CN108122314B - Doorbell call processing method, cloud server, medium and system - Google Patents
Doorbell call processing method, cloud server, medium and system Download PDFInfo
- Publication number
- CN108122314B CN108122314B CN201711342534.2A CN201711342534A CN108122314B CN 108122314 B CN108122314 B CN 108122314B CN 201711342534 A CN201711342534 A CN 201711342534A CN 108122314 B CN108122314 B CN 108122314B
- Authority
- CN
- China
- Prior art keywords
- visitor
- doorbell
- cloud server
- authentication
- voice
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/20—Individual registration on entry or exit involving the use of a pass
- G07C9/22—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
- G07C9/25—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
- G07C9/257—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition electronically
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Interconnected Communication Systems, Intercoms, And Interphones (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a doorbell call processing method, which comprises the following steps: the cloud server receives a call request sent by a doorbell according to the triggering operation of a visitor; the cloud server sends an authentication request audio frequency to the doorbell according to the call request, so that the doorbell plays the authentication request audio frequency to the visitor, and after the authentication request audio frequency is played, an authentication voice replied by the visitor is recorded; the cloud server receives the authentication voice fed back by the doorbell; the cloud server verifies the authentication voice; and the cloud server sends a control instruction to the doorbell when the authentication voice verification is successful, so that the doorbell controls the door lock to be opened. Correspondingly, the invention also discloses a cloud server, a medium and a system. The embodiment of the invention can improve the processing efficiency of doorbell calling and improve user experience.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a doorbell call request processing method, a cloud server, a medium and a system.
Background
In order to better manage resident visitors, doorbells are almost arranged in residential buildings so as to prompt residents that visitors visit and the residents decide whether to open the building entrance guard or not.
The traditional doorbell is only a simple message triggering system, namely a trigger is arranged at the door of a building, a receiver is arranged in the house, and when a visitor triggers the trigger, the receiver can receive a signal and send a sound to remind a resident in the house. The talkback or visual doorbell is added with a talkback or visual function on the basis of the traditional doorbell, and not only can transmit a trigger signal, but also can transmit voice or image information. The internet doorbell expands the channel of information transmission of talkback or visual doorbell, and connects the user terminal with the doorbell, so that doorbell calling can be transmitted to the user terminal of a resident.
However, whether traditional doorbell, talkback or visual doorbell or internet doorbell, when the visitor calls through the doorbell, all need the resident family to confirm the visitor's identity in person, and whether the decision needs to open the door again leads to doorbell call's processing efficiency low, and doorbell call can inform each resident family in the room through the mode of sound or message in addition for it is targeted not to call, and user experience is poor.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a doorbell call request processing method, a cloud server, a medium and a system, which can improve the doorbell call processing efficiency and improve the user experience.
The technical scheme provided by the invention for the technical problem is as follows:
the invention provides a doorbell call processing method, which comprises the following steps:
the cloud server receives a call request sent by a doorbell according to the triggering operation of a visitor;
the cloud server sends an authentication request audio frequency to the doorbell according to the call request, so that the doorbell plays the authentication request audio frequency to the visitor, and after the authentication request audio frequency is played, an authentication voice replied by the visitor is recorded;
the cloud server receives the authentication voice fed back by the doorbell;
the cloud server verifies the authentication voice;
and the cloud server sends a control instruction to the doorbell when the authentication voice verification passes, so that the doorbell controls the door lock to be opened.
In a preferred embodiment, the authentication request audio includes a request audio for inquiring an authentication password, and the authentication voice includes the authentication password;
the cloud server verifies the authentication voice, and specifically includes:
verifying whether the authentication password is consistent with a visitor password preset by an addressee; and if so, judging that the authentication voice verification is successful.
In another preferred embodiment, the authentication request audio includes a request audio inquiring an authentication password and a guest identity, and the authentication voice includes an authentication password and guest identity information;
the cloud server verifies the authentication voice, and specifically includes:
verifying whether the authentication password is consistent with a visitor password preset by an addressee;
if so, acquiring a visitor image sent by the doorbell, and matching a face image with the highest similarity with the visitor image from a pre-established face library; the visitor image is an image with a visitor face, which is acquired by the doorbell according to the triggering operation of the visitor;
verifying whether the visitor identity information is consistent with identity information corresponding to the visitor password preset by the visitor and identity information corresponding to the matched face image; and if the two are consistent, judging that the authentication voice verification is successful.
Further, the doorbell call processing method further comprises:
and when the authentication voice verification is successful, the cloud server correspondingly stores the visitor identity information and the visitor image in the face library.
Further, the doorbell call processing method further comprises:
the cloud server sends a request audio for inquiring a visiting intention to the doorbell when the authentication voice verification fails, so that the doorbell plays the request audio to the visitor, and records a visiting voice replied by the visitor after the request audio is played; the call voice comprises a call intention of the visitor;
the cloud server receives the visiting voice fed back by the doorbell;
and the cloud server sends a response audio corresponding to the visit intention and preset by the visitor to the doorbell, so that the doorbell plays the response audio to the visitor.
Further, the doorbell call processing method further comprises:
and when the authentication voice verification fails, the cloud server feeds back failure audio to the doorbell, sends a calling instruction to the user terminal, establishes communication connection between the user terminal and the doorbell, and enables the interviewee and the visitor to communicate directly.
Accordingly, the present invention provides a cloud server comprising:
the request receiving module is used for receiving a call request sent by a doorbell according to the triggering operation of a visitor;
the first audio sending module is used for sending an authentication request audio to the doorbell according to the call request, so that the doorbell plays the authentication request audio to the visitor, and after the authentication request audio is played, an authentication voice replied by the visitor is recorded;
the authentication voice feedback module is used for receiving the authentication voice fed back by the doorbell by the cloud server;
the verification module is used for verifying the authentication voice by the cloud server; and the number of the first and second groups,
and the control module is used for sending a control instruction to the doorbell by the cloud server when the authentication voice verification is successful, so that the doorbell controls the door lock to be opened.
In a preferred embodiment, the authentication request audio includes a request audio for inquiring an authentication password, and the authentication voice includes the authentication password;
the verification module is specifically configured to:
verifying whether the authentication password is consistent with a visitor password preset by an addressee; and if so, judging that the authentication voice verification is successful.
In another preferred embodiment, the authentication request audio includes a request audio inquiring an authentication password and a guest identity, and the authentication voice includes an authentication password and guest identity information;
the verification module specifically comprises:
the first verification unit is used for verifying whether the authentication password is consistent with a visitor password preset by an addressee;
the matching unit is used for acquiring the visitor image sent by the doorbell when the visitor images are consistent with each other, and matching the face image with the highest similarity with the visitor image from a pre-established face library; the visitor image is an image with a visitor face, which is acquired by the doorbell according to the triggering operation of the visitor; and the number of the first and second groups,
the second verification unit is used for verifying whether the visitor identity information is consistent with identity information corresponding to the visitor password preset by the visited person and identity information corresponding to the matched face image; and if the two are consistent, judging that the authentication voice verification is successful.
Further, the cloud server further includes:
and the storage module is used for correspondingly storing the visitor identity information and the visitor image in the face library when the authentication voice verification is successful.
Further, the cloud server further includes:
the second audio sending module is used for sending a request audio for inquiring the visiting intention to the doorbell when the authentication voice verification fails, so that the doorbell plays the request audio to the visitor, and records the visiting voice replied by the visitor after the request audio is played; the call voice comprises a call intention of the visitor;
the visit voice feedback module is used for receiving the visit voice fed back by the doorbell; and the number of the first and second groups,
and the answer audio sending module is used for sending answer audio which is preset by the interviewee and corresponds to the visit intention to the doorbell, so that the doorbell plays the answer audio to the visitor.
Further, the cloud server further includes:
and the instruction sending module is used for feeding back failure audio to the doorbell when the authentication voice verification fails, sending a calling instruction to the user terminal, and establishing communication connection between the user terminal and the doorbell so that an interviewee can directly communicate with a visitor.
Correspondingly, the invention also provides a computer-readable storage medium, which comprises a stored computer program, wherein when the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the doorbell call processing method.
Correspondingly, the invention also provides a doorbell call processing system, which comprises a doorbell, a cloud server and a door lock;
the doorbell is used for sending a call request to the cloud server according to the triggering operation of a user and controlling the door lock to be opened according to a control instruction sent by the cloud server;
the cloud server is the cloud server.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
when the visitor triggers the doorbell to enable the doorbell to send a call request, the cloud server sends authentication request audio to the doorbell, the cloud server actively interacts with the visitor to enable the visitor to enter authentication voice through the doorbell, then the cloud server verifies the authentication voice entered by the visitor, and opens the door lock to enable the visitor to enter when the verification is successful, the visitor can be called and processed without being participated in interaction, the processing efficiency is improved, and each resident in a room does not need to be notified, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart diagram illustrating one embodiment of a doorbell call processing method provided by the present invention;
FIG. 2 is a schematic structural diagram of one embodiment of a cloud server provided by the present invention;
fig. 3 is a schematic structural diagram of an embodiment of a doorbell call processing system provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
An embodiment of the present invention provides a method for processing a doorbell call, and referring to fig. 1, the method includes:
s1, the cloud server receives a call request sent by the doorbell according to the triggering operation of the visitor;
s2, the cloud server sends an authentication request audio frequency to the doorbell according to the call request, so that the doorbell plays the authentication request audio frequency to the visitor, and after the authentication request audio frequency is played, the authentication voice replied by the visitor is recorded;
s3, the cloud server receives the authentication voice fed back by the doorbell;
s4, the cloud server verifies the authentication voice;
and S5, when the authentication voice verification is successful, the cloud server sends a control instruction to the doorbell to enable the doorbell to control the door lock to be opened.
It should be noted that the doorbell generally comprises main hardware such as a call button, a microprocessor, a camera, a microphone, a speaker, and a network (WiFi) module, wherein the camera can record video data, the microphone can record audio data, the speaker can play audio data, and the network module can transmit recorded audio and video data to the cloud server in real time. Install application APP on the user terminal to use with the doorbell is supporting, behind the user terminal networking, APP on the user terminal communicates with cloud ware, with the information of receiving cloud ware transmission, APP on the user terminal still has auxiliary function such as user management and equipment management in addition. The cloud server is mainly used for establishing data connection with the doorbell and the user terminal respectively to achieve data communication between the doorbell and the user terminal.
In this embodiment, the cloud server constructs an AI program for human-computer interaction with the visitor using a machine learning method and a big data method. The visitor triggers a call button on the doorbell, namely after the visitor presses the call button, the doorbell sends a call request to the cloud server, and the cloud server activates the AI program, so that the AI program sends an authentication request audio to the doorbell, and the authentication request audio is played through the doorbell to actively ask a question to the visitor. After hearing the questions, the visitor answers correspondingly through voice, and the doorbell records the authentication voice replied by the visitor aiming at the questions. The doorbell feeds back recorded authentication voice to the cloud server, an AI program on the cloud server analyzes the authentication voice and judges whether more detailed information of a visitor needs to be acquired, if so, request audio continues to be fed back to the doorbell to solve more detailed problems of the user through the doorbell, if not, interaction is finished, the AI program verifies the authentication voice, and when the authentication voice meets the unlocking condition set by the visitor through the user terminal, a control instruction is sent to the doorbell, the doorbell can control the door lock to be opened, the visitor enters the doorbell, and meanwhile, the AI program sends a reminding notice to the user terminal.
The AI program running on the cloud server can meet the requirements of various visitors through continuous updating, and the corresponding correctness and execution efficiency of the visitors are improved. In addition, the AI program integrates ASR (automatic speech recognition) and NLU (natural language understanding) to analyze and recognize received audio data and understand the meaning expressed in the audio data.
In a preferred embodiment, the authentication request audio includes a request audio for inquiring an authentication password, and the authentication voice includes the authentication password;
the cloud server verifies the authentication voice, and specifically includes:
verifying whether the authentication password is consistent with a visitor password preset by an addressee; and if so, judging that the authentication voice verification is successful.
It should be noted that, the visited person may set a password (generally, a 4-digit password) of the visitor through the user terminal, and the visitor password is notified to the visitor before the visitor visits. The number of the visitor passwords can be multiple, and each password can be used for setting the number of times of use (for example, the password can be used only once or multiple times), a use object (for example, any person can use or a specified visitor can use the password), effective use time and the like.
If the visitor sets a visitor password to be usable by anyone, and sets the use time threshold and the effective use time of the visitor password, after an AI program running on the cloud server verifies that the authentication password in the authentication voice of the visitor is consistent with the visitor password, the current use time of the visitor password is judged to exceed the use time threshold, and the current time is judged to be within the effective use time, if the current use time of the visitor password does not exceed the use time threshold, and the current time is within the effective use time, the authentication is judged to be passed, and the door lock is opened through the doorbell to allow the visitor to enter.
In another preferred embodiment, the authentication request audio includes a request audio inquiring an authentication password and a guest identity, and the authentication voice includes an authentication password and guest identity information;
the cloud server verifies the authentication voice, and specifically includes:
verifying whether the authentication password is consistent with a visitor password preset by an addressee;
if so, acquiring a visitor image sent by the doorbell, and matching a face image with the highest similarity with the visitor image from a pre-established face library; the visitor image is an image with a visitor face, which is acquired by the doorbell according to the triggering operation of the visitor;
verifying whether the visitor identity information is consistent with identity information corresponding to the visitor password preset by the visitor and identity information corresponding to the matched face image; and if the two are consistent, judging that the authentication voice verification is successful.
It should be noted that, if the visitor sets a visitor password to be available for the designated visitor, and sets the threshold of the number of times of use and the effective use time of the visitor password, the AI program running on the cloud server verifies that the authentication password in the authentication voice of the visitor is consistent with the visitor password, and then the identity of the visitor needs to be verified. The AI program finds a face in a visitor image collected by a doorbell through the face detection capability, extracts face features, finds a face image with the highest similarity with the face of a visitor in a face library through the face search capability, so as to acquire identity information corresponding to the face image, judges whether the identity information is consistent with visitor identity information in authentication voice of the visitor and an appointed visitor corresponding to a password of the visitor, and if so, successfully verifies the identity of the visitor. And then, the AI program judges whether the use times of the current visitor password exceed the use time threshold value of the current visitor password and judges whether the current time is within the effective use time of the current visitor password, if the use times of the current visitor password do not exceed the use time threshold value of the current visitor password and the current time is within the effective use time of the current visitor password, the authentication is judged to be passed, and the door lock can be opened through the doorbell to allow the visitor to enter.
Further, the doorbell call processing method further comprises:
and when the authentication voice verification is successful, the cloud server correspondingly stores the visitor identity information and the visitor image in the face library.
It should be noted that the face library is a database that stores various face images and corresponding relationships between the face images and identity information thereof, and can be updated in real time. When a visitor gets home for the first time, the AI program running on the cloud server cannot identify the identity of the visitor, so that in the first interaction process with the visitor, the identity of the visitor, such as the name of the visitor and the like, can be inquired through the doorbell, the image of the visitor is collected, and the image of the visitor and the identity information of the visitor are automatically stored in the face library in a corresponding mode so that the identity of the visitor is identified when the visitor visits subsequently. In addition, the interviewee can update the face library through the user terminal, namely the interviewee imports the face image of the visitor and marks the identity of the visitor, and the cloud server stores the face image and the corresponding identity information of the visitor into the face library.
When the visitor subsequently visits, the cloud server correspondingly stores the visitor identity information and the visitor image in the face library whenever the authentication voice verification of the visitor is successful so as to enrich the face library and improve the accuracy of subsequent visitor identification.
Further, the doorbell call processing method further comprises:
the cloud server sends a request audio for inquiring a visiting intention to the doorbell when the authentication voice verification fails, so that the doorbell plays the request audio to the visitor, and records a visiting voice replied by the visitor after the request audio is played; the call voice comprises a call intention of the visitor;
the cloud server receives the visiting voice fed back by the doorbell;
and the cloud server sends a response audio corresponding to the visit intention and preset by the visitor to the doorbell, so that the doorbell plays the response audio to the visitor.
It should be noted that, for a visitor who has a visitor password agreed with the visitor in advance, the visitor can enter the system through authentication of the cloud server, and for an unexpected visit, such as a visit of a water delivery worker or a courier, the AI program running on the cloud server performs different processing through different visit intentions of the visitor. The processing mode can be set by the interviewee in advance. For example, the visit intention of the water delivery worker is water delivery, the AI program sends a reply audio of 'putting water at the door' to the doorbell, the water delivery worker directly puts water at the door after hearing the reply audio without calling the visited person for immediate processing, and meanwhile, the AI program sends a reminding message to the user terminal. The visit intention of the courier is to send the express, but the express is an important file and needs to be signed by the addressee, and the AI program sends a calling instruction to the user terminal to call the addressee for intervention.
In addition, through the analysis of the date data, the AI can determine the probability of each visit intention of a certain visitor, for example, after a certain fixed courier sends couriers frequently, the AI can find that the visitor is a familiar courier through image recognition, so that the voice interaction process is skipped, and the process of courier processing is directly entered.
In addition, when the cloud server is connected with the doorbell and the APP of the user terminal, the corresponding relation between the doorbell and at least one user terminal is established, and meanwhile, the user identity information of each user terminal is stored. Specifically indicating the object to be visited in the visitor's visit intention, the AI program sends reminding information or calling instruction to the user terminal APP corresponding to the object to inform the visitor of the object to be visited accurately and with pertinence, avoiding disturbing other users, and improving user experience.
Further, the doorbell call processing method further comprises:
and when the authentication voice verification fails, the cloud server feeds back failure audio to the doorbell, sends a calling instruction to the user terminal, establishes communication connection between the user terminal and the doorbell, and enables the interviewee and the visitor to communicate directly.
It should be noted that, if the door lock fails to be opened, the AI program sends a failure audio to the doorbell to explain the reason for the failure to the visitor. For example, if the password is authenticated incorrectly, the visitor may be asked to re-enter the password; the current time is earlier than the effective use time of the guest password, and the guest arrives earlier and may be asked to try again later. The AI program can also directly call the user terminal to make the visitor communicate with the addressee directly.
In addition, the whole interaction process of the visitor and the doorbell is stored in the cloud server, the visitor can check the historical records through the user terminal, and the whole interaction process can be monitored by checking live video in real time.
According to the embodiment of the invention, when the visitor triggers the doorbell to enable the doorbell to send the call request, the cloud server sends the authentication request audio to the doorbell to actively interact with the visitor, so that the visitor inputs the authentication voice through the doorbell, the cloud server verifies the authentication voice input by the visitor and opens the door lock to enable the visitor to enter when the verification is passed, the doorbell call can be processed without the visitor participating in interaction, the processing efficiency is improved, and each resident in a house is not required to be notified, so that the user experience is improved.
Correspondingly, an embodiment of the present invention further provides a cloud server, which can implement all the processes of the doorbell call processing method, and with reference to fig. 2, the cloud server includes:
a request receiving module 21, configured to receive a call request sent by a doorbell according to a trigger operation of a visitor;
the first audio sending module 22 is configured to send an authentication request audio to the doorbell according to the call request, so that the doorbell plays the authentication request audio to the visitor, and after the authentication request audio is played, records an authentication voice replied by the visitor;
the authentication voice feedback module 23 is configured to receive the authentication voice fed back by the doorbell by the cloud server;
a verification module 24, configured to verify the authentication voice by the cloud server; and the number of the first and second groups,
and the control module 25 is used for sending a control instruction to the doorbell by the cloud server when the authentication voice verification is successful, so that the doorbell controls the door lock to be opened.
In a preferred embodiment, the authentication request audio includes a request audio for inquiring an authentication password, and the authentication voice includes the authentication password;
the verification module is specifically configured to:
verifying whether the authentication password is consistent with a visitor password preset by an addressee; and if so, judging that the authentication voice verification is successful.
In another preferred embodiment, the authentication request audio includes a request audio inquiring an authentication password and a guest identity, and the authentication voice includes an authentication password and guest identity information;
the verification module specifically comprises:
the first verification unit is used for verifying whether the authentication password is consistent with a visitor password preset by an addressee;
the matching unit is used for acquiring the visitor image sent by the doorbell when the visitor images are consistent with each other, and matching the face image with the highest similarity with the visitor image from a pre-established face library; the visitor image is an image with a visitor face, which is acquired by the doorbell according to the triggering operation of the visitor; and the number of the first and second groups,
the second verification unit is used for verifying whether the visitor identity information is consistent with identity information corresponding to the visitor password preset by the visited person and identity information corresponding to the matched face image; and if the two are consistent, judging that the authentication voice verification is successful.
Further, the cloud server further includes:
and the storage module is used for correspondingly storing the visitor identity information and the visitor image in the face library when the authentication voice verification is successful.
Further, the cloud server further includes:
the second audio sending module is used for sending a request audio for inquiring the visiting intention to the doorbell when the authentication voice verification fails, so that the doorbell plays the request audio to the visitor, and records the visiting voice replied by the visitor after the request audio is played; the call voice comprises a call intention of the visitor;
the visit voice feedback module is used for receiving the visit voice fed back by the doorbell; and the number of the first and second groups,
and the answer audio sending module is used for sending answer audio which is preset by the interviewee and corresponds to the visit intention to the doorbell, so that the doorbell plays the answer audio to the visitor.
Further, the cloud server further includes:
and the instruction sending module is used for feeding back failure audio to the doorbell when the authentication voice verification fails, sending a calling instruction to the user terminal, and establishing communication connection between the user terminal and the doorbell so that an interviewee can directly communicate with a visitor.
According to the embodiment of the invention, when the visitor triggers the doorbell to enable the doorbell to send the call request, the cloud server sends the authentication request audio to the doorbell to actively interact with the visitor, so that the visitor inputs the authentication voice through the doorbell, the cloud server verifies the authentication voice input by the visitor and opens the door lock to enable the visitor to enter when the verification is successful, the doorbell call can be processed without the visitor participating in interaction, the processing efficiency is improved, and each resident in a house is not required to be notified, so that the user experience is improved.
Correspondingly, the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where the computer program controls, when running, a device where the computer-readable storage medium is located to execute the doorbell call processing method, and details are not described herein again.
Correspondingly, the invention also provides a doorbell call processing system, which comprises a doorbell 1, a cloud server 2 and a door lock 3, and is shown in FIG. 3;
the doorbell 1 is used for sending a call request to the cloud server 2 according to a trigger operation of a user and controlling the door lock 3 to be opened according to a control instruction sent by the cloud server 2;
the cloud server 2 is the cloud server.
According to the embodiment of the invention, when the visitor triggers the doorbell to enable the doorbell to send the call request, the cloud server sends the authentication request audio to the doorbell to actively interact with the visitor, so that the visitor inputs the authentication voice through the doorbell, the cloud server verifies the authentication voice input by the visitor and opens the door lock to enable the visitor to enter when the verification is successful, the doorbell call can be processed without the visitor participating in interaction, the processing efficiency is improved, and each resident in a house is not required to be notified, so that the user experience is improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A method for processing a doorbell call, comprising: the cloud server receives a call request sent by a doorbell according to the triggering operation of a visitor; the cloud server sends an authentication request audio frequency to the doorbell according to the call request, so that the doorbell plays the authentication request audio frequency to the visitor, and after the authentication request audio frequency is played, an authentication voice replied by the visitor is recorded; the cloud server receives the authentication voice fed back by the doorbell; the cloud server verifies the authentication voice; when the authentication voice verification is successful, the cloud server sends a control instruction to the doorbell to enable the doorbell to control the door lock to be opened; the doorbell call processing method comprises the following steps that the authentication request audio comprises a request audio for inquiring an authentication password and visitor identity, and the authentication voice comprises the authentication password and visitor identity information: the cloud server sends a request audio for inquiring a visiting intention to the doorbell when the authentication voice verification fails, so that the doorbell plays the request audio to the visitor, and records a visiting voice replied by the visitor after the request audio is played; the call voice comprises a call intention of the visitor; the cloud server receives the visiting voice fed back by the doorbell; and the cloud server sends a response audio corresponding to the visit intention and preset by the visitor to the doorbell, so that the doorbell plays the response audio to the visitor.
2. The doorbell call processing method according to claim 1, wherein the verifying the authentication voice by the cloud server specifically includes: verifying whether the authentication password is consistent with a visitor password preset by an addressee; if so, acquiring a visitor image sent by the doorbell, and matching a face image with the highest similarity with the visitor image from a pre-established face library; the visitor image is an image with a visitor face, which is acquired by the doorbell according to the triggering operation of the visitor; verifying whether the visitor identity information is consistent with identity information corresponding to the visitor password preset by the visitor and identity information corresponding to the matched face image; and if the two are consistent, judging that the authentication voice verification is successful.
3. The doorbell call processing method of claim 2, further comprising: and when the authentication voice verification is successful, the cloud server correspondingly stores the visitor identity information and the visitor image in the face library.
4. A cloud server, comprising: the request receiving module is used for receiving a call request sent by a doorbell according to the triggering operation of a visitor; the first audio sending module is used for sending an authentication request audio to the doorbell according to the call request, so that the doorbell plays the authentication request audio to the visitor, and after the authentication request audio is played, an authentication voice replied by the visitor is recorded; the authentication voice feedback module is used for receiving the authentication voice fed back by the doorbell by the cloud server; the verification module is used for verifying the authentication voice by the cloud server; the cloud server is used for sending a control instruction to the doorbell to enable the doorbell to control the door lock to be opened when the authentication voice verification is successful, wherein the authentication request audio comprises a request audio for inquiring an authentication password and visitor identity, and the authentication voice comprises the authentication password and visitor identity information;
the cloud server sends a request audio for inquiring a visiting intention to the doorbell when the authentication voice verification fails, so that the doorbell plays the request audio to the visitor, and records a visiting voice replied by the visitor after the request audio is played; the call voice comprises a call intention of the visitor; the cloud server receives the visiting voice fed back by the doorbell; and the cloud server sends a response audio corresponding to the visit intention and preset by the visitor to the doorbell, so that the doorbell plays the response audio to the visitor.
5. The cloud server of claim 4, wherein the verification module specifically comprises: the first verification unit is used for verifying whether the authentication password is consistent with a visitor password preset by an addressee; the matching unit is used for acquiring the visitor image sent by the doorbell when the visitor images are consistent with each other, and matching the face image with the highest similarity with the visitor image from a pre-established face library; the visitor image is an image with a visitor face, which is acquired by the doorbell according to the triggering operation of the visitor; the second verification unit is used for verifying whether the visitor identity information is consistent with identity information corresponding to the visitor password preset by the interviewee and identity information corresponding to the matched face image; and if the two are consistent, judging that the authentication voice verification is successful.
6. The cloud server of claim 5, wherein the cloud server further comprises: and the storage module is used for correspondingly storing the visitor identity information and the visitor image in the face library when the authentication voice verification is successful.
7. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus on which the computer-readable storage medium is located to perform the doorbell call handling method of any one of claims 1 to 3.
8. A doorbell call processing system is characterized by comprising a doorbell, a cloud server and a door lock; the doorbell is used for sending a call request to the cloud server according to the triggering operation of a user and controlling the door lock to be opened according to a control instruction sent by the cloud server; the cloud server according to any one of claims 4 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711342534.2A CN108122314B (en) | 2017-12-14 | 2017-12-14 | Doorbell call processing method, cloud server, medium and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711342534.2A CN108122314B (en) | 2017-12-14 | 2017-12-14 | Doorbell call processing method, cloud server, medium and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108122314A CN108122314A (en) | 2018-06-05 |
| CN108122314B true CN108122314B (en) | 2020-12-22 |
Family
ID=62230025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711342534.2A Active CN108122314B (en) | 2017-12-14 | 2017-12-14 | Doorbell call processing method, cloud server, medium and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108122314B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109118616A (en) | 2018-07-09 | 2019-01-01 | 深圳市商汤科技有限公司 | access control method and access control device |
| CN109741500B (en) * | 2018-12-29 | 2022-05-10 | 北京方正数码有限公司 | Temporary password setting and verification method for intelligent lock |
| CN110784682B (en) * | 2019-09-27 | 2021-11-09 | 深圳市海雀科技有限公司 | Video processing method and device and electronic equipment |
| CN110730330B (en) * | 2019-09-27 | 2021-11-09 | 深圳市海雀科技有限公司 | Sound processing method and device, doorbell and computer readable storage medium |
| CN111862411A (en) * | 2020-07-10 | 2020-10-30 | 广州博冠智能科技有限公司 | Intelligent household door lock control method, device, equipment and storage medium |
| CN112330865B (en) * | 2020-07-31 | 2024-04-30 | 深圳Tcl新技术有限公司 | Doorbell sharing method, doorbell sharing system and computer readable storage medium |
| CN112270816A (en) * | 2020-10-22 | 2021-01-26 | 江苏峰鑫网络科技有限公司 | Remote calling system based on cloud network |
| CN112687045B (en) * | 2020-12-25 | 2023-01-17 | 广州市果豆科技有限责任公司 | Intelligent building entrance guard intercom system |
| CN113114969B (en) * | 2021-04-17 | 2022-06-10 | 深圳市元睿城市智能发展有限公司 | Intelligent video intercom monitoring system and intercom monitoring method for intelligent building based on big data |
| CN113724455A (en) * | 2021-08-31 | 2021-11-30 | 北京小米移动软件有限公司 | Doorbell, control method thereof and storage medium |
| CN113763615A (en) * | 2021-10-28 | 2021-12-07 | 李金波 | Intelligent property access control management method and system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853535B (en) * | 2010-05-25 | 2013-04-24 | 无锡中星微电子有限公司 | Door control system and door control management method |
| CN103632416A (en) * | 2012-08-27 | 2014-03-12 | 青岛联合创新技术服务平台有限公司 | Voice recognition remote-control access and working method thereof |
| CN104167040B (en) * | 2014-09-02 | 2016-11-02 | 深圳攀多物联科技有限公司 | The long-range control method of a kind of electronic lock and system |
| CN104952138A (en) * | 2015-07-21 | 2015-09-30 | 金琥 | Voice interactive access control system and achievement method thereof |
| CN106097495A (en) * | 2016-06-03 | 2016-11-09 | 赵树龙 | A kind of intelligent voice control vocal print face authentication door access control system and method |
| CN106375641A (en) * | 2016-08-31 | 2017-02-01 | 深圳博科智能科技有限公司 | Home-entry video intercom robot and home-entry video intercom control method |
| CN106791665A (en) * | 2016-12-28 | 2017-05-31 | 重庆金鑫科技产业发展有限公司 | A kind of intelligent electronic door bell and intelligent domestic system |
-
2017
- 2017-12-14 CN CN201711342534.2A patent/CN108122314B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108122314A (en) | 2018-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108122314B (en) | Doorbell call processing method, cloud server, medium and system | |
| CN108154579B (en) | Intelligent access control system capable of interacting with visitors and interaction method | |
| CN111401826A (en) | Double-recording method and device for signing electronic contract, computer equipment and storage medium | |
| CN110213522A (en) | A kind of video data handling procedure, device and relevant device | |
| CN104078045B (en) | Identifying method and electronic device | |
| CN111971647A (en) | Speech recognition apparatus, cooperation system of speech recognition apparatus, and cooperation method of speech recognition apparatus | |
| EP3249570A1 (en) | Method and device for providing prompt indicating loss of terminal | |
| CN108665595B (en) | Intelligent visual access control system | |
| CN111862411A (en) | Intelligent household door lock control method, device, equipment and storage medium | |
| CN109830015A (en) | Visiting personnel recognition methods, device, intelligent peephole, server and storage medium | |
| CN110768942B (en) | Identity authentication system | |
| CN113706758A (en) | Visitor reception method, system, equipment and storage medium | |
| CN112008736A (en) | Welcome robot allocation method and device, storage medium and electronic device | |
| CN112927408A (en) | Visitor visiting processing method and device | |
| CN113820963A (en) | Intelligent home control method and system based on Internet of things | |
| CN112911207A (en) | Calling method and intelligent talkback system | |
| CN112087603A (en) | Intelligent examination room supervision method | |
| CN111368721A (en) | Identity recognition processing method and device, electronic equipment and storage medium | |
| CN108171185B (en) | Identity recognition method, device and system | |
| CN111310949A (en) | Method for feeding back user experience by intelligent hardware product, feedback device and service platform | |
| CN109871785A (en) | Visiting personnel recognition methods, device, intelligent peephole, server and storage medium | |
| CN115546952A (en) | Method and device for managing parent access through cloud, electronic equipment and storage medium | |
| CN113538763A (en) | Entrance guard opening method, intelligent terminal and server | |
| CN113160463A (en) | Method and device for starting user identification device of vehicle and automobile control cloud | |
| CN111353771A (en) | Method, device, equipment and medium for remotely controlling payment |
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 |