CN109036438B

CN109036438B - Storage cabinet control method, storage cabinet control device, computer equipment and storage medium

Info

Publication number: CN109036438B
Application number: CN201810947490.4A
Authority: CN
Inventors: 潘燕飞
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2018-08-20
Filing date: 2018-08-20
Publication date: 2023-07-28
Anticipated expiration: 2038-08-20
Also published as: CN109036438A

Abstract

The application relates to a data processing technology and provides a locker control method, a locker control device, computer equipment and a storage medium. The method comprises the following steps: acquiring voice information detected by a voice detector; extracting target voice content from the voice information through a voice recognition model, and extracting target voiceprint features from the voice information through a voiceprint recognition model; inquiring preset voice content matched with the target voice content and preset voiceprint features matched with the target voiceprint features; inquiring a locker identification corresponding to the preset voiceprint feature when the preset voice content and the preset voiceprint feature are inquired; sending a door opening control instruction to an electromagnetic lock corresponding to the locker identification; the door opening control instruction is used for indicating the electromagnetic lock to open the locker corresponding to the locker identification. By adopting the method, the safety of the storage cabinet can be improved.

Description

Storage cabinet control method, storage cabinet control device, computer equipment and storage medium

Technical Field

The present disclosure relates to the field of intelligent control technologies, and in particular, to a method and apparatus for controlling a storage cabinet, a computer device, and a storage medium.

Background

Along with the development of intelligent control technology, each of the shops and supermarkets is provided with a locker for storing and taking articles by self, so that people can store articles temporarily, and convenience is brought to life of people. At present, the locker is managed and controlled by a bar code technology, namely, a certificate for opening the locker door is a password bar with a bar code, and the locker door is opened by scanning the bar code on the password bar.

However, in the locker control method, the paper password bar is inconvenient to use and is easy to lose, so that the problem of lower locker safety exists.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a locker control method, apparatus, computer device, and storage medium that can improve locker safety.

A method of locker control, the method comprising:

acquiring voice information detected by a voice detector;

extracting target voice content from the voice information through a voice recognition model, and extracting target voiceprint features from the voice information through a voiceprint recognition model;

inquiring preset voice content matched with the target voice content and preset voiceprint features matched with the target voiceprint features;

Inquiring a locker identification corresponding to the preset voiceprint feature when the preset voice content and the preset voiceprint feature are inquired;

sending a door opening control instruction to an electromagnetic lock corresponding to the locker identification; the door opening control instruction is used for indicating the electromagnetic lock to open the locker corresponding to the locker identification.

In one embodiment, before the voice information detected by the voice detector is acquired, the method further includes:

acquiring a fetching instruction;

generating a pickup code according to the pickup instruction and displaying the pickup code through a display; the piece taking code is used as preset voice content matched with the target voice content;

the acquiring the voice information detected by the voice detector comprises the following steps:

acquiring voice information detected by a voice detector according to the pick-up instruction; the voice information carries the picking code.

In one embodiment, the querying the preset voice content matched with the target voice content and the preset voiceprint feature matched with the target voiceprint feature includes:

for each pre-stored candidate voice content, respectively calculating a first matching rate between the candidate voice content and the target voice content;

Determining candidate voice contents with the first matching rate meeting a first preset matching condition as preset voice contents matched with the target voice contents;

for each pre-stored candidate voiceprint feature, respectively calculating a second matching rate between the candidate voiceprint feature and the target voiceprint feature;

and determining the candidate voiceprint features with the second matching rate meeting a second preset matching condition as preset voiceprint features matched with the target voiceprint features.

In one embodiment, the method further comprises:

and when the electromagnetic lock starts the locker corresponding to the locker identification according to the door opening control instruction, deleting the corresponding relation between the locker identification and the preset voiceprint feature.

In one embodiment, before the door opening control command is sent to the electromagnetic lock corresponding to the locker identifier, the method further includes:

receiving article information detected and sent by an article detection device corresponding to the locker identification;

selecting question data from a prestored question set according to the article information;

generating corresponding questioning voice information according to the questioning data, and sending the questioning voice information to the voice detector;

Obtaining answer voice information corresponding to the question voice information detected by the voice detector;

extracting corresponding answer data from the answer voice information through the voice recognition model;

determining correct answers corresponding to the questioning data according to the article information;

and when the answer data is matched with the correct answer, correspondingly generating a door opening control instruction.

In one embodiment, the method further comprises:

acquiring the piece-storing voice information detected by the voice detector according to the piece-storing instruction;

extracting corresponding part-storing voiceprint features from the part-storing voice information through a voiceprint recognition model;

selecting a locker identification from candidate locker identifications, and establishing a corresponding relation between the sound print feature of the stored part and the locker identification;

correspondingly storing the voiceprint features of the stored part, the storage cabinet identification and the established corresponding relation; the stock voiceprint feature is used as a pre-stored preset voiceprint feature.

A locker control apparatus, the apparatus comprising:

the acquisition module is used for acquiring the voice information detected by the voice detector;

the extraction module is used for extracting target voice content from the voice information through a voice recognition model and extracting target voiceprint features from the voice information through a voiceprint recognition model;

The matching module is used for inquiring preset voice content matched with the target voice content and preset voiceprint features matched with the target voiceprint features;

the query module is used for querying a locker identification corresponding to the preset voiceprint feature when the preset voice content and the preset voiceprint feature are queried;

the sending module is used for sending a door opening control instruction to the electromagnetic lock corresponding to the locker identification; the door opening control instruction is used for indicating the electromagnetic lock to open the locker corresponding to the locker identification.

In one embodiment, the apparatus further comprises: deleting the module;

and the deleting module is used for deleting the corresponding relation between the locker identification and the preset voiceprint feature when the electromagnetic lock opens the locker corresponding to the locker identification according to the door opening control instruction.

A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:

acquiring voice information detected by a voice detector;

A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

acquiring voice information detected by a voice detector;

According to the locker control method, the locker control device, the computer equipment and the storage medium, when the voice information detected by the voice detector is acquired, the target voice content and the target voiceprint feature are respectively extracted from the acquired voice information, double authentication is carried out on the extracted target voice content and the target voiceprint feature, and when the double authentication is passed, the corresponding locker is opened. When the preset voice content matched with the target voice content and the preset voiceprint feature matched with the voice target voiceprint feature are inquired, the double authentication is judged to pass, the locker identification corresponding to the preset voiceprint feature is inquired, and a door opening control instruction is sent to an electromagnetic lock corresponding to the locker identification so as to open the locker. The method for controlling the storage cabinet based on double authentication of the voice information can effectively improve the safety of the storage cabinet.

Drawings

FIG. 1 is a diagram of an application scenario of a locker control method according to one embodiment;

FIG. 2 is a flow chart of a method of controlling a locker in one embodiment;

FIG. 3 is a flow chart of a method of controlling a locker according to another embodiment;

FIG. 4 is a block diagram of a locker control apparatus according to one embodiment;

FIG. 5 is a block diagram of a locker control apparatus according to another embodiment;

fig. 6 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

The locker control method provided by the application can be applied to an application environment shown in fig. 1. The locker control terminal 120 is electrically connected to the electromagnetic lock 140, and the locker control terminal 120 communicates with the electromagnetic lock 140 through an electrical signal. The locker control terminal 120 acquires the voice information detected by the voice detector, and extracts corresponding target voice content and target voiceprint features from the acquired voice information, respectively. When the preset voice content matched with the target voice content and the preset voiceprint feature matched with the target voiceprint feature are queried, the locker control terminal 120 queries the locker identification corresponding to the preset voiceprint feature and sends a door opening control instruction to the electromagnetic lock 140 corresponding to the queried locker identification so as to open the corresponding locker. Wherein, the electromagnetic lock 140 is more than one, such as electromagnetic lock 1, electromagnetic lock 2, electromagnetic lock n. The locker control terminal 120 controls more than one locker correspondingly, such as locker 1, locker 2, locker n. The lockers correspond to the electromagnetic locks 140, that is, each locker corresponds to a corresponding electromagnetic lock, for example, the electromagnetic lock 1 corresponds to the locker 1, and the locker control terminal 120 controls the corresponding locker through the electromagnetic lock 140.

In one embodiment, as shown in fig. 2, a locker control method is provided, and the locker control terminal in fig. 1 is taken as an example to illustrate the method, which includes the following steps:

s202, voice information detected by a voice detector is acquired.

Wherein the voice information is audio information detected by the voice detector when the user speaks. The voice information is audio information carrying target voice content and target voiceprint features. The target voice content refers to text content or information delivered when the user speaks. The target voiceprint feature is a timbre parameter that characterizes the user's voice feature.

Specifically, the locker control terminal obtains voice information through the voice detector. The voice detector is arranged in the locker control terminal, and the locker control terminal detects voice information in a specified range through the built-in voice detector. The voice detector may also be a separate component that is connected point-to-point with the locker control terminal. The voice detector detects voice information in a specified range and sends the detected voice information to the locker control terminal. Wherein the specified range is a region range specified in advance.

In one embodiment, the voice detector may be a microphone, in particular a directional microphone. The directional microphone can detect voice information within a specified range of a specified direction. The influence of environmental noise on the extraction of target voice content and target voiceprint features can be effectively reduced by collecting voice information through the directional microphone.

In one embodiment, when the locker control terminal obtains the order of taking a piece, the voice detector is started according to the obtained order of taking the piece, and voice information is detected through the voice detector. The fetching instruction is generated according to the detected specified fetching operation trigger triggered by the user. The specified pickup operation is, for example, a trigger operation of a user on the specified pickup control.

In one embodiment, when the locker control terminal detects that the target user exists in the specified range through the infrared sensor or the thermal sensor, voice prompt information for indicating that the password for taking the file is input is pushed to the target user through the loudspeaker, for example, the voice prompt information that the target voice content is "please speak the password for taking the file". Further, the locker control terminal detects voice information fed back by the target user aiming at the voice prompt information through the voice detector. In this embodiment, the step of speaker implementation may also be implemented by a voice detector.

S204, extracting target voice content from the voice information through the voice recognition model, and extracting target voiceprint features from the voice information through the voiceprint recognition model.

The voice recognition model is obtained by performing model training according to a pre-acquired training sample set and can be used for extracting corresponding target voice content from acquired voice information. The training sample set comprises a plurality of target voice information and target voice contents corresponding to each target voice information. The voiceprint recognition model is a model which is obtained by model training according to a pre-acquired training sample set and can be used for extracting corresponding target voiceprint characteristics from the acquired voice information. The training sample set comprises a plurality of target voice information and target voiceprint features corresponding to each target voice information. The plurality of target speech information in the training sample set for training the speech recognition model may be the same or different from the plurality of target speech information in the training sample set for training the voiceprint recognition model.

Specifically, the locker control terminal extracts corresponding target voice content from the acquired voice information through a pre-trained voice recognition model, and extracts corresponding target voiceprint features from the voice information through the pre-trained voiceprint recognition model.

In one embodiment, the locker control terminal obtains a plurality of target voice messages and determines target voice content and target voiceprint characteristics in each target voice message, respectively. The locker control terminal takes the target voice information as an input characteristic, takes the corresponding target voice content as an expected output characteristic, and trains the initialized voice recognition model to obtain a trained voice recognition model. Similarly, the locker control terminal takes the target voice information as an input characteristic, the corresponding target voiceprint characteristic as an expected output characteristic, and trains the initialized voiceprint recognition model to obtain a trained voiceprint recognition model. Among them, voiceprint models such as Artificial Neural Network (ANN), hidden Markov Model (HMM), gaussian Mixture Model (GMM), and the like.

In one embodiment, the voice recognition model and the voiceprint recognition model may be pre-trained by other computer devices and then transplanted to the locker control terminal. Or, the voice recognition model and/or the voiceprint recognition model which are trained in advance through other computer equipment are burnt into a processor arranged in the locker control terminal.

S206, inquiring preset voice content matched with the target voice content and preset voiceprint features matched with the target voiceprint features.

The preset voice content is preset voice content. The preset voice content may specifically be a voice content extracted from preset voice information in advance and stored in advance. Similarly, the preset voiceprint feature is a preset voiceprint feature, and specifically may be a voiceprint feature extracted from preset voice information in advance and stored in advance. The preset voice information is preset voice information, and specifically can be voice information which is acquired in the process of storing the part and corresponds to the user for storing the part.

Specifically, the locker control terminal inquires preset voice content matched with target voice content according to the target voice content extracted from the voice information. And the locker control terminal inquires preset voiceprint characteristics matched with the target voiceprint characteristics according to the target voiceprint characteristics extracted from the voice information.

In one embodiment, the locker control terminal respectively matches the extracted target voice content with pre-stored candidate voice content, and determines the candidate voice content successfully matched as preset voice content matched with the extracted target voice content. Similarly, the locker control terminal respectively matches the extracted target voiceprint features with the prestored candidate voiceprint features, and determines the candidate voiceprint features which are successfully matched as preset voiceprint features matched with the extracted target voiceprint features.

In one embodiment, the locker control terminal pre-stores a correspondence between candidate speech content and candidate voiceprint features. And the locker control terminal sequentially matches the extracted target voice content with the pre-stored candidate voice content. And when the matching is successful, the locker control terminal stops the matching operation between the currently executed target voice content and the candidate voice content, queries candidate voiceprint features corresponding to the candidate voice content according to the candidate voice content successfully matched, and matches the queried candidate voiceprint features with the extracted target voiceprint features. When the candidate voiceprint feature is successfully matched with the target voiceprint feature, the locker control terminal stops the matching operation between the currently executed candidate voiceprint feature and the target voiceprint feature, determines the successfully matched candidate voice content as preset voice content, and determines the successfully matched candidate voiceprint feature as the preset voiceprint feature.

Further, when the candidate voiceprint feature fails to match with the target voiceprint feature, the locker control terminal continues to execute the matching operation between the target voice content and the candidate voice content. When the matching result corresponding to the matching operation between the currently executed target voice content and the candidate voice content is that the matching fails, the locker control terminal continues to execute the matching operation between the target voice content and the candidate voice content. And when the matching result corresponding to the matching operation between the currently executed target voice content and the candidate voice content is successful, the locker control terminal executes the related step of inquiring the candidate voiceprint characteristics according to the candidate voice content.

In one embodiment, the locker control device reads the pre-stored candidate voice content and candidate voiceprint features as the target voice content and target voiceprint features are extracted from the voice information. The locker control terminal determines preset voice content matched with the target voice content from the read candidate voice content, and determines preset voiceprint characteristics matched with the target voiceprint characteristics from the read candidate voiceprint characteristics.

In one embodiment, the locker control terminal queries the memory for preset voice content matching the target voice content and preset voiceprint features matching the target voiceprint features. The memory can be built in the locker control terminal or can be an independent component in point-to-point connection with the locker control terminal.

S208, inquiring the storage cabinet identification corresponding to the preset voiceprint characteristics when the preset voice content and the preset voiceprint characteristics are inquired.

Wherein, locker identification is used for unique identification locker. The locker identification can be a character string consisting of at least one of a number, a letter and a coincidence character. The locker identification corresponds to the candidate voiceprint feature, and the locker control terminal prestores a corresponding relation between the locker identification and the candidate voiceprint feature.

Specifically, when the locker control terminal inquires the preset voice content matched with the extracted target voice content and inquires the preset voiceprint feature matched with the extracted target voiceprint feature, the locker control terminal inquires the locker identification corresponding to the preset voiceprint feature according to the inquired preset voiceprint feature.

In one embodiment, the locker control terminal pre-stores a correspondence between candidate voice content, candidate voiceprint features, and locker identification. When the preset voice content matched with the target voice content is queried from the prestored candidate voice content and the preset voiceprint feature matched with the target voiceprint feature is queried from the prestored candidate voiceprint features, the locker identification queries the corresponding locker identification according to the queried preset voice content and preset voiceprint feature and the corresponding relation.

In one embodiment, the locker control terminal pre-stores the correspondence between the candidate voice content, the candidate voiceprint feature, and the user identification, and the correspondence between the user identification and the locker identification. And the locker control terminal inquires corresponding user identifications according to the inquired preset voice content and the preset voiceprint characteristics, and further inquires corresponding locker identifications according to the inquired user identifications.

In one embodiment, the memory stores a correspondence between the predetermined voiceprint features and locker identification. When the preset voice content and the preset voiceprint feature are inquired, the locker control terminal inquires a locker identification corresponding to the preset voiceprint feature in a memory according to the preset voiceprint feature.

S210, sending a door opening control instruction to an electromagnetic lock corresponding to the locker identification; the door opening control instruction is used for indicating the electromagnetic lock to open the locker corresponding to the locker identification.

The door opening control instruction is an instruction for triggering and opening the electromagnetic lock corresponding to the storage cabinet so as to open the corresponding storage cabinet. The door opening control command may be a high-low level.

Specifically, when the locker identification corresponding to the preset voiceprint feature is queried, the locker control terminal queries an electromagnetic lock identification corresponding to the locker identification according to the queried locker identification. When the electromagnetic lock identification corresponding to the locker identification is inquired, the locker control terminal sends a door opening control instruction to the electromagnetic lock corresponding to the electromagnetic lock identification. The electromagnetic locks open the corresponding storage cabinets according to the received door opening control instructions, namely the electromagnetic locks execute unlocking operation according to the door opening control instructions so as to open the corresponding storage cabinets.

In one embodiment, when the preset voice content and the preset voiceprint feature are queried, the locker control terminal correspondingly generates a door opening control instruction. The locker control terminal can also generate a corresponding door opening control instruction according to the queried locker identification when the locker identification is queried. The locker control terminal can also generate a corresponding door opening control instruction according to the inquired electromagnetic lock identification when inquiring the electromagnetic lock identification corresponding to the locker identification.

In one embodiment, the memory stores a correspondence between locker identification and electromagnetic lock identification. And the locker control terminal inquires corresponding relations in the memory according to the locker identification.

According to the locker control method, when the voice information detected by the voice detector is acquired, the target voice content and the target voiceprint feature are respectively extracted from the acquired voice information, double authentication is carried out on the extracted target voice content and target voiceprint feature, and when the double authentication is passed, the corresponding locker is opened. When the preset voice content matched with the target voice content and the preset voiceprint feature matched with the voice target voiceprint feature are inquired, the double authentication is judged to pass, the locker identification corresponding to the preset voiceprint feature is inquired, and a door opening control instruction is sent to an electromagnetic lock corresponding to the locker identification so as to open the locker. The method for controlling the storage cabinet based on double authentication of the voice information can effectively improve the safety of the storage cabinet.

In one embodiment, before step S202, the locker control method further includes: acquiring a fetching instruction; generating a picking code according to the picking instruction and displaying the picking code through a display; the piece taking code is used as preset voice content matched with the target voice content; step S202 includes: acquiring voice information detected by a voice detector according to the pick-up instruction; the voice information carries the pick-up code.

The fetching instruction is an instruction triggered by a specified fetching operation. The fetching instruction is used for triggering related authentication operation during fetching. A specified pickup operation such as a pressing operation of a specified pickup button by a user or a clicking or sliding operation on a touch screen. The picking instruction is used for instructing the locker control terminal to authenticate the user triggering the appointed picking operation, and opening the corresponding locker when the authentication is passed. The pick may be a string of numbers and/or letters, such as 1357.

Specifically, when the specified fetching operation triggered by the user is detected, the locker control terminal generates a corresponding fetching instruction according to the detected specified fetching operation. And the locker control terminal randomly generates corresponding picking codes according to the generated picking instructions and displays the generated picking codes through a display. The locker control terminal stores the generated picking codes as candidate voice contents locally so that when the locker control terminal inquires preset voice contents matched with target voice contents extracted from voice information from prestored candidate voice contents, the locker control terminal takes the picking codes as the inquired preset voice contents matched with the target voice contents.

Further, when the locker control terminal displays the generated picking-up code through the display, the picking-up instruction is sent to the voice detector. When the voice detector receives the picking-up instruction, voice information carrying the picking-up code is detected in real time, and the detected voice information is sent to the locker control terminal.

In one embodiment, the locker control terminal generates a corresponding picking code according to the designated picking code format according to the picking instruction, and sends the generated picking code to the display to be displayed by the display. Wherein a pick-up code format, such as a 6-bit number, is specified. In one embodiment, the display may be built into the locker control terminal or may be a separate component that is connected point-to-point with the locker control terminal. In one embodiment, the locker control terminal dynamically refreshes the pick-up code displayed by the display according to a preset period.

In one embodiment, the voice detector may be built into the locker control terminal. The locker control terminal starts a voice detector according to the picking-up instruction so as to detect voice information through the voice detector.

For example, when the specified picking operation triggered by the user is detected, the locker control terminal generates a corresponding picking instruction, generates a picking code according to the picking instruction, and displays the picking code to the user through the display. And triggering voice information carrying the picking code according to the picking code displayed by the display by the user so as to facilitate the locker control terminal to authenticate the identity of the user according to the voice information.

In the above embodiment, the picking code is generated according to the picking instruction and displayed to the user, so that the user is prevented from forgetting to preset the picking code and cannot pick the workpiece, the picking efficiency is improved, and the control efficiency of the storage cabinet is improved.

In one embodiment, step S206 includes: for each pre-stored candidate voice content, respectively calculating a first matching rate between the candidate voice content and the target voice content; determining candidate voice contents with the first matching rate meeting a first preset matching condition as preset voice contents matched with target voice contents; for each pre-stored candidate voiceprint feature, respectively calculating a second matching rate between the candidate voiceprint feature and the target voiceprint feature; and determining the candidate voiceprint features with the second matching rate meeting the second preset matching condition as preset voiceprint features matched with the target voiceprint features.

The candidate voice content is a voice content which is prestored in the storage process and possibly determined to be preset voice content through matching operation. The first matching rate refers to a degree of matching between the candidate speech content and the target speech content. The first preset matching condition is a constraint condition for determining preset voice content matching the target voice content from the plurality of candidate voice contents, such as that the first matching rate reaches a first matching rate threshold.

Similarly, candidate voiceprint features are voiceprint features that are pre-stored during the storage process and that may be determined to be preset voiceprint features by a matching operation. The second matching rate refers to the degree of matching between the candidate voiceprint feature and the target voiceprint feature. The second preset matching condition is a constraint condition for determining a preset voiceprint feature matching the target voiceprint feature from the plurality of candidate voiceprint features, such as the second match rate reaching a second match rate threshold.

In one embodiment, the locker control terminal calculates a first matching rate between each pre-stored candidate voice content and the extracted target voice content, compares each first matching rate with a first matching rate threshold value, and determines the candidate voice content with the first matching rate reaching the first matching rate threshold value as the preset voice content matched with the target voice content. In one embodiment, when the locker control terminal obtains a first matching rate corresponding to each candidate voice content, a first matching rate with the largest value is selected from the plurality of first matching rates, and the selected first matching rate is compared with a first matching rate threshold. When the screened first matching rate reaches a first matching rate threshold value, the locker control terminal determines candidate voice contents corresponding to the screened first matching rate as preset voice contents. Similarly, the locker control terminal determines a preset voiceprint feature matching the target voiceprint feature from the plurality of candidate voiceprint features according to the processing logic described above.

In one embodiment, a memory stores a plurality of candidate speech content and a plurality of candidate voiceprint features. The locker control terminal determines preset voice content matched with target voice content from candidate voice content prestored in the memory, and determines preset voiceprint characteristics matched with the target voiceprint characteristics from candidate voiceprint characteristics prestored in the memory.

In the above embodiment, according to the calculated first matching rate and second matching rate, the preset voice content and the preset voiceprint feature are determined from the plurality of candidate voice contents and the plurality of candidate voiceprint features, so that the accuracy and the efficiency of determining the preset voice content and the preset voiceprint feature are improved, the control efficiency of the locker is improved, and the safety of the locker is improved.

In one embodiment, the locker control method further includes: when the electromagnetic lock opens the locker corresponding to the locker identification according to the door opening control instruction, deleting the corresponding relation between the locker identification and the preset voiceprint feature.

Specifically, when the electromagnetic lock opens the locker corresponding to the locker identification according to the door opening control instruction, the locker control terminal inquires the corresponding relation between the locker identification and the corresponding preset voiceprint feature according to the locker identification, namely inquires the corresponding relation between the locker identification and the candidate voiceprint feature serving as the preset voiceprint feature. And when the corresponding relation is inquired, the locker control terminal deletes the inquired corresponding relation.

In one embodiment, when deleting the correspondence between the locker identification and the preset voiceprint feature, the locker control terminal deletes the candidate voiceprint feature corresponding to the locker identification and the candidate voice content corresponding to the candidate voiceprint feature, and deletes the queried candidate voiceprint feature and candidate voice content. In one embodiment, the locker control terminal deletes the pick-up code generated and stored according to the pick-up instruction.

In one embodiment, when the locker is opened, the locker control terminal deletes the correspondence corresponding to the locker identification corresponding to the locker in the memory.

In one embodiment, when the electromagnetic lock opens the corresponding locker according to the door opening control instruction, the locker control terminal detects a correspondence deleting operation triggered by a user. When the corresponding relation deleting operation is detected, the corresponding relation between the corresponding locker identification and the preset voiceprint feature is correspondingly deleted by the locker control instruction. The correspondence deleting operation is, for example, a pressing operation of a specified button or a sliding operation on a touch screen or a clicking operation at a specified position when the user takes a piece and closes the locker. Therefore, the storage cabinet can be conveniently used by a user again, and the problem that the storage cabinet needs to be replaced when a part is taken halfway is effectively avoided.

In the above embodiment, when the locker is opened according to the door opening control instruction, the corresponding relation of the locker is deleted, so that the locker can be recycled, and the object of the current user can be prevented from being stolen due to the fact that the historical user passes the authentication according to the corresponding relation stored in the historical manner, thereby improving the safety of the locker.

In one embodiment, before sending the door opening control instruction to the electromagnetic lock corresponding to the locker identifier, the method further includes: receiving article information detected and sent by an article detection device corresponding to the locker identification; selecting question data from a prestored question set according to the article information; generating corresponding questioning voice information according to the questioning data, and sending the questioning voice information to a voice detector; obtaining answering voice information corresponding to the answering voice information detected by the voice detector; extracting corresponding answer data from the answer voice information through a voice recognition model; determining a correct answer corresponding to the questioning data according to the article information; when the answer data is matched with the correct answer, a door opening control instruction is correspondingly generated.

The article detection device is a device for collecting article information in the storage cabinet, such as a camera, an X-ray scanner or the like. The article information is information describing articles stored in the locker. The item information may include, in particular, the name, color, kind, number of items, or the like. The article information may specifically be picture information including the articles stored in the locker, which is photographed and transmitted by the camera, or scanned picture information which is scanned and transmitted by the X-ray scanner.

A question set is a set made up of a plurality of question data. Question data refers to question data from which questions are asked, such as "please say at least one item you store". And when asking the voice information, correspondingly generating voice information carrying the asking data according to the asking data. The answer data is voice information which is fed back by the user corresponding to the question data in the question voice information, and the voice information carries answer data of the user corresponding to the question data, namely the answer of the user.

Specifically, when the locker identification is queried, the locker control terminal sends an article detection instruction to an article detection device corresponding to the locker identification, so that the article detection device detects article information of a corresponding locker according to the received article detection instruction, and sends the detected article information to the locker control terminal. The locker control terminal randomly selects questioning data from a prestored question set according to the received article information, generates corresponding questioning voice information according to the selected questioning data, and pushes the generated questioning voice information to a user through a voice detector. The locker control terminal obtains answering voice information fed back by a user aiming at the questioning data in the questioning voice information through the voice detector, and extracts corresponding answering data from the obtained answering voice information through a pre-trained voice recognition model.

Further, when the locker control terminal selects question data from the question set, determining a correct answer corresponding to the selected question data according to the acquired article information, and matching the determined correct answer with answer data extracted from answer voice information. When the matching is successful, the locker control terminal triggers the generation of a door opening control instruction, and sends the generated door opening control instruction to the electromagnetic lock.

In one embodiment, the locker control terminal determines a matching rate between the correct answer and the answer data, and when the matching rate reaches a preset matching rate threshold, the locker control terminal triggers generation of a corresponding door opening control instruction.

In one embodiment, the set of questions is pre-stored in memory. And the locker control terminal selects question data from a question set prestored in the memory according to the received article information.

In the above embodiment, when the authentication based on the voice information passes, the corresponding user is asked based on the article information in the locker, so as to further verify the identity of the user, so that the problem that the article is lost due to the fact that other people pass the identity authentication in a mode of imitating or recording the voice information is avoided, and the safety of the locker is improved.

In one embodiment, the locker control method further includes: acquiring the piece-storing voice information detected by the voice detector according to the piece-storing instruction; extracting corresponding voice print characteristics of the stored part from voice information of the stored part through a voice print recognition model; selecting a locker identification from candidate locker identifications, and establishing a corresponding relation between the sound print feature of the stored part and the locker identification; correspondingly storing the voiceprint features of the stored part and the storage cabinet identifier and the established corresponding relation; the stock voiceprint feature is used as a pre-stored pre-set voiceprint feature.

Wherein the store instruction is an instruction triggered by a specified store operation. The specified deposit operation is a trigger operation when a user deposit is specified in advance, such as a pressing operation of a specified deposit button by the user, or a clicking or sliding operation of a specified position on the touch screen by the user. The storing instruction is used for indicating the locker control terminal to distribute the locker for a user triggering the appointed storing operation, and opening the distributed locker. Candidate locker identification refers to locker identification that may be selected as a correspondence to the deposited voiceprint feature. The locker corresponding to the candidate locker identification is the locker which is in the idle state currently.

Specifically, when the locker control terminal detects a specified deposit operation triggered by a user, a corresponding deposit instruction is generated according to the detected specified deposit operation, and the generated deposit instruction is sent to the voice detector. The voice detector detects the voice information of the corresponding user according to the received storage command, and sends the detected storage voice information to the locker control terminal. And the locker control terminal extracts corresponding part-storing voiceprint features from the received part-storing voice information through a pre-trained voiceprint recognition model. And the locker control terminal inquires candidate locker identifications, selects locker identifications from the inquired candidate locker identifications when inquiring the candidate locker identifications, and establishes a corresponding relation between the selected locker identifications and the extracted sound print characteristics of the stored articles.

Further, the locker control terminal stores the extracted stored voiceprint features as candidate voiceprint features locally, so that in a pickup authentication process for a corresponding user, the locker control terminal determines the candidate voiceprint features as preset voiceprint features matched with the voiceprint features of the user. And the locker control terminal prestores the established correspondence between the sound print characteristics of the stored part and the locker identification.

In one embodiment, after the locker control terminal establishes a correspondence between the stored voiceprint features and the locker identification, and the correspondence are stored in the memory.

In one embodiment, when the deposit instruction is acquired, the locker control terminal detects corresponding deposit voice information through a built-in voice detector.

In one embodiment, the locker control terminal correspondingly determines whether a locker currently in an idle state exists, and when the locker currently in the idle state exists, determines the locker identification corresponding to the locker currently in the idle state as a candidate locker identification.

In one embodiment, the locker control terminal queries a correspondence between pre-stored locker identifications and corresponding candidate voiceprint features, and determines candidate locker identifications according to the queried correspondence and a preset locker identification list. Specifically, for each locker identification in the preset locker identification list, the locker control terminal inquires a corresponding relation corresponding to the locker identification. And when no corresponding relation is queried, the locker control terminal determines the corresponding locker identification as a candidate locker identification. The preset locker identification list is a set formed by locker identifications corresponding to each locker.

In one embodiment, the locker control terminal extracts corresponding pieces of storage voice content from the pieces of storage voice information through a pre-trained voice recognition model, and stores the extracted pieces of storage voice content as candidate voice content locally. In one embodiment, when the locker control terminal extracts the deposit voiceprint feature and the deposit voice content from the deposit voice information respectively, a corresponding relationship between the deposit voiceprint feature, the deposit voice content and the selected locker identification is established, and the established corresponding relationship is stored locally. In one embodiment, the locker control terminal establishes a correspondence between the deposit voiceprint feature and the locker identification, and a correspondence between the deposit voiceprint feature and the deposit voice content, respectively.

In the above embodiment, when the deposit instruction is acquired, the corresponding deposit voiceprint feature is registered based on the detected deposit voice information, so that the user is authenticated based on the registered deposit voiceprint feature in the process of taking the deposit, the control efficiency of the storage cabinet is improved, and the safety of the storage cabinet is ensured.

As shown in fig. 3, in one embodiment, a locker control method is provided, which specifically includes the following steps:

S302, acquiring a fetching instruction.

S304, generating a pickup code according to the pickup instruction and displaying the pickup code through a display; the pick-up code is used as preset voice content matched with the target voice content.

S306, acquiring voice information detected by a voice detector according to the pick-up instruction; the voice information carries the pick-up code.

S308, extracting target voice content from the voice information through a voice recognition model, and extracting target voiceprint features from the voice information through a voiceprint recognition model.

S310, for each pre-stored candidate voice content, respectively calculating a first matching rate between the candidate voice content and the target voice content.

S312, determining the candidate voice content with the first matching rate meeting the first preset matching condition as the preset voice content matched with the target voice content.

S314, for each pre-stored candidate voiceprint feature, respectively calculating a second matching rate between the candidate voiceprint feature and the target voiceprint feature.

S316, determining the candidate voiceprint features with the second matching rate meeting the second preset matching condition as preset voiceprint features matched with the target voiceprint features.

S318, inquiring the storage cabinet identification corresponding to the preset voiceprint characteristics when the preset voice content and the preset voiceprint characteristics are inquired.

S320, receiving article information detected and sent by the article detection device corresponding to the locker identification.

S322, selecting question data from a prestored question set according to the article information.

S324, corresponding questioning voice information is generated according to the questioning data, and the questioning voice information is sent to the voice detector.

S326, answering voice information corresponding to the answering voice information detected by the voice detector is obtained.

S328, extracting corresponding answer data from the answer voice information through the voice recognition model.

S330, determining correct answers corresponding to the questioning data according to the article information.

S332, when the answer data is matched with the correct answer, a door opening control instruction is correspondingly generated.

S334, sending a door opening control instruction to an electromagnetic lock corresponding to the locker identification; the door opening control instruction is used for indicating the electromagnetic lock to open the locker corresponding to the locker identification.

S336, when the electromagnetic lock opens the locker corresponding to the locker identification according to the door opening control instruction, deleting the corresponding relation between the locker identification and the preset voiceprint feature.

In the above embodiment, the picking-up code is generated according to the acquired picking-up instruction, the voice information carrying the picking-up code is detected, the user identity is authenticated based on the target voice content and the target voiceprint feature in the voice information, when the authentication is passed, the user identity is verified again based on the article information corresponding to the corresponding locker, when the authentication is passed, the corresponding locker is opened, and the corresponding correspondence is deleted. Therefore, in the process of taking the article, the user identity is authenticated for a plurality of times, and the safety of the storage cabinet is improved.

In one embodiment, in each of the foregoing embodiments, the steps performed by the locker control terminal may be performed by a processor internal to the locker control terminal.

It should be understood that, although the steps in the flowcharts of fig. 2 and 3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2 and 3 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur in sequence, but may be performed alternately or alternately with at least a portion of the other steps or sub-steps of other steps.

In one embodiment, as shown in FIG. 4, there is provided a locker control apparatus 400 comprising: an acquisition module 402, an extraction module 404, a matching module 406, a query module 408, and a sending module 410, wherein:

An acquisition module 402, configured to acquire the voice information detected by the voice detector.

The extracting module 404 is configured to extract the target voice content from the voice information through the voice recognition model, and extract the target voiceprint feature from the voice information through the voiceprint recognition model.

The matching module 406 is configured to query the preset voice content matched with the target voice content and the preset voiceprint feature matched with the target voiceprint feature.

The query module 408 is configured to query a locker identifier corresponding to a preset voiceprint feature when the preset voice content and the preset voiceprint feature are queried.

A sending module 410, configured to send a door opening control instruction to an electromagnetic lock corresponding to the locker identifier; the door opening control instruction is used for indicating the electromagnetic lock to open the locker corresponding to the locker identification.

In one embodiment, the obtaining module 402 is further configured to obtain a fetch instruction; generating a picking code according to the picking instruction and displaying the picking code through a display; the piece taking code is used as preset voice content matched with the target voice content; the voice information detecting device is also used for obtaining the voice information detected by the voice detector according to the pick-up instruction; the voice information carries the pick-up code.

In one embodiment, the matching module 406 is further configured to calculate, for each of the pre-stored candidate voice contents, a first matching rate between the candidate voice content and the target voice content; determining candidate voice contents with the first matching rate meeting a first preset matching condition as preset voice contents matched with target voice contents; for each pre-stored candidate voiceprint feature, respectively calculating a second matching rate between the candidate voiceprint feature and the target voiceprint feature; and determining the candidate voiceprint features with the second matching rate meeting the second preset matching condition as preset voiceprint features matched with the target voiceprint features.

As shown in FIG. 5, in one embodiment, the locker control apparatus 400 further comprises: a delete module 412;

and the deleting module 412 is configured to delete a correspondence between the locker identifier and a preset voiceprint feature when the electromagnetic lock opens the locker corresponding to the locker identifier according to the door opening control instruction.

In one embodiment, the locker control apparatus 400 further comprises: a question-answering module 414;

the question-answering module 414 is configured to receive article information detected and sent by the article detection device corresponding to the locker identifier; selecting question data from a prestored question set according to the article information; generating corresponding questioning voice information according to the questioning data, and sending the questioning voice information to a voice detector; obtaining answering voice information corresponding to the answering voice information detected by the voice detector; extracting corresponding answer data from the answer voice information through a voice recognition model; determining a correct answer corresponding to the questioning data according to the article information; when the answer data is matched with the correct answer, a door opening control instruction is correspondingly generated.

In one embodiment, the locker control apparatus 400 further comprises: a stock registration module 416;

the deposit registration module 416 is configured to obtain the deposit voice information detected by the voice detector according to the deposit instruction; extracting corresponding voice print characteristics of the stored part from voice information of the stored part through a voice print recognition model; selecting a locker identification from candidate locker identifications, and establishing a corresponding relation between the sound print feature of the stored part and the locker identification; correspondingly storing the voiceprint features of the stored part and the storage cabinet identifier and the established corresponding relation; the stock voiceprint feature is used as a pre-stored pre-set voiceprint feature.

For specific limitations of the locker control apparatus, reference may be made to the limitations of the locker control method hereinabove, and no further description is given here. The modules in the locker control device may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a locker control terminal, the internal structure of which may be as shown in FIG. 6. The computer device includes a processor, a memory, a communication interface, a voice detector, and a display connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing the pre-stored candidate voiceprint characteristics and candidate voice contents in the registration process and the corresponding relation between the candidate voiceprint characteristics and the locker identification. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a locker control method.

It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided comprising a memory storing a computer program and a processor that when executing the computer program performs the steps of: acquiring voice information detected by a voice detector; extracting target voice content from voice information through a voice recognition model, and extracting target voiceprint features from the voice information through a voiceprint recognition model; inquiring preset voice content matched with the target voice content and preset voiceprint characteristics matched with the target voiceprint characteristics; inquiring a locker identification corresponding to the preset voiceprint feature when the preset voice content and the preset voiceprint feature are inquired; sending a door opening control instruction to an electromagnetic lock corresponding to the locker identification; the door opening control instruction is used for indicating the electromagnetic lock to open the locker corresponding to the locker identification.

In one embodiment, before the step of obtaining the voice information detected by the voice detector is implemented when the processor executes the computer program, the following steps are also implemented: acquiring a fetching instruction; generating a picking code according to the picking instruction and displaying the picking code through a display; the piece taking code is used as preset voice content matched with the target voice content; acquiring the voice information detected by the voice detector, including: acquiring voice information detected by a voice detector according to the pick-up instruction; the voice information carries the pick-up code.

In one embodiment, querying preset voice content matching the target voice content and preset voiceprint features matching the target voiceprint features comprises: for each pre-stored candidate voice content, respectively calculating a first matching rate between the candidate voice content and the target voice content; determining candidate voice contents with the first matching rate meeting a first preset matching condition as preset voice contents matched with target voice contents; for each pre-stored candidate voiceprint feature, respectively calculating a second matching rate between the candidate voiceprint feature and the target voiceprint feature; and determining the candidate voiceprint features with the second matching rate meeting the second preset matching condition as preset voiceprint features matched with the target voiceprint features.

In one embodiment, the processor when executing the computer program further performs the steps of: when the electromagnetic lock opens the locker corresponding to the locker identification according to the door opening control instruction, deleting the corresponding relation between the locker identification and the preset voiceprint feature.

In one embodiment, before the step of sending the door opening control command to the electromagnetic lock corresponding to the locker identification is implemented when the processor executes the computer program, the following steps are further implemented: receiving article information detected and sent by an article detection device corresponding to the locker identification; selecting question data from a prestored question set according to the article information; generating corresponding questioning voice information according to the questioning data, and sending the questioning voice information to a voice detector; obtaining answering voice information corresponding to the answering voice information detected by the voice detector; extracting corresponding answer data from the answer voice information through a voice recognition model; determining a correct answer corresponding to the questioning data according to the article information; when the answer data is matched with the correct answer, a door opening control instruction is correspondingly generated.

In one embodiment, the processor when executing the computer program further performs the steps of: acquiring the piece-storing voice information detected by the voice detector according to the piece-storing instruction; extracting corresponding voice print characteristics of the stored part from voice information of the stored part through a voice print recognition model; selecting a locker identification from candidate locker identifications, and establishing a corresponding relation between the sound print feature of the stored part and the locker identification; correspondingly storing the voiceprint features of the stored part and the storage cabinet identifier and the established corresponding relation; the stock voiceprint feature is used as a pre-stored pre-set voiceprint feature.

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring voice information detected by a voice detector; extracting target voice content from voice information through a voice recognition model, and extracting target voiceprint features from the voice information through a voiceprint recognition model; inquiring preset voice content matched with the target voice content and preset voiceprint characteristics matched with the target voiceprint characteristics; inquiring a locker identification corresponding to the preset voiceprint feature when the preset voice content and the preset voiceprint feature are inquired; sending a door opening control instruction to an electromagnetic lock corresponding to the locker identification; the door opening control instruction is used for indicating the electromagnetic lock to open the locker corresponding to the locker identification.

In one embodiment, before the step of obtaining the speech information detected by the speech detector is implemented when the computer program is executed by the processor, the following steps are also implemented: acquiring a fetching instruction; generating a picking code according to the picking instruction and displaying the picking code through a display; the piece taking code is used as preset voice content matched with the target voice content; acquiring the voice information detected by the voice detector, including: acquiring voice information detected by a voice detector according to the pick-up instruction; the voice information carries the pick-up code.

In one embodiment, the computer program when executed by the processor further performs the steps of: when the electromagnetic lock opens the locker corresponding to the locker identification according to the door opening control instruction, deleting the corresponding relation between the locker identification and the preset voiceprint feature.

In one embodiment, before the step of sending the door opening control command to the electromagnetic lock corresponding to the locker identification is implemented when the computer program is executed by the processor, the following steps are further implemented: receiving article information detected and sent by an article detection device corresponding to the locker identification; selecting question data from a prestored question set according to the article information; generating corresponding questioning voice information according to the questioning data, and sending the questioning voice information to a voice detector; obtaining answering voice information corresponding to the answering voice information detected by the voice detector; extracting corresponding answer data from the answer voice information through a voice recognition model; determining a correct answer corresponding to the questioning data according to the article information; when the answer data is matched with the correct answer, a door opening control instruction is correspondingly generated.

In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring the piece-storing voice information detected by the voice detector according to the piece-storing instruction; extracting corresponding voice print characteristics of the stored part from voice information of the stored part through a voice print recognition model; selecting a locker identification from candidate locker identifications, and establishing a corresponding relation between the sound print feature of the stored part and the locker identification; correspondingly storing the voiceprint features of the stored part and the storage cabinet identifier and the established corresponding relation; the stock voiceprint feature is used as a pre-stored pre-set voiceprint feature.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims

1. A method of controlling a locker, the method comprising:

acquiring voice information detected by a voice detector;

inquiring preset voice content matched with the target voice content and preset voiceprint features matched with the target voiceprint features; the preset voice information comprises the preset voice content and the preset voiceprint characteristics, and the preset voice information is voice information corresponding to a storage user, which is acquired in the storage process;

receiving article information detected and sent by an article detection device corresponding to the locker identification; selecting question data from a prestored question set according to the article information; generating corresponding questioning voice information according to the questioning data, and sending the questioning voice information to the voice detector; obtaining answer voice information corresponding to the question voice information detected by the voice detector; extracting corresponding answer data from the answer voice information through the voice recognition model; determining correct answers corresponding to the questioning data according to the article information; when the answer data is matched with the correct answer, correspondingly generating a door opening control instruction;

2. The method of claim 1, wherein prior to the obtaining the voice information detected by the voice detector, the method further comprises:

Acquiring a fetching instruction;

3. The method of claim 1, wherein the querying the pre-set voice content that matches the target voice content and the pre-set voiceprint features that match the target voiceprint features comprises:

4. The method according to claim 1, wherein the method further comprises:

5. The method according to any one of claims 1 to 4, further comprising:

6. A locker control apparatus, the apparatus comprising:

The matching module is used for inquiring preset voice content matched with the target voice content and preset voiceprint features matched with the target voiceprint features; the preset voice information comprises the preset voice content and the preset voiceprint characteristics, and the preset voice information is voice information corresponding to a storage user, which is acquired in the storage process;

the question-answering module is used for receiving article information detected and sent by the article detection device corresponding to the locker identification; selecting question data from a prestored question set according to the article information; generating corresponding questioning voice information according to the questioning data, and sending the questioning voice information to the voice detector; obtaining answer voice information corresponding to the question voice information detected by the voice detector; extracting corresponding answer data from the answer voice information through the voice recognition model; determining correct answers corresponding to the questioning data according to the article information; when the answer data is matched with the correct answer, correspondingly generating a door opening control instruction;

7. The apparatus of claim 6, wherein the acquisition module is further configured to acquire a fetch instruction; generating a pickup code according to the pickup instruction and displaying the pickup code through a display; the piece taking code is used as preset voice content matched with the target voice content; acquiring voice information detected by a voice detector according to the pick-up instruction; the voice information carries the picking code.

8. The apparatus of claim 6, wherein the apparatus further comprises: deleting the module;

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.