KR20190077558A - Recovery system - Google Patents

Abstract

The classifier 11 classifies the input time series data and outputs a plurality of estimated failure contents. The classifier 13 classifies the input attribute data and outputs a plurality of estimated failure contents. The fault identification unit 14 specifies the contents of the fault occurring in the elevator apparatus based on the estimated fault contents output by the classifier 11 and the estimated fault contents output by the classifier 13. [ The task specifying unit (15) specifies the contents of the task with respect to a specific failure content by the failure specifying unit (14).

Description

Recovery system

This invention relates to a recovery system.

Patent Document 1 discloses a system for remotely recovering an elevator apparatus after an earthquake has occurred. In the system described in Patent Document 1, when the operation of the elevator apparatus is stopped by an earthquake, a signal indicating that the operation is stopped and a signal indicating the state of the car are transmitted to the management center. In the management center, the received signal is displayed on the indicator. The manager of the management center sees what is displayed on the indicator and sends a signal to reset the earthquake detector.

Patent Document 1: Japanese Patent Application Laid-Open No. 2007-254039

Patent Document 1 discloses a system for restoring an elevator apparatus whose operation is stopped by an earthquake. When the operation is stopped by an earthquake, the elevator apparatus often has no trouble. Therefore, the elevator apparatus can be easily restored by resetting the seismic sensor.

On the other hand, a failure occurs in the elevator apparatus. When a failure occurs in the elevator apparatus, it is necessary to perform an operation corresponding to a failure that has occurred. Conventionally, the elevator apparatus can not be remotely restored because a proper operation can not be grasped when a failure occurs in the elevator apparatus.

The present invention has been made to solve the above-mentioned problems. SUMMARY OF THE INVENTION It is an object of the present invention to provide a restoration system capable of specifying an appropriate work content for a failure when a failure occurs in an elevator apparatus.

The restoration system according to the present invention includes receiving means for receiving time series data from an elevator apparatus, a first classifier for receiving the time series data received by the receiving means, classifying the inputted time series data and outputting a plurality of estimated failure contents, A second classifier for receiving the attribute data acquired by the acquisition means and classifying the input attribute data and outputting a plurality of estimated failure contents; A failure specifying means for specifying a failure occurring in the elevator apparatus on the basis of the estimated failure content and the estimated failure content output by the second classifier, and a job specifying means for specifying the job content for the specific failure content Respectively.

The restoration system according to the present invention includes: storage means for storing a probability that each of the content of the work is selected for each of a plurality of failure contents, a plurality of work contents, and the failure contents; A first classifier for receiving the time series data received by the receiving means and classifying the inputted time series data and outputting an estimated occurrence probability for each of the failure contents stored in the storage means; A second classifier for inputting the attribute data acquired by the acquisition means and classifying the input attribute data and outputting an estimated occurrence probability for each of the failure contents stored in the storage means; Based on the estimated occurrence probability outputted from the first classifier, the estimated occurrence probability outputted from the second classifier, and the probability stored in the storage means, Among the information stored in the work billion means comprises a specifying means for specifying one.

In the restoration system according to the present invention, for example, the contents of the failure occurring in the elevator apparatus are specified based on the estimated failure contents outputted by the first classifier and the estimated failure contents outputted by the second classifier. In addition, the content of the work for the specified trouble content is specified. With the recovery system according to the present invention, when a failure occurs in the elevator apparatus, it is possible to specify an appropriate work content for a failure that has occurred.

1 is a diagram showing an example of a restoration system according to the first embodiment of the present invention.
2 is a diagram showing an example of a management center.
3 is a flowchart showing an example of the operation of the restoration system according to the first embodiment of the present invention.
4 is a flowchart showing another operation example of the restoration system according to the first embodiment of the present invention.
5 is a diagram showing another example of the management center.
6 is a flowchart showing another operation example of the restoration system according to the first embodiment of the present invention.
7 is a diagram showing an example of a decision tree.
8 is a diagram showing an example of a management center.
9 is a flowchart showing an example of the operation of the restoration system according to the second embodiment of the present invention.
10 is a diagram showing the hardware configuration of the management center.

BRIEF DESCRIPTION OF THE DRAWINGS Fig. Duplicate descriptions may be simplified or omitted as appropriate. In the drawings, the same reference numerals denote the same or corresponding parts.

Embodiment 1

1 is a diagram showing an example of a restoration system according to the first embodiment of the present invention. The management center 1 is capable of communicating with a plurality of remote elevator devices. Each elevator apparatus includes, for example, an elevator car 2 and a balance weight 3. The elevator car (2) and the balance weight (3) are suspended from the hoistway by the main rope (4). The traction machine has, for example, a drive sheave 5 and an electric motor 6. The main rope 4 is wound on the driving sheave 5. The drive sheave 5 is driven by the electric motor 6. The electric motor (6) is controlled by the control device (7). And the communication device 8 is connected to the control device 7. [ The communication device 8 communicates with an external device. Each elevator device communicates with the management center 1 by means of the communication device 8.

When a failure occurs in the elevator apparatus, a snapshot of the signal value indicative of the elevator condition, that is, trace data is acquired by the communication device 8. [ The trace data is an example of a group of signals including a plurality of signals. For example, a signal for specifying the elevator apparatus itself is included in the trace data. A signal indicating time is included in the trace data. A signal indicating the current value and the voltage value of the control device 7 is included in the trace data. A signal indicating the speed and torque of the electric motor 6 is included in the trace data. A signal indicating the position of the car 2 is included in the trace data. The signals included in the trace data are not limited to these examples. Some of the illustrated signals need not be included in the trace data. Other signals may be included in the trace data.

When a failure occurs in the elevator apparatus, the communication device 8 acquires the trace data for a predetermined time before and after occurrence of the failure. For example, when a failure occurs in the elevator apparatus, the communication apparatus 8 acquires trace data every 5 ms for a period from 50 ms before a failure occurs to 50 ms after a failure occurs. When the communication device 8 acquires the trace data, it transmits the acquired trace data to the management center 1.

Further, when a failure occurs in the elevator apparatus, the communication device 8 transmits the diagnostic code to the management center 1 together with the acquired trace data. The diagnostic code includes data indicating the cause of the failure.

Fig. 2 is a diagram showing an example of the management center 1. Fig. The management center 1 includes a storage unit 9, a receiving unit 10, a classifier 11, an acquiring unit 12, a classifier 13, a failure specifying unit 14, a job specifying unit 15, A determination section 16, a transmission section 17, and a notification control section 18. The functions and operations of the present restoration system will be described below with reference also to Fig. 3 is a flowchart showing an example of the operation of the restoration system according to the first embodiment of the present invention.

When a failure occurs in any of the elevator apparatuses, trace data and diagnostic code are transmitted from the communication apparatus 8 of the elevator apparatus to the management center 1. The data transmitted from the communication device 8 is received by the receiving unit 10 in the management center 1 (S101). When data from the communication device 8 is received by the receiving unit 10, the management center 1 determines whether or not the received data is time series data (S102).

The classifier 11 outputs the estimated failure content from the input data. Time series data is input to the classifier 11. The trace data received by the receiving unit 10 includes a plurality of time series data. For example, the transition of the signal indicating the current value of the control device 7 is time series data. The transition of the signal indicating the speed of the electric motor 6 is time series data. That is, the receiving unit 10 is an example of means for receiving time series data from the elevator apparatus. In the classifier 11, among the data received by the receiving unit 10 in S101, data determined to be time series data in S102 is input.

The classifier 11 classifies the input time series data (S103) and estimates the failure contents (S104). The classifier 11 outputs a plurality of estimated failure contents based on the classification result. The estimated failure content output from the classifier 11 may be provided with additional information such as the probability of occurrence of the estimated failure.

The classifier 13 outputs the estimated failure content from the input data. Attribute data is input to the classifier 13. The attribute data is data that is not time-series data among data relating to the elevator apparatus. For example, the diagnostic code is attribute data. The data indicating the model of the elevator apparatus is attribute data. The data indicating the rated speed is attribute data. The data representing the layer of the building in which the elevator apparatus is provided is attribute data.

The acquisition unit 12 acquires the attribute data. When the receiving unit 10 receives the trace data and the diagnostic code, the acquiring unit 12 acquires attribute data relating to the elevator apparatus that has transmitted the data. For example, the acquiring unit 12 acquires the attribute data from the data received by the receiving unit 10. The acquisition unit 12 may acquire the attribute data from the data stored in the storage unit 9. [ In the classifier 13, data determined not to be time-series data is input in S102.

The classifier 13 classifies the input attribute data (S105) and estimates the failure content (S106). The classifier 13 outputs a plurality of estimated failure contents based on the classification result. Additional information such as the probability of occurrence of the estimated failure may be added to the estimated failure content output from the classifier 13. [

The fault identification unit 14 specifies the contents of the fault occurring in the elevator apparatus (S107). The failure specifying unit 14 performs the above-described specification based on, for example, the estimated failure content output from the classifier 11 and the estimated failure content output from the classifier 13. [ For example, if the probability of occurrence among the estimated failure contents output from the classifier 11 is the highest and the probability of occurrence among the estimated failure contents output from the classifier 13 is the highest, the failure identification unit 14 determines that the estimated failure The content is specified as a failure content occurring in the elevator apparatus. The failure identifying section 14 may specify one failure content based on a value obtained by multiplying the probability of occurrence of the estimated failure content.

The task specifying unit 15 specifies the task content for the failure content specified by the failure specifying unit 14 (S108). For example, with respect to each failure content that can be specified by the failure specifying unit 14, the contents of a job to be selected are set in advance. The setting contents are stored in the storage unit 9, for example. The task specifying unit 15 may specify the contents of the task with respect to the failure contents by referring to the setting contents stored in the storage unit 9. [

The judging unit 16 judges whether the work content specified by the job specifying unit 15 is executable by remote operation (S109). For example, if the contents of the work such as " resetting of the elevator apparatus " are specified in S108, the answer is YES in S109. If it is determined by the determination section 16 that it is executable by the remote operation, the transmission section 17 transmits a command for executing the job content specified by the job specifying section 15 in S108 to the elevator device in which the failure occurred S110).

On the other hand, if the contents of the work requiring dispatch of the repair source such as " exchange of the substrate " are specified in S108, No is determined in S109. For example, the notification control unit 18 causes the notification unit 22 to inform the job specifying unit 15 of the job content specified in S108 (S111). The notification control unit 18 may notify the notification unit 22 of the result of the determination made by the determination unit 16 in S109 together with the contents of the operation. The notification control unit 18 determines whether or not the operation specified by the operation specifying unit 15 in step S108 and the result of the determination made by the determination unit 16 in step S109 It may be notified from the notification device 22. The alerter 22 is provided, for example, in the management center 1.

According to the example shown in this embodiment, when a failure occurs in the elevator apparatus, it is possible to specify an appropriate work content for a failure that has occurred. Particularly, in the example of this embodiment, the content of the work is specified based on the estimated failure contents obtained by classifying the time series data and the estimated failure contents obtained by classifying the attribute data. Since class classification by a plurality of classifiers using independent data is performed for the same event, the reliability of a specific result can be improved.

In the example shown in Fig. 3, in S110, a command for executing the work content is automatically transmitted. This is an example. Even if the job specifying unit 15 notifies the notification unit 22 of the contents of the job specified in S108 and the result of the determination made by the determination unit 16 in S109 in the case where it is determined to be Yes in S109 do. In this case, a command for carrying out the job content is transmitted by the manager's judgment.

In the example shown in Fig. 3, it is judged in S109 whether the work content specified by the job specifying section 15 is executable by remote operation. This is an example. The job specifying unit 15 may notify the notification unit 22 of the job content specified in S108 without performing the above determination after the processing of S108 is performed. In this case, the judgment as to whether or not the work content is executable by the remote operation is made by the manager.

4 is a flowchart showing another operation example of the restoration system according to the first embodiment of the present invention. Fig. 4 shows a specific example of the process shown in S109 of Fig. The determination section 16 may determine whether the work content specified by the job specification section 15 is executable by remote operation based on the time series data received by the reception section 10 in S101.

For example, the judging unit 16 judges whether a person is riding in the elevator car 2 of the elevator apparatus in which a failure occurs, from a signal indicating a balance value included in the trace data (S201). The judging section 16 does not judge that the work contents specified by the work specifying section 15 can be carried out by the remote operation when the person is riding in the car 2. [ The determining section 16 may determine whether the main rope 4 is normal from the signal included in the trace data (S202). The judging section 16 does not judge that the work contents specified by the work specifying section 15 can be carried out by remote operation if an abnormality has been issued to the main ropes 4. [

The judging unit 16 may judge whether or not the braking for stopping the driving sheave 5 is normal from the signal included in the trace data (S203). If the abnormality is issued to the brake, the judging unit 16 does not judge that the work contents specified by the work specifying unit 15 can be performed by remote operation. The determination items shown in S201 to S203 are an example. Only one of the determination items S201 to S203 may be employed, or a plurality of the determination items may be employed. Other judgment items may be employed as necessary. For example, the judging unit 16 judges whether or not the work content specified by the job specifying unit 15 is remote (not shown) based on the time-series data received by the receiving unit 10 as well as the attribute data acquired by the acquiring unit 12 It may be determined whether or not it is practicable by an operation. If the determination section 16 determines that all the adopted determination items are Yes, the transmission section 17 transmits a command for executing the job content specified in step S108 to the elevator apparatus in which the failure has occurred (S110).

Fig. 5 is a diagram showing another example of the management center 1. Fig. In the example shown in Fig. 5, the management center 1 further includes an update unit 19 and an update unit 20 in addition to the elements shown in Fig. The updating unit (19) updates the classifier (11). The updating unit 20 updates the classifier 13. [ Hereinafter, functions and operations of the updating unit 19 and the updating unit 20 will be described with reference to Figs. 6 and 7. Fig. 6 is a flowchart showing another operation example of the restoration system according to the first embodiment of the present invention.

When a failure occurs in any of the elevator apparatuses, trace data and diagnostic code are transmitted from the communication apparatus 8 of the elevator apparatus to the management center 1. The data transmitted from the communication device 8 is received by the receiving unit 10 in the management center 1 (S301). The data received by the receiving section 10 is stored in the storage section 9.

The storage unit 9 stores data received from a plurality of elevator apparatuses. The storage unit 9 also stores other data related to the elevator apparatus. For example, the details of the work performed in the elevator apparatus in which the failure occurs in the storage unit 9 are stored. This work is, for example, data input by a maintenance worker who has actually performed the work. The storage unit 9 may store the specific failure content judged by the repairer. The contents of this fault are the data entered by the worker who performed the work after the work. As another example, data such as the model, rated speed, and rated speed of each elevator apparatus is stored in the storage unit 9. In the storage unit 9, data such as a layered structure of a building provided with each elevator apparatus is stored. The updating unit 19 and the updating unit 20 perform update processing based on these data stored in the storage unit 9. [

The updating unit 19 performs learning based on the time series data received by the receiving unit 10 from each elevator apparatus (S303) and updates the classifying unit 11 (S304). The processing of S302 is the same as the processing of S102 shown in Fig. The update unit 19 receives the data determined to be time series data in S302.

The updating unit 19 may update the classifier 11 by any method. For example, regarding time series data, [x ₁ , x ₂ , ..., , x _M ] ^T as an input to the updating unit 19. Where [·] ^T denotes transposition. The updating unit 19 performs supervised learning based on the data input by the maintenance worker after the work by, for example, a neural network NN.

The updating unit 20 performs learning based on the attribute data of each elevator apparatus (S305), and updates the classifier 13 (S306). The update unit 20 receives the data determined not to be the time series data in S302.

The updating unit 20 may update the classifier 13 by any method. For example, the following Table 1 shows an example of the attribute data stored in the storage unit 9. The updating unit 20 generates a decision tree as shown in FIG. 7, for example, and performs learning. 7 is a diagram showing an example of a decision tree. In addition, the learning method by the updating unit 20 is not limited to the determination tree. For example, pattern mining or the like may be employed as the learning by the updating unit 20. [

Rated speed Rated capacity ... Diagnostic Codes Fault description (input of repair source) 100m / min 1500kg ... 0001 B1 failure 200m / min 2000kg ... 0001 B2 failure 150m / min 1800kg ... 0101 B3 failure : : : : : 800m / min 2500kg ... 1111 Bn failure

In the example shown in Figs. 5 and 6, since learning using independent data is performed for each classifier for the same event, the reliability of the specific result can be improved.

Embodiment 2 Fig.

An example of the restoration system in this embodiment is the same as the example shown in Fig. Fig. 8 is a diagram showing an example of the management center 1. Fig. In the example shown in this embodiment, the management center 1 includes, for example, a storage unit 9, a receiving unit 10, a classifier 11, an acquiring unit 12, a classifier 13, A determination section 16, a transmission section 17, and a notification control section 18.

In the storage unit 9, for example, a failure list, a work list, and a probability list are stored. Table 2 shows an example of a failure list. The fault list includes a plurality of fault contents that can occur in the elevator apparatus.

No. Failure content One B1 failure 2 B2 failure : n Bn failure

Table 3 shows an example of the work list. The work list includes a plurality of work contents that can be performed in the elevator apparatus in which the failure occurs.

No. Work contents One ○ P1 operation 2 ○ P2 operation : k ○ Pk operation

Table 4 shows an example of a probability list. The probability list includes the probability that each of the task contents included in the task list is selected for each of the failure contents included in the failure list.

Failure content Work contents Selection probability

B1 failure ○ P1 operation 0.55 ○ P2 operation 0.21 : : ○ Pk operation 0.06

B2 failure ○ P1 operation 0.44 ○ P2 operation 0.29 : : ○ Pk operation 0.02 :

Bn failure ○ P1 operation 0.61 ○ P2 operation 0.13 : : ○ Pk operation 0.01

The functions and operations of the present restoration system will be described below with reference also to Fig. 9 is a flowchart showing an example of the operation of the restoration system according to the second embodiment of the present invention.

When a failure occurs in any of the elevator apparatuses, trace data and diagnostic code are transmitted from the communication apparatus 8 of the elevator apparatus to the management center 1. The data transmitted from the communication device 8 is received by the receiving unit 10 in the management center 1 (S401). When the data from the communication device 8 is received by the receiving unit 10, the management center 1 determines whether or not the received data is time series data (S402).

In the present embodiment, the classifier 11 outputs an estimated occurrence probability for each of the failure contents included in the failure list, from the input data. In the classifier 11, for example, time series data received by the receiving section 10 is input. The classifier 11 classifies the input time series data (S403) and estimates the occurrence probability (S404). The classifier 11 outputs the estimated occurrence probability P _u (x _i ) for each failure content based on the classification result. Here, x _i is the i-th failure content written in the failure list.

The classifier 13 outputs an estimated occurrence probability for each of the failure contents included in the failure list, from the input data. In the classifier 13, for example, attribute data acquired by the acquisition unit 12 is input. The classifier 13 classifies the input attribute data (S405) and estimates the occurrence probability (S406). The classifier 13 outputs an estimated occurrence probability P _v (x _i ) for each failure content based on the classification result.

The specifying unit 21 specifies one of the contents of the work included in the work list (S408). The specifying unit 21 performs the specification based on the estimated occurrence probability output from the classifier 11, the estimated occurrence probability output from the classifier 13, and the probability included in the probability list. For example, a result obtained by multiplying the estimated occurrence probability P _u (x _i ) output from the classifier 11 by the probability included in the probability list is P _u (x _i ) P (x _i | z _j ). It is referred to as | (z _j x _i) is multiplied by the result made probability included in the estimated probability P _v (x _i) and a probability list output from the classifier _{(11) P v (x i} ) P. Here, z _j is the i-th work content described in the work list. Specification unit 21 is, for example, P _u (x _i), P is the average of | | (z _j x _i) selecting the highest work (x _i z _j), and P _v (x _i) P .

The judging unit 16 judges whether the work content specified by the specifying unit 21 is executable by remote operation (S409). If it is determined by the determination section 16 that it is executable by the remote operation, the transmission section 17 transmits a command for causing the specifying section 21 to execute the job content specified in S408 to the elevator device in which the failure occurred S410).

On the other hand, if it is not determined by the determination section 16 that the operation can be performed by remote operation, for example, the notification control section 18 determines whether or not the specification section 21 has received the operation content specified in S408 from the notification device 22 (S411). The notification control unit 18 may notify the notification unit 22 of the result determined by the determination unit 16 in step S409 together with the contents of the operation. When the determination unit 16 determines that the operation can be performed by the remote operation, the notification control unit 18 notifies the operation contents specified in S408 and the determination result of the determination unit 16 in S409 It may be notified from the device 22.

According to the example shown in this embodiment, when a failure occurs in the elevator apparatus, it is possible to specify an appropriate work content for a failure that has occurred. Particularly, in the example of this embodiment, the contents of work are specified based on the estimated occurrence probability obtained by classifying the time series data and the estimated occurrence probability obtained by classifying the attribute data. Since class classification by a plurality of classifiers using independent data is performed for the same event, the reliability of a specific result can be improved.

In the example shown in Fig. 9, in S410, a command for carrying out the work contents is automatically transmitted. This is an example. If the determination in S409 is YES, the specifying unit 21 may notify the informer 22 of the contents of the job specified in S408 and the determination result of the determining unit 16 in S409 without automatically transmitting the command . In this case, a command for carrying out the job content is transmitted by the manager's judgment.

In the example shown in Fig. 9, it is judged in S409 whether or not the work contents specified by the specifying section 21 can be performed by remote operation. This is an example. The determination unit 21 may notify the notification unit 22 of the job content specified in S408 after the process of S408 is performed. In this case, the judgment as to whether or not the work content is executable by the remote operation is made by the manager.

In the example shown in this embodiment, the determination unit 16 also determines whether the operation content specified by the specifying unit 21 can be performed by remote operation, based on the time series data received by the receiving unit 10 in step S401 . That is, an operation example shown in Fig. 4 may be employed. The determining section 16 determines whether or not the contents of the work specified by the specifying section 21 have been received by the remote operation based on the attribute data acquired by the acquiring section 12 as well as the time series data received by the receiving section 10 It may be determined whether or not it is practicable.

The management center 1 may further include an update unit 19 and an update unit 20 in addition to the elements shown in Fig. The updating unit 19 performs learning based on the time series data received by the receiving unit 10 from each elevator apparatus, for example, and updates the classifying unit 11. The updating unit 19 may update the classifier 11 by any method. The update unit 19 performs map learning based on the data input by the maintenance worker after the work, for example, by the neural network NN. The updating unit 20 updates the classifier 13 by performing learning based on, for example, attribute data about each elevator apparatus. The updating unit 20 may update the classifier 13 by any method. The update unit 20 generates a decision tree, for example, and performs learning.

Elements indicated by reference numerals 9 to 21 denote functions of the management center 1. Fig. 10 is a diagram showing the hardware configuration of the management center 1. Fig. The management center 1 has a processing circuit including, for example, a processor 23 and a memory 24 as hardware resources. The function of the storage unit 9 is realized by the memory 24. [ The management center 1 executes the programs stored in the memory 24 by the processor 23 to realize the functions of the respective parts indicated by reference numerals 10 to 21. [

The processor 23 is also referred to as a CPU (Central Processing Unit), a central processing unit, a processing unit, a computing unit, a microprocessor, a microcomputer, or a DSP. As the memory 24, a semiconductor memory, a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD may be employed. Examples of the semiconductor memory that can be employed include a RAM, a ROM, a flash memory, an EPROM, and an EEPROM.

Some or all of the functions of the management center 1 may be realized by hardware. As the hardware for realizing the functions of the management center 1, a single circuit, a complex circuit, a programmed processor, a parallelized programmed processor, an ASIC, an FPGA, or a combination thereof may be employed.

Industrial availability

The restoration system according to the present invention can be applied to a system capable of communicating with an elevator apparatus.

1: Management center 2: Elevator car
3: Balance weight 4; Main rope
5: Driving sheave 6: Electric motor
7: Control device 8: Communication device
9: storage unit 10:
11: Classifier 12: Acquisition unit
13: Classifier 14:
15: task specifying unit 16:
17: Transmission unit 18:
19: Updating unit 20: Updating unit
21: SPECIFIC PART 22: ALARM
23: Processor 24: Memory

Claims (10)

Reception means for receiving time-series data from the elevator apparatus,
A first classifier for receiving the time series data received by the receiving means and classifying the input time series data and outputting a plurality of estimated failure contents;
An acquiring means for acquiring attribute data relating to the elevator apparatus;
A second classifier for inputting the attribute data acquired by the acquisition means, for classifying the input attribute data and outputting a plurality of estimated failure contents,
Fault identification means for specifying a fault occurring in the elevator apparatus based on the estimated fault content output by the first classifier and the estimated fault details output by the second classifier,
And a task specifying means for specifying a content of a task for a specific failure content by the failure specifying means. The method according to claim 1,
Further comprising determination means for determining whether or not the operation specifying means is operable by a remote operation. The method of claim 2,
Further comprising: transmission means for transmitting, to the elevator apparatus, an instruction for causing the operation specifying means to execute a specific job content, if it is determined by the determination means that the job can be performed by remote operation. Storage means for storing a probability that each of the plurality of fail contents, the plurality of work contents, and the fail contents is selected for each of the fail contents,
Reception means for receiving time-series data from the elevator apparatus,
A first classifier for receiving the time series data received by said receiving means and classifying the inputted time series data and outputting an estimated occurrence probability for each of the failure contents stored in said storage means;
An acquiring means for acquiring attribute data relating to the elevator apparatus;
A second classifier for inputting the attribute data acquired by the acquisition means and classifying the input attribute data and outputting an estimated occurrence probability for each of the failure contents stored in the storage means;
Based on the estimated occurrence probability output by the first classifier, the estimated occurrence probability output by the second classifier, and the probability stored in the storage means, The recovery system comprising: The method of claim 4,
Further comprising determining means for determining whether or not the specifying means is operable by a remote operation. The method of claim 5,
Further comprising transmitting means for transmitting to said elevator apparatus a command for executing a specific job content by said specifying means when it is determined by said determining means that it is executable by remote operation. The method according to claim 2 or 5,
Wherein the determination means determines whether or not the work content is executable by a remote operation based on the time series data received by the receiving means. The method according to claim 2 or 5,
Wherein the determination means determines whether or not the work content is executable by a remote operation based on the time series data received by the receiving means and the attribute data acquired by the acquisition means. The method according to claim 2 or 5,
And an alarm control means for informing an alarm from the determination result of the determination means. The method according to any one of claims 1 to 9,
First updating means for performing learning based on time-series data received by said receiving means to update said first classifier,
Further comprising second updating means for performing learning based on attribute data relating to the elevator apparatus and updating the second classifier.

Images