CN111824879B - Intelligent voice contactless elevator control method, system and storage medium - Google Patents
Intelligent voice contactless elevator control method, system and storage medium Download PDFInfo
- Publication number
- CN111824879B CN111824879B CN202010628700.0A CN202010628700A CN111824879B CN 111824879 B CN111824879 B CN 111824879B CN 202010628700 A CN202010628700 A CN 202010628700A CN 111824879 B CN111824879 B CN 111824879B
- Authority
- CN
- China
- Prior art keywords
- real
- time
- voice
- temporary
- elevator
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/34—Details, e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
- B66B1/46—Adaptations of switches or switchgear
- B66B1/468—Call registering systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/02—Control systems without regulation, i.e. without retroactive action
- B66B1/06—Control systems without regulation, i.e. without retroactive action electric
- B66B1/14—Control systems without regulation, i.e. without retroactive action electric with devices, e.g. push-buttons, for indirect control of movements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B2201/00—Aspects of control systems of elevators
- B66B2201/40—Details of the change of control mode
- B66B2201/46—Switches or switchgear
- B66B2201/4607—Call registering systems
- B66B2201/4638—Wherein the call is registered without making physical contact with the elevator system
- B66B2201/4646—Wherein the call is registered without making physical contact with the elevator system using voice recognition
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B2201/00—Aspects of control systems of elevators
- B66B2201/40—Details of the change of control mode
- B66B2201/46—Switches or switchgear
- B66B2201/4607—Call registering systems
- B66B2201/4676—Call registering systems for checking authorization of the passengers
Abstract
The invention relates to an intelligent voice contactless elevator control method, a system and a storage medium, wherein the intelligent voice contactless elevator control method comprises the steps of recording a plurality of owner voice characteristics of an owner in advance; real-time voice in front of the elevator door is collected and recorded in real time, and real-time voice characteristics in the real-time voice are recognized; matching real-time voice features corresponding to the owner voice features; calculating the dispersion of the matched real-time voice features in the time domain position in the real-time voice feature set, calculating the separation of the matched real-time voice features and the adjacent real-time voice features, wherein one matched real-time voice corresponds to one dispersion and one separation, all the matched real-time voice features form a dispersion matrix and a separation matrix, and calculating the convolution sum of the dispersion matrix and the separation matrix; and if the convolution sum result is within a preset judgment preset range, opening the use authority of the elevator. The elevator system has the effect that the owner or the temporary visitor brought by the owner can use the elevator without the card.
Description
Technical Field
The invention relates to the technical field of elevator control, in particular to an intelligent voice contactless elevator control method, an intelligent voice contactless elevator control system and a storage medium.
Background
At present, an elevator becomes a facility which people must have in a working place or a living place, and people do not want to be free and have irrelevant people to use the elevator frequently when using the elevator, so that only an owner with authority can use the elevator frequently, and even the irrelevant stranger can be forbidden to use the elevator preferably to improve the safety of a cell or an office building, therefore, a set of elevator control system is arranged on the elevator in a high-grade place or a part of cells to control the use authority of the elevator. After the elevator control system is installed on the elevator, only after a user swipes a card or performs other types of information verification, the elevator control system judges that the user has legal authority, and then the control command of the user can be executed, so that the elevator can be normally used only by an owner, and foreign strangers cannot use the elevator, and the safety of a community is improved.
After installing elevator control system on the elevator among the prior art, though can prevent that external personnel from using the elevator, when nevertheless the owner gets home, if forget to take the card, also can't use the elevator to, if have interim visitor, interim visitor also can't control the elevator, under this kind of condition, the owner just calls the telephone and notifies property personnel, lets him carry out remote operation on the computer, or the owner goes downstairs in person and guides interim visitor upstairs, these have all increased a great deal of inconvenience for the life of owner.
Therefore, how to enable the owner or the temporary visitor to use the elevator without the card is a technical problem to be solved urgently.
Disclosure of Invention
The invention aims to provide an intelligent voice contactless elevator control method which has the characteristic that an owner or a temporary visitor brought by the owner can use an elevator under the condition that no card is brought.
The above object of the present invention is achieved by the following technical solutions:
an intelligent voice contactless ladder control method comprises the following steps:
s1: recording a plurality of owner voice characteristics of an owner in advance to form an owner voice characteristic set;
s2: real-time voice in front of the elevator door is collected and recorded in real time, real-time voice features in the real-time voice are recognized, and a real-time voice feature set is formed;
s3: matching real-time voice features corresponding to the main voice features in the main voice feature set from the real-time voice feature set;
s4: calculating the dispersion of the matched real-time voice features in the time domain position in the real-time voice feature set, calculating the separation of the matched real-time voice features and the adjacent real-time voice features in the real-time voice feature set, wherein one matched real-time voice corresponds to one dispersion and one separation, all the matched real-time voice features form a dispersion matrix and a separation matrix, and calculating the convolution sum of the dispersion matrix and the separation matrix; and the number of the first and second groups,
s5: and if the convolution sum result is within a preset judgment preset range, opening the use authority of the elevator and continuing for a first set time.
By adopting the technical scheme, the voice characteristics of the owner are recorded in advance, then the real-time voice in front of the elevator door is collected in real time when the elevator actually runs, the voice is analyzed, the real-time voice characteristics corresponding to the voice characteristics of the owner are extracted, namely, the effect similar to a specific person-to-password is formed, namely, the owner-to-password is obtained, if the owner gives the password, namely, the convolution and the result are located in the preset judgment preset range, the representative owner needs to use the elevator under the condition that the card is not used, the use permission of the elevator is opened at the moment, and the owner or the owner can use the elevator by a temporary visitor under the condition that the card is not used.
The present invention in a preferred example may be further configured to: also comprises the following steps:
s6: after the using authority of the elevator is closed, matching temporary voice features between adjacent real-time voice features from the real-time voice;
s7: extracting temporary voice attribute parameters of the temporary voice features; and the number of the first and second groups,
s8: and opening the use authority of the elevator for the temporary voice feature with the temporary voice attribute parameter for a second set time.
Through adopting above-mentioned technical scheme, interim pronunciation characteristic is the characteristic of the interim visitor that the owner brought, and the owner can carry out intercommunication with interim visitor in the time of using the elevator, records the characteristic of interim visitor this moment to for its open elevator permission of use that lasts in the second settlement time, need not the owner and take when making most interim visitor leave.
The present invention in a preferred example may be further configured to: the temporary speech attribute parameters are the frequency of the speech and the loudness of the speech, and in the time domain, the track of the temporary speech overlaps the track of the real-time speech.
By adopting the technical scheme, the frequency of the voice can distinguish the owner from the temporary visitor, and the audio track overlapping can analyze two voices simultaneously, so that the recognition time is shortened, and the recognition efficiency is improved.
The present invention in a preferred example may be further configured to: the real-time voice is recorded, and simultaneously, the real-time image in front of the elevator door is also stored;
the method further comprises the following steps:
s9: intercepting a temporary image corresponding to the appearance time of the temporary voice attribute parameters from the real-time image;
s10: shooting an image in front of the elevator door in real time, and calculating the similarity between the image in front of the elevator door and the temporary image; and the number of the first and second groups,
s11: and if the similarity is smaller than the preset set similarity value, closing the use permission of the elevator and continuing for a third set time.
By adopting the technical scheme, the change of the image is used as assistance when the voice characteristic is recognized, if the voice accords with the image, the use authority of the elevator is closed, the safety is improved, and the voice of others is prevented from being played by others.
The present invention in a preferred example may be further configured to: in S10, the parameters for calculating the similarity include the color different from the elevator door and the area occupied by the color.
By adopting the technical scheme, the similarity of the images is identified, people in the images do not need to be identified carefully, the auxiliary identification function is achieved, the occupation of computing resources can be reduced, the use efficiency of the computing resources is improved, and the requirement on hardware is lowered.
The invention also aims to provide an intelligent voice contactless elevator control system which has the characteristic that a proprietor or a temporary visitor brought by the proprietor can use an elevator under the condition of not taking a card.
The second aim of the invention is realized by the following technical scheme:
an intelligent voice contactless ladder control system comprises the following modules:
the pre-input module is used for pre-inputting a plurality of owner voice characteristics of an owner to form an owner voice characteristic set;
the acquisition and recognition module is used for acquiring and recording real-time voice in front of the elevator door in real time, recognizing real-time voice features in the real-time voice and forming a real-time voice feature set;
the matching feature module is used for matching real-time voice features corresponding to the main voice features in the main voice feature set from the real-time voice feature set;
the data calculating module is used for calculating the dispersion of the matched real-time voice features in the time domain position of the real-time voice feature set, calculating the separation of the matched real-time voice features and the adjacent real-time voice features in the real-time voice feature set, wherein one matched real-time voice corresponds to one dispersion and one separation, all the matched real-time voice features form a dispersion matrix and a separation matrix, and the convolution sum of the dispersion matrix and the separation matrix is calculated; and the number of the first and second groups,
and the judgment execution module is used for opening the use permission of the elevator and continuing for a first set time if the convolution sum result is within a preset judgment preset range.
By adopting the technical scheme, the pre-entry module records owner voice characteristics in advance, then when the elevator actually runs, the acquisition and recognition module acquires real-time voice in front of the elevator door in real time, the matching characteristic module analyzes the voice, the calculation data module extracts the real-time voice characteristics corresponding to the owner voice characteristics, namely, an effect similar to a specific person-to-password is formed, namely, the owner-to-password, if the owner gives the password, namely, the convolution and the result are located in a preset judgment preset range, the representative owner needs to use the elevator under the condition that the card is not used, at the moment, the calculation data module opens the use permission of the elevator, and the owner or the owner can use the elevator under the condition that the temporary visitor is not provided with the card.
The present invention in a preferred example may be further configured to: the system also comprises the following modules:
the temporary matching module is used for matching temporary voice features between adjacent real-time voice features from the real-time voice after the using authority of the elevator is closed;
the temporary extraction module is used for extracting temporary voice attribute parameters of the temporary voice features, the temporary voice attribute parameters are the frequency of voice and the loudness of the voice, and in a time domain, the sound track of the temporary voice is overlapped with the sound track of the real-time voice; and the number of the first and second groups,
and the temporary execution module is used for opening the use permission of the elevator for the temporary voice feature with the temporary voice attribute parameter and lasting for a second set time.
Through adopting above-mentioned technical scheme, interim pronunciation characteristic is the characteristic of the interim visitor that the owner brought, and the owner can communicate with each other with interim visitor in the time of using the elevator, and the interim characteristics of interim visitor are taken notes to the interim matching module this moment, and the interim pronunciation attribute parameter of interim pronunciation characteristic is drawed to the module of temporarily drawing to interim execution module is its open elevator permission of use that lasts in the second settlement time, and it takes to need not the owner when making most interim visitor leave.
The present invention in a preferred example may be further configured to: the real-time voice is recorded, and simultaneously, the real-time image in front of the elevator door is also stored;
the system also comprises the following modules:
the image capturing module is used for capturing a temporary image corresponding to the temporary voice attribute parameter occurrence time from the real-time image;
the similarity calculation module is used for shooting an image in front of the elevator door in real time, calculating the similarity between the image in front of the elevator door and the temporary image, wherein the parameter for calculating the similarity comprises the color different from the elevator door and the area occupied by the color; and the number of the first and second groups,
and the similarity judgment module is used for closing the use permission of the elevator and continuing for a third set time if the similarity is smaller than a preset set similarity value.
By adopting the technical scheme, the voice characteristics are recognized, the image module is intercepted, the change of the image is used as assistance, the similar calculation module calculates the image, if the voice accords with the image, the image does not accord with the image, the similar judgment module closes the use permission of the elevator, the safety is improved, and the situation that someone intentionally plays the voice of others is avoided.
The third purpose of the invention is to provide a computer storage medium which can store corresponding programs and has the characteristic that the owner or the temporary visitor brought by the owner can use the elevator under the condition of not taking the card.
The third object of the invention is realized by the following technical scheme:
a computer readable storage medium storing a computer program that can be loaded by a processor and executed to perform any of the above intelligent voice contactless ladder control methods.
In summary, the invention includes at least one of the following beneficial technical effects:
1. the method comprises the steps of recording voice characteristics of an owner in advance, collecting real-time voice in front of an elevator door in real time, extracting real-time voice characteristics corresponding to the voice characteristics of the owner, simulating a scene of the owner on a password, using convolution and a result to reflect a result of the password, realizing automatic judgment, and obtaining an accurate result, wherein the convolution and the result are located in a preset judgment preset range, so that the owner needs to use the elevator under the condition that the card is not used, the use authority of the elevator is opened at the moment, and the owner or the owner can use the elevator under the condition that a temporary visitor is brought without the card;
2. in order to avoid the situation that someone intentionally plays the voice of others in order to use the elevator, the owner communicates with the temporary visitors in the elevator using time, at the moment, the characteristics of the temporary visitors talking with the owner are recorded, and the change of the image is used as an auxiliary identification means, so that the elevator use permission lasting for the second set time is opened, most of the temporary visitors leave without being brought by the owner, if the voice is matched and the image is not matched, the elevator use permission is closed, and the safety is improved.
Drawings
FIG. 1 is a schematic flow chart of a method according to an embodiment of the present invention.
Fig. 2 is a block diagram of a system architecture according to an embodiment of the present invention.
Reference numerals: 1. a pre-entry module; 2. an acquisition identification module; 3. a matching feature module; 4. a data calculating module; 5. a judgment execution module; 6. a temporary matching module; 7. a temporary extraction module; 8. a temporary execution module; 9. an image intercepting module; 10. a similarity calculation module; 11. and a similarity judgment module.
Detailed Description
The present embodiment is only for explaining the present invention, and it is not limited to the present invention, and those skilled in the art can make modifications of the present embodiment without inventive contribution as needed after reading the present specification, but all of them are protected by patent law within the scope of the claims of the present invention. In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship, unless otherwise specified.
The embodiments of the present invention will be described in further detail with reference to the drawings attached hereto.
The first embodiment is as follows:
an intelligent voice contactless ladder control method is shown in fig. 1, and comprises the following steps:
s1: a plurality of owner voice characteristics of an owner are recorded in advance to form an owner voice characteristic set. A plurality of microphones are installed in front of the elevator door and in the elevator for collecting the sound in front of the elevator door and in the elevator. The sound signal collected by the microphone is converted into a voltage signal and output to a processing center connected with the processing center, and the processing center can adopt but is not limited to MCU, PLC or FPGA. The processing center uses fast Fourier transform to convert the time domain signal into frequency domain signal, thereby recognizing the sound with different frequencies, and then recognizing the speaking person and the speaking character, the recognition method adopts the voice recognition method in the prior art, including but not limited to flying voice recognition, flying voice recognition or hundredth voice recognition.
S2: real-time voice in front of the elevator door is collected and recorded in real time, real-time voice features in the real-time voice are recognized, and a real-time voice feature set is formed. The voice real-time monitoring system is characterized in that real-time voice is recorded, a real-time image in front of an elevator door is saved, a camera is correspondingly arranged beside a microphone and used for shooting images, preferably, a color camera is used for shooting color images, the color images can be transmitted to a processing center, an existing human body identification program is arranged in the processing center, a human body, clothes on the human body and colors of the human body are identified, the human body wearing the color clothes can form image blocks in the images, and the image blocks are beneficial to subsequent image comparison.
S3: and matching the real-time voice features corresponding to the main voice features in the main voice feature set from the real-time voice feature set. For example, voice password: "XX is XX number, XXX is in XX ladder", wherein the "building", "number", "use" and "ladder" can be real-time voice features, the loudness and frequency of four words after pronunciation are different and not similar, so the dispersion of the features is large, and in the time domain axis position, the positions are uniformly distributed, so the separation is minimum.
S4: calculating the dispersion of the matched real-time voice features in the time domain position of the real-time voice feature set, calculating the separation of the matched real-time voice features and the adjacent real-time voice features in the real-time voice feature set, wherein one matched real-time voice corresponds to one dispersion and one separation, all the matched real-time voice features form a dispersion matrix and a separation matrix, and calculating the convolution sum of the dispersion matrix and the separation matrix. And (5) calibrating the position by taking the time domain axis as a coordinate axis, and then calculating the dispersion and the separation.
S5: and if the convolution sum result is within a preset judgment preset range, opening the use authority of the elevator and continuing for a first set time. The owner can normally use the elevator within the first set time.
S6: and after the using authority of the elevator is closed, matching temporary voice features between adjacent real-time voice features from the real-time voice.
S7: and extracting temporary voice attribute parameters of the temporary voice features. The temporary speech attribute parameters are the frequency of the speech and the loudness of the speech, and in the time domain, the track of the temporary speech overlaps the track of the real-time speech. The frequency of the voice can distinguish the owner from the temporary visitor, and the overlapping of the sound tracks can analyze two voices simultaneously, so that the recognition time is shortened, and the recognition efficiency is improved.
S8: and opening the use authority of the elevator for the temporary voice feature with the temporary voice attribute parameter for a second set time. The temporary visitor together with the owner before can use the elevator normally within the first set time.
S9: and intercepting a temporary image corresponding to the temporary voice attribute parameter occurrence time from the real-time image.
S10: and shooting an image in front of the elevator door in real time, and calculating the similarity between the image in front of the elevator door and the temporary image. The parameters for calculating the similarity include the color to be distinguished from the elevator door and the area occupied by the color. The similarity of the images is recognized, the face, the expression and the action of people in the images do not need to be recognized carefully, the auxiliary recognition effect is achieved, the occupation of computing resources can be reduced, the use efficiency of the computing resources is improved, and the requirement on hardware is lowered.
And, S11: and if the similarity is smaller than the preset set similarity value, closing the use permission of the elevator and continuing for a third set time. The voice characteristics are recognized, the change of the images is used as assistance, if the voice accords with the images, the use authority of the elevator is closed, the safety is improved, and people are prevented from playing the voice of others intentionally.
The method comprises the steps of recording voice characteristics of an owner in advance, then collecting real-time voice in front of an elevator door in real time when the elevator actually runs, analyzing the voice, extracting the real-time voice characteristics corresponding to the voice characteristics of the owner, namely forming an effect similar to a specific person-to-password, namely the owner-to-password, and if the owner gives the password, namely the convolution and the result are located within a preset judgment preset range, representing that the owner needs to use the elevator under the condition that the card is not used, opening the use permission of the elevator at the moment, and enabling the owner or the owner to bring temporary visitors to normally use the elevator under the condition that the card is not used. The temporary voice characteristic is the characteristic of a temporary visitor brought by the owner, the owner can communicate with the temporary visitor in the time of using the elevator, the characteristic of the temporary visitor communicated with the owner is recorded at the moment, and after the judgment is successful, the elevator use permission lasting for the second set time is opened for the temporary client together with the owner, so that most of the temporary visitors do not need to be brought by the owner when leaving. If someone records the owner and the temporary client of the conversation in advance and plays the recording to try to acquire the use permission of the elevator, the picture shot by the camera in the elevator door and the picture shot by the camera in the elevator door are compared, if the difference between the picture and the image of the owner and the temporary visitor during the conversation is large, the use permission of the elevator can be closed, and the safety is improved.
Example two:
an intelligent voice contactless ladder control system is shown in fig. 2 and comprises the following modules:
the pre-inputting module 1 is used for pre-inputting a plurality of owner voice characteristics of an owner to form an owner voice characteristic set.
And the acquisition and recognition module 2 is used for acquiring and recording real-time voice in front of the elevator door in real time, recognizing real-time voice characteristics in the real-time voice and forming a real-time voice characteristic set. Real-time images in front of the elevator door are also saved while real-time voice is recorded.
And the matching feature module 3 is used for matching the real-time voice features corresponding to the main voice features in the main voice feature set from the real-time voice feature set.
And the data calculating module 4 is used for calculating the dispersion of the matched real-time voice features in the time domain position of the real-time voice feature set, calculating the separation of the matched real-time voice features and the adjacent real-time voice features in the real-time voice feature set, wherein one matched real-time voice corresponds to one dispersion and one separation, all the matched real-time voice features form a dispersion matrix and a separation matrix, and calculating the convolution sum of the dispersion matrix and the separation matrix.
And the judgment execution module 5 is used for opening the use permission of the elevator and continuing for a first set time if the convolution sum result is within a preset judgment preset range.
And the temporary matching module 6 is used for matching temporary voice features between adjacent real-time voice features from the real-time voice after the using authority of the elevator is closed.
And the temporary extraction module 7 is configured to extract a temporary voice attribute parameter of the temporary voice feature, where the temporary voice attribute parameter is a frequency of the voice and a loudness of the voice, and in a time domain, a sound track of the temporary voice overlaps a sound track of the real-time voice.
And a temporary execution module 8, which is used for opening the use authority of the elevator for the temporary voice feature with the temporary voice attribute parameter and lasting for a second set time.
And an image capturing module 9, configured to capture a temporary image corresponding to the occurrence time of the temporary voice attribute parameter from the real-time image.
The similarity calculation module 10 is used for shooting the image in front of the elevator door in real time, calculating the similarity between the image in front of the elevator door and the temporary image, wherein the parameter for calculating the similarity comprises the color different from the elevator door and the area occupied by the color.
And the similarity judgment module 11 is used for closing the use permission of the elevator and continuing for a third set time if the similarity is smaller than a preset set similarity value.
The pre-entry module 1 records owner voice features in advance, then when the elevator actually runs, the acquisition and recognition module 2 acquires real-time voice in front of the elevator door in real time, the matching feature module 3 analyzes the voice, the calculation data module 4 extracts the real-time voice features corresponding to the owner voice features, namely, the effect similar to a specific person-to-password is formed, namely, the owner-to-password, if the owner gives the password, namely, convolution and the result are located in a preset judgment preset range, the representative owner needs to use the elevator under the condition that the card is not used, at the moment, the calculation data module 4 opens the use permission of the elevator, and the owner or the owner can use the elevator with a temporary visitor under the condition that the card is not used. The temporary voice feature is the feature of the temporary visitor brought by the owner, the owner can communicate with the temporary visitor in the time of using the elevator, the temporary matching module 6 records the feature of the temporary visitor at the moment, the temporary voice attribute parameter of the temporary voice feature is extracted by the temporary extracting module 7, and therefore the temporary executing module 8 is open to continue the elevator using permission in the second set time, and most of the temporary visitors do not need to be brought by the owner when leaving. The image capturing module 9 is used for assisting in recognizing the voice characteristics, the image change is used as an aid by the similarity calculating module 10, if the voice accords with the image, the image does not accord with the voice, the use permission of the elevator is closed by the similarity judging module 11, the safety is improved, and the voice of others is prevented from being played by others intentionally.
Example three:
a computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the computer program according to one embodiment.
Claims (9)
1. An intelligent voice contactless ladder control method is characterized by comprising the following steps:
s1: recording a plurality of owner voice characteristics of an owner in advance to form an owner voice characteristic set;
s2: real-time voice in front of the elevator door is collected and recorded in real time, real-time voice features in the real-time voice are recognized, and a real-time voice feature set is formed;
s3: matching real-time voice features corresponding to the main voice features in the main voice feature set from the real-time voice feature set;
s4: calculating the dispersion of the matched real-time voice features in the time domain position in the real-time voice feature set, calculating the separation of the matched real-time voice features and the adjacent real-time voice features in the real-time voice feature set, wherein one matched real-time voice corresponds to one dispersion and one separation, all the matched real-time voice features form a dispersion matrix and a separation matrix, and calculating the convolution sum of the dispersion matrix and the separation matrix; and the number of the first and second groups,
s5: and if the convolution sum result is within a preset judgment preset range, opening the use authority of the elevator and continuing for a first set time.
2. The method of claim 1, further comprising the steps of:
s6: after the using authority of the elevator is closed, matching temporary voice features between adjacent real-time voice features from the real-time voice;
s7: extracting temporary voice attribute parameters of the temporary voice features; and the number of the first and second groups,
s8: and opening the use authority of the elevator for the temporary voice feature with the temporary voice attribute parameter for a second set time.
3. The method of claim 2, wherein the temporary speech attribute parameters are the frequency of speech and the loudness of speech, and wherein the soundtrack of the temporary speech overlaps the soundtrack of the real-time speech in the time domain.
4. The method of claim 2, wherein the real-time voice is recorded while a real-time image in front of the elevator door is also saved;
the method further comprises the following steps:
s9: intercepting a temporary image corresponding to the appearance time of the temporary voice attribute parameters from the real-time image;
s10: shooting an image in front of the elevator door in real time, and calculating the similarity between the image in front of the elevator door and the temporary image; and the number of the first and second groups,
s11: and if the similarity is smaller than the preset set similarity value, closing the use permission of the elevator and continuing for a third set time.
5. The method of claim 4, wherein in the step S10, the parameters for calculating the similarity include a color different from the elevator door and an area occupied by the color.
6. The utility model provides an intelligence pronunciation contactless ladder accuse system which characterized in that includes following module:
the system comprises a pre-input module (1) for pre-inputting a plurality of owner voice characteristics of an owner to form an owner voice characteristic set;
the acquisition and recognition module (2) is used for acquiring and recording real-time voice in front of the elevator door in real time, recognizing real-time voice features in the real-time voice and forming a real-time voice feature set;
the matching feature module (3) is used for matching real-time voice features corresponding to the main voice features in the main voice feature set from the real-time voice feature set;
the data calculating module (4) is used for calculating the dispersion of the matched real-time voice features in the time domain position of the real-time voice feature set, calculating the separation of the matched real-time voice features and the adjacent real-time voice features in the real-time voice feature set, wherein one matched real-time voice corresponds to one dispersion and one separation, all the matched real-time voice features form a dispersion matrix and a separation matrix, and the convolution sum of the dispersion matrix and the separation matrix is calculated; and the number of the first and second groups,
and the judgment execution module (5) is used for opening the use authority of the elevator and continuing for a first set time if the convolution sum result is within a preset judgment preset range.
7. The system of claim 6, further comprising the following modules:
the temporary matching module (6) is used for matching temporary voice features between adjacent real-time voice features from the real-time voice after the using authority of the elevator is closed;
the temporary extraction module (7) is used for extracting temporary voice attribute parameters of the temporary voice features, the temporary voice attribute parameters are the frequency of voice and the loudness of the voice, and in a time domain, the sound track of the temporary voice is overlapped with the sound track of the real-time voice; and the number of the first and second groups,
and the temporary execution module (8) is used for opening the use authority of the elevator for the temporary voice feature with the temporary voice attribute parameter and lasting for a second set time.
8. The system of claim 6, wherein real-time speech is recorded while a real-time image in front of the elevator door is also saved;
the system also comprises the following modules:
the image capturing module (9) is used for capturing a temporary image corresponding to the temporary voice attribute parameter occurrence time from the real-time image;
the similarity calculation module (10) is used for shooting an image in front of the elevator door in real time and calculating the similarity between the image in front of the elevator door and the temporary image, and the parameters for calculating the similarity comprise the color different from the elevator door and the area occupied by the color; and the number of the first and second groups,
and the similarity judgment module (11) is used for closing the use permission of the elevator and continuing for a third set time if the similarity is smaller than a preset set similarity value.
9. A computer-readable storage medium, in which a computer program is stored which can be loaded by a processor and which executes the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010628700.0A CN111824879B (en) | 2020-07-02 | 2020-07-02 | Intelligent voice contactless elevator control method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010628700.0A CN111824879B (en) | 2020-07-02 | 2020-07-02 | Intelligent voice contactless elevator control method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111824879A CN111824879A (en) | 2020-10-27 |
| CN111824879B true CN111824879B (en) | 2021-03-30 |
Family
ID=72900201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010628700.0A Active CN111824879B (en) | 2020-07-02 | 2020-07-02 | Intelligent voice contactless elevator control method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111824879B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112927689A (en) * | 2021-01-28 | 2021-06-08 | 上海浩宜信息科技有限公司 | Intelligent voiceprint ladder control |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006235243A (en) * | 2005-02-24 | 2006-09-07 | Secom Co Ltd | Audio signal analysis device and audio signal analysis program for |
| CN101040564A (en) * | 2004-10-19 | 2007-09-19 | 索尼株式会社 | Audio signal processing device and audio signal processing method |
| CN101667425A (en) * | 2009-09-22 | 2010-03-10 | 山东大学 | Method for carrying out blind source separation on convolutionary aliasing voice signals |
| CN107613429A (en) * | 2016-07-12 | 2018-01-19 | 杜比实验室特许公司 | The assessment and adjustment of audio installation |
| US9953634B1 (en) * | 2013-12-17 | 2018-04-24 | Knowles Electronics, Llc | Passive training for automatic speech recognition |
| CN108376215A (en) * | 2018-01-12 | 2018-08-07 | 上海大学 | A kind of identity identifying method |
| CN110767218A (en) * | 2019-10-31 | 2020-02-07 | 南京励智心理大数据产业研究院有限公司 | End-to-end speech recognition method, system, device and storage medium thereof |
| CN110827801A (en) * | 2020-01-09 | 2020-02-21 | 成都无糖信息技术有限公司 | Automatic voice recognition method and system based on artificial intelligence |
| CN111348499A (en) * | 2020-03-02 | 2020-06-30 | 北京声智科技有限公司 | Elevator control method, elevator control device, electronic equipment and computer-readable storage medium |
-
2020
- 2020-07-02 CN CN202010628700.0A patent/CN111824879B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101040564A (en) * | 2004-10-19 | 2007-09-19 | 索尼株式会社 | Audio signal processing device and audio signal processing method |
| JP2006235243A (en) * | 2005-02-24 | 2006-09-07 | Secom Co Ltd | Audio signal analysis device and audio signal analysis program for |
| CN101667425A (en) * | 2009-09-22 | 2010-03-10 | 山东大学 | Method for carrying out blind source separation on convolutionary aliasing voice signals |
| US9953634B1 (en) * | 2013-12-17 | 2018-04-24 | Knowles Electronics, Llc | Passive training for automatic speech recognition |
| CN107613429A (en) * | 2016-07-12 | 2018-01-19 | 杜比实验室特许公司 | The assessment and adjustment of audio installation |
| CN108376215A (en) * | 2018-01-12 | 2018-08-07 | 上海大学 | A kind of identity identifying method |
| CN110767218A (en) * | 2019-10-31 | 2020-02-07 | 南京励智心理大数据产业研究院有限公司 | End-to-end speech recognition method, system, device and storage medium thereof |
| CN110827801A (en) * | 2020-01-09 | 2020-02-21 | 成都无糖信息技术有限公司 | Automatic voice recognition method and system based on artificial intelligence |
| CN111348499A (en) * | 2020-03-02 | 2020-06-30 | 北京声智科技有限公司 | Elevator control method, elevator control device, electronic equipment and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111824879A (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106251874B (en) | A kind of voice gate inhibition and quiet environment monitoring method and system | |
| CN106599866B (en) | Multi-dimensional user identity identification method | |
| CN108074310B (en) | Voice interaction method based on voice recognition module and intelligent lock management system | |
| CN109118616A (en) | access control method and access control device | |
| WO2019137066A1 (en) | Electric appliance control method and device | |
| CN105427421A (en) | Entrance guard control method based on face recognition | |
| CN111881726B (en) | Living body detection method and device and storage medium | |
| CN104361276A (en) | Multi-mode biometric authentication method and multi-mode biometric authentication system | |
| CN106599660A (en) | Terminal safety verification method and terminal safety verification device | |
| JPS58102300A (en) | Person identification method and apparatus | |
| CN107360157A (en) | A kind of user registering method, device and intelligent air conditioner | |
| TWI780366B (en) | Facial recognition system, facial recognition method and facial recognition program | |
| CN102176746A (en) | Intelligent monitoring system used for safe access of local cell region and realization method thereof | |
| CN110853646A (en) | Method, device and equipment for distinguishing conference speaking roles and readable storage medium | |
| CN111824879B (en) | Intelligent voice contactless elevator control method, system and storage medium | |
| CN109410387A (en) | A kind of recognition of face prison safeguard management method and system | |
| CN111429638B (en) | Access control method based on voice recognition and face recognition | |
| CN109829691B (en) | C/S card punching method and device based on position and deep learning multiple biological features | |
| CN112785765A (en) | Intelligent home remote control user authorization method based on big data analysis and intelligent home cloud control platform | |
| CN112794174B (en) | Real-time video judgment elevator door opening and closing abnormity scheme based on big data | |
| CN108573033A (en) | Cyborg network of vein method for building up based on recognition of face and relevant device | |
| CN205541026U (en) | Double - circuit entrance guard device | |
| CN114913452A (en) | Office place-based violation detection system and method | |
| CN113221672A (en) | A facial recognition equipment for electric power instrument storehouse | |
| CN111159676A (en) | Multi-dimensional identity authentication system and method based on face recognition |
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 |