feature Feature；When inquiring default voice content and default vocal print feature, locker mark corresponding with default vocal print feature is inquired Know；Corresponding electromagnetic lock, which is identified, to locker sends enabling control instruction；Enabling control instruction is used to indicate electromagnetic lock and opens storage Object cabinet identifies corresponding locker.
In one embodiment, it is realized when computer program is executed by processor and obtains the voice that speech detector detects Before the step of information, also performs the steps of and obtain pickup instruction；It is instructed according to pickup and generates pickup code and pass through display It is shown；Pickup code is used as the default voice content to match with target voice content；Obtain what speech detector detected Voice messaging, comprising: obtain the speech detector voice messaging detected according to pickup instruction；Voice messaging carries pickup Code.
In one embodiment, inquire the default voice content to match with target voice content, and with target vocal print The default vocal print feature that feature matches, comprising: for pre-stored each candidate speech content, calculate separately in candidate speech Hold the first matching rate between target voice content；In the candidate speech that first matching rate is met to the first preset matching condition Hold, is determined as the default voice content to match with target voice content；For each of pre-stored candidate vocal print feature, respectively Calculate the second matching rate between candidate vocal print feature and target vocal print feature；Second matching rate is met into the second preset matching item The candidate vocal print feature of part is determined as the default vocal print feature to match with target vocal print feature.
In one embodiment, it is also performed the steps of when computer program is executed by processor when electromagnetic lock is according to opening Door control instruction open locker identify corresponding locker when, delete locker mark with it is corresponding between default vocal print feature Relationship.
In one embodiment, it is realized when computer program is executed by processor to locker and identifies corresponding electromagnetic lock hair Before the step of sending enabling control instruction, also performs the steps of and receive the corresponding article detection apparatus detection of locker mark And the Item Information sent；It is selected to put question to data from pre-stored problem set according to Item Information；It is raw according to enquirement data Voice messaging is putd question at corresponding, and voice messaging will be putd question to be sent to speech detector；It obtains detected by speech detector With put question to voice messaging corresponding answer voice messaging；It is extracted from answer voice messaging by speech recognition modeling corresponding Answer data；Correct option corresponding with data are putd question to is determined according to Item Information；When answer data match with correct option When, it is corresponding to generate enabling control instruction.
In one embodiment, acquisition speech detector is also performed the steps of when computer program is executed by processor Part voice messaging is deposited detected by part instruction according to depositing；It is corresponding from extraction in part voice messaging is deposited by Application on Voiceprint Recognition model Deposit part vocal print feature；The selection locker mark from candidate locker mark, part vocal print feature is deposited in foundation and locker identifies it Between corresponding relationship；Part vocal print feature and locker mark will be deposited, and the corresponding storage of the corresponding relationship established；It is special to deposit part vocal print As pre-stored default vocal print feature.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, To any reference of memory, storage, database or other media used in each embodiment provided herein, Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms, Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.

Claims (10)

1. a kind of storage cabinet control, which comprises
Obtain the voice messaging that speech detector detects；
Target voice content is extracted from the voice messaging by speech recognition modeling, and by Application on Voiceprint Recognition model from described Target vocal print feature is extracted in voice messaging；
The default voice content that inquiry matches with the target voice content, and match with the target vocal print feature Default vocal print feature；
When inquiring the default voice content and the default vocal print feature, inquire corresponding with the default vocal print feature Locker mark；
Corresponding electromagnetic lock, which is identified, to the locker sends enabling control instruction；The enabling control instruction is used to indicate described Electromagnetic lock opens the locker and identifies corresponding locker.
2. the method according to claim 1, wherein it is described obtain the voice messaging that detects of speech detector it Before, the method also includes:
Obtain pickup instruction；
It is instructed according to the pickup and generates pickup code and shown by display；The pickup code be used as in target voice Hold the default voice content to match；
The voice messaging for obtaining speech detector and detecting, comprising:
Obtain the speech detector voice messaging detected according to pickup instruction；The voice messaging carries described take Part code.
3. the method according to claim 1, wherein it is described inquiry match with the target voice content it is pre- If voice content, and the default vocal print feature to match with the target vocal print feature, comprising:
For pre-stored each candidate speech content, calculate separately the candidate speech content and the target voice content it Between the first matching rate；
The candidate speech content that first matching rate is met to the first preset matching condition is determined as and the target voice content phase Matched default voice content；
For each of pre-stored candidate vocal print feature, calculate separately the candidate vocal print feature and the target vocal print feature it Between the second matching rate；
The candidate vocal print feature that second matching rate is met to the second preset matching condition is determined as and the target vocal print feature phase Matched default vocal print feature.
4. the method according to claim 1, wherein the method also includes:
When the electromagnetic lock, which opens the locker according to the enabling control instruction, identifies corresponding locker, described in deletion Corresponding relationship between locker mark and the default vocal print feature.
5. the method according to claim 1, wherein described identify corresponding electromagnetic lock transmission to the locker Before enabling control instruction, the method also includes:
It receives the locker and identifies the Item Information that corresponding article detection apparatus is detected and sent；
It is selected to put question to data from pre-stored problem set according to the Item Information；
Corresponding enquirement voice messaging is generated according to the enquirement data, and the enquirement voice messaging is sent to the voice Detector；
Obtain answer voice messaging corresponding with the enquirement voice messaging detected by the speech detector；
Corresponding answer data are extracted from the answer voice messaging by the speech recognition modeling；
Correct option corresponding with the enquirement data is determined according to the Item Information；
It is corresponding to generate enabling control instruction when the answer data and the correct option match.
6. method according to any one of claims 1 to 5, which is characterized in that the method also includes:
Obtain speech detector according to deposit part instruction detected by deposit part voice messaging；
By Application on Voiceprint Recognition model from it is described deposit to extract in part voice messaging deposit part vocal print feature accordingly；
Selection locker identifies from candidate locker mark, is deposited between part vocal print feature and locker mark described in foundation Corresponding relationship；
Part vocal print feature and locker mark are deposited by described, and the corresponding storage of the corresponding relationship established；It is described to deposit Part vocal print spy is used as pre-stored default vocal print feature.
7. a kind of locker control device, which is characterized in that described device includes:
Obtain module, the voice messaging detected for obtaining speech detector；
Extraction module for extracting target voice content from the voice messaging by speech recognition modeling, and passes through vocal print Identification model extracts target vocal print feature from the voice messaging；
Matching module, for inquiring the default voice content to match with the target voice content, and with the target sound The default vocal print feature that line feature matches；
Enquiry module, for when inquiring the default voice content and the default vocal print feature, inquiry to be preset with described The corresponding locker mark of vocal print feature；
Sending module sends enabling control instruction for identifying corresponding electromagnetic lock to the locker；The enabling control refers to Order is used to indicate the electromagnetic lock and opens the corresponding locker of the locker mark.
8. device according to claim 7, which is characterized in that described device further include: removing module；
Removing module identifies corresponding storing for opening the locker according to the enabling control instruction when the electromagnetic lock When cabinet, the corresponding relationship between the locker mark and the default vocal print feature is deleted.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
CN201810947490.4A 2018-08-20 2018-08-20 Storage cabinet control method, storage cabinet control device, computer equipment and storage medium Active CN109036438B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810947490.4A CN109036438B (en) 2018-08-20 2018-08-20 Storage cabinet control method, storage cabinet control device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810947490.4A CN109036438B (en) 2018-08-20 2018-08-20 Storage cabinet control method, storage cabinet control device, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN109036438A true CN109036438A (en) 2018-12-18
CN109036438B CN109036438B (en) 2023-07-28

Family

ID=64631467

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810947490.4A Active CN109036438B (en) 2018-08-20 2018-08-20 Storage cabinet control method, storage cabinet control device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN109036438B (en)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109559750A (en) * 2019-01-28 2019-04-02 上海与德通讯技术有限公司 Article access method, device, Intelligent storage cabinet and storage medium
CN109685950A (en) * 2018-12-20 2019-04-26 深圳市华智创科智能科技有限公司 A kind of gate inhibition's unlocking method and its device based on shake mobile terminal
CN109754512A (en) * 2019-02-28 2019-05-14 四川长虹电器股份有限公司 A kind of vocal print adds the intelligent access control system of code word
CN111429908A (en) * 2020-03-30 2020-07-17 北京声智科技有限公司 Intelligent electronic lock control method and device
CN111894582A (en) * 2020-08-04 2020-11-06 中国矿业大学 Control method of coal mining machine
CN111951811A (en) * 2020-07-15 2020-11-17 珠海市杰理科技股份有限公司 Bluetooth headset control method and device, Bluetooth headset and preset information importing method
CN112037767A (en) * 2020-09-11 2020-12-04 中航华东光电（上海）有限公司 Control method and system of intelligent voice shoe cabinet
CN112735049A (en) * 2021-01-07 2021-04-30 深圳市智莱科技股份有限公司 Pickup method, device, equipment and computer readable storage medium
CN112863032A (en) * 2019-11-28 2021-05-28 比亚迪汽车工业有限公司 Gate control method and device, storage medium and electronic equipment
CN112885360A (en) * 2019-11-29 2021-06-01 安徽智恒信科技股份有限公司 Cabinet door opening control method and device
CN113112648A (en) * 2021-04-07 2021-07-13 二十二冶集团装备制造有限公司 Online learning system based on Internet of things
CN114724311A (en) * 2022-05-16 2022-07-08 北京三快在线科技有限公司 Cabinet opening method, device and equipment of storage cabinet and computer readable storage medium
CN114724312A (en) * 2022-05-16 2022-07-08 北京三快在线科技有限公司 Cabinet opening method, device and equipment of storage cabinet and computer readable storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040153325A1 (en) * 2003-01-31 2004-08-05 Vecommerce Limited Service ordering system and method
CN102737634A (en) * 2012-05-29 2012-10-17 百度在线网络技术（北京）有限公司 Authentication method and device based on voice
CN106897921A (en) * 2017-02-28 2017-06-27 广州市诚毅科技软件开发有限公司 A kind of commodity purchasing method and apparatus based on express delivery cabinet
CN107886958A (en) * 2017-11-10 2018-04-06 广州势必可赢网络科技有限公司 A kind of express delivery cabinet pickup method and device based on vocal print
CN108109277A (en) * 2017-12-05 2018-06-01 中科富创（北京）科技有限公司 A kind of express delivery pickup method and system
CN108154735A (en) * 2016-12-06 2018-06-12 爱天教育科技（北京）有限公司 Oral English Practice assessment method and device
CN108417216A (en) * 2018-03-15 2018-08-17 深圳市声扬科技有限公司 Speech verification method, apparatus, computer equipment and storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040153325A1 (en) * 2003-01-31 2004-08-05 Vecommerce Limited Service ordering system and method
CN102737634A (en) * 2012-05-29 2012-10-17 百度在线网络技术（北京）有限公司 Authentication method and device based on voice
CN108154735A (en) * 2016-12-06 2018-06-12 爱天教育科技（北京）有限公司 Oral English Practice assessment method and device
CN106897921A (en) * 2017-02-28 2017-06-27 广州市诚毅科技软件开发有限公司 A kind of commodity purchasing method and apparatus based on express delivery cabinet
CN107886958A (en) * 2017-11-10 2018-04-06 广州势必可赢网络科技有限公司 A kind of express delivery cabinet pickup method and device based on vocal print
CN108109277A (en) * 2017-12-05 2018-06-01 中科富创（北京）科技有限公司 A kind of express delivery pickup method and system
CN108417216A (en) * 2018-03-15 2018-08-17 深圳市声扬科技有限公司 Speech verification method, apparatus, computer equipment and storage medium

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109685950A (en) * 2018-12-20 2019-04-26 深圳市华智创科智能科技有限公司 A kind of gate inhibition's unlocking method and its device based on shake mobile terminal
CN109559750B (en) * 2019-01-28 2021-02-26 昆山品源知识产权运营科技有限公司 Article storing and taking method and device, intelligent storage cabinet and storage medium
CN109559750A (en) * 2019-01-28 2019-04-02 上海与德通讯技术有限公司 Article access method, device, Intelligent storage cabinet and storage medium
CN109754512A (en) * 2019-02-28 2019-05-14 四川长虹电器股份有限公司 A kind of vocal print adds the intelligent access control system of code word
CN112863032A (en) * 2019-11-28 2021-05-28 比亚迪汽车工业有限公司 Gate control method and device, storage medium and electronic equipment
CN112885360A (en) * 2019-11-29 2021-06-01 安徽智恒信科技股份有限公司 Cabinet door opening control method and device
CN111429908A (en) * 2020-03-30 2020-07-17 北京声智科技有限公司 Intelligent electronic lock control method and device
CN111951811A (en) * 2020-07-15 2020-11-17 珠海市杰理科技股份有限公司 Bluetooth headset control method and device, Bluetooth headset and preset information importing method
CN111894582A (en) * 2020-08-04 2020-11-06 中国矿业大学 Control method of coal mining machine
CN111894582B (en) * 2020-08-04 2021-09-24 中国矿业大学 Control method of coal mining machine
CN112037767A (en) * 2020-09-11 2020-12-04 中航华东光电（上海）有限公司 Control method and system of intelligent voice shoe cabinet
CN112735049A (en) * 2021-01-07 2021-04-30 深圳市智莱科技股份有限公司 Pickup method, device, equipment and computer readable storage medium
CN113112648A (en) * 2021-04-07 2021-07-13 二十二冶集团装备制造有限公司 Online learning system based on Internet of things
CN114724311A (en) * 2022-05-16 2022-07-08 北京三快在线科技有限公司 Cabinet opening method, device and equipment of storage cabinet and computer readable storage medium
CN114724312A (en) * 2022-05-16 2022-07-08 北京三快在线科技有限公司 Cabinet opening method, device and equipment of storage cabinet and computer readable storage medium

Also Published As

Publication number Publication date
CN109036438B (en) 2023-07-28

Similar Documents

Publication Publication Date Title
CN109036438A (en) Storage cabinet control, device, computer equipment and storage medium
CN109273009A (en) Access control method, device, computer equipment and storage medium
CN105468950B (en) Identity authentication method and device, terminal and server
CN109165940B (en) Anti-theft method and device and electronic equipment
US9268990B2 (en) Apparatus and method for producing an identification device
Alegre et al. A one-class classification approach to generalised speaker verification spoofing countermeasures using local binary patterns
CN109450850A (en) Auth method, device, computer equipment and storage medium
US9430627B2 (en) Method and system for enforced biometric authentication
CN109741738A (en) Sound control method, device, computer equipment and storage medium
WO2016172872A1 (en) Method and device for verifying real human face, and computer program product
CN104778416B (en) A kind of information concealing method and terminal
CN106920303A (en) A kind of method for unlocking and its intelligent door lock system based on speech recognition
CN101494690A (en) Mobile terminal and unlocking method thereof
US20150142439A1 (en) System and method of speaker recognition
KR20170140397A (en) Method of acquiring account information, terminal, server and system
CN109767572B (en) Method and device for storing mailings, computer equipment and storage medium
CN109727342A (en) Recognition methods, device, access control system and the storage medium of access control system
CN110246503A (en) Blacklist vocal print base construction method, device, computer equipment and storage medium
CN109446772A (en) Accrediting amount calculation method, device, computer equipment and storage medium
CN109118626B (en) Lock control method and device, storage medium and electronic device
CN104965589A (en) Human living body detection method and device based on human brain intelligence and man-machine interaction
CN107464328A (en) Unlocking method, device, storage medium and the smart lock of smart lock
JPH08305798A (en) Method for finding of reference character element by using character pattern element by handwriting of identical person
US11611881B2 (en) Integrated systems and methods for passive authentication
CN109658548A (en) Use the method for access control system inspection access authorization

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
GR01 Patent grant
GR01 Patent grant