JP7404046B2 - Repair support system - Google Patents

Description

The present invention relates to a repair support system and program.

In recent years, techniques for supporting equipment repair have been proposed.
For example, the technology described in Patent Document 1 is configured as follows. In other words, we confirm customer requests using customer information obtained from a customer information database and repair information obtained from a repair information database, etc. To provide a failure diagnosis and repair request site that performs failure diagnosis processing for target equipment using the obtained information regarding failure diagnosis, and also performs processing for accepting repairs from customers using fee information obtained from a fee information database.

Japanese Patent Application Publication No. 2002-358383

Generally, when a repair company goes to a location where a device to be repaired is located, it is desirable to estimate the location of the failure. This is because repairs can be completed in one visit by bringing the necessary tools for repairs and parts to replace broken parts. Therefore, it is desirable to be able to estimate the failure location with high accuracy.
SUMMARY OF THE INVENTION An object of the present invention is to provide a repair support system and the like that can estimate a failed part with high accuracy.

The present invention, which was completed based on these objectives, provides first information regarding the product name and symptoms of gas appliances, second information regarding weather information, and information about failure locations in the gas appliance, including heat generating parts, remote controls, and ignition parts. a storage unit that stores repair information in which repair information is linked; a reception unit that receives information on a failure request; and the first information and second information regarding the gas appliance for which the failure request was received by the reception unit. , and the repair information stored in the storage unit, an estimation unit that estimates the failure part of the gas appliance based on the repair information stored in the storage unit, and a prediction unit that predicts the failure part from the failure part estimated by the estimation unit. and a derivation unit that derives the cost required for repairing the failed part predicted by the prediction unit, and the storage unit associates with the failed part predicted by the prediction unit, and stores information about the product including the failed part. The derivation unit further includes a secondary prediction unit that stores the manufacturer name, model name, and repair date of the failed part, and predicts a secondary failed part that will fail next to the failed part, and the derivation unit The secondary prediction unit derives the total cost required for repairing the failed part and the secondary failure part, and the secondary prediction unit calculates the total cost required for repairing the failed part and the secondary failure part, and the secondary prediction unit calculates the total cost for repair of the failed part predicted by the prediction unit. Then, when a repair request is received again after the faulty part has been repaired, the number of repair requests is counted for each faulty part targeted for repair, and the parts with a large number of counts are predicted as secondary faulty parts. , a repair support system.
Moreover, you may have a display control part which displays on a display part the said total cost derived by the said derivation part, and the cost when the said gas appliance is replaced.
Further, the device may include a prediction estimating unit that predicts the day on which the secondary failure component is expected to fail in consideration of the family structure.
In addition, the present invention, which was completed based on this purpose, includes first information regarding the product name and symptoms of gas appliances, and second information at least from among the manufacturer name, region, weather information, and failure diagnosis sheet information. and a learned model obtained by machine learning using the first information and the failed parts of the gas appliance, including the heat generating part, the remote control, and the ignition part, which are stored in association with the first information and the second information. a storage unit that stores information on a failure request, a reception unit that receives information on a failure request, the first information and second information regarding the gas appliance for which the failure request has been received by the reception unit, and the learned model. an inference unit that infers the failure part of the gas appliance; a prediction unit that predicts a failure part from the failure part inferred by the inference unit; and a prediction unit that estimates the cost required for repairing the failure part predicted by the prediction unit. and a derivation unit for deriving the faulty part, and the storage unit stores, in association with the faulty part predicted by the prediction unit, the manufacturer name and model name of the product having the faulty part, and the repair date on which the faulty part was repaired. further comprising a secondary prediction unit that stores and predicts a secondary failure part that will fail next to the failure part, and the derivation unit derives a total cost required for repairing the failure part and the secondary failure part, When the secondary prediction unit receives a repair request again after repairing the failed part from a list of repairs for which the manufacturer name and model name of the product having the failed part predicted by the prediction unit are the same. The system counts the number of repair requests for each faulty part that is subject to repair, and predicts the parts with a large number of counts as secondary faulty parts .
Moreover, you may have a display control part which displays on a display part the said total cost derived by the said derivation part, and the cost when the said gas appliance is replaced.
Furthermore, the device may include a prediction unit that predicts the day when the secondary failure component will fail in consideration of the family structure.
In addition, the present invention, which was completed with such an objective, stores repair information that links first information regarding the product name and symptoms of gas appliances, second information regarding weather information, and the malfunctioning part of the gas appliance. a storage unit that receives information on a failure request, a reception unit that receives information on a failure request, the first information and the second information regarding the gas appliance for which the failure request was received by the reception unit, and the information stored in the storage unit. an estimation unit that estimates a failure part of the gas appliance based on the repair information; a prediction unit that predicts a failed part from the failure part estimated by the estimation unit; and the failure predicted by the prediction unit. The storage unit includes a derivation unit that derives the cost required for repairing a component, and a secondary prediction unit that predicts a secondary failure component that will fail next to the failure component, and the storage unit stores information about the failure component predicted by the prediction unit. , the manufacturer name and model name of the product having the faulty part, and the date of repair of the faulty part are stored in association with After deriving the cost, the secondary prediction unit repairs the failed part from a list of repairs that have the same manufacturer name and model name of the product that has the failed part predicted by the prediction unit, and then requests the repair again. This repair support system is characterized by counting the number of repair requests for each faulty part targeted for repair when receiving a request for repair, and predicting a part with a large number of counts as a secondary faulty part.
Here, it may include a display control section that causes a display section to display the total cost derived by the derivation section and the cost when replacing the gas appliance.
Furthermore, the device may include a prediction unit that predicts the day when the secondary failure component will fail in consideration of the family structure.
In addition, the present invention, which was completed based on this purpose, includes first information regarding the product name and symptoms of gas appliances, and second information at least from among the manufacturer name, region, weather information, and failure diagnosis sheet information. a storage unit that stores a learned model obtained by machine learning using the first information and the second information and the failure part of the gas appliance stored in association with the failure part; and information on the failure request. a reception unit that receives the request, and an inference unit that infers a failure part of the gas appliance based on the first information and second information regarding the gas appliance for which the failure request has been received by the reception unit, and the learned model. a prediction unit that predicts a failed part from the failure part inferred by the inference unit; a derivation unit that derives the cost required to repair the failed part predicted by the prediction unit; a secondary prediction unit that predicts a secondary failure part that is predicted by the prediction unit, and the storage unit stores, in association with the failure part predicted by the prediction unit, the manufacturer name and model name of the product having the failure part, and The repair date when the failed part was repaired is stored, the derivation unit derives the total cost required for repairing the failed part and the secondary failed part, and the secondary prediction unit calculates the total cost of repairing the failed part predicted by the prediction unit. The number of repair requests for each failed part targeted for repair when a repair request is received again after the failed part has been repaired from a list of repairs for which the manufacturer name and model name of the product with the same name are the same. This repair support system is characterized by counting components and predicting components with a large number of counts as secondary failed components.
Here, it may include a display control section that causes a display section to display the total cost derived by the derivation section and the cost when replacing the gas appliance.
Furthermore, the device may include a prediction unit that predicts the day when the secondary failure component will fail in consideration of the family structure.

According to the present invention, it is possible to provide a repair support system and the like that can estimate a failed part with high accuracy.

FIG. 1 is a diagram illustrating an example of a schematic configuration of a repair support system according to a first embodiment. FIG. 1 is a diagram illustrating an example of a schematic configuration of an information processing device. FIG. 1 is a diagram illustrating an example of a schematic configuration of a server device according to a first embodiment. It is a figure which shows an example of the repair information which a memory|storage part stores. FIG. 3 is a diagram illustrating an example of a schematic configuration of a server device according to a second embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings.
<First embodiment>
FIG. 1 is a diagram showing an example of a schematic configuration of a repair support system 1 according to the first embodiment.
The repair support system 1 includes an information processing device 10 owned by a maintenance company M that receives repair requests from customers, and a server that estimates the failure part of a device to be repaired in response to a request from the information processing device 10. A device 20 is provided. There are a plurality of maintenance companies M, and each maintenance company M is assigned a region R that it is in charge of, and receives requests from customers residing in the region R that it is responsible for to repair malfunctions in equipment owned by the customers. In this embodiment, the device can be exemplified as a gas device that is used by burning gas as fuel.

The information processing device 10 and the server device 20 are able to communicate with each other via the network 5. The network 5 is not particularly limited as long as it is a communication network used for data communication between devices, and examples include the Internet, WAN (Wide Area Network), and LAN (Local Area Network). The communication line used for data communication may be wired or wireless, and both may be used in combination.

(Information processing device 10)
FIG. 2 is a diagram showing an example of a schematic configuration of the information processing device 10.
The information processing device 10 includes a control unit 11 that controls the entire device, a storage unit 12 that is used to store data, etc., a display unit 13 that is used to display an operation reception screen and images, and receives input operations from the user. It includes an operation section 14 and a communication section 15 used for communication with an external device. These control section 11 , storage section 12 , display section 13 , operation section 14 , and communication section 15 are connected via a bus 16 .

The control unit 11 includes a CPU (Central Processing Unit) (not shown), a ROM (Read Only Memory) (not shown), and a RAM (Random Access Memory) (not shown). The ROM stores a basic program (operation system) executed by the CPU, various settings, and the like. The CPU uses the RAM as a work area and executes application programs read from the ROM or storage unit 12. Each part of the information processing device 10 is controlled by the CPU executing the program.

The storage unit 12 can be exemplified by a storage device such as a semiconductor memory or an HDD (Hard Disk Drive).
The display unit 13 can be exemplified by a liquid crystal display or an organic EL display.
The operation unit 14 can be exemplified by a button, a switch, or a touch panel.
The communication unit 15 can be exemplified as a communication interface (communication I/F).
The information processing device 10 configured as described above can be used as a notebook PC, a desktop PC, a tablet PC, a tablet terminal, a personal digital assistant (PDA), a multifunctional mobile phone (so-called "smartphone"), a mobile phone (so-called "feature phone"), and a mobile phone (so-called "feature phone"). ”), etc.

The control unit 11 controls a receiving unit 111 that receives information transmitted from an external device such as the server device 20, a transmitting unit 112 that transmits information to the external device such as the server device 20, and a display unit 13. A display control unit 113 is provided.

The receiving unit 111 receives a repair request from a customer via the network 5. For example, the receiving unit 111 may receive a repair request from a customer by email or by posting on a website provided by the maintenance company M. When receiving a repair request, the receiving unit 111 receives information such as the name of the product to be repaired and symptoms, and also receives other information posted by the customer in an email or on a website. Note that the repair requests received by the receiving unit 111 include those received by an employee of the maintenance company M over the telephone from a customer and input via the operation unit 14.
The receiving unit 111 also receives information about the failed part and predicted failed parts from the server device 20 .

When the receiving unit 111 receives a repair request, the transmitting unit 112 transmits a request to the server device 20 to estimate a failed part of the product to be repaired. At that time, the transmitter 112 transmits information provided by the customer, such as the product name and symptom information received by the receiver 111 to be repaired, to the server device 20 .
The display control unit 113 causes the display unit 13 to display the information received by the receiving unit 111.

The control unit 11 also includes a derivation unit 114 that derives information such as the cost to be charged to the customer and the period until the repair is completed regarding the repair request received by the reception unit 111. This derivation unit 114 will be explained in detail later.

(Configuration of server device 20)
FIG. 3 is a diagram showing an example of a schematic configuration of the server device 20. As shown in FIG.
The server device 20 includes a control section 21 that controls the entire device, a storage section 22 that is used to store data, etc., a display section 23 that is used to display an operation reception screen and images, and an operation section that receives user input operations. section 24, and a communication section 25 used for communication with an external device. These control section 21 , storage section 22 , display section 23 , operation section 24 , and communication section 25 are connected via a bus 26 .

The control unit 21 includes a CPU (not shown), a ROM (not shown), a RAM (not shown), and the like.
The storage unit 22 can be exemplified by a storage device such as a semiconductor memory or an HDD.
The display unit 23 is a display device that displays still images, moving images, and the like. Examples include a liquid crystal display and an organic EL display.
The operation unit 24 is an input device that accepts operations from the user. Examples include buttons, switches, and touch panels.
The communication unit 25 can be exemplified as a communication interface (communication I/F).

The ROM of the control unit 21 stores a basic program (operation system) executed by the CPU, various settings, and the like. The CPU uses the RAM as a work area and executes application programs read from the ROM or the storage unit 22. When the CPU executes the program, the functions of the control unit 21 described below are realized.

The control unit 21 includes a receiving unit 211 that receives information transmitted from an external device such as the information processing device 10, and a transmitting unit 212 that transmits information to the external device such as the information processing device 10. . The control unit 21 also includes an estimation unit 214 that estimates a failure part using weather information, a prediction unit 215 that predicts a failed part that would have failed from the failure part estimated by the estimation unit 214; It has a secondary prediction unit 216 that predicts a component that will fail next to the failed component predicted by (hereinafter, a component that will fail next may be referred to as a "secondary failed component").

The receiving unit 211 receives information transmitted from the information processing device 10. For example, the receiving unit 211 receives information on a repair request received by the maintenance company M, information on how the maintenance company M handled the repair, and the like. The receiving unit 211 then stores the received repair information regarding the repair in the storage unit 22 .
Further, the receiving unit 211 receives a request from the maintenance company M for estimating the failure part, which is transmitted from the information processing device 10 .

FIG. 4 is a diagram illustrating an example of repair information stored in the storage unit 22.
The storage unit 22 stores information sent from the information processing device 10 regarding the repair of gas appliances performed by the maintenance company M.
As shown in Figure 4, the repair information includes the reception number for which the repair was received, reception date, repair completion date, product name, symptoms, manufacturer name, model name, customer number, number of family members, maintenance company M number, and elapsed years. , information on the failure diagnosis sheet, failure location, failure part, details of countermeasures, cause of failure, repair cost, etc. are stored in association with each other.

Here, the customer number is a number given to each customer, and the customer's address, telephone number, family composition, etc. may be stored in association with the number.
The number of the maintenance company M is a number given to each maintenance company M, and the region R that the maintenance company M is in charge of is stored in association with the number.
The number of years that have passed is the number of years that have passed since the user started using the product. Note that the number of years that have passed since the date the product was manufactured may also be stored.
The information on the failure diagnosis sheet can be exemplified as the information on the number displayed on the remote control. Alternatively, it may be the details of the failure, such as combustion fan abnormality or malfunction, which are written on the failure diagnosis sheet. These can be exemplified as records of information conveyed from a customer over the phone, for example.

The failure part is a part that has actually failed, and can be exemplified by, for example, a heat-generating part inside the main body of the water heater, a remote control, and an ignition part.
The term "failure component" refers to a component that has failed, and includes, for example, a fan motor, an electrical board, and a heat exchanger.
The details of the response are the details of the process performed in response to the failure, such as replacing the failed part with a new one, replacing the failed product with a new one, or changing the location of the part without replacing the part. Examples include reinstallation in the correct position and repair of a part without replacing it.

The cause of failure stores a possible cause of the failure. For example, if the failure was caused by lightning, it is stored as lightning, if the failure was caused by typhoon, it is stored as typhoon, if it simply deteriorated, it is stored as aged deterioration, and if it was installed incorrectly, it is stored as poor installation. These can be exemplified as causes that were known to the person who performed the repair when the repair was actually performed.

In addition, the storage unit 22 stores, for each product, the manufacturer's name, model name, unit price, name of the part that the product with that model name has, manufacturer name, model name, unit price of the part, whether it is in stock, and if it is out of stock. The number of days required from ordering to delivery is memorized.

Here, the reason why the storage unit 22 stores repair information including weather information and the estimating unit 214 makes an estimation taking the weather information into consideration is as follows. For example, when a unique natural phenomenon such as a storm, heavy rain, heavy snow, flood, earthquake, tsunami, eruption, or lightning occurs, the probability that gas appliances will break down increases. In particular, water heaters located outdoors are susceptible to unique natural phenomena. For example, when a typhoon causes strong winds and heavy rain, rainwater may enter the water heater from the exhaust port. Also, if lightning strikes, there is a possibility that the electrical board will malfunction.
In view of this matter, the server device 20 estimates the failure location by also considering weather information. The estimation unit 214 makes an estimation using the weather information included in the failure request received by the reception unit 211. Note that since the information provided by the customer when requesting repair may not include weather information, the server device 20 may acquire the weather information itself. For example, the receiving unit 211 periodically acquires weather information, for example via the network 5, and stores the acquired weather information in the storage unit 22. The storage unit 22 stores weather information for the past month, for example. Then, the estimating unit 214 acquires the weather information of the area where the product to be repaired is located before the date of receipt of the repair request from the weather information stored in the storage unit 22, and also uses the acquired weather information. It is recommended to use this method to estimate the failure location.

For example, the estimating unit 214 includes the product name (e.g., water heater, gas stove) and symptoms (e.g., no hot water) of the gas appliance for which the failure request was received by the receiving unit 211, weather information, and the storage unit 22. The location of the failure in the gas appliance is estimated based on the repair information stored in the . The estimating unit 214 counts the number of failed parts stored in the repair information in the storage unit 22 in association with, for example, a product name, a symptom, and specific weather information (for example, lightning), and also counts the number of failed parts that are stored in the repair information in the storage unit 22. An example of this is estimating the failure part as the current failure part.
Note that the estimation unit 214 counts the number of each failure part stored in the storage unit 22 in association with the failure parts stored in the storage unit 22 in association with the product name, symptoms, and weather information. A plurality of high-ranking (for example, five) faulty parts with a large number of counts may be estimated as the current faulty part.

The prediction unit 215 predicts a failed part that is likely to have failed based on the failure location estimated by the estimation unit 214 based on the repair information stored in the storage unit 22 . The storage unit 22 stores failed parts in association with failed parts. For example, the prediction unit 215 counts the number of each failed component stored in the storage unit 22 in association with the failed part estimated by the estimation unit 214, and selects the failed component with the highest count as the current failed component. Prediction can be exemplified.

The prediction unit 215 may predict failed parts by considering the number of years that have passed. For example, if a customer provides information on the age of the target product when requesting repair, the prediction unit 215 stores the information in the storage unit 22 in association with the failure part estimated by the estimation unit 214. The number of failed parts whose age is greater than or equal to the age of the provided target product may be counted. Thereby, prediction accuracy can be improved.
Note that the prediction unit 215 counts the number of each failed component stored in the storage unit 22 in association with the failed part estimated by the estimation unit 214, and selects the top multiple (for example, five) failed components with the highest number of counts. may be predicted as the currently failed part.

The secondary prediction unit 216 predicts secondary failure parts based on the failure parts predicted by the prediction unit 215 and the information stored in the storage unit 22. The storage unit 22 stores, in association with a failed part predicted by the prediction unit 215, the manufacturer name and model name of the product having the failed part, and the repair date on which the failed part was repaired. Therefore, the secondary prediction unit 216 can predict secondary failure parts as follows. The secondary prediction unit 216 first extracts a list of repairs in which the manufacturer name and model name of the product having the failed part predicted by the prediction unit 215 are the same. After that, the secondary prediction unit 216 counts the number of repair requests for each failed part that is the target of repair when a repair request is received again after the failed part has been repaired from the extracted list. At the same time, the failed component with the largest number of counts is predicted as the secondary failed component. Note that the secondary prediction unit 216 counts the number of each failed part that is the target of repair when a repair request is received after repairing the failed part, and also counts the number of each failed part that is the target of repair (for example, 5). ) may be predicted as a secondary failed component.

Further, the secondary prediction unit 216 predicts the day when the secondary failure component is expected to fail. The storage unit 22 stores the number of days that have elapsed from the reception date when the failure of the failed component predicted by the prediction unit 215 was received to the reception date when the failure of the secondary failure component was received. Therefore, for example, the secondary prediction unit 216 predicts the day when the average value of the elapsed days is added to the reception date when the current failure is received as the day when the secondary failure component is expected to fail. Can be done.

Further, the secondary prediction unit 216 may consider the customer's family structure when predicting the day when the secondary failure component is expected to fail. For example, if the storage unit 22 stores the number of family members of the customer used to calculate the average number of days elapsed, the average number of family members is calculated. Then, the secondary prediction unit 216 divides the current customer's family size by this average family size to calculate the coefficient α (=current customer's family size/average family size) for the average number of elapsed days. The value obtained by multiplying the value is added to the reception date of the current failure, and the date is predicted as the expected failure date of the secondary failure component. In other words, the secondary prediction unit 216 can use the following equation (1) to predict the expected failure date.
Expected failure date = reception date + average value of elapsed days / α... (1)

As described above, the prediction unit 215 predicts a failed component, and the secondary prediction unit 216 predicts a secondary failure component or a day when the secondary failure component is expected to fail. The transmitting unit 212 then transmits the information predicted by the predicting unit 215 and the secondary predicting unit 216 to the information processing device 10.

(Derivation unit 114 of control unit 11 of information processing device 10)
Next, the derivation unit 114 of the control unit 11 of the information processing device 10 will be explained.
The derivation unit 114 derives the repair cost required to repair the failed component predicted by the prediction unit 215. The deriving unit 114 considers the unit price of a new part that is to be installed after removing the failed part that has been received by the receiving unit 111 and predicted by the predicting unit 215, the work cost required to install the new part, etc. Determine repair costs. For example, the derivation unit 114 derives the repair cost by substituting the unit price of a new part and the work cost into a predetermined formula. Note that the unit price of the new part may be acquired from the server device 20 via the network 5, or may be stored in the storage unit 12 in advance and acquired from the storage unit 12. In addition, it can be exemplified that the work cost is determined for each new part.

Further, the derivation unit 114 derives the period predicted by the prediction unit 215 until the repair of the failed component is completed. For example, the deriving unit 114 sets a predetermined number of days to the number of days from the date when the receiving unit 111 receives the information on the failed part predicted by the predicting unit 215 to the date when the maintenance company M that performs the repair acquires the new part. For example, the number of days obtained by adding up the number of days can be derived as the period. Note that the number of days until the new component is to be acquired may be acquired from the server device 20 via the network 5, or may be stored in the storage unit 12 in advance and acquired from the storage unit 12. In addition, the predetermined number of days is the number of days required from the day maintenance company M acquires new parts to the time of repair, and if maintenance company M performs repairs on the day following the day on which new parts are acquired, It takes 1 day.

Further, the derivation unit 114 derives the secondary repair cost required to repair the secondary failed component predicted by the secondary prediction unit 216. The derivation unit 114 calculates the unit price of the secondary new part that is to be newly installed after removing the secondary failed part predicted by the secondary prediction unit 216, which is received by the receiving unit 111, and the unit price required to install the secondary new part. Determine secondary repair costs by considering secondary work costs, etc. For example, the deriving unit 114 derives the secondary repair cost by substituting the unit price of the secondary new part and the secondary work cost into a predetermined formula. Note that the unit price of the secondary new part may be acquired from the server device 20 via the network 5, or may be stored in the storage unit 12 in advance and acquired from the storage unit 12. Further, it can be exemplified that the secondary work cost is determined for each secondary new part.

In addition, the derivation unit 114 adds the current repair cost and the secondary repair cost to calculate the total repair cost estimated to be necessary in the future if the currently used product is continued to be used. Deduce.
Further, the derivation unit 114 derives the purchase cost when the currently used product is replaced with a new one. In such a case, the derivation unit 114 may derive the cost of purchasing a product with exactly the same model name as the one currently in use. However, if the product with the model name that you are currently using has been discontinued, the derivation unit 114 determines that if you purchase a successor product of the product or a product with the same performance as the product you are currently using, It is also possible to derive the cost of

As explained above, the derivation unit 114 calculates the repair cost required to repair the failed part predicted by the secondary prediction unit 216, the period until the repair is completed, the secondary repair cost required to repair the secondary failed part, the total Determine the repair cost for the product, purchase cost for replacing the currently used product, etc. Then, the display control unit 113 preferably causes the display unit 13 to display this information derived by the derivation unit 114. This allows employees of maintenance company M to recognize this information. Furthermore, the employees of the maintenance company M can print out this information and show it to the customer so that the customer can recognize it.

The repair support system 1 configured as described above stores repair information that links first information regarding the product name and symptoms of gas appliances, second information regarding weather information, and the failure part of the gas appliance. It includes a storage unit 22 and a receiving unit 111 as an example of a receiving unit that receives information on failure requests. Furthermore, the repair support system 1 determines whether the gas appliance is repaired based on the first information and second information regarding the gas appliance for which the failure request has been received by the receiving unit 111 and the repair information stored in the storage unit 22. It includes an estimator 214 that estimates a failure part. According to this repair support system 1, a failed part can be estimated with higher accuracy than when the failed part is not estimated using weather information.

The repair support system 1 also includes a prediction unit 215 that predicts a failed part from the failure location estimated by the estimation unit 214. Thereby, according to the repair support system 1, it is possible to estimate failed parts with high accuracy.
The repair support system 1 also includes a derivation unit 114 that derives the cost required to repair the failed component predicted by the prediction unit 215. Thereby, according to the repair support system 1, it is possible to make the customer recognize the cost required for repair with high accuracy.

The repair support system 1 further includes a secondary prediction unit 216 that predicts a secondary failure component that will fail next to the failure component, and the derivation unit 114 calculates the total cost required to repair the failure component and the secondary failure component. Deduce. Thereby, according to the repair support system 1, it becomes possible to make the customer aware of the total cost including the cost necessary for repairing a failure that will occur in the future.
The repair support system 1 further includes a display control unit 113 that causes the display unit 13 to display the total cost derived by the derivation unit 114 and the cost of replacing the gas appliance. Thereby, according to the repair support system 1, the employees of the maintenance company M can recognize the total cost and the cost of replacing the product, and can make the customer aware of this.

Furthermore, the repair support system 1 includes a secondary prediction unit 216 as an example of a prediction unit that predicts the day when a secondary failure component will fail in consideration of the family structure. Thereby, according to the repair support system 1, the employees of the maintenance company M can recognize the date when the total cost is required, and can make the customer recognize this. As a result, the customer can easily choose between completing the requested repair or purchasing a new product.

Further, in the above-described repair support system 1, the information processing device 10 requests the server device 20 to estimate a failure part, etc., but the present invention is not limited to this mode. For example, the control unit 11 of the information processing device 10 acquires repair information stored in the storage unit 22 of the server device 20 and stores it in the storage unit 12, and the control unit 11 acquires the repair information stored in the storage unit 12. The information may be used to estimate the location of the failure or to predict the failure part. That is, the control unit 11 of the information processing device 10 may have the functions of the estimation unit 214, the prediction unit 215, and the secondary prediction unit 216 of the control unit 21. In such a case, the information processing device 10 includes a storage unit that stores repair information that links first information regarding the product name and symptoms of the gas appliance, second information regarding weather information, and the failure part of the gas appliance. 12, and a receiving section 111 as an example of a receiving section that receives information on failure requests. Further, the information processing device 10 determines whether the gas appliance is repaired based on the first information and second information regarding the gas appliance for which the failure request has been received by the receiving unit 111 and the repair information stored in the storage unit 12. A control unit 11 that estimates a failure part is provided.

The processing performed by the server device 20 described above can be realized through cooperation between software and hardware resources. In this case, the CPU of the control unit 21 of the server device 20 executes a program that implements each function of the server device 20, thereby realizing each of these functions. For example, a non-temporary computer-readable recording medium on which a program is recorded is provided to the server device 20, and the CPU of the server device 20 reads the program stored in the recording medium. In this case, the program itself read from the recording medium realizes the functions of the embodiments described above, and the program itself and the recording medium on which it is recorded constitute the present invention.

A program that realizes the functions of the server device 20 stores, in the computer, first information regarding the product name and symptoms of the gas appliance, second information regarding weather information, and repair information that links the failure part of the gas appliance. the first information and the second information regarding the gas appliance for which the received failure request has been made; and the repair information. Achieve the function of estimating body parts.
Examples of recording media for supplying such programs include flexible disks, CD-ROMs, DVD-ROMs, hard disks, optical disks, magneto-optical disks, CD-Rs, magnetic tapes, nonvolatile memory cards, and ROMs. I can give an example.

<Second embodiment>
FIG. 5 is a diagram showing an example of a schematic configuration of the server device 30 according to the second embodiment.
The repair support system 2 according to the second embodiment includes the information processing device 10, a server device 30 that performs inference of a failed part of a device to be repaired in response to a request from the information processing device 10, and the like. It is equipped with The server device 30 differs from the server device 20 according to the first embodiment in that a failure part is estimated using so-called artificial intelligence (AI). Hereinafter, the differences between the server device 30 and the server device 20 will be mainly explained. Components having the same functions in the server device 20 and the server device 30 are given the same reference numerals, and detailed explanation thereof will be omitted.
The server device 30 includes a control section 31 that controls the entire device, a storage section 32, a display section 23, an operation section 24, and a communication section 25. These control section 31 , storage section 32 , display section 23 , operation section 24 , and communication section 25 are connected via a bus 36 . The storage unit 32 stores repair information illustrated in FIG. 4 .

The control unit 31 includes a CPU (not shown), a ROM (not shown), a RAM (not shown), and the like. The control unit 31 includes a receiving unit 311 that receives information transmitted from an external device such as the information processing device 10, and a transmitting unit 212 that transmits information to the external device such as the information processing device 10. . Further, the control unit 31 includes a creation unit 313 that creates a trained model, and an inference unit 314 that infers a faulty part using the trained model created by the creation unit 313. The control unit 31 also includes a prediction unit 215 that predicts a failed component that would have failed based on the failure part inferred by the inference unit 314, and a prediction unit 215 that predicts a component that will fail next to the failed component predicted by the prediction unit 215. and a next prediction unit 216.

The receiving unit 311 receives information transmitted from the information processing device 10. For example, in addition to the functions that the receiving unit 211 has, the receiving unit 311 receives a request from the maintenance company M to infer a failure part, which is transmitted from the information processing device 10 .

The creation unit 313 creates a learned model by performing machine learning using so-called artificial intelligence (AI). Machine learning can be exemplified as deep learning. The creation unit 313 creates a learned model using the repair information stored in the storage unit 32. At that time, the creation unit 313 inputs the product name of the gas appliance (for example, water heater, gas stove), symptom (for example, no hot water), manufacturer name, region, weather information, failure diagnosis sheet information, etc. in the input layer. , the repair information stored in the storage unit 32 is input. In addition, training data (correct answer) such as the failure part of the gas appliance, for example, "heat-generating part inside the main body of the water heater" is provided to the output layer. Further, the creation unit 313 creates a trained model by calculating the connection strength (weighting) of neurons in the intermediate layer so that the input and output match. The creation unit 313 stores the created learned model in the storage unit 32.

When the inference unit 314 receives a request from the maintenance company M to infer the failure part, the inference unit 314 infers the failure part from the information regarding the failure received by the reception unit 311 using the trained model. The information regarding the failure received by the receiving unit 311, in other words, the information provided when the customer requests repair, includes the product name of the gas appliance such as the water heater, and symptoms such as no hot water. Since this is common, the inference unit 314 inputs the first information regarding the product name and symptoms to the learned model. Furthermore, the inference unit 314 also uses second information, which is information regarding the failure received by the receiving unit 311 and is information other than the product name and symptoms, as information to be input into the learned model. The second information is exemplified as at least one of the following: the name of the manufacturer that manufactured the failed product, the area in charge of the maintenance company M who requested the inference, weather information for the area, and information on the failure diagnosis sheet. can do. Note that when inputting the first information and the second information to the trained model, the inference unit 314 inputs the first information and the second information after converting them into data in a predetermined format.

The prediction unit 215 predicts a failed part that is likely to have failed based on the failure part inferred by the inference unit 314 based on the repair information stored in the storage unit 32 . The storage unit 32 stores failed parts in association with failed parts. For example, the prediction unit 215 counts the number of each failed component stored in the storage unit 32 in association with the failed part inferred by the inference unit 314, and selects the failed component with the highest count as the current failed component. Prediction can be exemplified.
Note that the prediction unit 215 may predict failed parts by considering the number of years that have passed.
In addition, the prediction unit 215 counts the number of each failed component stored in the storage unit 32 in association with the failed part inferred by the inference unit 314, and also selects the top plurality of failed components (for example, five) with the highest number of counts. may be predicted as the currently failed part.

As described above, the prediction unit 215 predicts a failed component, and the secondary prediction unit 216 predicts a secondary failure component or a day when the secondary failure component is expected to fail. The transmitting unit 212 then transmits the information predicted by the predicting unit 215 and the secondary predicting unit 216 to the information processing device 10.

The repair support system 2 configured as above includes first information regarding the product name and symptoms of the gas appliance, and second information including at least one of the manufacturer name, region, weather information, and failure diagnosis sheet information. , a storage unit 32 that stores a learned model obtained by machine learning using the first information, the second information, and the failure part of the gas appliance stored in association with each other. The repair support system 2 also includes a reception unit 111 as an example of a reception unit that receives information on failure requests, first information and second information regarding gas appliances for which failure requests have been received by the reception unit 111, and information on the learned information. and an inference unit 314 that infers a failure part of the gas appliance based on the model. According to this repair support system 2, it is possible to estimate a faulty part with higher accuracy than when the faulty part is not inferred using a trained model.

The repair support system 2 also includes a prediction unit 215 that predicts a failed part from the failure location inferred by the inference unit 314. Thereby, according to the repair support system 2, it is possible to estimate failed parts with high accuracy.

Note that in the repair support system 2 described above, the creation unit 313 preferably updates the learned model at a predetermined timing. An example of the predetermined timing is when new failure information is stored in the storage unit 32. In addition, the predetermined timing may be when a plurality of pieces (for example, 10 pieces) of new failure information are stored in the storage unit 32. Alternatively, the time may be a predetermined time, such as midnight every day or midnight on the first day of every month.

Further, in the repair support system 2 described above, the inference unit 314 infers a failed part using the learned model, and the prediction unit 215 predicts a failed part from the failed part inferred by the inference unit 314. The present invention is not limited to this embodiment. For example, the inference unit 314 may infer a failed component using a learned model. In such a case, the creation unit 313 inputs information such as the product name, symptoms, manufacturer name, region, weather information, and failure diagnosis sheet information of the gas appliance into the input layer, and inputs the information of the gas appliance into the output layer. Provide training data (correct answers) for faulty parts, for example, "electrical board" and "motor." Further, the creation unit 313 creates a trained model by calculating the connection strength (weighting) of neurons in the intermediate layer so that the input and output match. The creation unit 313 preferably stores the created trained model in the storage unit 32.

Further, in the repair support system 2 described above, the information processing device 10 requests the server device 30 to infer the location of the failure, etc., but the present invention is not particularly limited to this mode. For example, the control unit 11 of the information processing device 10 acquires the trained model stored in the storage unit 32 of the server device 30 and stores it in the storage unit 12, and the control unit 11 acquires the learned model stored in the storage unit 12. The trained model may be used to infer the location of failure, predict failure parts, and the like. That is, the control unit 11 of the information processing device 10 may have the functions of the inference unit 314, the prediction unit 215, and the secondary prediction unit 216 of the control unit 31. In such a case, the information processing device 10 includes first information regarding the product name and symptoms of the gas appliance, second information including at least one of the manufacturer name, region, weather information, and failure diagnosis sheet information; The storage unit 12 includes a storage unit 12 that stores a learned model obtained by machine learning using the first information and the failure part of the gas appliance stored in association with the second information. The information processing device 10 also includes a receiving unit 111 as an example of a receiving unit that receives information on a failure request, first information and second information regarding the gas appliance for which the failure request has been received by the receiving unit 111, and the learned information. and a control unit 11 that infers a failure location of the gas appliance based on the model. Furthermore, the control unit 11 of the information processing device 10 may have the function of the creation unit 313 of the control unit 31 of the server device 30 to create a trained model.

The processing performed by the server device 30 described above can be realized through cooperation between software and hardware resources. In this case, the CPU of the control unit 31 of the server device 30 executes a program that implements each function of the server device 30, thereby realizing each of these functions. For example, a non-temporary computer-readable recording medium on which a program is recorded is provided to the server device 30, and the CPU of the server device 30 reads the program stored in the recording medium. In this case, the program itself read from the recording medium realizes the functions of the embodiments described above, and the program itself and the recording medium on which it is recorded constitute the present invention.

The program that realizes the functions of the server device 30 causes the computer to send first information about the product name and symptoms of the gas appliance, and second information such as at least one of the manufacturer name, region, weather information, and failure diagnosis sheet information. and a function to store a learned model by performing machine learning using the first information and the second information and the failure part of the gas appliance stored in association with each other, and a function to receive information on a failure request. and a function of inferring a failure part of the gas appliance based on the first information and the second information regarding the gas appliance for which the received failure request was made, and the learned model.

DESCRIPTION OF SYMBOLS 1, 2... Repair support system, 5... Network, 10... Information processing device, 11... Control part, 12... Storage part, 20, 30... Server device, 21, 31... Control part, 22, 32... Storage part, 111 ...Receiving section, 112... Transmitting section, 113... Display control section, 114... Deriving section, 211, 311... Receiving section, 212... Transmitting section, 214... Estimating section, 215... Predicting section, 216... Secondary predicting section, 313 ...creation section, 314...reasoning section

Claims (12)

A storage unit that stores repair information that links first information regarding the product name and symptoms of the gas appliance, second information regarding weather information, and failure parts of the gas appliance, including a heat-generating part, a remote control, and an ignition part. and,
A reception department that receives information on malfunction requests;
Based on the first information and the second information regarding the gas appliance for which the failure request was received by the reception unit, and the repair information stored in the storage unit, the failure location of the gas appliance is determined. an estimation unit that estimates
a prediction unit that predicts a failed part from the failure part estimated by the estimation unit;
a derivation unit that derives the cost required to repair the failed part predicted by the prediction unit;
Equipped with
The storage unit stores, in association with the failed part predicted by the prediction unit, the manufacturer name and model name of the product having the failed part, and the date of repair of the failed part,
further comprising a secondary prediction unit that predicts a secondary failure component that will fail next to the failure component,
The derivation unit derives a total cost required for repairing the failed part and the secondary failed part,
When the secondary prediction unit receives a repair request again after repairing the failed part from a list of repairs for which the manufacturer name and model name of the product having the failed part predicted by the prediction unit are the same. In addition to counting the number of repair requests for each faulty part that was subject to repair, the parts with a large number of counts are predicted as secondary faulty parts.
Repair support system. The repair support system according to claim 1 , further comprising a display control section that causes a display section to display the total cost derived by the derivation section and the cost when replacing the gas appliance. 3. The repair support system according to claim 2 , further comprising a prediction unit that predicts a day when the secondary failure component will fail in consideration of family structure. Linking the first information regarding the product name and symptoms of the gas appliance, the second information of at least one of the manufacturer name, region, weather information, and failure diagnosis sheet information, and the first information and the second information. a storage unit that stores a learned model obtained by machine learning using the faulty parts of the gas appliance, including the heat generating part, the remote control, and the ignition part, stored in the memory;
A reception department that receives information on malfunction requests;
an inference unit that infers the failure part of the gas appliance based on the first information and the second information regarding the gas appliance for which the failure request has been received by the reception unit and the learned model;
a prediction unit that predicts a failed part from the failure part inferred by the inference unit;
a derivation unit that derives the cost required to repair the failed part predicted by the prediction unit;
Equipped with
The storage unit stores, in association with the failed part predicted by the prediction unit, the manufacturer name and model name of the product having the failed part, and the date of repair of the failed part,
further comprising a secondary prediction unit that predicts a secondary failure component that will fail next to the failure component,
The derivation unit derives a total cost required for repairing the failed part and the secondary failed part,
When the secondary prediction unit receives a repair request again after repairing the failed part from a list of repairs for which the manufacturer name and model name of the product having the failed part predicted by the prediction unit are the same. In addition to counting the number of repair requests for each faulty part that was subject to repair, the parts with a large number of counts are predicted as secondary faulty parts.
Repair support system. The repair support system according to claim 4 , further comprising a display control section that causes a display section to display the total cost derived by the derivation section and the cost when replacing the gas appliance. 6. The repair support system according to claim 5 , further comprising a prediction unit that predicts the day when the secondary failure component will fail in consideration of family structure. a storage unit that stores repair information that links first information regarding the product name and symptoms of the gas appliance, second information regarding weather information, and a malfunctioning part of the gas appliance;
A reception department that receives information on malfunction requests;
Based on the first information and the second information regarding the gas appliance for which the failure request has been received by the reception unit, and the repair information stored in the storage unit, the failure part of the gas appliance is determined. an estimator that estimates;
a prediction unit that predicts a failed part from the failure part estimated by the estimation unit;
a derivation unit that derives the cost required to repair the failed part predicted by the prediction unit;
a secondary prediction unit that predicts a secondary failure component that will fail next to the failure component;
Equipped with
The storage unit stores, in association with the failed part predicted by the prediction unit, the manufacturer name and model name of the product having the failed part, and the date of repair of the failed part,
The derivation unit derives a total cost required for repairing the failed part and the secondary failed part,
When the secondary prediction unit receives a repair request again after repairing the failed part from a list of repairs for which the manufacturer name and model name of the product having the failed part predicted by the prediction unit are the same. In addition to counting the number of repair requests for each faulty part that was subject to repair, the parts with a large number of counts are predicted as secondary faulty parts.
A repair support system characterized by: The repair support system according to claim 7 , further comprising a display control unit that causes a display unit to display the total cost derived by the derivation unit and the cost when replacing the gas appliance. 9. The repair support system according to claim 8 , further comprising a prediction unit that predicts a day when the secondary failure component will fail in consideration of family structure. Linking the first information regarding the product name and symptoms of the gas appliance, the second information of at least one of the manufacturer name, region, weather information, and failure diagnosis sheet information, and the first information and the second information. a storage unit that stores a trained model obtained by machine learning using the fault location of the gas appliance stored in the storage unit;
A reception department that receives information on malfunction requests;
an inference unit that infers a failure part of the gas appliance based on the first information and the second information regarding the gas appliance for which the failure request was received by the reception unit and the learned model;
a prediction unit that predicts a failed part from the failure part inferred by the inference unit;
a derivation unit that derives the cost required to repair the failed part predicted by the prediction unit;
a secondary prediction unit that predicts a secondary failure component that will fail next to the failure component;
Equipped with
The storage unit stores, in association with the failed part predicted by the prediction unit, the manufacturer name and model name of the product having the failed part, and the date of repair of the failed part,
The derivation unit derives a total cost required for repairing the failed part and the secondary failed part,
When the secondary prediction unit receives a repair request again after repairing the failed part from a list of repairs for which the manufacturer name and model name of the product having the failed part predicted by the prediction unit are the same. In addition to counting the number of repair requests for each faulty part that was subject to repair, the parts with a large number of counts are predicted as secondary faulty parts.
A repair support system characterized by: The repair support system according to claim 10 , further comprising a display control section that causes a display section to display the total cost derived by the derivation section and the cost when replacing the gas appliance. 12. The repair support system according to claim 11 , further comprising a prediction unit that predicts a day when the secondary failure component will fail in consideration of family structure.

Images