CN113428748B - Elevator control method, storage medium and equipment - Google Patents
Elevator control method, storage medium and equipment Download PDFInfo
- Publication number
- CN113428748B CN113428748B CN202110907196.2A CN202110907196A CN113428748B CN 113428748 B CN113428748 B CN 113428748B CN 202110907196 A CN202110907196 A CN 202110907196A CN 113428748 B CN113428748 B CN 113428748B
- Authority
- CN
- China
- Prior art keywords
- voice information
- elevator
- model
- control
- control instruction
- 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
- B66B1/02—Control systems without regulation, i.e. without retroactive action
- B66B1/06—Control systems without regulation, i.e. without retroactive action electric
-
- 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
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B50/00—Energy efficient technologies in elevators, escalators and moving walkways, e.g. energy saving or recuperation technologies
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Indicating And Signalling Devices For Elevators (AREA)
- Elevator Control (AREA)
Abstract
The invention discloses an elevator control method, a storage medium and equipment. The method utilizes the characteristic that an attention mechanism end-to-end model can pay attention to a specific part of input voice information, can greatly shorten the processes of voice information identification and elevator control, improves the data processing speed, and realizes the real-time control of the elevator.
Description
Technical Field
The invention relates to the technical field of intelligent equipment, in particular to an elevator control method, a storage medium and equipment.
Background
The goods lift transportation is widely applied in practice, but when the goods lift is unloaded at every time, the opening and closing control of the elevator door needs manual keys of workers, the workers continuously and manually control the opening and closing state of the goods lift for a long time, and the working efficiency is greatly reduced. Partial goods lift has the button of long switch function, but the operation is carved board, and is not flexible enough, and when the unloading often appears, the door carries out the switch by oneself, to workman and goods, has very big potential safety hazard. The application of voice control to the elevator has been exemplified, but only basic voice recognition is focused on, and ordinary door opening and closing are carried out, particularly in the aspect of transporting goods elevators, and no relevant door opening and closing control waiting strategy exists. In the aspect of voice control technology, most of the current voice recognition terminal control systems adopt the technologies of voice front-end signal processing, voice recognition, semantic understanding, skill hit, terminal control issuing and the like, the process is complex, and the response speed is generally low. Because terminal control of the goods elevator has higher requirements on response speed and safety, the conventional voice control technology is difficult to meet the high requirements of goods elevator scenes on real-time performance.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the problem of low real-time performance of a method for controlling an elevator by utilizing voice in the prior art is solved.
In order to solve the technical problem, the invention provides an elevator control method, a storage medium and equipment.
In a first aspect of the present invention, there is provided an elevator control method including:
receiving voice information;
inputting the voice information into a pre-trained attention mechanism end-to-end model to obtain a first control instruction corresponding to the voice information, wherein the first control instruction is used for indicating a target running state of the elevator;
controlling the elevator based on the first control command.
In some embodiments, the target operational state includes at least one of waiting, opening, closing, and traveling to a target floor.
In some embodiments, when the target operating state is a wait, the method further comprises:
inputting the receiving time of the voice information and/or the type of the transported article into a clustering neural network model to obtain a second control instruction, wherein the second control instruction is used for indicating the waiting time of the elevator;
controlling the elevator based on the first control command, comprising:
controlling the elevator based on the first control command and the second control command.
In some embodiments, the method further comprises:
responding to an instruction that the receiving time of the voice information exceeds a preset time range, and acquiring a default waiting time length;
controlling the elevator based on the first control command and the default waiting duration.
In some embodiments, the method further comprises:
recording the receiving time and the continuous waiting time of the voice information;
updating the clustering neural network model based on the receiving time of the voice information and the continuous waiting duration.
In some embodiments, the clustering neural network model comprises a single gaussian model, a gaussian mixture model, a K-MEANS model, or a self-organizing map model.
In some embodiments, the attention mechanism end-to-end model is constructed based on the following steps:
acquiring the voice information, framing the voice information and using the voice information as a training sample set;
inputting the training sample set into the attention mechanism end-to-end model, and training the attention mechanism end-to-end model by taking the first control instruction corresponding to the voice information as a target;
and obtaining the trained attention mechanism end-to-end model.
In some embodiments, the method further comprises: and prompting the target running state of the elevator in a voice and/or display mode.
In a second aspect of the present invention, a storage medium is provided, in which a computer program is stored, which computer program, when being executed by a processor, is able to carry out an elevator control method according to any one of the above.
In a third aspect of the invention, an apparatus is provided, which comprises a memory and a controller, the memory having stored therein a computer program, which computer program, when executed by the controller, is capable of implementing an elevator control method as defined in any one of the above.
Compared with the prior art, one or more embodiments in the above scheme can have the following advantages or beneficial effects:
the elevator control method provided by the invention is applied to receive the voice information, input the voice information into the pre-trained attention mechanism end-to-end model, and obtain the first control instruction corresponding to the voice information, wherein the first control instruction is used for indicating the target running state of the elevator, and the elevator is controlled based on the first control instruction. The method utilizes the characteristic that an attention mechanism end-to-end model can pay attention to a specific part of input voice information, can greatly shorten the processes of voice information identification and elevator control, improves the data processing speed, and realizes the real-time control of the elevator.
Drawings
The scope of the present disclosure may be better understood by reading the following detailed description of exemplary embodiments in conjunction with the accompanying drawings. Wherein the included drawings are:
fig. 1 shows a flow chart diagram illustrating an elevator control method according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a method for constructing an end-to-end model of an attention mechanism according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of an elevator control method according to a second embodiment of the present invention;
fig. 4 shows a schematic structural diagram of an apparatus provided in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the following will describe in detail an implementation method of the present invention with reference to the accompanying drawings and embodiments, so that how to apply technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented.
The goods lift transportation is widely applied in practice, but when the goods lift is unloaded at every time, the opening and closing control of the elevator door needs manual keys of workers, the workers continuously and manually control the opening and closing state of the goods lift for a long time, and the working efficiency is greatly reduced. Partial goods lift has the button of long opening and closing function, but the operation is carved board, and is not flexible enough, and often appears when unloading, and the door is opened and shut by oneself, to workman and goods, has very big potential safety hazard. The use of voice control in elevators has been exemplified, but it only focuses on basic voice recognition, and makes ordinary door opening and closing, especially in the transport of freight elevators, without the associated waiting strategy for door opening and closing control. In the aspect of voice control technology, most of the current voice recognition terminal control systems adopt technologies such as voice front-end signal processing, voice recognition, semantic understanding, skill hit and issuing terminal control, and the like, so that the process is complex, and the response speed is generally low. Because terminal control of the goods elevator has higher requirements on response speed and safety, the conventional voice control technology is difficult to meet the high requirements of goods elevator scenes on real-time performance.
In view of the above, the present invention provides an elevator control method, which receives voice information, inputs the voice information into a pre-trained attention mechanism end-to-end model, obtains a first control instruction corresponding to the voice information, where the first control instruction is used to indicate a target operation state of an elevator, and controls the elevator based on the first control instruction. The method utilizes the characteristic that an attention mechanism end-to-end model can pay attention to a specific part of input voice information, can greatly shorten the processes of voice information identification and elevator control, improves the data processing speed, and realizes the real-time control of the elevator.
Example one
Referring to fig. 1, fig. 1 is a schematic flow chart of an elevator control method according to an embodiment of the present invention, which may include:
step S101: receiving voice information;
step S102: inputting voice information into a pre-trained attention mechanism end-to-end model to obtain a first control instruction corresponding to the voice information, wherein the first control instruction is used for indicating a target running state of the elevator;
step S103: the elevator is controlled based on the first control command.
In some embodiments, step S101 may be embodied by receiving voice information through a voice device on the elevator; in other embodiments, step S101 may also be implemented for receiving voice information via other terminals that establish a communication connection with the elevator. By way of example, the voice message may include voice content such as "open door", "close door", or "i want to go to floor 5".
In this embodiment of the present invention, step S102 may specifically be to input the speech information into a pre-trained attention mechanism end-to-end model, and obtain a first control instruction corresponding to the speech information after decoding. Wherein the first control order is used to indicate a target operating state of the elevator.
In some embodiments, the target operational state may include at least one of waiting, opening, closing, and traveling to the target floor, wherein waiting may be a state of remaining open and suspended. In other embodiments, other target operation states may also be set according to requirements.
In the embodiment of the present invention, referring to fig. 2, fig. 2 is a flowchart illustrating a method for constructing an attention mechanism end-to-end model according to an embodiment of the present invention, where the method may include:
step S1021: acquiring voice information, framing the voice information and using the voice information as a training sample set;
step S1022: inputting the training sample set into an attention mechanism end-to-end model, and training the attention mechanism end-to-end model by taking a first control instruction corresponding to the voice information as a target;
step S1023: and obtaining a well-trained attention mechanism end-to-end model.
In the embodiment of the present invention, step S1021 may use historical speech information collected based on the elevator as a training sample, or may obtain some speech information as a training sample in other manners. The voice message may include voice commands for some commonly used elevators, such as "open door", "close door", "wait for" or "i want to go to floor 5", etc. In the embodiment of the invention, the training sample set is constructed based on the voice information after framing, which is beneficial to improving the accuracy of processing the voice information and further beneficial to improving the accuracy of controlling the elevator. It should be noted that, in other embodiments, the framing processing may not be performed on the voice information.
In this embodiment of the present invention, step S1022 may specifically be to input the attention mechanism end-to-end model after performing feature extraction on the speech information in the training sample set by using Mel-frequency cepstral coefficients (MFCCs). The first control instruction corresponds to voice information, and as an example, it may be defined that the first control command 0x0000 corresponds to voice information of "door open", and the first control command 0x0001 corresponds to voice information of "door close". And taking the voice information after framing as input, taking the corresponding first control instruction as output to train the attention mechanism end-to-end model, and finally obtaining the trained attention mechanism end-to-end model.
In the embodiment of the invention, by constructing the attention mechanism end-to-end model for elevator control, on one hand, the mapping relation between the voice information and the first control instruction can be constructed, the voice information searching network map of the shortest path is formed, and the real-time performance of control is improved; on the other hand, the attention mechanism end-to-end model only focuses on the properties of specific parts of sentences, has better canonicalization capability and can be flexibly applied to various scenes.
As an example, when the elevator waiting needs to be controlled, the attention mechanism end-to-end model is trained by taking "wait" as a training sample, and the weight of the word "wait" can be increased in the training process. When the voice information is 'waiting for me for a while' in the application process, even if the training sample set does not contain the piece of voice information, the piece of voice information can be mapped to the same first control command as 'waiting for me' by adopting the attention mechanism end-to-end model.
In some embodiments, after obtaining the trained attention mechanism end-to-end model, the obtained attention mechanism end-to-end model may be further adjusted based on the test sample set to further optimize the model.
In some embodiments, in order to improve the use feeling of the user, the training sample set can be enriched and customized.
As an example, in the training process for one target operation state, the voice information may be selected from a plurality of types, for example, the target operation state is "open door", and the voice information in the training sample may include "open door", "caution", "wait for one time", and "open door". And performing customized processing, namely setting different first control commands for the voice information of the top layer, based on the highest floor number corresponding to the actual application floor.
In the embodiment of the present invention, step S103 may specifically be controlling the elevator based on the first control instruction to execute the target operation state.
It should be noted that after the first control instruction corresponding to the voice information is obtained, the target operation state of the elevator can be prompted in a voice and/or display manner, so that a user can conveniently confirm whether the mapped first control instruction is accurate.
In the elevator control method provided by the embodiment of the invention, the voice information is received and input into the pre-trained attention mechanism end-to-end model, so that the first control instruction corresponding to the voice information is obtained, the first control instruction is used for indicating the target running state of the elevator, and the elevator is controlled based on the first control instruction. The method utilizes the characteristic that an attention mechanism end-to-end model can pay attention to a specific part of input voice information, can greatly shorten the processes of voice information identification and elevator control, improves the data processing speed, realizes the real-time control of the elevator and improves the safety.
In order to further solve the problems that when the elevator needs to wait for a long time, the operation of controlling the elevator in a waiting state is inconvenient, the working efficiency is affected, and the safety is low, the elevator control method provided by the embodiment of the invention is also provided, and specific reference is made to the description in the second embodiment.
Example two
Referring to fig. 3, fig. 3 is a schematic flow chart of an elevator control method according to a second embodiment of the present invention, which may include:
step S201: receiving voice information;
step S202: inputting voice information into a pre-trained attention mechanism end-to-end model to obtain a first control instruction corresponding to the voice information, wherein the first control instruction is used for indicating the waiting of the elevator;
step S203: inputting the receiving time of the voice information and/or the type of the transported article into the clustering neural network model to obtain a second control instruction, wherein the second control instruction is used for indicating the waiting time of the elevator;
step S204: and controlling the elevator based on the first control command and the second control command.
Step S201 and step S202 may be performed in the same manner as step S101 and step S102 in the first embodiment, and are not described herein again for brevity.
In some embodiments, step S203 may specifically be inputting the receiving time of the voice information into the clustering neural network model, and obtaining the second control instruction corresponding to the voice information. The voice message may correspond to the same or different second control commands at different receiving times. In other embodiments, step S203 may be further embodied to input the receiving time of the voice message and the type of the article to be transported into the clustering neural network model, and obtain a second control instruction, where the second control instruction may correspond to the receiving time of the voice message and the type of the article to be moved. Wherein the type of the transported item may be obtained based on the image capture device.
As an example, when the voice information of "long open" is acquired, the corresponding waiting control instruction is acquired based on "long open", the time of receiving the voice information is 10 am, the type of the transported article is a bucket, and the waiting time duration can be acquired to be 4 minutes based on the clustering neural network model; as another example, when the voice information of "long open" is acquired, the corresponding waiting control instruction is acquired based on "long open", the time when the voice information is received is 10 am, the type of the transported item is a cart, and the waiting time period is 3 minutes based on the clustering neural network model. Based on the method, the elevator can be flexibly and intelligently controlled according to different time periods and different types of transported articles, and the use safety and convenience of users are improved.
In some embodiments, the clustered neural network model may be pre-constructed based on the time of receipt of voice information, including long-open voice commands, etc., and the corresponding continuous wait periods for the elevators.
The clustering neural network model can comprise a single Gaussian model, a Gaussian mixture model, a K-MEANS model or a self-organizing mapping model.
Step S204 may specifically be controlling the elevator to wait for a corresponding waiting duration according to the first control instruction and the second control instruction.
In the embodiment of the present invention, the method may further include:
step S205: responding to an instruction that the receiving time of the voice information exceeds a preset time range, and obtaining default waiting time length;
step S206: the elevator is controlled based on the first control order and a default waiting period.
It should be noted that step S205 and step S206 may be sequentially executed after step S202, the preset time range may correspond to a voice information receiving time range based on the construction of the neuro-clustering network or an applicable time range of the model, and when the receiving time of the voice information exceeds the preset time range, the second control instruction cannot be obtained based on the neuro-clustering network model, but a preset default waiting duration is obtained. In addition, the default waiting duration may also be adjusted.
In the embodiment of the present invention, after step S204 or step S206, the method may further include:
step S207: recording the receiving time and the continuous waiting time of the voice information;
step S208: and updating the clustering neural network model based on the receiving time of the voice information and the continuous waiting duration.
The continuous waiting time is the actual waiting time, as an example, when a worker transports goods, 9:30 in morning receives voice information of 'long open', an elevator is kept open and starts to be closed after waiting for the time of T1, the elevator is opened and is closed after waiting for the time of T2 after being closed completely, the receiving time of the voice information is recorded as '9: 30 in morning', the continuous waiting time is T1+ T2, and the clustering neural network model is updated iteratively based on '9: 30 in morning' and the continuous waiting time, so that the clustering neural network model is continuously optimized according to the actual use condition, and the accuracy of predicting the waiting time is improved.
As an example, when the clustering neural network model is a single gaussian model, the single gaussian model may be expressed as:
wherein σ represents a standard deviation of the gaussian distribution, μ represents an expectation of the gaussian distribution, N represents a gaussian distribution function, T represents a reception time of the voice information, T' represents a set of all reception times in one day, and T represents a continuous waiting time.
As an example, when the clustering neural network model is a gaussian mixture model, the gaussian mixture model can be expressed as:
where pi represents a gaussian component vector, Σ represents a gaussian distribution standard deviation vector, μ represents a gaussian distribution expectation, i represents the number of gaussian components, N represents a gaussian distribution function, T represents a reception time of voice information, T' represents a set of all reception times in one day, and T represents a continuous waiting time.
It should be noted that, before step S208 is executed after the receiving time of the voice information and the continuous waiting duration are recorded in step S207, at least a part of the initial data may be deleted, for example, the clustering neural network model may be adjusted based on the receiving time of the historical voice information and the corresponding historical waiting duration in the 7-day time, and the receiving time of the historical voice information and the corresponding historical waiting duration on the first day may be deleted by day 8, instead of adjusting the clustering neural network model with the receiving time of the voice information and the continuous waiting duration recorded on day 8.
The second control instruction is used for indicating the waiting time of the elevator, the receiving time of the voice information and/or the type of the transported object are/is input into the clustering neural network model, the second control instruction is obtained and is used for indicating the waiting time of the elevator, and the elevator is controlled based on the first control instruction and the second control instruction.
Another aspect of the present invention also provides a storage medium having a computer program stored therein, where the computer program, when executed by a processor, can implement the elevator control method according to any one of the above embodiments.
The processes, functions, methods, and/or software described above may be recorded, stored, or fixed in one or more computer-readable storage media that include program instructions to be implemented by a computer to cause a processor to execute the program instructions. The storage media may also include program instructions, data files, data structures, etc., either alone or in combination. The storage media or program instructions may be those specially designed and understood by those skilled in the computer software arts, or they may be of the kind well known and available to those having skill in the computer software arts. Examples of computer readable media include: magnetic media such as hard disks, floppy disks, and magnetic tape; optical media, such as CDROM disks and DVDs; magneto-optical media, e.g., optical disks; and hardware devices specifically configured to store and execute program instructions, such as Read Only Memory (ROM), Random Access Memory (RAM), flash memory, and the like. Examples of program instructions include both machine code, such as produced by a compiler, and files containing higher level code that may be executed by the computer using an interpreter. The described hardware devices may be configured to act as one or more software modules to perform the operations and methods described above, and vice versa. In addition, computer readable storage media may be distributed over network coupled computer systems and may store and execute computer readable code or program instructions in a distributed fashion.
Another aspect of the present invention provides an apparatus, as shown in fig. 4, fig. 4 shows a schematic structural diagram of an apparatus provided in an embodiment of the present invention, which includes a memory 41 and a controller 42, where the memory 41 stores a computer program, and the computer program, when executed by the controller 42, can implement the elevator control method according to the first embodiment or the second embodiment.
It should be noted that the apparatus may include one or more controllers 42 and a memory 41, and the controllers 42 and the memory 41 may be connected by a bus or other means. Memory 41, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The controller 42 executes various functional applications and data processing of the device by running the nonvolatile software program, instructions, and modules stored in the memory 41, that is, implements the elevator control method according to the first or second embodiment.
As an example, the device may be an elevator, which may include an elevator body, a memory, a controller, and a voice device. It should be noted that the elevator may be a passenger elevator or a cargo elevator for transporting goods, and is not limited in the embodiment of the present invention.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. An elevator control method, characterized by comprising:
receiving voice information;
inputting the voice information into a pre-trained attention mechanism end-to-end model to obtain a first control instruction corresponding to the voice information, wherein the first control instruction is used for indicating a target running state of the elevator;
responding to an instruction that the receiving time of the voice information exceeds a preset time range, and obtaining default waiting time length; controlling the elevator based on the first control command and the default waiting duration;
when the target running state is waiting, inputting the receiving time of the voice information and the type of the transported article into a clustering neural network model to obtain a second control instruction, wherein the second control instruction is used for indicating the waiting time of the elevator;
recording the receiving time and the continuous waiting time of the voice information; updating the clustering neural network model based on the receiving time of the voice information and the continuous waiting duration;
controlling the elevator based on the first control command and the second control command.
2. The method of claim 1, wherein the target operational state further comprises at least one of opening, closing, and operating to a target floor.
3. The method of claim 1, wherein the clustering neural network model comprises a single gaussian model, a gaussian mixture model, a K-MEANS model, or a self-organizing map model.
4. The method of claim 1, wherein the attention mechanism end-to-end model is constructed based on the steps of:
acquiring the voice information, framing the voice information and using the voice information as a training sample set;
inputting the training sample set into the attention mechanism end-to-end model, and training the attention mechanism end-to-end model by taking the first control instruction corresponding to the voice information as a target;
and obtaining the trained attention mechanism end-to-end model.
5. The method according to any one of claims 1 to 4, further comprising: and prompting the target running state of the elevator in a voice and/or display mode.
6. A storage medium, characterized in that a computer program is stored in the storage medium, which computer program, when being executed by a processor, is capable of implementing an elevator control method according to any one of claims 1 to 5.
7. An apparatus, characterized in that the apparatus comprises a memory and a controller, the memory having stored therein a computer program which, when executed by the controller, is capable of implementing the elevator control method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110907196.2A CN113428748B (en) | 2021-08-09 | 2021-08-09 | Elevator control method, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110907196.2A CN113428748B (en) | 2021-08-09 | 2021-08-09 | Elevator control method, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113428748A CN113428748A (en) | 2021-09-24 |
| CN113428748B true CN113428748B (en) | 2022-05-20 |
Family
ID=77763054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110907196.2A Active CN113428748B (en) | 2021-08-09 | 2021-08-09 | Elevator control method, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113428748B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005298125A (en) * | 2004-04-09 | 2005-10-27 | Toshiba Elevator Co Ltd | Operation control device of elevator |
| CN103635408A (en) * | 2011-11-25 | 2014-03-12 | 三菱电机株式会社 | Elevator apparatus |
| CN111392532A (en) * | 2020-04-07 | 2020-07-10 | 上海爱登堡电梯集团股份有限公司 | Elevator outbound call device with voice parameter setting function, elevator parameter debugging method and elevator |
| CN111833872A (en) * | 2020-07-08 | 2020-10-27 | 北京声智科技有限公司 | Voice control method, device, equipment, system and medium for elevator |
-
2021
- 2021-08-09 CN CN202110907196.2A patent/CN113428748B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005298125A (en) * | 2004-04-09 | 2005-10-27 | Toshiba Elevator Co Ltd | Operation control device of elevator |
| CN1946624A (en) * | 2004-04-09 | 2007-04-11 | 东芝电梯株式会社 | Elevator operation controller |
| CN103635408A (en) * | 2011-11-25 | 2014-03-12 | 三菱电机株式会社 | Elevator apparatus |
| CN111392532A (en) * | 2020-04-07 | 2020-07-10 | 上海爱登堡电梯集团股份有限公司 | Elevator outbound call device with voice parameter setting function, elevator parameter debugging method and elevator |
| CN111833872A (en) * | 2020-07-08 | 2020-10-27 | 北京声智科技有限公司 | Voice control method, device, equipment, system and medium for elevator |
Non-Patent Citations (1)
| Title |
|---|
| 《端到端语音识别研究综述》;郭宗昱等;《科技创新》;20201231;7-8页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113428748A (en) | 2021-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210117801A1 (en) | Augmenting neural networks with external memory | |
| US20180336889A1 (en) | Method and Apparatus of Building Acoustic Feature Extracting Model, and Acoustic Feature Extracting Method and Apparatus | |
| JP2018528458A (en) | How to handle utterances | |
| CN112685565A (en) | Text classification method based on multi-mode information fusion and related equipment thereof | |
| CN108922564B (en) | Emotion recognition method and device, computer equipment and storage medium | |
| US11436451B2 (en) | Multimodal fine-grained mixing method and system, device, and storage medium | |
| US20130080165A1 (en) | Model Based Online Normalization of Feature Distribution for Noise Robust Speech Recognition | |
| US11048293B2 (en) | Electronic device and system for deciding duration of receiving voice input based on context information | |
| CN111783439A (en) | Man-machine interaction dialogue processing method and device, computer equipment and storage medium | |
| WO2020073532A1 (en) | Method and device for identifying conversation state of customer service robot, electronic device, and computer-readable storage medium | |
| US20180232632A1 (en) | Efficient connectionist temporal classification for binary classification | |
| KR20180109465A (en) | Electronic device and method for screen controlling for processing user input using the same | |
| CN108632653A (en) | Voice management-control method, smart television and computer readable storage medium | |
| CN112364147A (en) | Cross-domain multi-turn dialogue method based on knowledge graph and implementation system | |
| CN112836521A (en) | Question-answer matching method and device, computer equipment and storage medium | |
| US20070256435A1 (en) | Air Conditioner Control Device and Air Conditioner Control Method | |
| CN114708856A (en) | Voice processing method and related equipment thereof | |
| CN112149419A (en) | Method, device and system for normalized automatic naming of fields | |
| CN113428748B (en) | Elevator control method, storage medium and equipment | |
| CN108897517A (en) | A kind of information processing method and electronic equipment | |
| CN114582333A (en) | Voice recognition method and device, electronic equipment and storage medium | |
| US11705110B2 (en) | Electronic device and controlling the electronic device | |
| WO2021068247A1 (en) | Neural network scheduling method and apparatus, computer device, and readable storage medium | |
| CN112489644B (en) | Voice recognition method and device for electronic equipment | |
| CN115862604A (en) | Voice wakeup model training and voice wakeup method, device and computer equipment |
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 |