CN109492368B - Secondary authentication method suitable for voice command response of intelligent equipment - Google Patents
Secondary authentication method suitable for voice command response of intelligent equipment Download PDFInfo
- Publication number
- CN109492368B CN109492368B CN201811257075.2A CN201811257075A CN109492368B CN 109492368 B CN109492368 B CN 109492368B CN 201811257075 A CN201811257075 A CN 201811257075A CN 109492368 B CN109492368 B CN 109492368B
- Authority
- CN
- China
- Prior art keywords
- voice command
- voice
- door
- command
- sound source
- 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
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000004044 response Effects 0.000 title claims abstract description 31
- 238000012790 confirmation Methods 0.000 claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 7
- 230000008859 change Effects 0.000 claims description 8
- 230000003068 static effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 11
- 230000003993 interaction Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000004807 localization Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
- H04L12/282—Controlling appliance services of a home automation network by calling their functionalities based on user interaction within the home
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/2133—Verifying human interaction, e.g., Captcha
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Linguistics (AREA)
- Automation & Control Theory (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Lock And Its Accessories (AREA)
Abstract
The invention discloses a secondary authentication method suitable for voice command response of intelligent equipment, which comprises the following steps: voice monitoring, namely acquiring a monitored voice command; dividing the types into control type commands and non-control type commands in advance; and for the monitoring voice command identification, executing when the command is identified as a non-control column command, otherwise, extracting a characteristic threshold value at a certain voice frequency and comparing the characteristic threshold value with pre-constructed voice sample information to judge whether the added person is a child: if yes, alarming and refusing to execute; otherwise, according to the comparison between the recognized sound source direction and the sound source sample direction at the door, judging whether the applicator is positioned at the door direction: if the door is located in the non-door direction, executing a command, otherwise, executing whether the door is in the door direction for secondary confirmation: comparing the re-identified sound source direction with the sound source sample direction, and judging that the sound source is positioned outside the doorway when the sound source is judged to be positioned at the doorway again; otherwise, the door is judged to be positioned at the inner side of the doorway and the command is executed. The invention realizes effective safety control on the intelligent equipment.
Description
Technical Field
The invention relates to a secondary authentication method suitable for voice command response of intelligent equipment, belonging to the technical field of safety control.
Background
In the smart device, compared with the traditional sound box, the smart sound box is a product of sound box upgrading. The latter is used as the terminal of the whole sound system, which only converts the audio frequency electric energy into the corresponding sound energy and radiates the sound energy to the space; the intelligent sound box is considered as an entrance of the internet of things era. In the internet era, users face an organic whole rather than a scattered combination of various household appliances and mobile devices, and a sound system is not exceptional. The sound box with the function of becoming intelligent gradually inherits the function of the traditional sound system and is an important component of the smart home, which is a tool for home consumers to surf the internet by voice, such as song-on-demand, online shopping or weather forecast understanding, and can also control smart home equipment, such as opening an intelligent door/window lock, setting the temperature of a refrigerator, raising the temperature of a water heater in advance and the like.
People have to pay more and more attention to the following safety problems while enjoying the convenience brought to life by the intelligent sound box, in particular to the following two problems:
1. children in families also have the same authority as parents, and the intelligent sound box is controlled through voice so as to control intelligent household equipment in the families, for example, an intelligent door/window lock is opened, the temperature of a refrigerator is set, a water heater is heated in advance, and the like, so that the corresponding safety cannot be ensured;
2. the voice command applier is located in the direction of the entrance door, particularly suspicious people outside the entrance door, controls the intelligent sound box through voice to carry out unauthorized online shopping or directly opens the intelligent door/window lock, so that the property of the family is lost;
therefore, the premise that the sound box drives the intelligent management and control home equipment is that the family is authorized by a person responsible for the household, especially the confirmation of the voice command is realized, namely the intelligent sound box has a secondary authentication function for responding to the voice command. However, for such problems, the existing smart speaker solutions generally have significant drawbacks:
1. most intelligent sound boxes are more focused on audio on demand and man-machine interaction, and intelligent household equipment is controlled, so that the entrance of the internet of things era is better realized, and the safety problem is not followed, so that the functional loss of the intelligent sound boxes is caused;
2. some intelligent sound boxes resolve such problems into voice recognition of a specific person, only research is carried out on an algorithm to process voiceprint characteristics, and the voiceprint characteristics of the specific person and the voiceprint characteristics of the unspecified person are distinguished under the support of a corresponding hardware unit, so that the complexity of the background processing mechanism of the intelligent sound box is caused;
3. some intelligent sound boxes attribute to the fact that a safety chip/hardware unit needs to be added, and hardware units such as a touch screen, fingerprint identification and a camera are added to the basic configuration of the intelligent sound box to be used for identifying a person responsible for a family, so that the manufacturing cost of the intelligent sound box is greatly increased;
4. some smart enclosures attribute such problems to the need for cross-validation on the "cloud platform" under the account of other things such as: the intelligent equipment such as cell-phone, panel computer obtain the identifying code, and then confirm corresponding security problem to lead to as above intelligent audio amplifier serious dependence other equipment, destroyed the smoothness nature of human-computer interaction.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a secondary authentication method suitable for voice command response of intelligent equipment, and solves the problem of unsafe operation control of the intelligent equipment due to the fact that the intelligent equipment is not provided with authority identification and cannot identify unauthorized instructions.
The invention specifically adopts the following technical scheme to solve the technical problems:
a secondary authentication method suitable for intelligent equipment voice command response comprises the following steps:
the intelligent equipment monitors voice to obtain a monitored voice command;
the voice command types are divided into control type commands and non-control type commands according to whether safety control is involved or not in advance;
identifying the type of the monitored voice command, executing a corresponding control command according to the monitored voice command when the monitored voice command is identified as a non-control command, otherwise, extracting a characteristic threshold value at a certain voice frequency in the monitored voice command and comparing the characteristic threshold value with pre-constructed voice sample information to judge whether a voice command applier is a child:
when the child is judged to be the child, voice alarm is carried out and the operation command corresponding to the voice command is refused to be executed;
otherwise, when the person is judged to be an adult, the sound source direction identified according to the monitored voice command is compared with the sound source sample direction arranged at the doorway to judge whether the voice command applier is positioned at the doorway direction: if the door-opening direction is judged to be located, executing a corresponding control command according to the monitored voice command, otherwise, executing secondary confirmation whether the sound source direction of the monitored voice command is the door-opening direction, wherein the secondary confirmation comprises the following steps:
the intelligent equipment plays the voice file, the voice command applier responses the voice command again, the sound source direction identified by the voice command which is responded again is compared with the sound source sample direction arranged at the door, and whether the voice command applier is arranged at the door direction is judged again: when the door opening direction is judged again, the voice command applier is judged to be positioned outside the door opening, the preset authentication problem is played and randomly selected, the voice responding to the voice command applier is identified, and the control command corresponding to the voice command which is responded again is controlled to be executed or not executed according to the identification result; otherwise, when the voice command applier is judged to be positioned in the direction other than the doorway, the voice command applier is judged to be positioned in the inner side of the doorway, and the corresponding control command is executed according to the voice command responded again.
Further, as a preferred technical solution of the present invention: the method also comprises the steps of identifying and judging whether the monitored voice is awakened or not according to the keywords in the monitored voice, if the keywords can not be identified, not awakening and continuing to be in a monitoring standby state, otherwise, extracting and obtaining the monitored voice command.
Further, as a preferred technical solution of the present invention: the pre-constructed voice sample information in the method is composed of voice characteristics of voice command appliers of different ages and different sexes.
Further, as a preferred technical solution of the present invention: the method also includes updating the pre-constructed speech sample information.
Further, as a preferred technical solution of the present invention: the method also includes setting a delay time to wait for the voice command applier to respond to the voice command again.
Further, as a preferred technical solution of the present invention: the method further comprises the step of setting a sound source azimuth angle change range, judging the direction of the door when the difference value obtained by comparing the sound source direction identified by replying the voice command again with the sound source sample direction set at the door is in the sound source azimuth angle change range, and otherwise, judging the direction of the door is not in the door.
Further, as a preferred technical solution of the present invention: the safety problem is set by a user in a self-defined mode.
Further, as a preferred technical solution of the present invention: in the method, the keywords in the voice which answer the authentication problem to the voice command applier are identified, if the keywords are identified, the control command corresponding to the voice command is responded again, otherwise, the voice alarm is not executed.
Further, as a preferred technical solution of the present invention: in the method, the intelligent equipment is movable or static intelligent equipment.
By adopting the technical scheme, the invention can produce the following technical effects:
the invention provides a secondary authentication method suitable for voice command response of intelligent equipment, which is characterized in that on the basis of basic configuration of the intelligent equipment, corresponding algorithm overhead and hardware units are not required to be added, and other intelligent equipment under a cloud platform account is not required to be matched and confirmed, so that the following conditions related to safety are effectively avoided: on the first hand, a child controls the intelligent household equipment through voice, so that potential safety hazards are caused; in the second aspect, the intelligent home equipment is controlled by entrance door direction, especially by suspicious people outside the entrance door, and unauthorized instructions of foreign people cause property loss of users. The intelligent sound box brings convenience to life when people enjoy the intelligent sound box, and meanwhile, the effective safety guarantee of the control type voice command is achieved, so that a smooth man-machine interaction secondary authentication method is achieved, and the intelligent sound box has the advantages of being low in power consumption and high in safety.
Drawings
Fig. 1 is a schematic flow chart of a secondary authentication method applicable to a voice command response of an intelligent device according to the present invention.
Fig. 2 is a schematic flow chart illustrating secondary confirmation of whether the sound source direction is the doorway direction in the method of the present invention.
Detailed Description
The following describes embodiments of the present invention with reference to the drawings.
As shown in fig. 1, the invention designs a secondary authentication method suitable for a voice command response of an intelligent device, in the method, the intelligent device performs type recognition on a monitored voice command, performs a general command execution response if no safe non-control command is involved, and determines whether to refuse to execute a corresponding control command for a child according to characteristic threshold values of voice sample information if the safe control command is involved, thereby effectively preventing the child from operating the intelligent home device through voice. The intelligent device carries out direction recognition on the monitored voice command so as to determine whether an applier of the voice command is located in the door direction, directly carries out voice confirmation response on the received voice command from the non-door direction, and simultaneously executes a corresponding control command. For the monitored voice command from the door direction, further secondary confirmation of the door direction instruction needs to be executed to determine whether the voice command comes from the outside of the entrance. The method can be realized by software or hardware, and the invention can be implemented on movable intelligent equipment or fixed non-movable static intelligent equipment, and according to the application of the intelligent equipment in the method, the intelligent equipment can be roughly divided into two types: in the first category, stationary intelligent devices, such as intelligent speakers, intelligent refrigerators, etc., are provided in a substantially fixed position or are less mobile; in the second category, the mobile intelligent devices with real-time position changes, such as the intelligent robot, the sweeping robot, etc., are not limited to this. The embodiment takes an intelligent sound box in a non-mobile intelligent device which is fixedly arranged as an example, and specifically, the implementation method comprises the following steps:
And 102, monitoring by the intelligent sound box according to the voice, and judging whether to be awakened or not according to the recognized keywords in the voice. If the keyword cannot be identified, the keyword is not awakened and is continuously in a monitoring standby state; otherwise, the monitored voice command is obtained if the keyword is recognized, and step 103 is performed to perform type recognition of the monitored voice command.
And 103, identifying the type of the voice command monitored by the intelligent sound box. The intelligent sound box divides voice commands into two types according to whether safety control is involved in advance: control-class commands that involve security and non-control-class commands that do not involve security. Voice commands related to security control classes include, but are not limited to, opening smart door/window locks, setting refrigerator temperature, warming water heaters in advance, etc. Non-control type commands that do not relate to security include playing music, increasing or decreasing volume, human-computer interaction, etc.
And 104, classifying the voice command by the intelligent sound box. Identifying the type of the monitored voice command, and if the type of the monitored voice command is identified as a non-control command, performing a general command response, and entering step 105; otherwise, when a control class command is identified, and step 106 is entered.
And step 105, responding to the general voice command by the intelligent sound box. The type of voice command does not relate to safety control, and the non-control type of command includes but is not limited to audio on demand, man-machine interaction and the like, and the corresponding control command is executed according to the monitored voice command.
And 106, when the control command is identified, extracting a characteristic threshold value at a certain voice frequency in the monitored voice command by the intelligent sound box. The smart speaker distinguishes whether the voice command applier is a child or an adult according to the feature thresholds of the child and the adult at certain voice frequencies, for example, the feature thresholds of the voice frequencies at 0.8kHz and 1.4kHz, respectively, and proceeds to step 107.
And step 107, the intelligent sound box compares the extracted voice command characteristic threshold value with pre-constructed voice sample information. The voice command feature threshold is related to factors such as gender, command application time, background noise, etc. of the applicator, and voice sample information may be formed by voice features of a plurality of groups of voice command applicators of different ages and different genders, stored in a local storage medium of the smart speaker, and the process proceeds to step 108.
And step 109, the intelligent sound box performs voice alarm and refuses to execute the corresponding control command.
And step 110, the intelligent sound box carries out sound source positioning on the monitored voice command. The smart speaker performs sound source orientation recognition on the monitored voice command to determine whether the voice command applier is located in the doorway direction, and proceeds to step 111.
And step 111, the intelligent sound box compares the voice command sound source direction information obtained by analysis with a preset sound source sample direction located at the door. When the intelligent sound box is used for the first time or after the position is adjusted, a user sends a 'door positioning' voice instruction near the entrance door, the intelligent sound box controls the microphone array to collect sound wave information, and then the sound source sample direction is determined according to the collected sound wave information. The intelligent sound box forms a sound source direction sample by using a plurality of groups of sound wave information and stores the sound source direction sample in a local storage medium of the intelligent sound box. Considering that this operation involves security control, it should be performed by an adult family accountant.
In this embodiment, sound source positioning is performed by using microphones in an intelligent sound box, generally, sound source positioning algorithms based on microphone arrays exist in many ways, and a method based on beam forming is adopted in this embodiment, but the present invention is not limited to this, and other methods can also be applied to the sound source positioning process. Specifically, the sound source positioning method based on beam forming, which is adopted by the invention, is based on the controllable beam forming technology Beamforming of the maximum output power, the principle is that signals collected by each array element are weighted and summed to form a beam, the beam is guided by searching the possible position of a sound source, and the weight is modified to enable the output signal power of a microphone array to be maximum. So that the localization can get the voice command sound source direction information.
And when the voice command sound source direction information obtained by analysis is compared with the sound source sample direction preset at the door to be the direction mismatching, judging that the voice command applier is positioned at the non-door direction, otherwise, when the voice command sound source direction information obtained by analysis is compared with the sound source sample direction preset at the door to be the direction matching, judging that the voice command applier is positioned at the door direction. And, the process proceeds to step 112.
And step 112, the intelligent sound box executes control according to the judgment whether the voice command applier is positioned in the door opening direction. When the voice command applier is judged to be located in the non-door direction, and the monitored voice command from the non-door direction is directly subjected to voice confirmation response after the voice and sound source sample data is updated, and the monitored voice command is controlled to be executed to execute the corresponding control command. When the door is determined to be located in the doorway direction, and the monitored voice command from the doorway direction needs to be further confirmed whether the voice command is from outside the door, the process proceeds to step 113.
In step 113, the smart speaker performs secondary confirmation as to whether the sound source direction of the monitored voice command is the door direction, and proceeds to step 114.
And step 114, updating voice and sound source sample data in the constructed voice sample information by the intelligent sound box.
As shown in fig. 2, in the second confirmation process of the method for confirming whether the sound source direction of the monitored voice command is the door direction, the smart speaker confirms whether the voice command applier is located outside the entrance door through the preliminary determination and the secondary determination. The intelligent sound box directly performs voice confirmation response on the user judged to be positioned at the inner side of the doorway, and executes corresponding control at the same time, so that a smooth man-machine interaction secondary authentication method is achieved; and if the answer is correct, the voice confirms the response and executes corresponding control, otherwise, the voice alarms and refuses to execute corresponding control. The method may be implemented by software or hardware, and is not particularly limited thereto. The process specifically comprises the following steps:
In step 206, when the smart speaker determines that the direction is not the door, it determines that the voice command applier is located inside the door, i.e. responds to the voice command again from the inside of the entrance door, and directly performs voice confirmation response and controls to execute a corresponding control command.
And step 208, playing the authentication problem, preferably the security problem, by the intelligent sound box. When the intelligent sound box is used for the first time, a user can answer the questions according to the preset questions of a manufacturer, or the user sets the questions in a user-defined mode and answers the questions, keywords in the corresponding answers are analyzed and recorded by the intelligent sound box and serve as preset authentication questions, and the keywords are stored in a local storage medium of the intelligent sound box. Authentication issues cover content including but not limited to personal/family information, preferences, etc. Considering that this operation involves security control, it should be performed by an adult family accountant, and proceeds to step 209.
In the method, some voice commands in the doorway direction need to be identified, and then corresponding operations are carried out, so as to ensure safety.
For the stationary intelligent device fixedly arranged in the first type, because the position is relatively stable, the method of calibrating the door opening direction in advance can be simply adopted, taking an intelligent sound box as an example: when the intelligent sound box is used for the first time or after the position is adjusted, a user sends a 'door positioning' voice instruction near the entrance door, the intelligent sound box controls the microphone array to collect sound wave information, and then the sound source sample direction is determined according to the collected sound wave information.
For the second type of mobile intelligent device, because the position of the mobile intelligent device changes in real time, the method can be implemented by means of node positioning in a wireless sensor network, that is: and determining the position information of other nodes in the network by a positioning technology according to the position information of a few known nodes in the network. Such as using radio frequency identification RFID technology. The technical principle of positioning is mainly realized by calculating the flight time of electromagnetic waves in space, further converting the distance and realizing point-to-point or triangular positioning. In the method, the RFID label can be attached to an object with a certain position, for example, fixedly attached to an entrance door, and stable reference position information is provided for the mobile intelligent device to judge the direction of the entrance door. The secondary authentication function of the voice command is realized by combining the position information of the radio frequency identification with the authentication process of the voice command.
In conclusion, on the basis of the basic configuration of the intelligent sound box, the method does not need to increase corresponding algorithm overhead and hardware units, and does not need to be confirmed by other intelligent equipment under the account of the cloud platform, thereby effectively avoiding potential safety hazards, effectively guaranteeing the safety of the control voice command and further achieving a smooth human-computer interaction secondary authentication method.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (9)
1. A secondary authentication method suitable for voice command response of intelligent equipment is characterized by comprising the following steps:
the intelligent equipment monitors voice to obtain a monitored voice command;
the voice command types are divided into control type commands and non-control type commands according to whether safety control is involved or not in advance;
identifying the type of the monitored voice command, executing a corresponding control command according to the monitored voice command when the monitored voice command is identified as a non-control command, otherwise, extracting the characteristics of a certain voice frequency in the monitored voice command and comparing the characteristics with pre-constructed voice sample information to judge whether the voice command applier is a child:
when the child is judged, voice alarm is carried out and the operation command corresponding to the voice command is refused to be executed;
otherwise, when the person is judged to be an adult, the sound source direction identified according to the monitored voice command is compared with the sound source sample direction arranged at the doorway to judge whether the voice command applier is positioned at the doorway direction: if the door-opening direction is judged to be located, executing a corresponding control command according to the monitored voice command, otherwise, executing secondary confirmation whether the sound source direction of the monitored voice command is the door-opening direction, wherein the secondary confirmation comprises the following steps:
the intelligent equipment plays the voice file, the voice command applier responses the voice command again, the sound source direction identified by the voice command which is responded again is compared with the sound source sample direction arranged at the door, and whether the voice command applier is arranged at the door direction is judged again: when the door opening direction is judged again, the voice command applier is judged to be positioned outside the door opening, the preset authentication problem is played and randomly selected, the voice responding to the voice command applier is identified, and the control command corresponding to the voice command which is responded again is controlled to be executed or not executed according to the identification result; otherwise, when the voice command applier is judged to be positioned in the direction other than the doorway, the voice command applier is judged to be positioned in the inner side of the doorway, and the corresponding control command is executed according to the voice command responded again.
2. The secondary authentication method for the voice command response of the intelligent device according to claim 1, wherein: the method also comprises the steps of identifying and judging whether the monitored voice is awakened or not according to the keywords in the monitored voice, if the keywords can not be identified, not awakening and continuing to be in a monitoring standby state, otherwise, extracting and obtaining the monitored voice command.
3. The secondary authentication method for the voice command response of the intelligent device according to claim 1, wherein: the pre-constructed voice sample information in the method is composed of voice characteristics of voice command appliers of different ages and different sexes.
4. The secondary authentication method for the voice command response of the intelligent device according to claim 1, wherein: the method also includes updating the pre-constructed speech sample information.
5. The secondary authentication method for the voice command response of the intelligent device according to claim 1, wherein: the method also includes setting a delay time to wait for the voice command applier to respond to the voice command again.
6. The secondary authentication method for the voice command response of the intelligent device according to claim 1, wherein: the method further comprises the step of setting a sound source azimuth angle change range, judging the direction of the door when the difference value obtained by comparing the sound source direction identified by replying the voice command again with the sound source sample direction set at the door is in the sound source azimuth angle change range, and otherwise, judging the direction of the door is not in the door.
7. The secondary authentication method for the voice command response of the intelligent device according to claim 1, wherein: the preset authentication problem is set by a user in a self-defined way.
8. The secondary authentication method for the voice command response of the intelligent device according to claim 1, wherein: in the method, the keywords in the voice which answer the authentication problem to the voice command applier are identified, if the keywords are identified, the control command corresponding to the voice command is responded again, otherwise, the voice alarm is not executed.
9. The secondary authentication method for the voice command response of the intelligent device according to claim 1, wherein: in the method, the intelligent equipment is movable or static intelligent equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811257075.2A CN109492368B (en) | 2018-10-26 | 2018-10-26 | Secondary authentication method suitable for voice command response of intelligent equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811257075.2A CN109492368B (en) | 2018-10-26 | 2018-10-26 | Secondary authentication method suitable for voice command response of intelligent equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109492368A CN109492368A (en) | 2019-03-19 |
| CN109492368B true CN109492368B (en) | 2021-07-27 |
Family
ID=65693172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811257075.2A Active CN109492368B (en) | 2018-10-26 | 2018-10-26 | Secondary authentication method suitable for voice command response of intelligent equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109492368B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648664A (en) * | 2019-10-11 | 2020-01-03 | 广东美的白色家电技术创新中心有限公司 | Household appliance control method and device with storage function |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060293891A1 (en) * | 2005-06-22 | 2006-12-28 | Jan Pathuel | Biometric control systems and associated methods of use |
| CN107483997A (en) * | 2017-08-25 | 2017-12-15 | 四川长虹电器股份有限公司 | Children's lock control system and method |
| CN111508489B (en) * | 2017-12-19 | 2022-10-18 | 深圳市欧瑞博科技股份有限公司 | Speech recognition method, speech recognition device, computer equipment and storage medium |
| CN108304155A (en) * | 2018-01-26 | 2018-07-20 | 广州源创网络科技有限公司 | A kind of man-machine interaction control method |
| CN108632653B (en) * | 2018-05-30 | 2022-04-19 | 腾讯科技（深圳）有限公司 | Voice control method, smart television and computer readable storage medium |
-
2018
- 2018-10-26 CN CN201811257075.2A patent/CN109492368B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109492368A (en) | 2019-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10923130B2 (en) | Electronic device and method of performing function of electronic device | |
| EP3483851B1 (en) | Intelligent sound classification and alerting | |
| US20220317641A1 (en) | Device control method, conflict processing method, corresponding apparatus and electronic device | |
| CN109412910A (en) | The method and apparatus for controlling smart home device | |
| US9043210B1 (en) | Biometric voice command and control switching device and method of use | |
| US11056114B2 (en) | Voice response interfacing with multiple smart devices of different types | |
| US20170116986A1 (en) | System and method for speech-enabled personalized operation of devices and services in multiple operating environments | |
| WO2019133908A1 (en) | Intelligent identification and provisioning of devices and services for a smart home environment | |
| US20190103005A1 (en) | Multi-resolution audio activity tracker based on acoustic scene recognition | |
| US20200219384A1 (en) | Methods and systems for ambient system control | |
| Ntalampiras | A novel holistic modeling approach for generalized sound recognition | |
| Arif et al. | Voice spoofing countermeasure for logical access attacks detection | |
| US11776550B2 (en) | Device operation based on dynamic classifier | |
| CN110415694A (en) | A kind of method that more intelligent sound boxes cooperate | |
| CN108038947B (en) | Intelligent door lock system based on Bluetooth | |
| CN109492368B (en) | Secondary authentication method suitable for voice command response of intelligent equipment | |
| US20220027725A1 (en) | Sound model localization within an environment | |
| Alrumayh et al. | Context aware access control for home voice assistant in multi-occupant homes | |
| US20190327128A1 (en) | Using a local hub device as a substitute for an unavailable backend device | |
| CN114220442A (en) | Control method of intelligent home system and intelligent home system | |
| US11240641B1 (en) | Automated device grouping | |
| CN110149618A (en) | Smart machine cut-in method, device, equipment and medium based on vocal print authorization | |
| US20240071408A1 (en) | Acoustic event detection | |
| KR102621897B1 (en) | Speaker recognition apparatus and operation method thereof | |
| Huang et al. | WalkID: Towards context awareness of smart home by identifying walking sounds |
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 |