JP6717555B1 - Troubleshooting system with notification function - Google Patents

Abstract

PROBLEM TO BE SOLVED: To promptly notify a serviceman of an event that has occurred in a work machine, and clearly indicate to the serviceman the action corresponding to this event. A troubleshooting system S includes a forklift 1, a server 2, and a terminal 3. The forklift 1 transmits output data of a sensor that detects an operating state of the forklift 1 and internal data of control software that controls the forklift 1 to the server 2. The server 2 detects an event that has occurred in the forklift 1 based on the received output data of the sensor and the internal data of the control software, and a list of lower-level events or measures corresponding to the detected event is generated in the forklift 1. At the same time, it is transmitted to the terminal 3 used by the service person P1. [Selection diagram] Figure 1

Description

The present invention relates to a troubleshooting system having a notification function for work machines.

When a trouble such as an accident or a failure occurs in the work machine, a service person related to the work machine such as a crane truck or a forklift takes some measures to solve the phenomenon of the work machine caused by the trouble. Skilled service personnel are familiar with the treatment of various events on the work machine. On the other hand, an inexperienced service person often does not know an appropriate treatment for this event, and it is difficult to easily recognize an appropriate treatment.

Therefore, for example, there is a failure diagnosis method disclosed in Patent Document 1. The failure diagnosis unit of the machine tool control device disclosed in Patent Document 1 includes a unit storage unit, a phenomenon storage unit, a failure occurrence predicted component storage unit, a treatment method storage unit, a solution storage unit, and a failure diagnosis control. And a section. An operator selects a unit in which a failure has occurred using the display unit consisting of a touch panel, selects a failure phenomenon corresponding to each unit, selects a part that may cause a failure corresponding to each phenomenon, and selects each part. Select the corrective action method to narrow down the problem solution. As a result, even an inexperienced worker can deal with the event of the machine tool.

By the way, when the operator recognizes that a trouble has occurred in the work machine, there has been a problem that a serious event has already occurred in the work machine. Further, in the case of an unmanned work machine that performs unmanned work, even if a trouble occurs, the administrator may not be nearby. In this case, since the administrator later recognizes the trouble and then contacts the service person, there is also a problem that the situation worsens over time. Therefore, when a trouble occurs in the work machine, it is preferable to immediately notify the service person or other related person of the work machine of the event.

JP, 2017-68678, A

In view of the above circumstances, the problem to be solved by the present invention is to provide a troubleshooting system capable of promptly notifying a serviceman of an event that has occurred in a work machine and clearly indicating to the serviceman the action corresponding to this event. To provide.

In order to solve the above problems, a troubleshooting system having a notification function for a working machine according to the present invention,
The working machine,
A storage unit that stores events that can occur in the work machine and actions that correspond to the events,
A display unit that displays the entered information,
An input unit for inputting an event that has occurred in the work machine or event information consisting of a part of the event,
When event information is input, a morphological analysis unit that divides the event information into words,
Using the past multiple events that occurred in the work machine described in multiple reports as learning data, the relationship between each word in the report was unsupervised using a neural network and was divided into words. When the entered event information is input, it corresponds to the meaning of the input word based on the relationship between the learned words and the relationship between the words included in the event information. A trained vector output neural network that outputs a distributed expression vector that
The event information divided for each word by the morpheme analysis unit, a word vectorization unit for converting each word into a distributed expression vector by the learned vector output neural network,
The input event information, based on the distributed expression vector for each word contained in the event information, an event vectorization unit that converts the distributed expression vector in event information units,
The event in the storage unit that has been morphologically analyzed in advance by the morpheme analysis unit, distributed expression vectorization for each word by the word vectorization unit, and distributed expression vectorization by event unit by the event vectorization unit. And a vector expression storage unit that stores the event in association with each event in the storage unit,
Based on the cosine similarity between the event information that has been distributed representation vectorized by the event vectorization unit and the distributed representation vectorized event stored in the vector representation storage unit, the input A similarity calculation unit that calculates a similarity between the event information and the event stored in the storage unit;
Before the list or treatment of lower events corresponding to the input event information is acquired from the storage unit, output to the display unit , and the similarity calculation unit calculates a degree of similarity equal to or more than a predetermined value. An output unit for outputting a list of the events to the display unit ,
An event detector,
And a notification unit,
The work machine has a data transmission unit that transmits output data of a sensor that detects an operating state of the work machine and internal data of control software that controls the work machine to the event detection unit,
The event detection unit detects an event that has occurred in the work machine based on the received output data of the sensor and internal data of the control software,
The notification unit acquires a list of lower-level events or actions corresponding to the events detected by the event detection unit from the storage unit, and a serviceman or the work together with the events generated in the work machine. It is characterized by notifying other parties of the machine or both.

The troubleshooting system is preferably
The event detection unit further detects an event with an occurrence probability of a predetermined value or more, based on the received output data of the sensor and internal data of the control software,
The notification unit further acquires from the storage unit a list of low-order events or actions corresponding to the events whose occurrence probabilities detected by the event detection unit are equal to or greater than a predetermined value, Notify the service person and/or other related parties of the work machine together with the event.

The troubleshooting system is preferably
When the correlation between the output data of the sensor, the internal data of the control software and the phenomenon occurring in the work machine is learned as teacher data, and the output data of the sensor and the internal data of the control software are input. Further comprising a learned first neural network that outputs an event that has occurred in the work machine or has a probability of occurrence of a predetermined value or more, or both.
The event detection unit uses the learned first neural network to detect an event that has occurred in the work machine or has an occurrence probability of a predetermined value or more from the output data of the sensor and the internal data of the control software, or both. To detect.

The above troubleshooting system, for example,
The notification unit further notifies the event having an occurrence probability of a predetermined value or more as important information, and notifies the event that has occurred in the work machine as emergency information.

The troubleshooting system is preferably
Further comprising a terminal and a server capable of mutually communicating with the terminal and the work machine,
The terminal includes the display unit, the input unit, and the output unit,
The server includes the storage unit, the event detection unit, and the notification unit,
The terminal is used by the service person,
The notification unit performs by transmitting the notification to the service person to the terminal,
The display unit further displays a list of events received by the terminal, and a list of lower-level events corresponding to the events, or treatment.

The troubleshooting system is preferably
The distributed expression vector corresponding to the meaning of the input word is based on the distributed expression vector of the subword extracted by dividing the input word into N-grams.

The troubleshooting system according to the present invention can promptly notify the serviceman of an event that has occurred in the work machine and clearly indicate to the serviceman the action corresponding to this event.

1 is an overall view showing a schematic configuration of an embodiment of a troubleshooting system according to the present invention. It is a block diagram of the troubleshooting system of FIG. It is a figure which shows an example of the report in which the past event was described. It is a figure which shows an example of the input screen displayed on the display part of FIG. It is a figure which shows another example of an input screen. It is an example of the treatment displayed on the display part of FIG.

An embodiment of a troubleshooting system having a notification function according to the present invention will be described below with reference to the drawings. The working machine in the present embodiment is the forklift 1, but it is merely an example and is not limited to this.

FIG. 1 is an overall view showing a schematic configuration of a troubleshooting system S according to this embodiment. In the troubleshooting system S, the operating state of the forklift 1 is transmitted from time to time to the server 2 via the network 100, and the server 2 analyzes the operating state of the forklift 1 to detect an event occurring in the forklift 1 and promptly detect the event. It is configured to notify the service person P1. Hereinafter, each configuration will be specifically described.

<Forklift>
As shown in FIG. 2, the forklift 1 includes a sensor 10, control software 11, and a data transmission unit 12.

The sensor 10 is for detecting the operation of the forklift 1, and is provided in each unit of the forklift 1. The sensor 10 may include, for example, any or all of a torque sensor, a vibration sensor, an image sensor, a distance sensor, a position sensor, a temperature sensor, a humidity sensor, a flow rate sensor, a light amount sensor, and a pressure sensor. Further, the sensor 10 may include, for example, a surrounding environment sensor that detects a surrounding environment state of the forklift 1.

The control software 11 is software for controlling the forklift 1. For example, the control software 11 controls the operations of the cylinder, the motor, the steering unit, and the like. The internal data of the control software 11 may include, for example, any or all of torque, position, velocity, acceleration, current and voltage. Further, the control software information is included in the internal data of the control software 11. The control command information is the content of the command to each unit by the control software 11, and corresponds to, for example, a normal rotation command or a stop command to the motor.

The data transmission unit 12 transmits the output data of the sensor 10 and the internal data of the control software 11 to the server 2 as needed via the network 100. The data transmission unit 12 may accumulate data for a certain period of time and transmit the accumulated data as needed. As a result, for example, the transition of the moving speed of the forklift 1 after the stop command to the motor by the control software 11 is transmitted.

<Server>
The server 2 can communicate with the terminal 3 and the forklift 1 via the network 100. The server 2 includes a storage unit 20, a learned first neural network (hereinafter, referred to as “learned first NN”) 21, an event detection unit 22, a notification unit 23, a morpheme analysis unit 24, and a word vectorization unit. 25, a learned second neural network (hereinafter, referred to as “learned second NN”) 26, an event vectorization unit 27, a similarity calculation unit 28, and a vector expression storage unit 29. The learned second NN corresponds to the “learned vector output neural network” of the present invention.

The storage unit 20 stores an event that can occur in the forklift 1 and a treatment that corresponds to this event. The event and the action are extracted from a plurality of trouble cases including the event that occurred in the forklift 1 in the past and the action performed for the event. The event and the action may be extracted from the trouble case in the report 300 (see FIG. 3) described by the service person P1. The storage unit 20 also stores the causal relationship between the events, which associates the upper event with the lower event.

When the output data of the sensor 10 and the internal data of the control software 11 are input, the learned first NN 21 outputs an event that has occurred in the forklift 1 or has an occurrence probability of a predetermined value or more, or both. The learned first NN 21 is pre-learned for its correlation by using the combination of the output data of the sensor 10, the internal data of the control software 11 and the event occurring in the forklift 1 as the teacher data, and the output data of the sensor 10 and the control software 11 When the internal data is input, an event that has occurred in the forklift 1 or has an occurrence probability of a predetermined value or more, or both, is output. The learned first NN 21 may use deep learning and may use a convolutional neural network, a recurrent neural network, or both. Further, the learned first NN 21 may be configured by a plurality of neural networks and subjected to ensemble learning.

Using the learned first NN 21, the event detection unit 22 detects an event that has occurred in the forklift 1 or has an occurrence probability of a predetermined value or more, or both, from the output data of the sensor 10 and the internal data of the control software 11. The event whose occurrence probability is equal to or higher than a predetermined value includes an event whose probability of occurrence within a predetermined time or a predetermined number of days is equal to or higher than a predetermined value, or an event whose probability of occurrence is equal to or higher than a predetermined value or both.

The notification unit 23 acquires from the storage unit 20 a list of low-level events or actions corresponding to this event together with the event detected by the event detection unit 22, and notifies the serviceman P1 and the other related person P2 of the forklift 1 to it. .. Thereby, the service person P1 and the other related persons P2 can promptly recognize the event that has occurred or is likely to occur in the forklift 1. Further, this notification includes the event detected by the event detection unit 22 as well as a list of lower-level events or measures corresponding to this event, so that even an inexperienced service person can quickly respond to the notified event. can do.

The other party P2 corresponds to, for example, a manager or an operator of the forklift 1. The notification unit 23 may notify only the event detected by the event detection unit 22 to the service person P1 and other related parties P2. In addition, the notification unit 23 sorts the notification destinations based on the event detected by the event detection unit 22 whether to notify both the service person P1 and the other related person P2 or only the service person P1. May be.

The notification method by the notification unit 23 notifies the serviceman P1 and the other related person P2 by transmitting the notification to the terminal 3 used by the service person P1 and the computer used by the other related person P2. The notification method by the notification unit 23 may be e-mail, for example, and is not particularly limited. The notification unit 23 notifies the event detected by the event detection unit 22 as emergency information if the event has occurred in the forklift 1, and notifies as important information if the probability of occurrence in the forklift 1 is greater than or equal to a predetermined value. Good.

When the event information is input by the input unit 31 (see the terminal 3 in FIG. 2), the morphological analysis unit 24 divides the input event information into words. The event information is a word group or words that expresses an event that occurs in the forklift 1 as a sentence such as "the engine does not start" or a keyword such as "engine" or "does not start". The event information is divided by the morphological analysis unit 24 with a space for each word, and is divided into words. For example, the event information that "the engine does not start" is divided into "engine", "ga", "starting", and "not". As a tool for morphological analysis, for example, "Mecab" may be used. In addition, a corpus for the forklift 1 created in advance may be used as a morphological analysis tool. This is preferable because each noun in the event information is appropriately extracted.

The word vectorization unit 25 converts the event information divided by the morpheme analysis unit 24 for each word into a distributed expression vector for each word by the learned second NN 26.

When a word is input, the learned second NN 26 outputs a distributed expression vector corresponding to the meaning of the input word. The learned second NN 26 is unsupervised in advance by using a neural network with the events described in the plurality of past reports 300 divided for each word as learning data, and the events divided for each word. When information is input, a distributed expression vector corresponding to the meaning of each word is output based on the relationship between the words included in the event information.

In the learned second NN 26, a highly relevant word such as a word that is likely to appear in the same event (co-occurrence) or a word that is likely to appear in a close position in the same event is input. Has been pre-learned so that similar distributed expression vectors are output. This is based on the distribution hypothesis that words that appear in similar contexts are also semantically similar (Harrs, 1954, Rubenstein & Goodenough, 1965). As the word vectorization unit 25, for example, a language model such as “Word2Vec”, “Glove”, “Fasttext” based on neural network technology may be used. For the distributed expression and Word2Vec, "MIKOLOV, Tomas, et al. Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems. 2013. p. 3111-3119." can be referred to. Regarding Grove, "PENNINGTON, Jeffrey; SOCHER, Richard; MANNING, Christopher D. Glove: Global Vectors for Word Representation. In: EMNLP. 2014. p. 1532-1543." and the like can be referred to. For Fasttext, "JOULIN, Armand, et al. Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759, 2016." and the like can be referred to.

As a method of outputting the distributed expression vector of each word, the learned second NN 26 preferably creates the distributed expression vector in consideration of the subwords included in each word. Specifically, the word vectorization unit 25 divides the input word into N-grams to extract subwords, and determines the distributed expression vector corresponding to the meaning of the input word as the sum of the distributed expression vectors of the subwords or It is preferable to average it. For example, in the case of the word "intake hose", the subwords correspond to "intake", "intake", "ki ho", "ho", "su", and "su". As a result, the learned second NN 26 outputs a similar distributed expression vector to, for example, the “intake hose”, the “intake hose”, and the “hose”. Can also be accommodated. As a tool for creating a distributed expression vector in consideration of subwords, for example, "Fasttext" may be used.

As shown in FIG. 3, in the report 300, the event that occurred in the forklift 1 is described in the fault content column by each person in charge (service person P1). Therefore, in the report 300, each event is described in various expressions together with the personality of the person. The learned second NN 26 can appropriately convert each word included in event information of various expressions into a distributed expression vector by using the description of these events as learning data.

The event vectorization unit 27 uses the word vectorization unit 25 for each word so that the similarity calculation unit 28 can calculate the similarity between the input event information and the event stored in the storage unit 20. The distributed representation vectorized event information is converted into a distributed representation vector of event information units based on the distributed representation vector for each word. The event vectorization unit 27 may use the average of the distributed expression vectors of the words included in the event information as the feature vector of the event information itself, as a method of converting the event information into the distributed expression vector. Alternatively, the event vectorization unit 27 may use a feature vector average using SCDV (Sparse Composite Document Vectors) as a method of converting event information into a distributed representation vector with higher accuracy. Regarding SCDV, “Dheeraj Mekala et al.: SCDV: Sparse Composite Document Vectors using soft clustering over distributional representations, Proc of EMNLP, 2017” can be referred to.

The similarity calculation unit 28 calculates the similarity between the input event information and the event stored in the storage unit 20. The events in the storage unit 20 are morphologically analyzed in advance by the morpheme analysis unit 24, decentralized expression vectorized for each word by the word vectorization unit 25, and decentralized expression vectorization by event unit by the event vectorization unit 27. There is.

The vector expression storage unit 29 stores the events in the storage unit 20, which are distributed representation vectorized by the event vectorization unit 27, in association with each event in the storage unit 20.

The similarity calculation unit 28 receives the input event information based on the cosine similarity between the distributed representation vectorized event information and the distributed representation vectorized event stored in the vector representation storage unit 29. The degree of similarity with the event in the storage unit 20 is calculated. The cosine similarity is a similarity calculation method used when comparing documents in a vector space model. Since the cosine similarity expresses the closeness of the angle formed by the vectors, the input event information and the event in the storage unit 20 are more similar if the cosine similarity is close to 1, and are close to 0. It would be less similar.

<Terminal>
The terminal 3 includes a display unit 30, an input unit 31, and an output unit 32. Although the terminal 3 is a tablet in the present embodiment, it is merely an example, and may be, for example, a laptop computer or a smartphone.

The display unit 30 displays the input information. The display unit 30 corresponds to the display of a tablet. Further, the display unit 30 displays a list of the events received from the notification unit 23 and a subordinate event corresponding to this event, or a treatment.

The input unit 31 is a tool for inputting event information and the like. In the case of a tablet, the display is a touch panel and serves as both the display unit 30 and the input unit 31. The input unit 31 may be, for example, a mouse or a keyboard. Basic information and event information including any or all of service person information, date and time information, place information, and customer information regarding the service person P1 are input by the input unit 31. Further, an event (event information) is selected and input by the input unit 31 from the event list displayed on the display unit 30 by the output unit 32. Further, from the event list transmitted from the server 2 and displayed on the display unit 30, an event (event information) is selectively input by the input unit 31.

The output unit 32 acquires a list of lower-level events or actions corresponding to the input event information from the storage unit 20 and outputs the acquired list to the display unit 30. The output unit 32 also outputs to the display unit 30 a list of events for which the similarity calculation unit 28 has calculated the similarity of a predetermined value or more. Further, when an event is selected and input from the list of events, the output unit 32 acquires a list of events or a treatment corresponding to the input event from the storage unit 20 and outputs the acquired list or treatment to the display unit 30.

Next, the troubleshooting by the terminal 3 will be specifically described with reference to the drawings.

Basic information and the like are input to the terminal 3 by the input unit 31 from the service person P1.

As shown in FIG. 4, when a screen 400 for inputting the forklift 1 information and the event information is displayed on the display unit 30, the service person P1 displays the brand, type, model, and the like of the forklift 1 in the image areas 400a to 400d. The model, the part where the event occurred, and the error code of the event are directly or selectively input.

Next, as shown in FIG. 5, when the screen 500 for selecting the top event is displayed on the display unit 30 and the event information 500a and 500b are displayed, one of the event information is selected by the service person P1. Is entered. At this time, the event information corresponding to the event that occurred in the forklift 1 may not be included in the displayed event information. In this case, the service person P1 inputs the event information into the keyword input area 400e shown in FIG.

The similarity calculation unit 28 calculates the similarity between the input event information and the event stored in the storage unit 20, and transmits the event for which the similarity of a predetermined value or more is calculated to the terminal 3. The output unit 32 outputs and displays the received list of events on the display unit 30. Next, when the service person P1 newly selects and inputs the event corresponding to the event that has occurred in the forklift 1 from the displayed event list, the output unit 32 newly stores the list of events corresponding to the input event. And output to the display unit 30.

As shown in FIG. 6, when the serviceman P1 selects and inputs the lowest event, the output unit 32 outputs the treatment 600a corresponding to this event to the display unit 30 for display. Even an inexperienced service person P1 can identify the treatment corresponding to the event occurring in the forklift 1 by referring to this treatment.

<A series of operations of the troubleshooting system>
Heretofore, each configuration of the troubleshooting system S according to the present embodiment has been described. A series of operations of the forklift 1, the server 2, and the terminal 3 in the troubleshooting system S are summarized as follows.

(1) The data transmission unit 12 of the forklift 1 transmits its operating state to the server 2 as needed.

(2) When the event detection unit 22 detects an event that has occurred in the forklift 1 or an event with an occurrence probability of a predetermined value or more, the server 2 notifies the serviceman P1 and other related parties P2 by the notification unit 23.

(3) When the terminal 3 receives the event that has occurred in the forklift 1 from the server 2, the terminal 3 displays the received event on the display unit 30 and the treatment corresponding to this event on the display unit 30. As a result, even an inexperienced service person P1 can immediately deal with a forklift event.

(4) Further, when the terminal 3 receives from the server 2 an event having a probability of occurring in the forklift 1 that is equal to or greater than a predetermined value, the terminal 3 displays the received event on the display unit 30 and displays the action corresponding to this event on the display unit 30. indicate. As a result, the serviceman P1 can prevent the trouble of the forklift 1 from occurring by taking measures before the event occurs.

(5) Further, when the terminal 3 receives the event list together with the detected event, the terminal 3 displays the detected event and a subordinate event list of the event on the display unit 30.

(6) Next, in the terminal 3, the serviceman P1 identifies which event in the lower event list is occurring in the forklift 1, and inputs the identified event (event information). ..

(7) Next, the terminal 3 acquires the treatment corresponding to the event specified by the service person P1 from the storage unit 20 of the server 2 and displays it on the display unit 30. Thereby, the service person P1 can perform the displayed treatment on the forklift 1.

Although one embodiment of the troubleshooting system S according to the present invention has been described above, the present invention is not limited to the above embodiment.

(1) In the troubleshooting system S, the terminal 3 may have the configuration of the server 2. In this case, the transmission unit transmits the output data of the sensor 10 and the internal data of the control software 11 to the terminal 3.

(2) The storage unit 20 may further store technical data corresponding to the treatment. In this case, the output unit 32 may output the technical data corresponding to the treatment to the display unit 30 and display the technical data corresponding to the treatment on the display unit 30. As a result, even an inexperienced service person P1 can be appropriately treated.

(3) The event detection unit 22 may use another learned model as long as it can detect an event that has occurred in the forklift 1 using the data received from the data transmission unit.

(4) The event detector 22 may be provided in the forklift 1. In this case, the data transmission unit 12 transmits the output data of the sensor 10 and the internal data of the control software 11 to the event detection unit 22. In addition, the event detected by the event detection unit 22 is transmitted to the server 2 via the network 100, and the notification unit 23 displays a list or treatment of this event and lower events corresponding to this event as a serviceman P1 or forklift 1. Other interested parties P2 or both are notified.

1 Forklift 10 Sensor 11 Control Software 12 Data Transmission Unit 2 Server 20 Storage Unit 21 Learned First Neural Network 22 Event Detection Unit 23 Notification Unit 24 Morphological Analysis Unit 25 Word Vectorization Unit 26 Learned Second Neural Network 27 Event Vectorization Unit 28 similarity calculation unit 29 vector expression storage unit 3 terminal 30 display unit 31 input unit 32 output unit

Claims (6)

A troubleshooting system with a notification function for work machines,
The working machine,
A storage unit that stores events that can occur in the work machine and actions that correspond to the events,
A display unit that displays the entered information,
An input unit for inputting an event that has occurred in the work machine or event information consisting of a part of the event,
When event information is input, a morphological analysis unit that divides the event information into words,
Using the past multiple events that occurred in the work machine described in multiple reports as learning data, the relationship between each word in the report was unsupervised using a neural network and was divided into words. When the entered event information is input, it corresponds to the meaning of the input word based on the relationship between the learned words and the relationship between the words included in the event information. A trained vector output neural network that outputs a distributed expression vector that
The event information divided for each word by the morpheme analysis unit, a word vectorization unit for converting each word into a distributed expression vector by the learned vector output neural network,
The input event information, based on the distributed expression vector for each word contained in the event information, an event vectorization unit that converts the distributed expression vector in event information units,
The event in the storage unit that has been morphologically analyzed in advance by the morpheme analysis unit, distributed expression vectorization for each word by the word vectorization unit, and distributed expression vectorization by event unit by the event vectorization unit. And a vector expression storage unit that stores the event in association with each event in the storage unit,
Based on the cosine similarity between the event information that has been distributed representation vectorized by the event vectorization unit and the distributed representation vectorized event stored in the vector representation storage unit, the input A similarity calculation unit that calculates a similarity between the event information and the event stored in the storage unit;
Before the list or treatment of lower events corresponding to the input event information is acquired from the storage unit, output to the display unit , and the similarity calculation unit calculates a degree of similarity equal to or more than a predetermined value. An output unit for outputting a list of the events to the display unit ,
An event detector,
And a notification unit,
The work machine has a data transmission unit that transmits output data of a sensor that detects an operating state of the work machine and internal data of control software that controls the work machine to the event detection unit,
The event detection unit detects an event that has occurred in the work machine based on the received output data of the sensor and internal data of the control software,
The notification unit acquires a list of lower-level events or actions corresponding to the events detected by the event detection unit from the storage unit, and a serviceman or the work together with the events generated in the work machine. A troubleshooting system characterized by notifying other parties on the machine or both. The event detection unit further detects an event with a probability of occurrence of a predetermined value or more, based on the received output data of the sensor and internal data of the control software,
The notification unit further obtains a list of lower-level events or actions corresponding to the events with the occurrence probability detected by the event detection unit being a predetermined value or more from the storage unit, and the occurrence probability before the occurrence probability is a predetermined value or more. The troubleshooting system according to claim 1, wherein the service person or another person concerned with the work machine or both are notified together with the event. When the correlation between the output data of the sensor, the internal data of the control software and the phenomenon occurring in the work machine is learned as teacher data, and the output data of the sensor and the internal data of the control software are input. Further comprising a learned first neural network that outputs an event that has occurred in the work machine or has a probability of occurrence of a predetermined value or more, or both.
The event detection unit uses the learned first neural network to detect an event that has occurred in the work machine or has an occurrence probability of a predetermined value or more from the output data of the sensor and the internal data of the control software, or both. The troubleshooting system according to claim 2, wherein the troubleshooting system detects. 4. The notification unit according to claim 2, wherein the notification unit further notifies the event that the occurrence probability is a predetermined value or more as important information, and notifies the event that occurred in the work machine as emergency information. Troubleshooting system. Further comprising a terminal and a server capable of mutually communicating with the terminal and the work machine,
The terminal includes the display unit, the input unit, and the output unit,
The server includes the storage unit, the event detection unit, and the notification unit,
The terminal is used by the service person,
The notification unit performs by transmitting the notification to the service person to the terminal,
The troubleshooting system according to any one of claims 1 to 4, wherein the display unit further displays a list of events received by the terminal and a subordinate event corresponding to the event or a treatment. .. The distributed expression vector corresponding to the meaning of the input word is based on the distributed expression vector of the subword extracted by dividing the input word into N-grams.
The troubleshooting system according to any one of claims 1 to 5, wherein:

Images