CN110342357A - A kind of elevator scheduling method, device, computer equipment and storage medium - Google Patents
A kind of elevator scheduling method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110342357A CN110342357A CN201910441380.5A CN201910441380A CN110342357A CN 110342357 A CN110342357 A CN 110342357A CN 201910441380 A CN201910441380 A CN 201910441380A CN 110342357 A CN110342357 A CN 110342357A
- Authority
- CN
- China
- Prior art keywords
- image
- floor
- elevator
- time ladder
- machine learning
- 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.)
- Pending
Links
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
- B66B1/3476—Load weighing or car passenger counting devices
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mechanical Engineering (AREA)
- Elevator Control (AREA)
- Indicating And Signalling Devices For Elevators (AREA)
Abstract
Present invention discloses a kind of elevator scheduling method, device, computer equipment and storage mediums, belong to technical field of face recognition, and the elevator scheduling method includes: the time ladder instruction for receiving a floor；Obtain the image in the time ladder of the floor；The fisrt feature in the image in the time ladder of the floor is obtained, the first eigenvector of the image in the time ladder of the floor is formed；The first eigenvector of image in the time ladder of the floor is input to the first machine learning model, first machine learning model export the image in the time ladder of the floor whether include face information result；If not including face information in the image in the time ladder of the floor, the time ladder instruction of the floor is removed.The operational process for thus optimizing elevator shortens the time of each operation of elevator, improves the operational efficiency of elevator, substantially reduces the waiting time of user, improves the time ladder experience of user.
Description
Technical field
The present invention relates to technical field of face recognition, more particularly to a kind of elevator scheduling method, device, computer equipment
And storage medium.
Background technique
Since in the prior art, elevator is all to follow specific operation program operation, and when elevator, waiting halls someone is pressed
When uplink button or descending button awaiting elevator, elevator will reach the floor to pick user up and down.When the floor
Not waiting person, but be pressed uplink button or descending button before elevator, but when elevator does not reach also, elevator still can be according to
Specific program stops in the floor, opens the door, closes the door and leave, then goes to execute Next Command.This adds increased the time of user ladders
Time, the time ladder experience of user is reduced, and cause energy, the waste in resource, the unnecessary conversion modalities of elevator also can
Reduce its service life.
Summary of the invention
Based on this, to solve the technical issues of existing elevator dispatching scheme will increase user's waiting time in the related technology,
The present invention provides a kind of elevator scheduling method, device, computer equipment and storage mediums.
In a first aspect, providing a kind of elevator scheduling method, comprising:
Receive the time ladder instruction of a floor；
Obtain the image in the time ladder of the floor；
The fisrt feature in the image in the time ladder of the floor is obtained, the image in the time ladder of the floor is formed
First eigenvector；
The first eigenvector of image in the time ladder of the floor is input to the first machine learning model, described the
One machine learning model export the floor time ladder in image whether include face information result；
If not including face information in the image in the time ladder of the floor, the time ladder instruction of the floor is removed.
In one of the embodiments, after removing the time ladder instruction of the floor, the method also includes:
Receive the floor instruction in elevator；
The fisrt feature in the image in the elevator is obtained, the first eigenvector of the image in the elevator is formed；
The first eigenvector of image in the elevator is input to the first machine learning model, first engineering
Practise model export the image in the elevator whether include face information result；
If not including face information in the image in the elevator, all floors instruction in the elevator is removed.
First machine learning model trains as follows in one of the embodiments:
The first image pattern collection is constituted with the set comprising positive sample and negative sample, wherein the positive sample is to include people
The image of face information, the negative sample are the image not comprising face information.
The fisrt feature of each of the first image sample set image pattern is obtained, the first image sample is formed
The first eigenvector of each of this collection image pattern；
The first eigenvector of each of the first image sample set image pattern is inputted into the first machine one by one
Learnt in learning model, first machine learning model output whether include face information judging result, if right
Do not include the judging result for meeting face information in positive sample output, or includes the judgement knot of face information for negative sample output
Fruit adjusts the first machine learning model, and the first machine learning model is made to export opposite judging result.
In one of the embodiments, after removing the time ladder instruction of the floor, the method also includes:
Receive the floor instruction in elevator；
Obtain the load-carrying weight in the elevator；
Judge whether the load-carrying weight is more than predetermined starting threshold value；
If the load-carrying weight is less than predetermined starting threshold value, all floors instruction in the elevator is removed.
In one of the embodiments, after receiving the time ladder instruction of floor, the method also includes:
Obtain the load-carrying weight in the elevator；
Judge the load-carrying weight whether be more than predetermined load-bearing threshold value and predetermined load-bearing difference difference, wherein the load-bearing
Difference, which is used to indicate, will increase the value of elevator loading；
If the load-carrying weight is more than the difference of predetermined load-bearing threshold value and predetermined load-bearing difference, the elevator is controlled only according to electricity
Floor in ladder, which instructs, to be stopped.
The image in the time ladder of the floor is obtained in one of the embodiments, is specifically included:
The image in the time ladder of the floor is obtained from different directions, and the different directions are not parallel to each other；
The image of described two different directions is synthesized into the stereo-picture in the time ladder of the floor.
Judging whether the load-carrying weight is more than that predetermined load-bearing threshold value and predetermined load-bearing are poor in one of the embodiments,
Before the difference of value, the first eigenvector of the image in the time ladder of the floor is input to the first machine learning model, institute
State the first machine learning model export the floor time ladder in image whether include face information result after, may be used also
To include:
If first machine learning model exports the knot that the image in the time ladder of the floor includes face information
Fruit positions all portraits in the stereo-picture in the time ladder of the floor；
The second feature in each portrait in the stereo-picture in the time ladder of the floor is obtained respectively, respectively group
At the second feature vector of the face；
The second feature vector of the face is input to the second machine learning model, second machine learning model is defeated
The weight value of the portrait out；
The predetermined load-bearing difference is determined according to the weight value of all portraits；
Wherein, second machine learning model trains as follows:
Obtain the second image pattern set of the stereo-picture in the time ladder of the floor including portrait, second image
Each stereo-picture sample in sample set posts weight label in advance；
The second feature of each of the second image pattern collection stereo-picture sample is obtained, first figure is formed
The second feature vector of each of decent collection image pattern；
The second feature vector of each of second image pattern collection stereo-picture sample is inputted second one by one
Machine learning model, the weight that the output of the second machine learning model determines, compares with the weight label posted, such as inconsistent, then
Second machine learning model is adjusted, keeps the weight of the machine learning model output consistent with label.
Second aspect provides a kind of elevator dispatching device, comprising:
Instruction acquisition unit, the time ladder for receiving floor instruct；
Image acquisition unit, the image in time ladder for obtaining the floor；
Feature acquiring unit, the fisrt feature in the image in time ladder for obtaining the floor, forms the building
The first eigenvector of image in the time ladder of layer；
Face identification unit, the first eigenvector for the image in the time ladder by the floor are input to the first machine
Device learning model, whether the image that first machine learning model exports in the time ladder of the floor includes face information
As a result；
Clearing cell is instructed, if not including face information in the image interior for the time ladder of the floor, described in removing
The time ladder of floor instructs.
The third aspect provides a kind of computer equipment, including memory and processor, is stored with meter in the memory
Calculation machine readable instruction, when the computer-readable instruction is executed by the processor, so that processor execution is described above
The step of elevator scheduling method.
Fourth aspect provides a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction
When being executed by one or more processors, so that the step of one or more processors execute elevator scheduling method described above.
The technical scheme provided by this disclosed embodiment can include the following benefits:
Above-mentioned elevator scheduling method, device, computer equipment and storage medium, by being instructed in the time ladder for receiving floor
Afterwards, it begins to obtain the image in the time ladder of the floor whether to be judged in described image according to described image comprising face letter
Breath.If including face information, show that someone is waiting, if not including face information, show that nobody is waiting, so that it may
It is removed with instructing marquis's ladder of the floor, is not stopped in the floor, continue to execute other tasks.Thus optimize elevator
Operational process, shorten the time of each operation of elevator, improve the operational efficiency of elevator, so that user is waiting terraced process
In will not occur elevator nobody wait ladder floor braking open the door, substantially reduce the waiting time of user, improve use
The time ladder at family is experienced.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
Fig. 1 is the implementation environment figure of the elevator scheduling method provided in one embodiment.
Fig. 2 is a kind of flow chart of elevator scheduling method shown according to an exemplary embodiment.
Fig. 3 is the flow chart of another elevator scheduling method shown in corresponding embodiment according to fig. 2.
Fig. 4 is a kind of specific reality of the first machine learning model training method according to fig. 2 or shown in Fig. 3 corresponding embodiment
Existing flow chart.
Fig. 5 is the flow chart of another elevator scheduling method shown in corresponding embodiment according to fig. 2.
Fig. 6 is the flow chart of another elevator scheduling method shown in corresponding embodiment according to fig. 2.
Fig. 7 is a kind of specific implementation flow according to step S110 in the elevator scheduling method shown in Fig. 6 corresponding embodiment
Figure.
Fig. 8 is the flow chart of another elevator scheduling method shown according to Fig. 7 corresponding embodiment.
Fig. 9 is a kind of specific implementation stream according to the second machine learning model training method shown in Fig. 8 corresponding embodiment
Cheng Tu.
Figure 10 is a kind of block diagram of elevator dispatching device shown according to an exemplary embodiment.
Figure 11 schematically shows a kind of electronic equipment example block diagram for realizing above-mentioned elevator scheduling method.
Figure 12 schematically shows a kind of computer readable storage medium for realizing above-mentioned elevator scheduling method.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Fig. 1 is the implementation environment figure of the elevator scheduling method provided in one embodiment, as shown in Figure 1, in the implementation ring
In border, including computer equipment 100, elevator terminal 200 and vision facilities 300.
Computer equipment 100 is elevator dispatching equipment, and for example, computers such as the computer, server at elevator dispatching center are set
It is standby.Elevator terminal 200 be elevator in and wait ladder it is interior realize elevator controlling elevator up and down floor terminal, e.g. wait ladder in
Have the control panel of upper lower button or floor button either and have the control panel etc. of floor button in lift car.Vision facilities
300 be that setting for the interior realtime graphic of ladder is waited in acquisition between being arranged in elevator realtime graphic in acquisition elevator or being arranged in time ladder
It is standby.
In running process of elevator, ladder instruction is waited to computer equipment when user is sent in floor by elevator terminal 200
After 100, computer equipment 100 first passes through the terraced interior image of time that vision facilities 300 obtains the floor, described getting
After image in the time ladder of floor, the fisrt feature in the image in the time ladder of the floor is extracted, the floor is formed
Time ladder in image first eigenvector, then by the first eigenvector input machine learning model, by first
Machine learning model judges whether the image in the time ladder of the floor includes face information, if not including face information, card
There is no someone to wait ladder for the bright floor, just needs to remove the time ladder instruction of the elevator terminal 200 of the floor at this time.
It should be noted that computer equipment 100 can be server, host, server cluster etc., but it is not limited to
This.Vision facilities 300 can be camera, video camera, camera etc., and however, it is not limited to this.Computer equipment 100 and elevator
Bluetooth, USB (Universal Serial Bus, universal serial bus) can be passed through between terminal 200 and vision facilities 300
Or other communication connection modes are attached, the present invention is herein with no restrictions.
As shown in Fig. 2, in one embodiment it is proposed that a kind of elevator scheduling method, the elevator scheduling method can answer
For can specifically include following steps in above-mentioned computer equipment 100:
Step S110 receives the time ladder instruction of a floor；
Step S120 obtains the image in the time ladder of the floor；
It is terraced in the time that floor presses uplink or descending button and issues when receiving user in one of the embodiments,
After instruction, the image in the time ladder of the floor is obtained when the elevator will slow down and stop the floor, because one
In the case of kind, if user is since it is desired that handling some minor matters and away from keyboard (such as losing rubbish after initiating the time ladder instruction of floor
Rubbish goes home to take key etc.), before running to the floor to elevator, returned between time ladder again, it this when, can not be simple
When being judged as that user abandons waiting, therefore whether including face information in judging described image, it should will be subtracted with the elevator
Speed is stopped subject to the image obtained when the floor.
In another embodiment, the image in the time ladder of the floor is obtained, it may also is that
In the time ladder instruction for receiving floor to the time ladder instruction for waiting or removing the floor in floor stop
In time, every a scheduled time, the image in the time ladder of the floor is obtained.
The predetermined time can be 0.5 second, 2 seconds, 7 seconds etc., and the present invention is it is not limited here.The method is compared to upper
The method of face one embodiment is more advantageous to and makes more detailed programming dispatching for the elevator.
Step S130 obtains the fisrt feature in the image in the time ladder of the floor, forms the time ladder of the floor
The first eigenvector of interior image；
The fisrt feature includes the average RGB value of the image of the acquisition, mean pixel in one of the embodiments,
Value etc..Then the first eigenvector is made of average RGB value, the average pixel value of image etc. of the acquisition, such as can be with
It is expressed as
A=[r g b p]
Wherein p represents the average pixel value of the image of the acquisition, and the image that r, g, b are obtained with statement respectively is averaged
Average R value, average G value and average B value in rgb value, the value range of described r, g, b and p are between 0~255.
In another embodiment, the fisrt feature includes the average RGB in the presumptive area of the image of the acquisition
Value, average pixel value etc..The presumptive area is often to be easy to mend the place for capturing face, e.g. four sides of described image
Or the center of described image.
In another embodiment, the fisrt feature includes being averaged in multiple presumptive areas of the image of the acquisition
Rgb value, average pixel value etc..The multiple presumptive area be, for example, described image be divided into four parts after four pieces of regions.
The first eigenvector can be expressed as
A=[A1 A2 A3 A4]T
Wherein vector A1、A2、A3And A4It is all satisfied formula
An=[rn gn bn pn]
Wherein n=1,2,3,4, A1~A4Respectively indicate four pieces of regions, pnRepresent the mean pixel of the area image
Value, rn、gn、bnRespectively with average R value, average G value and the average B value in the average RGB value for stating the area image, institute
State rn、gn、bnAnd pnValue range between 0~255.
The first eigenvector of image in the time ladder of the floor is input to the first machine learning mould by step S140
Type, first machine learning model export the floor time ladder in image whether include face information result；
Step S150 removes the time of the floor if not including face information in the terraced interior image of the time of the floor
Ladder instruction.
In one embodiment of the invention, if first machine learning model is judged in the time ladder of the floor
Image in do not include face information, then can prove in the floor that nobody is waiting ladder, at this moment computer 100 will be removed
The time ladder of the floor instructs.If first machine learning model is judged
Face information can then prove that someone is waiting ladder in the floor, and at this moment computer 100 would not remove the time of the floor
Ladder instruction, elevator will reach the floor according to program instruction and stop, and wait terraced user's boarding to allow.
The main object of the present invention is the operational process in order to optimize elevator, shortens the time of elevator operation, improves operation
Efficiency.Therefore in the inventive solutions, after receiving the time ladder instruction of floor, between the time ladder for beginning to obtain the floor
Whether interior image judges in described image according to described image comprising face information.If including face information, show have
People is waiting, if not including face information, shows that nobody is waiting, so that it may and marquis's ladder of the floor is instructed and is removed,
It is not stopped in the floor, continues to execute other tasks.
Fig. 3 is shown in one embodiment, after the step S150 in Fig. 2 corresponding embodiment, the elevator dispatching side
Method can also include the following steps.
Step S210 receives the floor instruction in elevator；
Step S220 obtains the image in the elevator；
Step S230 obtains the fisrt feature in the image in the elevator, forms first of the image in the elevator
Feature vector；
The first eigenvector of image in the elevator is input to the first machine learning model by step S240, described
First machine learning model export the image in the elevator whether include face information result；
Step S250 removes all floors in the elevator if not including face information in image in the elevator
Instruction.
It in the prior art, is after thering is user to have issued floor instruction in elevator, to be reached in elevator there are also a kind of situation
Before the designated floor, no matter elevator is interior either with or without people, and the elevator can all reach the floor that the user specifies, and stop in the layer
Only, it opens the door, close the door and leave, then go to execute Next Command.It is slack-off that elevator efficiency is also resulted in this way, when increasing user's time ladder
Between, reduce elevator service life.Therefore this programme also is provided with Face datection in addition to having Face datection in time ladder in elevator,
Judge in the elevator whether someone if someone in the elevator shows to go to accordingly there are also user by Face datection
Floor, if not having, can remove in the elevator all floors instruction.
The image in the elevator is obtained in one of the embodiments, may is that
When the elevator executes shutdown instruction every time, the image in the elevator is obtained.
Because referring to season when elevator executes shutdown every time, the user of floor has been moved off electricity where showing destination elevator
Ladder, the elevator will execute next task, at this moment, if showing described if the image in elevator includes face information
It needs to go to other floors there are also user in elevator, if showing in elevator if the image in elevator does not include face information
At this moment all floors in elevator can be instructed and be removed by nobody.
Wherein, judge that the first machine learning mould can also be passed through whether comprising face information in the image in the elevator
Type is realized.
Fig. 4 is shown in one embodiment, the training side of the first machine learning model in Fig. 2 and 3 corresponding embodiments
Method:
Step S41 constitutes the first image pattern collection with the set comprising positive sample and negative sample, wherein the positive sample
For the image comprising face information, the negative sample is the image not comprising face information；
Step S42 obtains the fisrt feature of each of the first image sample set image pattern, forms described the
The first eigenvector of each of one image pattern collection image pattern；
Step S43 inputs the first eigenvector of each of the first image sample set image pattern one by one
Learnt in first machine learning model, first machine learning model output whether include face information judgement knot
Fruit if not including the judging result for meeting face information for positive sample output, or believes negative sample output comprising face
The judging result of breath adjusts the first machine learning model, and the first machine learning model is made to export opposite judging result.
Since the known sample is positive sample or negative sample, so whether being with the data of the format convention are met
Know.Using the known result as desired output, the training machine learning model.The mode of study are as follows: inputted in the external world
Constantly change the connection weight of network under the stimulation of sample.The essence of study is to carry out dynamic adjustment to each connection weight.Due to
Desired output is known, each with regard to adjust automatically if the result of machine learning model output is not inconsistent with the desired output
Connection weight, until obtained output result is consistent with desired output.In this way, just having trained the first machine learning model.
When the training of the first machine learning model enough to it is good after, as long as by the fisrt feature of the interior image zooming-out of the time ladder from floor to
Amount inputs the first machine learning model a group by a group, and the first machine learning model will export the figure in the time ladder of the floor
It seem no comprising face information.
Fig. 5 is shown in one embodiment, after the step S150 in Fig. 2 corresponding embodiment, the elevator dispatching side
Method can also include the following steps.
Step S310 receives the floor instruction in elevator；
Step S320 obtains the load-carrying weight in the elevator；
Step S330 judges whether the load-carrying weight is more than predetermined starting threshold value；
Step S340, if the load-carrying weight is less than predetermined starting threshold value, all floors removed in the elevator refer to
It enables.
Judge in elevator whether someone when, can also be confirmed by the load-carrying in elevator, the elevator is in empty compartment state
Under load-carrying weight and someone's state under load-carrying weight be differentiated, when occupied elevator, in elevator load-carrying weight
Amount will increase, therefore can be confirmed by the load-carrying in elevator, i.e., when the load-carrying weight of the elevator is more than certain weight, institute
Stating elevator just can star, and the even described load-carrying weight is less than predetermined starting threshold value, remove all floors in the elevator
Instruction；If the load-carrying weight is more than predetermined starting threshold value, all floors instruction in the elevator is not removed, elevator is according to electricity
Floor instruction in ladder brings into operation.
It wherein obtains the load-carrying weight in the elevator and can be and obtained in real time after door-opened elevator, is also possible in elevator
It is obtained before starting at closing time or after closing the door.Why not obtaining in startup stage or deboost phase is because at this time in carriage
Substance be in state of weightlessness, the load-carrying weight at this time obtained is inaccurate.
Wherein, the predetermined starting threshold value can be 20 kilograms, 25 kilograms, 30 kilograms etc., can as the case may be into
Row setting, but should not be arranged excessively high, because in the environment that elevator uses needing that elevator is used alone in view of school-ager
The case where, it similarly, also should not be arranged too low, to prevent underage child (lighter in weight) to be strayed into elevator, elevator recognizes someone
And mistake the case where being run, the present invention is it is not limited here.
Fig. 6 is shown in one embodiment, after the step S110 in Fig. 2 corresponding embodiment, the elevator dispatching side
Method can with the following steps are included:
Step S410 obtains the load-carrying weight in the elevator；
Step S420, judge the load-carrying weight whether be more than predetermined load-bearing threshold value and predetermined load-bearing difference difference, wherein
The load-bearing difference, which is used to indicate, will increase the value of elevator loading；
Step S430 controls the electricity if the load-carrying weight is more than the difference of predetermined load-bearing threshold value and predetermined load-bearing difference
Ladder is only instructed according to the floor in elevator and is stopped.
In the prior art, there are also a kind of situation be in elevator load-carrying distance overload people have certain surplus, but
The surplus is less than the weight of a people, and elevator can still be stopped according to ladder instruction is waited in the floor that time ladder instruction issues at this time,
As soon as but the user of the floor only come in people when, will limit overload, this also reduces the operational efficiency of elevator.
Therefore this programme is also set with load-bearing difference other than being set with load-bearing threshold value, wherein the load-bearing difference is used for
It indicates that the value of elevator loading will be increased.Specifically, elevator will as be entered, so that the load-carrying progress of elevator is increased heavy
Amount.When load-carrying weight in the elevator is not up to load-bearing threshold value, if the load-carrying weight be less than predetermined load-bearing threshold value with
The difference of predetermined load-bearing difference then shows the load-carrying weight in elevator there are also having more than needed, and the Residual Loading Capacity of elevator is loaded to enough
A few people, i.e. at least one people enter the load-carrying that elevator increases elevator, and the phenomenon that overload will not occur in elevator, then simultaneously
It instructs and stops according to the time ladder of floor instruction and each floor in elevator；If the load in the load-bearing threshold value of the elevator and its elevator
The difference of heavy amount is less than the load-bearing difference, then shows that the load-carrying weight in elevator is larger, the Residual Loading Capacity of elevator compared with
It is small, it less than the value that will increase elevator load bearing, then still only instructs and stops according to the floor in elevator, elevator fortune can be shortened in this way
The capable time improves the efficiency of elevator operation, reduces the time ladder and riding time of user, optimizes the usage experience of user.
Wherein the predetermined load-bearing threshold value can be 180 kilograms, 190 kilograms, 200 kilograms etc., specifically can be according to elevator
Specification and service condition set, be the elevator in the process of running, the maximum load value that carriage is able to bear, this hair
It is bright it is not limited here.
The predetermined load-bearing difference can be 40 kilograms, 50 kilograms, 55 kilograms etc., should be the body of a normal adult
Weight, can specifically be configured, the present invention is it is not limited here according to the service condition of elevator.
Optionally, Fig. 7 be according to the datail description of step S110 in the elevator scheduling method shown in Fig. 6 corresponding embodiment,
In the elevator scheduling method, step S110 be may comprise steps of:
Step S111, obtains the image in the time ladder of the floor from different directions, and the different directions are two phases
The direction of friendship；
The image of described two different directions is synthesized the stereo-picture in the time ladder of the floor by step S112.
Fig. 8 is shown in one embodiment, after the step S110 in Fig. 7 corresponding embodiment, before step S420, and institute
Stating elevator scheduling method can also include the following steps.
Step S530, if it includes face that first machine learning model, which exports the image in the time ladder of the floor,
Information as a result, position the floor time ladder in stereo-picture in all portraits；
Step S540 obtains the second spy in each portrait in the stereo-picture in the time ladder of the floor respectively
Sign, separately constitutes the second feature vector of the face；
Described second feature includes the height of the portrait, measurements of the chest, waist and hips etc. in one of the embodiments,.
The second feature vector of the face is input to the second machine learning model, second machine by step S550
Learning model exports the weight value of the portrait；
Step S560 determines the predetermined load-bearing difference according to the weight value of all portraits.
It, can be by the weight of all portraits in one of the embodiments, when determining the predetermined load-bearing difference
Minimum value in value is as the predetermined load-bearing difference, in this way when elevator stops the floor, weight in the terraced user of the time
Most light one can boarding leave, improve the capacity of elevator.
It, can be by the weight value of all portraits when determining the predetermined load-bearing difference in another real-time example
In maximum value as the predetermined load-bearing difference because in daily life, when elevator stops the floor, the weight
Most light time ladder user not necessarily can first enter carriage, surpass when the terraced user of heavier times of an individual weight enters carriage and triggers
Again after alarm, the lightest time ladder user of the body just has very maximum probability to abandon into carriage, when also just having wasted in this way
Between.Therefore in the present embodiment using the maximum value in the weight value of all portraits as the predetermined load-bearing difference.
Fig. 9 is shown in one embodiment, the training method of the second machine learning model in Fig. 8 corresponding embodiment:
Step S51 obtains the second image pattern set of the stereo-picture in the time ladder of the floor including portrait, described
Each stereo-picture sample in second image pattern set posts weight label in advance；
Step S52 obtains the second feature of each of the second image pattern collection stereo-picture sample, forms institute
State the second feature vector of each of the first image pattern collection image pattern；
Step S53, one by one by the second feature vector of each of the second image pattern collection stereo-picture sample
The second machine learning model is inputted, the weight that the output of the second machine learning model determines is compared with the weight label posted, if not
Unanimously, then second machine learning model is adjusted, keeps the weight of the machine learning model output consistent with label.
Due to having posted weight label on the sample, so the weight of the portrait is known.This is known
As a result desired output, the training machine learning model are used as.The mode of study are as follows: under the stimulation of extraneous input sample constantly
Change the connection weight of network.The essence of study is to carry out dynamic adjustment to each connection weight.Since desired output is known
, if the result of machine learning model output is not inconsistent with the desired output, with regard to each connection weight of adjust automatically, until obtaining
Output result it is consistent with desired output.In this way, just having trained the second machine learning model.When the second machine learning model
Training is enough to after good, as long as inputting the second machine a group by a group from the second feature vector of the image zooming-out in the time ladder of floor
Device learning model, the second machine learning model will export the weight of the portrait.
As shown in Figure 10, in one embodiment, a kind of elevator dispatching device is provided, which can collect
It is obtained in above-mentioned computer equipment 100, can specifically include instruction acquisition unit 110, image acquisition unit 120, feature
Take unit 130, face identification unit 140 and instruction clearing cell 150.
Instruction acquisition unit 110, the time ladder for receiving a floor instruct；
Image acquisition unit 120, the image in time ladder for obtaining the floor；
Feature acquiring unit 130, the fisrt feature in the image in time ladder for obtaining the floor, described in composition
The first eigenvector of image in the time ladder of floor；
Face identification unit 140, the first eigenvector for the image in the time ladder by the floor are input to the
One machine learning model, first machine learning model export whether the image in the time ladder of the floor includes face letter
The result of breath；
Clearing cell 150 is instructed, if removing institute for not including face information in the image in the time ladder of the floor
State the time ladder instruction of floor.
The function of modules and the realization process of effect are specifically detailed in right in above-mentioned elevator scheduling method in above-mentioned apparatus
The realization process of step is answered, details are not described herein.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/
Or a step is decomposed into execution of multiple steps etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, mobile terminal or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 500 of this embodiment according to the present invention is described referring to Figure 11.The electricity that Figure 11 is shown
Sub- equipment 500 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 11, electronic equipment 500 is showed in the form of universal computing device.The component of electronic equipment 500 can be with
Including but not limited to: at least one above-mentioned processing unit 510, at least one above-mentioned storage unit 520, the different system components of connection
The bus 530 of (including storage unit 520 and processing unit 510).
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 510
Row, so that various according to the present invention described in the execution of the processing unit 510 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 510 can execute step S110 as shown in Figure 2, one is received
The time ladder of floor instructs；Step S120 obtains the image in the time ladder of the floor；Step S130 obtains the floor
The fisrt feature in the image in ladder is waited, the first eigenvector of the image in the time ladder of the floor is formed；Step
The first eigenvector of image in the time ladder of the floor is input to the first machine learning model by S140, and described first
Machine learning model export the floor time ladder in image whether include face information result；Step S150, if institute
It states in the image in the time ladder of floor and does not include face information, remove the time ladder instruction of the floor.
Storage unit 520 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 5201 and/or cache memory unit 5202, it can further include read-only memory unit (ROM) 5203.
Storage unit 520 can also include program/utility with one group of (at least one) program module 5205
5204, such program module 5205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 530 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 500 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 500 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 500 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 550.Also, electronic equipment 500 can be with
By network adapter 560 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 560 is communicated by bus 530 with other modules of electronic equipment 500.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 500, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
With reference to shown in Figure 12, the program product for realizing the above method of embodiment according to the present invention is described
600, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
Claims (10)
1. a kind of elevator scheduling method, which is characterized in that the described method includes:
Receive the time ladder instruction of a floor；
Obtain the image in the time ladder of the floor；
The fisrt feature in the image in the time ladder of the floor is obtained, the of the image in the time ladder of the floor is formed
One feature vector；
The first eigenvector of image in the time ladder of the floor is input to the first machine learning model, first machine
Device learning model export the floor time ladder in image whether include face information result；
If not including face information in the image in the time ladder of the floor, the time ladder instruction of the floor is removed.
2. the method as described in claim 1, which is characterized in that after removing the time ladder instruction of the floor, the method
Further include:
Receive the floor instruction in elevator；
Obtain the image in the elevator；
The fisrt feature in the image in the elevator is obtained, the first eigenvector of the image in the elevator is formed；
The first eigenvector of image in the elevator is input to the first machine learning model, the first machine learning mould
Type export the image in the elevator whether include face information result；
If not including face information in the image in the elevator, all floors instruction in the elevator is removed.
3. method according to claim 1 or 2, which is characterized in that first machine learning model trains as follows:
The first image pattern collection is constituted with the set comprising positive sample and negative sample, wherein the positive sample is to believe comprising face
The image of breath, the negative sample are the image not comprising face information；
The fisrt feature of each of the first image sample set image pattern is obtained, the first image sample set is formed
Each of image pattern first eigenvector；
The first eigenvector of each of the first image sample set image pattern is inputted into the first machine learning one by one
Learnt in model, first machine learning model output whether include face information judging result, if for just
Sample output does not include the judging result for meeting face information, or includes the judging result of face information for negative sample output,
The first machine learning model is adjusted, the first machine learning model is made to export opposite judging result.
4. the method as described in claim 1, which is characterized in that after removing the time ladder instruction of the floor, the method
Further include:
Receive the floor instruction in elevator；
Obtain the load-carrying weight in the elevator；
Judge whether the load-carrying weight is more than predetermined starting threshold value；
If the load-carrying weight is less than predetermined starting threshold value, all floors instruction in the elevator is removed.
5. the method as described in claim 1, which is characterized in that after receiving the time ladder instruction of floor, the method is also wrapped
It includes:
Obtain the load-carrying weight in the elevator；
Judge the load-carrying weight whether be more than predetermined load-bearing threshold value and predetermined load-bearing difference difference, wherein the load-bearing difference
The value of elevator loading will be increased by being used to indicate；
If the load-carrying weight is more than the difference of predetermined load-bearing threshold value and predetermined load-bearing difference, the elevator is controlled only according in elevator
Floor instruct stop.
6. method as claimed in claim 5, which is characterized in that obtain the image in the time ladder of the floor, specifically include:
The image in the time ladder of the floor is obtained from different directions, and the different directions are not parallel to each other；
The image of described two different directions is synthesized into the stereo-picture in the time ladder of the floor.
7. method as claimed in claim 6, which is characterized in that judging whether the load-carrying weight is more than predetermined load-bearing threshold value
And before the difference of predetermined load-bearing difference, the first eigenvector of the image in the time ladder of the floor is input to the first machine
Learning model, first machine learning model export the floor time ladder in image whether include face information knot
After fruit, can also include:
If it includes face information as a result, fixed that first machine learning model, which exports the image in the time ladder of the floor,
All portraits in stereo-picture in the time ladder of the position floor；
The second feature in each portrait in the stereo-picture in the time ladder of the floor is obtained respectively, separately constitutes institute
State the second feature vector of face；
The second feature vector of the face is input to the second machine learning model, second machine learning model exports institute
State the weight value of portrait；
The predetermined load-bearing difference is determined according to the weight value of all portraits；
Wherein, second machine learning model trains as follows:
Obtain the second image pattern set of the stereo-picture in the time ladder of the floor including portrait, second image pattern
Each stereo-picture sample in set posts weight label in advance；
The second feature of each of the second image pattern collection stereo-picture sample is obtained, the first image sample is formed
The second feature vector of each of this collection image pattern；
The second feature vector of each of second image pattern collection stereo-picture sample is inputted into the second machine one by one
Learning model, the weight that the output of the second machine learning model determines, compares with the weight label posted, such as inconsistent, then adjusts
Second machine learning model keeps the weight of the machine learning model output consistent with label.
8. a kind of elevator dispatching device, which is characterized in that described device includes:
Instruction acquisition unit, the time ladder for receiving floor instruct；
Image acquisition unit, the image in time ladder for obtaining the floor；
Feature acquiring unit, the fisrt feature in the image in time ladder for obtaining the floor, forms the floor
Wait the first eigenvector of the image in ladder；
Face identification unit, the first eigenvector for the image in the time ladder by the floor are input to the first engineering
Practise model, first machine learning model export the floor time ladder in image whether include face information knot
Fruit；
Clearing cell is instructed, if removing the floor for not including face information in the image in the time ladder of the floor
Time ladder instruction.
9. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, it is described
When computer-readable instruction is executed by the processor, so that the processor is executed as described in any one of claims 1 to 7
Method.
10. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes, so that one or more processors execute the method as described in any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910441380.5A CN110342357A (en) | 2019-05-24 | 2019-05-24 | A kind of elevator scheduling method, device, computer equipment and storage medium |
| PCT/CN2020/090712 WO2020238661A1 (en) | 2019-05-24 | 2020-05-16 | Elevator scheduling method, device, computer apparatus, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910441380.5A CN110342357A (en) | 2019-05-24 | 2019-05-24 | A kind of elevator scheduling method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110342357A true CN110342357A (en) | 2019-10-18 |
Family
ID=68174431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910441380.5A Pending CN110342357A (en) | 2019-05-24 | 2019-05-24 | A kind of elevator scheduling method, device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110342357A (en) |
| WO (1) | WO2020238661A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020238661A1 (en) * | 2019-05-24 | 2020-12-03 | 深圳壹账通智能科技有限公司 | Elevator scheduling method, device, computer apparatus, and storage medium |
| CN112560986A (en) * | 2020-12-25 | 2021-03-26 | 上海商汤智能科技有限公司 | Image detection method and device, electronic equipment and storage medium |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113370216A (en) * | 2021-06-29 | 2021-09-10 | 上海有个机器人有限公司 | Ladder waiting method and device for robot to take ladder, robot and storage medium |
| CN114261858A (en) * | 2021-11-19 | 2022-04-01 | 北京声智科技有限公司 | Data processing method, device, equipment, system and computer storage medium |
| CN114229637B (en) * | 2021-12-03 | 2024-02-27 | 北京声智科技有限公司 | Elevator floor determination method, device, equipment and computer readable storage medium |
| CN114476891A (en) * | 2022-03-02 | 2022-05-13 | 北京云迹科技股份有限公司 | Method, device, equipment and storage medium for preventing tailing in elevator |
| CN115504341A (en) * | 2022-09-29 | 2022-12-23 | 深圳市明源云科技有限公司 | Elevator running method, device, terminal equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101200252A (en) * | 2007-12-10 | 2008-06-18 | 中国科学院计算技术研究所 | Target place optimized dispatching method and system |
| CN102674095A (en) * | 2012-05-24 | 2012-09-19 | 西南交通大学 | Energy-saving dispatching control method of elevator for passenger detection based on binocular vision |
| CN103010874A (en) * | 2011-09-26 | 2013-04-03 | 联想(北京)有限公司 | Elevator dispatching method and system |
| JP2013177236A (en) * | 2012-02-29 | 2013-09-09 | Mitsubishi Electric Corp | Elevator control device |
| CN103508282A (en) * | 2012-06-28 | 2014-01-15 | 株式会社日立制作所 | Elevator monitoring device and monitoring method |
| CN106956981A (en) * | 2016-01-12 | 2017-07-18 | 株式会社日立大厦系统 | The load detecting adjusting apparatus and elevator of elevator |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060100527A (en) * | 2005-03-17 | 2006-09-21 | 김건엽 | Apparatus for automatic revoke of elevator calling and method thereof |
| JP2010111444A (en) * | 2008-11-04 | 2010-05-20 | Mitsubishi Electric Corp | Landing call registration management device for elevator car |
| CN102821272B (en) * | 2012-08-16 | 2015-03-04 | 安徽中科智能高技术有限责任公司 | Video monitoring system with elevator invalid request signal removing function |
| CN103538981B (en) * | 2013-10-12 | 2015-10-28 | 福建工程学院 | The device and method that please stop is cancelled when elevator presses rear unmanned time ladder or elevator cars with full load |
| CN104709786A (en) * | 2013-12-14 | 2015-06-17 | 李淑华 | Intelligent elevator |
| CN207713204U (en) * | 2017-06-26 | 2018-08-10 | 西安电子科技大学 | Number detecting system in lift car based on fuzzy reasoning |
| CN108566534A (en) * | 2018-04-23 | 2018-09-21 | Oppo广东移动通信有限公司 | Alarm method, device, terminal based on video monitoring and storage medium |
| CN110342357A (en) * | 2019-05-24 | 2019-10-18 | 深圳壹账通智能科技有限公司 | A kind of elevator scheduling method, device, computer equipment and storage medium |
-
2019
- 2019-05-24 CN CN201910441380.5A patent/CN110342357A/en active Pending
-
2020
- 2020-05-16 WO PCT/CN2020/090712 patent/WO2020238661A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101200252A (en) * | 2007-12-10 | 2008-06-18 | 中国科学院计算技术研究所 | Target place optimized dispatching method and system |
| CN103010874A (en) * | 2011-09-26 | 2013-04-03 | 联想(北京)有限公司 | Elevator dispatching method and system |
| JP2013177236A (en) * | 2012-02-29 | 2013-09-09 | Mitsubishi Electric Corp | Elevator control device |
| CN102674095A (en) * | 2012-05-24 | 2012-09-19 | 西南交通大学 | Energy-saving dispatching control method of elevator for passenger detection based on binocular vision |
| CN103508282A (en) * | 2012-06-28 | 2014-01-15 | 株式会社日立制作所 | Elevator monitoring device and monitoring method |
| CN106956981A (en) * | 2016-01-12 | 2017-07-18 | 株式会社日立大厦系统 | The load detecting adjusting apparatus and elevator of elevator |
Non-Patent Citations (1)
| Title |
|---|
| 周永章，张良均，张奥多，王俊著: "《地球科学大数据挖掘与机器学习》", 30 September 2018, 中山大学出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020238661A1 (en) * | 2019-05-24 | 2020-12-03 | 深圳壹账通智能科技有限公司 | Elevator scheduling method, device, computer apparatus, and storage medium |
| CN112560986A (en) * | 2020-12-25 | 2021-03-26 | 上海商汤智能科技有限公司 | Image detection method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020238661A1 (en) | 2020-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110342357A (en) | A kind of elevator scheduling method, device, computer equipment and storage medium | |
| JP6619760B2 (en) | Elevator apparatus, elevator system, and autonomous robot control method | |
| CN113682908B (en) | Intelligent scheduling method based on deep learning | |
| AU2012323116B2 (en) | Elevator system with multiple cars | |
| JP2013173595A (en) | Elevator arrival time estimating device and elevator system | |
| US11513522B2 (en) | Robot using an elevator and method for controlling the same | |
| CN106586738A (en) | Multi-car elevator dispatching method based on visual inspection | |
| CN106892307A (en) | The method and elevator device of information alert | |
| CN105960372A (en) | Smart watch for elevator use | |
| CN106744089B (en) | Elevator control method and device | |
| Cortés et al. | Fuzzy logic based controller for peak traffic detection in elevator systems | |
| CN108975101A (en) | Elevator control method, device, system, equipment and storage medium | |
| CN110342354A (en) | A kind of elevator scheduling method, device, elevator device and storage medium | |
| WO2018230654A1 (en) | Interaction device, interaction method, and program | |
| CN108249236A (en) | The method, apparatus and computer readable storage medium of Intelligent controlled elevator | |
| CN112607534A (en) | User elevator taking guiding method and system | |
| CN110884971A (en) | Energy saving method and system for group control elevator and computer storage medium | |
| CN116443682A (en) | Intelligent elevator control system | |
| CN114890258B (en) | Intelligent speed control method and system for elevator | |
| CN110347496A (en) | Resource handles dispatching method, device, computer equipment and storage medium | |
| CN115783915A (en) | Control method, system, equipment and storage medium of building equipment | |
| CN210854833U (en) | Multi-car elevator control system | |
| CN114057051A (en) | Reminding method and system for calling elevator in car | |
| CN113896063A (en) | Elevator intelligent dispatching system based on AI intelligence | |
| CN114684680B (en) | Elevator control method and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information |
Address after: 201, room 518000, building A, No. 1, front Bay Road, Qianhai Shenzhen Guangdong Shenzhen Hong Kong cooperation zone (Qianhai business secretary) Applicant after: ONECONNECT FINANCIAL TECHNOLOGY Co.,Ltd. (SHANGHAI) Address before: 518000 Guangdong city of Shenzhen province Qianhai Shenzhen Hong Kong cooperation zone before Bay Road No. 1 building 201 room A Applicant before: ONECONNECT FINANCIAL TECHNOLOGY Co.,Ltd. (SHANGHAI) |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191018 |
|
| RJ01 | Rejection of invention patent application after publication |