Insurance Terms Proposal Program

Abstract

To propose an insurance condition for maintenance cost compensation.SOLUTION: An insurance condition proposal program causes a computer execute an information acquisition step of acquiring facility data from a facility on which maintenance is performed, and a proposal step of proposing an insurance condition by using the three or more stages of relevance between reference facility data acquired from the facility in the past and the insurance condition, based on reference facility data according to the facility data acquired in the information acquisition step.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an insurance condition proposal program capable of planning and proposing conditions for compensation insurance related to maintenance costs.

Background Art

[0002] Various facilities such as electricity, gas, and water supply are indispensable infrastructures for forming the life lines of life. Such various facilities also deteriorate over time through long-term use, and eventually, a time when maintenance is required will come. When performing maintenance on such various facilities, it is often the case that the work is entrusted to a contractor specialized in that maintenance. Such maintenance contractors also each have their own fields of expertise, and whether they can respond immediately depending on the degree of congestion of the contractor's work also becomes a problem, and the maintenance cost also changes accordingly.

[0003] For this reason, a system that can reduce the labor of selecting such contractors in relation to maintenance costs as much as possible each time the user side entrusts the maintenance of facilities has been desired conventionally, but such technology has not been proposed yet. Also, when a problem actually occurs before the expiration of the estimated maintenance-free period and appropriate maintenance becomes necessary, if insurance for compensating maintenance costs is set in advance and compensation for maintenance costs can be received from the insurance, an economic mechanism that enables long-term leveling of the total customer cost has been attempted. In this case, a system that estimates the insurance conditions without relying on the skills, knowledge, and experience of specific individuals has been desired conventionally, but such insurance design support technology has not been proposed yet.

Summary of the Invention

Problems to be Solved by the Invention

[0004] Therefore, the present invention was devised in view of the above-mentioned problems, and its purpose is to introduce an economic mechanism that enables the long-term leveling of overall customer costs by having a business that acts on behalf of the customer's insured interests take out maintenance cost compensation insurance in advance, so that if a malfunction actually occurs before the estimated maintenance-free period expires and appropriate maintenance becomes necessary, the customer can receive compensation for maintenance costs from said insurance, and to provide an insurance condition proposal program that can estimate the necessary insurance conditions without relying on the skills, knowledge, and experience of a specific person. [Means for solving the problem]

[0005] The insurance condition proposal program according to the present invention comprises an information acquisition step of acquiring equipment data from equipment to be maintained, and a proposal step of proposing insurance conditions based on reference equipment data corresponding to the equipment data acquired in the information acquisition step, using reference equipment data with three or more levels of correlation between reference equipment data acquired from equipment in the past and insurance conditions. In the information acquisition step described above, vendor status information regarding the status of vendors is acquired. In the proposal step described above, the computer is made to use the combination of the above reference equipment data and the reference vendor status information regarding the status of vendors, and the correlation degree of the vendor to be selected, with a correlation degree of three or more levels. Furthermore, the computer is made to propose insurance conditions based on the reference vendor status information corresponding to the vendor status information acquired in the information acquisition step described above. The correlation degree is composed of nodes in a neural network in artificial intelligence. It is characterized by the following. [Effects of the Invention]

[0006] The plan involves implementing an economic mechanism that enables the long-term leveling of overall customer costs. This is achieved by having a business that acts on behalf of the customer to take out maintenance cost coverage insurance in advance. If a malfunction actually occurs before the estimated maintenance-free period expires and appropriate maintenance becomes necessary, the customer can receive compensation for the maintenance costs from that insurance. Furthermore, the necessary insurance conditions for this can be estimated without relying on the skills, knowledge, or experience of any particular person. [Brief explanation of the drawing]

[0007] [Figure 1] This is a block diagram showing the overall configuration of a system to which the present invention is applied. [Figure 2] This figure shows a specific example of the configuration of the search device. [Figure 3] This is a diagram illustrating the operation of the present invention. [Figure 4] This is a diagram illustrating the operation of the present invention. [Figure 5] This is a diagram illustrating the operation of the present invention. [Figure 6] This is a diagram illustrating the operation of the present invention. [Figure 7] This is a diagram illustrating the operation of the present invention. [Figure 8] This is a diagram illustrating the operation of the present invention. [Figure 9] This is a diagram illustrating the operation of the present invention. [Figure 10] This is a diagram illustrating the operation of the present invention. [Figure 11] This is a diagram illustrating the operation of the present invention. [Modes for carrying out the invention]

[0008] First Embodiment The maintenance contractor selection program to which the present invention is applied will be described in detail below with reference to the drawings.

[0009] Figure 1 is a block diagram showing the overall configuration of a maintenance contractor selection system 1 in which a maintenance contractor selection program applying the present invention is implemented. The maintenance contractor selection system 1 comprises an information acquisition unit 9, a search device 2 connected to the information acquisition unit 9, and a database 3 connected to the search device 2.

[0010] The information acquisition unit 9 is a device for users of this system to input various commands and information, and specifically consists of a keyboard, buttons, touch panel, mouse, switch, etc. The information acquisition unit 9 is not limited to a device for inputting text information, but may also consist of a device capable of detecting sound and converting it into text information, such as a microphone. The information acquisition unit 9 may also be configured as an imaging device capable of capturing images, such as a camera. The information acquisition unit 9 may also consist of a scanner equipped with the function to recognize strings of characters from paper documents. The information acquisition unit 9 may also be integrated with the search device 2, which will be described later. The information acquisition unit 9 outputs the detected information to the search device 2. The information acquisition unit 9 may also consist of a means for identifying location information by scanning map information. The information acquisition unit 9 may also consist of a temperature sensor, humidity sensor, wind direction sensor, and illuminance sensor for measuring temperature. The information acquisition unit 9 may also consist of a communication interface for acquiring weather data from the Japan Meteorological Agency or private weather forecasting companies. The information acquisition unit 9 may also consist of a body sensor worn on the body to detect bodily data, and this body sensor may consist of sensors for detecting, for example, body temperature, heart rate, blood pressure, steps, walking speed, and acceleration. Furthermore, the body sensor may acquire biological data not only from humans but also from animals. The information acquisition unit 9 may also be configured as a device that acquires information by scanning drawings or other information, or by reading it from a database. In addition to the above, the information acquisition unit 9 may also consist of an odor sensor that detects odors or scents.

[0011] Database 3 stores various information necessary for solution searching.

[0012] The search device 2 is composed of electronic devices such as a personal computer (PC), but it may also be implemented using any other electronic devices such as mobile phones, smartphones, tablet devices, and wearable devices. The user can obtain a search solution using this search device 2.

[0013] Figure 2 shows a specific configuration example of the search device 2. This search device 2 includes a control unit 24 for controlling the entire search device 2, an operation unit 25 for inputting various control commands via an operation button, a keyboard, etc., a communication unit 26 for performing wired or wireless communication, a discrimination unit 27 for performing various determinations, and a storage unit 28 represented by a hard disk or the like for storing a program for performing a search to be executed, which are respectively connected to an internal bus 21. Further, a display unit 23 as a monitor for actually displaying information is connected to this internal bus 21.

[0014] The control unit 24 is a so-called central control unit for controlling each component implemented in the search device 2 by transmitting a control signal via the internal bus 21. Also, this control unit 24 transmits various control commands via the internal bus 21 in response to an operation via the operation unit 25.

[0015] The operation unit 25 is implemented by a keyboard or a touch panel, and an execution command for executing a program is input from a user. When this execution command is input from the user, this operation unit 25 notifies the control unit 24 of this. The control unit 24 that has received this notification will execute a desired processing operation in cooperation with each component including the discrimination unit 27. This operation unit 25 may be implemented as the aforementioned information acquisition unit 9.

[0016] The discrimination unit 27 discriminates a search solution. When executing the discrimination operation, this discrimination unit 27 reads out various information stored in the storage unit 28 and various information stored in the database 3 as necessary information. This discrimination unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any well-known artificial intelligence technology. [[ID=十六]]

[0017] [[ID=十七]] The display unit 23 is composed of a graphic controller that creates a display image based on the control by the control unit 24. This display unit 23 is realized by, for example, a liquid crystal display (LCD) or the like.

[0018] When the storage unit 28 is composed of a hard disk, based on the control by the control unit 24, predetermined information is written to each address and read out as necessary. Further, a program for executing the present invention is stored in the storage unit 28. This program will be read out and executed by the control unit 24.

[0019] The operation of the maintenance contractor selection system 1 having the above-described configuration will be described.

[0020] In the maintenance contractor selection system 1, for example, as shown in FIG. 3, it is premised that a three-stage or more correlation between reference facility data and the degree of deterioration of water pipes is preset. The reference facility data is data directly obtained from facilities (devices) necessary for creating an environment in which people live, move, work, or conduct communication, play, various ceremonies, and events. In other words, this reference facility data is composed of all data obtained from various facilities of various building structures (houses, buildings, transportation facilities, various facilities, commercial facilities, factories, plants). The facilities here are various facilities via electricity, gas, water, etc., and are integrally and inseparably attached inside the building structure, and do not include those that are independently traded like home appliances.

[0021] Electrical equipment includes, but is not limited to, lighting, power distribution systems, air conditioners, bathroom dryers, electric heaters, kitchens, toilets, ventilation systems, and factory electrical control systems. Maintenance of electrical equipment involves repair, replacement, upkeep, restoration work, and proactive fault detection. Maintenance of water supply equipment includes all water-using facilities, whether public water supply, sewage, or plants. Maintenance targets include repair, replacement, upkeep, restoration work, and proactive fault detection for issues such as clogged toilets, leaks, and malfunctions, clogged kitchen and bathroom sinks, clogged bath drains, and leaks and malfunctions of showers and faucets. Gas equipment refers to gas equipment used in bathrooms, kitchens, etc., and its maintenance involves repair, replacement, upkeep, restoration work, and proactive fault detection.

[0022] Reference equipment data includes all data obtained by directly or indirectly attaching sensors and measuring instruments to such equipment. For example, power, electricity, voltage, vibration, sound, light, radio waves (hereinafter collectively referred to as physical data), air and liquid flow rates, and wastewater volume in drainage facilities supplied to the various types of equipment mentioned above are all considered reference equipment data. The system detects data consisting of one or more of the following: physical data that operates the equipment, gas flow rate data for supplying or exhausting gas, solar power generation data, and light intensity data for irradiating light. By detecting this data, it is possible to understand whether the current state of the environment is normal or whether some kind of abnormality is occurring. Furthermore, by detecting this operational data, it is possible to estimate whether the environment is likely to experience an abnormality in the near future or whether it will remain normal.

[0023] Regarding the vibration data included in the reference equipment data, the method of detecting vibration waves may vary; for example, in addition to vibration sensors and strain sensors, if the vibration manifests as sound waves, it may be detected by ultrasonic sensors or the like. Furthermore, equipment data consisting of electromagnetic waves and light may consist of ordinary image data or spectral data. Reference equipment data also includes data utilizing any type of wave used in non-destructive testing.

[0024] Furthermore, reference equipment data and equipment data may include not only data detected by cameras and sensors, but also data obtained from conversations with customers requiring maintenance. In such cases, the conversations from customer phone calls to the call center may be converted into text data, or text data entered by customers in emails or on the inquiry website may be obtained and analyzed using natural language processing. In fact, intentions and degrees are obtained from the relationships between verbs and the noun phrases and adjectives that relate to them, and this is converted into data.

[0025] These reference equipment data can be managed in any time-series unit, including yearly, monthly, weekly, daily, hourly, and minute-by-minute units.

[0026] The contractors to be selected are those who perform the various maintenance services mentioned above as a business, and consist of a company name or individual name. In addition to the specific company name, the contractors to be selected may also indicate the type of business office or branch office.

[0027] In the example shown in Figure 3, the input data consists of reference equipment data P01, P02, and P03. These reference equipment data P01, P02, and P03, which serve as input data, are linked to the vendor, which is the output.

[0028] The reference equipment data P01, P02, and P03 are interconnected with vendors A-D, which represent the output solution, through a correlation degree of three or more levels. These vendors are indicated, for example, as follows: vendor A is 95% associated, vendor B is 60% associated, and so on. The reference equipment data are arranged on the left side via this correlation degree, and each vendor is arranged on the right side via this correlation degree. The correlation degree indicates the degree to which each reference equipment data is highly related to a particular vendor. In other words, this correlation degree is an indicator of which vendor each reference equipment data is most likely to be linked to, and it demonstrates the accuracy in selecting the most likely vendor for each reference equipment data. In the example in Figure 3, correlation degrees w13-w19 are shown. As shown in Table 1 below, w13 to w19 are represented on a 10-point scale. A score closer to 10 indicates a higher degree of correlation between each combination of intermediate nodes and the output vendors, while a score closer to 1 indicates a lower degree of correlation between each combination of intermediate nodes and the output vendors.

[0029] [Table 1]

[0030] Search device 2 pre-acquires correlation degrees w13 to w19 of three or more levels as shown in Figure 3. In other words, in order to determine the actual search solution, search device 2 accumulates past datasets of reference equipment data and which of the contractors was adopted and evaluated in that case, and creates the correlation degrees shown in Figure 3 by analyzing and interpreting these. Note that the reference equipment data is not limited to time-series data, for example, but may consist of data converted to the frequency axis through FFT transformation.

[0031] This analysis may be performed using artificial intelligence. In such cases, each reference equipment data set and the corresponding vendor dataset are used for training. For example, if equipment data P01 has many cases for vendor A, the correlation score leading to the evaluation of this vendor is set higher, and if there are many cases for vendor B, the correlation score leading to the evaluation of this vendor is set higher. For example, in the reference equipment data example for equipment data P01, it is linked to vendor A and vendor C, but the correlation score of w13 leading to vendor A from previous cases is set to 7 points, and the correlation score of w14 leading to vendor C is set to 2 points.

[0032] Furthermore, the correlation coefficient shown in Figure 3 may be composed of nodes in a neural network in artificial intelligence. That is, the weighting coefficients for the output of these neural network nodes correspond to the correlation coefficient described above. Moreover, it may not be limited to a neural network, but may be composed of any decision-making factors that constitute artificial intelligence.

[0033] In such cases, as shown in Figure 4, reference equipment data for each region is input as input data, and contractors are output as output data. At least one hidden layer may be provided between the input node and the output node to perform machine learning. The aforementioned correlation degree is set in either the input node or the hidden layer node, or both, and this becomes the weight for each node, and the output is selected based on this. Furthermore, the output may be selected if this correlation degree exceeds a certain threshold.

[0034] This degree of correlation is what artificial intelligence calls "trained data." After creating this trained data, when actually identifying new businesses, the aforementioned trained data is used to search for businesses. Alternatively, the system could determine which of the pre-defined categories of businesses the business belongs to.

[0035] When searching for a new contractor, we will accept input of equipment data. Details of the equipment data will be omitted below, as they are described in the above-mentioned explanation of the reference equipment data.

[0036] Next, the input equipment data is compared with reference equipment data. In such cases, the correlation degree shown in Figure 3 (Table 1), which was obtained in advance, is referred to. For example, if the newly acquired equipment data is the same as or similar to P02, then contractor B is associated with w15 and contractor C with correlation degree w16 via the correlation degree. In such cases, contractor B, which has the highest correlation degree, is selected as the optimal solution. However, it is not mandatory to select the one with the highest correlation degree as the optimal solution; contractor C, which has a lower correlation degree but whose relationship itself is recognized, may also be selected as the optimal solution. Furthermore, it is also possible to select an output solution that does not have any connected arrows, and any other priority order based on the correlation degree is acceptable.

[0037] Incidentally, when comparing equipment data with reference equipment data, if these data are expressed as average values ​​over a certain period, the determination of whether they are identical or similar may be made based on whether the average value falls within ±10%. Alternatively, if the equipment data is shown as a time-series trend graph, the determination may be made based on the similarity of the trends.

[0038] In this way, the most suitable contractor can be found and displayed to the user based on the newly acquired equipment data. By viewing these search results, it is possible to suggest which contractor would be preferable to entrust with the work on that equipment.

[0039] The example in Figure 5 illustrates the formation of a correlation between reference equipment data and reference vendor status information regarding the vendor's situation. Reference vendor status information consists of the vendor's work order status, congestion level, past customer reputation, arrangement status and progress of other maintenance work if currently undertaken, repair record and history for each maintenance category, information on the quality of those repairs, the service engineer's current location, estimated arrival time at the customer site, estimated repair start time, estimated repair completion time, and the location of the vendor's branch office. This reference vendor status information may be obtained from a database managed by the vendor itself.

[0040] The reference vendor status information may consist of data obtained by performing various statistical processes on the aforementioned data, such as average values, or standard deviations of time-series measured data. It may also consist of the trend of change in time-series measured data itself, or a classification of these trends.

[0041] The system relies on both equipment data and vendor status information when selecting a vendor. Therefore, by combining reference vendor status information with reference equipment data in the training data, vendors can be identified with higher accuracy. For this reason, the aforementioned correlation index is formed by combining reference vendor status information with reference equipment data.

[0042] In the example in Figure 5, the input data is assumed to be, for example, reference equipment data P01-P03 and reference contractor status information P14-17. The intermediate node shown in Figure 5 is formed by combining the reference equipment data with the reference contractor status information. Each intermediate node is further connected to an output. In this output, the contractor is displayed as the output solution.

[0043] Each combination of reference equipment data and reference vendor status information (intermediate node) is interconnected with the vendor through a correlation degree of three or more levels, resulting in this output solution. The reference equipment data and reference vendor status information are arranged on the left side via this correlation degree, and the vendors are arranged on the right side via the correlation degree. The correlation degree indicates the degree to which the reference equipment data and reference vendor status information arranged on the left side are highly related to a vendor. In other words, this correlation degree is an indicator of which vendor each piece of reference equipment data and reference vendor status information is most likely to be linked to, and it demonstrates the accuracy in selecting the most likely vendor from the reference equipment data and reference vendor status information. Therefore, the optimal vendor will be searched using these combinations of reference equipment data and reference vendor status information.

[0044] In the example in Figure 5, the degree of association is shown as w13 to w22. As shown in Table 1, w13 to w22 is shown on a 10-point scale. A score closer to 10 indicates that each combination of intermediate nodes is highly related to the output, while a score closer to 1 indicates that each combination of intermediate nodes is less related to the output.

[0045] Search device 2 pre-acquires correlation degrees w13 to w22 of three or more levels as shown in Figure 5. In other words, in order to determine the actual search solution, search device 2 accumulates past data on reference equipment data, reference contractor status information, and which contractor was suitable in that case, and creates the correlation degrees shown in Figure 5 by analyzing and interpreting this data.

[0046] This analysis may be performed using artificial intelligence. In such cases, for example, if the reference equipment data P01 is the reference vendor status information P16, the vendor is analyzed from past data. If there are many cases of vendor A, the correlation degree to vendor A is set higher. If there are many cases of vendor B and few cases of vendor A, the correlation degree to vendor B is set higher and the correlation degree to vendor A is set lower. For example, in the case of intermediate node 61a, it is linked to the outputs of vendor A and vendor B, but the correlation degree of w13 leading to vendor A is set to 7 points based on previous cases, and the correlation degree of w14 leading to vendor B is set to 2 points.

[0047] Furthermore, the correlation coefficient shown in Figure 5 may be composed of nodes in a neural network in artificial intelligence. That is, the weighting coefficients for the output of these neural network nodes correspond to the correlation coefficient described above. Moreover, it may be composed of any decision-making factors that constitute artificial intelligence, not just neural networks. The rest of the configuration of artificial intelligence is the same as explained in Figure 4.

[0048] In the example of correlation shown in Figure 5, node 61b is a node representing the combination of reference equipment data P01 and reference vendor status information P14, with a correlation degree of w15 for vendor C and w16 for vendor E. Node 61c is a node representing the combination of reference equipment data P02 and reference vendor status information P15 and P17, with a correlation degree of w17 for vendor B and w18 for vendor D.

[0049] This degree of correlation is what artificial intelligence calls "trained data." After creating this trained data, it will be used when actually identifying businesses. In this case, the region in which the businesses to be identified will be input in the same way. Then, the equipment data and business status information organized for each region in database 3 will be retrieved.

[0050] Based on the newly acquired equipment data and vendor status information, the optimal vendor is searched for. In such cases, the correlation degree shown in Figure 5 (Table 1), which was acquired in advance, is referred to. For example, if the newly acquired equipment data is the same as or similar to P02, and the vendor status information is the same as or similar to P17, then node 61d is associated via the correlation degree, and this node 61d is associated with vendor C at w19 and vendor D at correlation degree w20. In such cases, vendor C, which has the highest correlation degree, is selected as the optimal solution. However, it is not mandatory to select the one with the highest correlation degree as the optimal solution; vendor D, which has a low correlation degree but whose relationship itself is recognized, may also be selected as the optimal solution. Furthermore, it is also possible to select an output solution that does not have any connected arrows, and any other priority order based on the correlation degree is acceptable.

[0051] Furthermore, Table 2 below shows examples of correlation degrees w1 to w12 that extend from the input.

[0052] [Table 2]

[0053] Intermediate node 61 may be selected based on the correlation degrees w1 to w12 extending from this input. In other words, the larger the correlation degrees w1 to w12, the heavier the weight given to the selection of intermediate node 61. However, the correlation degrees w1 to w12 may all be the same value, and the weight given to each of them in the selection of intermediate node 61 may be the same.

[0054] Furthermore, according to the present invention, in addition to the reference equipment data described above, instead of the reference contractor status information described above, a combination of this data and reference weather information relating to the weather at the location of the equipment may be used to perform the solution search based on a correlation of three or more levels with the contractor for that combination.

[0055] This reference weather information, added as an explanatory variable in place of reference contractor status information, includes all information about the weather at the location of the equipment, such as weather (sunny, cloudy, rainy), disasters (typhoon, heavy rain, etc.), temperature, and humidity. Since the need for maintenance, urgency, and the time it takes for contractors to arrive are all affected by such weather conditions, this is also included as reference information. The acquisition of reference weather information and weather information can be done by obtaining the weather at that time from data provided by the Japan Meteorological Agency or private contractors, or by inputting the weather conditions that the user has observed.

[0056] During the solution search, equipment data for the proposed facility and weather information for the location of that facility are acquired. Based on the newly acquired equipment data and weather information, the most suitable contractor is searched for. In such cases, the previously acquired correlation score is referred to, and the contractor is searched for based on the method described above.

[0057] Furthermore, according to the present invention, in addition to the reference equipment data described above, a solution search may be performed based on a combination of the reference equipment status information described above and reference location information relating to the location of the equipment, and a correlation degree of three or more levels with the contractor for that combination.

[0058] This reference location information, added as an explanatory variable in place of reference contractor status information, is information about the location of the proposed equipment, and is displayed as, for example, GPS coordinates or address. This equipment location is also included as an explanatory variable because it is determined by how quickly a contractor can arrive depending on the urgency.

[0059] During the solution search, the equipment data and its location information are acquired. Based on the newly acquired equipment data and location information, the most suitable contractor is searched for. In such cases, the previously acquired correlation score is referred to, and the contractor is searched for based on the method described above.

[0060] Furthermore, according to the present invention, in addition to the reference equipment data described above, a solution search may be performed based on a combination of reference traffic congestion information relating to the traffic congestion status of the roads leading to the equipment location, instead of the reference contractor status information described above, and a correlation degree of three or more levels with the contractor for that combination.

[0061] This reference congestion information, added as an explanatory variable in place of reference vendor status information, may be obtained from data provided by road traffic management agencies, representing the degree of traffic congestion on the road leading to the equipment's location, or it may be determined from images of the road captured by cameras installed on the road. In such cases, image analysis may be performed, utilizing well-known image analysis techniques or well-known deep learning techniques. The density of vehicles on the road is measured in this way, and after statistical processing as necessary, it is quantified as a degree of congestion.

[0062] During the solution search, the system acquires actual equipment data and traffic congestion information for the roads leading to the location of the proposed equipment. The method for acquiring traffic congestion information is the same as the method for acquiring reference traffic congestion information described above. When acquiring traffic congestion information, the system may use the image analysis described above, and even artificial intelligence, for identification. Next, the system searches for the most suitable contractor based on the newly acquired equipment data and traffic congestion information. In this case, the system searches for a contractor based on the method described above, referring to the previously acquired correlation score.

[0063] Furthermore, according to the present invention, in addition to the reference equipment data described above, a solution search may be performed based on a combination of the reference external environment information relating to the external environment instead of the reference vendor status information described above, and a correlation of three or more levels with the vendor for that combination.

[0064] This reference external environmental information, added as an explanatory variable in place of reference business information, is typified by economic data (GDP, employment statistics, industrial production index, capital investment, labor force survey, etc.), household data (household consumption survey, household data, average weekly working hours, savings statistics, annual income statistics, etc.), real estate data (office vacancy rate, price per square meter, rental market rates, land prices, vacant house data, etc.), and natural environment data (disaster data, temperature data, precipitation data, wind direction data, humidity data, etc.). External environmental information includes not only data that reflects some or all of these, but also all information outside of the company being reviewed. Reference external environmental information may also be categorized based on the external environment itself. For example, it may be classified by separating data in employment statistics. Alternatively, it may be categorized by patterns (for example, whether the GDP growth rate is rapid or gradually increasing).

[0065] During the solution search, actual equipment data and external environmental information at the time of proposal are acquired. The method for acquiring external environmental information is the same as the method for acquiring reference external environmental information described above. Next, the optimal contractor is searched for based on the newly acquired equipment data and external environmental information. In this case, the previously acquired correlation degree is referred to, and the contractor is searched for based on the method described above.

[0066] Furthermore, according to the present invention, in addition to the reference equipment data described above, a solution search may be performed based on a combination of reference usage information regarding the usage status of the equipment instead of the reference vendor status information described above, and a correlation degree of three or more levels with the vendor for that combination.

[0067] This reference usage information, added as an explanatory variable in place of reference vendor status information, indicates the usage status of the equipment and consists of data such as the equipment's years of use, installation date, and frequency of use. The reference usage information may be categorized by patterns of usage frequency (for example, patterns such as whether the rate of increase in the time-series change in usage is rapid or gradual). The method for obtaining the reference usage information and usage information may be to use a database managed by the individual or corporation that owns the equipment, or to obtain it from the reference equipment data and equipment data described above.

[0068] During the solution search, actual equipment data and usage information for the target equipment are acquired. The method for acquiring usage information is the same as the method for acquiring reference usage information described above. Next, the optimal contractor is searched for based on the newly acquired equipment data and usage information. In this case, the previously acquired correlation score is referred to, and the contractor is searched for based on the method described above.

[0069] Furthermore, according to the present invention, in addition to the reference equipment data described above, a combination of reference failure history information relating to the equipment's past failure history and a correlation degree of three or more levels with the vendor for that combination may be used to perform the solution search.

[0070] This reference failure history information, added as an explanatory variable in place of reference vendor status information, shows the equipment's failure history and consists of data such as whether the equipment has ever failed, and if so, the date, number, frequency, and nature of the failure. The reference failure history information may be categorized by failure patterns (for example, patterns such as whether the rate of increase in the number of failures over time is rapid or gradual). The reference failure history information and failure history information can be obtained using a database managed by the individual or corporation that owns the equipment, or by obtaining them from the reference equipment data and equipment data mentioned above.

[0071] During the solution search, the equipment data and failure history information for the target equipment are actually acquired. The method for acquiring the failure history information is the same as the method for acquiring the reference failure history information described above. Next, the optimal contractor is searched for based on the newly acquired equipment data and failure history information. In this case, the previously acquired correlation score is referred to, and the contractor is searched for based on the method described above.

[0072] Furthermore, according to the present invention, in addition to the reference equipment data described above, a solution search may be performed based on a combination of the reference equipment type information relating to the type of equipment instead of the reference vendor status information described above, and a correlation degree of three or more levels with the vendor for that combination.

[0073] This reference equipment type information, added as an explanatory variable in place of reference vendor status information, indicates the type of equipment and may be subdivided to the level of the model numbers of the products that make up the equipment, in addition to broad categories such as lighting equipment, air conditioning equipment, ventilation equipment, elevators and other lifting equipment, and water supply equipment. The method for obtaining the reference equipment type information and equipment type information may be to use a database managed by the individual or corporation that owns the equipment, or it may be obtained from the reference equipment data and equipment data mentioned above.

[0074] During the solution search, the actual equipment data and equipment type information for the target equipment are obtained. The method for obtaining equipment type information is the same as the method for obtaining reference equipment type information described above. Next, the optimal contractor is searched for based on the newly obtained equipment data and equipment type information. In this case, the previously obtained correlation degree is referred to, and the contractor is searched for based on the method described above.

[0075] Furthermore, according to the present invention, in addition to the reference equipment data described above, a solution search may be performed based on a combination of the reference customer preference information regarding the customer's preference for using the equipment instead of the reference vendor status information described above, and a correlation degree of three or more levels with the vendor for that combination.

[0076] This reference customer preference information, added as an explanatory variable in place of reference vendor status information, represents all of the customer's preferences regarding equipment maintenance, including delivery dates, costs, actual maintenance methods, preferred vendors or their representatives, and the attributes of the representatives (level of experience, gender, age, etc.) and the type of equipment. This can range from broad categories such as lighting equipment, air conditioning equipment, ventilation equipment, elevators and other lifting equipment, and plumbing equipment, to more detailed categories down to the model number of the components that make up the equipment. Reference customer preference information may be obtained by inputting preferences gathered from customers who have actually ordered maintenance into a database.

[0077] During the solution search, the system obtains actual equipment data and customer preference information gathered from customers who will be using the equipment in question. The method for obtaining customer preference information is the same as the method for obtaining reference customer preference information described above. Next, the system searches for the most suitable vendor based on the newly obtained equipment data and customer preference information. In this case, the system searches for a vendor by referring to the previously obtained correlation score and using the method described above.

[0078] Furthermore, according to the present invention, in addition to the reference equipment data described above, a combination of reference atmosphere information relating to the atmosphere around the equipment and the relationship between the equipment and the contractor (a relationship of three or more levels) may be used instead of the reference contractor status information described above to perform the solution search.

[0079] This reference ambient information, added as an explanatory variable in place of reference contractor status information, consists of all data related to the atmosphere around the equipment, including temperature, humidity, and sound. Temperature and humidity are measured using thermometers and hygrometers, while sound is measured using acoustic meters and sound sensors.

[0080] During the solution search, actual equipment data and atmospheric information gathered from customers using the target equipment are acquired. The method for acquiring atmospheric information is the same as the method for acquiring reference atmospheric information described above. Next, the optimal contractor is searched for based on the newly acquired equipment data and atmospheric information. In this case, the previously acquired correlation score is referred to, and the contractor is searched for based on the method described above.

[0081] In the correlation scale described above, the degree of correlation is expressed on a 10-point scale, but it is not limited to this; any correlation scale of 3 or more is acceptable, and conversely, any scale of 3 or more is acceptable, even 100 or 1000 points. On the other hand, this correlation scale does not include those expressed on a 2-point scale, that is, those expressed as either 1 or 0, indicating whether or not the items are related to each other.

[0082] According to the present invention, which has the configuration described above, anyone can easily identify and search for businesses without any special skills or experience. Furthermore, according to the present invention, it is possible to judge the search solution with higher accuracy than a human can. Moreover, by constructing the correlation degree described above with artificial intelligence (such as a neural network) and training it, the accuracy of the identification can be further improved.

[0083] Furthermore, since the input and output data described above often do not exist that are completely identical during the learning process, the information may be classified by type. In other words, the information P01, P02, ..., P15, 16, ... that constitute the input data may be classified according to criteria predetermined by the system or user based on the content of the information, and a dataset may be created between the classified input and output data for learning.

[0084] Furthermore, as shown in Figure 6, the present invention identifies a business operator based on the degree of correlation between two or more types of information, namely reference information U and reference information V. Reference information U is reference equipment data, and reference information V is any other type of reference information besides reference equipment data.

[0085] In this case, the output obtained for reference information U may be used directly as input data and associated with the output (vendor) via an intermediate node 61 that combines it with reference information V. For example, for reference information U (reference equipment data), after obtaining the output solution as shown in Figure 3, this may be used directly as input, and the degree of association with other reference information V may be used to search for the output (vendor).

[0086] Furthermore, the present invention is characterized by performing the search for the optimal solution through a correlation degree set to three or more levels. The correlation degree can be described by a numerical value from 0 to 100%, for example, in addition to the 10 levels mentioned above, but is not limited to this and may consist of any level that can be described by a numerical value of three or more levels.

[0087] By identifying the most likely vendor based on a correlation score expressed in three or more numerical levels, it becomes possible to search for and display multiple potential solutions in order of their correlation score, even when multiple candidates exist. Displaying solutions in this order of correlation score allows for prioritizing the display of more likely solutions.

[0088] In addition, according to the present invention, even discrimination results with extremely low correlation levels, such as 1%, can be judged without being overlooked. Even discrimination results with extremely low correlation levels can be linked as slight indicators, and it is possible to remind the user that such discrimination results may be useful once in dozens or hundreds of trials.

[0089] Furthermore, according to the present invention, by performing the search based on three or more levels of correlation, there is an advantage in that the search strategy can be determined by how the threshold is set. If the threshold is set low, even correlations of 1% can be picked up without fail, but the possibility of detecting a more appropriate discrimination result is low, and a lot of noise may be picked up. On the other hand, if the threshold is set high, the probability of detecting the optimal search solution is high, but a suitable solution that is usually overlooked due to its low correlation but appears once every tens or hundreds of searches may be missed. Which to prioritize can be decided based on the user's and system's perspectives, but it is possible to increase the degree of freedom in choosing which points to prioritize.

[0090] Furthermore, the present invention may also update the correlation degree described above. This update may, for example, reflect information provided via public communication networks such as the Internet. In addition, if various reference information, including reference equipment data, is acquired, and knowledge, information, and data regarding the businesses involved are obtained, the correlation degree may be increased or decreased accordingly.

[0091] In such cases, the reference information, including the reference equipment data, is collected to determine whether or not it actually occurred, and examples of the results of the contractor selection are collected. The degree of correlation is then increased or decreased according to the number of such examples. At this time, information corresponding to the reference information, including the aforementioned equipment data, may be acquired and used to make the determination, and updates may be made based on this information.

[0092] In other words, this update is equivalent to learning in artificial intelligence. It can be considered a learning activity because it involves acquiring new data and reflecting it in the previously learned data.

[0093] Furthermore, the initial process of creating a trained model, as well as the updates described above, may utilize not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, etc. In the case of unsupervised learning, instead of training by loading input and output data datasets, the model may be trained by loading information equivalent to the input data, and from that, it may self-form the degree of association related to the output data.

[0094] Furthermore, according to the present invention, the system may automatically arrange for maintenance services to be provided to the selected construction company. In such a case, the name of the proposed contractor (company name, individual name, business office, branch office, etc.) is obtained as text data. Then, the text data of that name is inserted into one of the pre-prepared electronic document formats, such as an estimate, request form, completion report, or invoice, to complete the document. At that time, the date and details of the request are inserted into the document as appropriate. The details of the request may be extracted from the reference information mentioned above, and may be obtained from the customer's desired status.

[0095] The completed electronic documents will be sent to the email address of the selected vendor, or, if managed on a website, uploaded to that website.

[0096] Second Embodiment The second embodiment will now be described. In implementing this second embodiment, the vendor proposal system 1, information acquisition unit 9, search device 2, and database 3 used in the first embodiment will be used in the same way. The descriptions of each of these components will be omitted below by referring to the description of the first embodiment.

[0097] In the second embodiment, the search solution involves determining the maintenance costs associated with the aforementioned maintenance. The maintenance costs are the fees paid to the company that actually performed the maintenance. When constructing the training data, the maintenance costs actually paid may be stored and then read out and included in the dataset.

[0098] In such cases, the model is first trained using reference equipment data and a maintenance cost dataset.

[0099] In the example shown in Figure 7, the input data consists of reference equipment data P01, P02, and P03 for each region. This reference equipment data P01, P02, and P03, used as input data, is linked to the maintenance costs, which are the output.

[0100] The reference equipment data P01, P02, and P03 are interconnected with the output solutions, maintenance costs A and B, through a correlation degree of three or more levels. The reference equipment data are arranged on the left side via this correlation degree, and each maintenance cost is arranged on the right side via the correlation degree. The correlation degree indicates the degree to which each reference equipment data is highly related to which maintenance cost. In other words, this correlation degree is an indicator of which maintenance cost each reference equipment data is most likely to be linked to, and demonstrates the accuracy in selecting the most probable maintenance cost for each reference equipment data.

[0101] Furthermore, this correlation coefficient may be composed of nodes in a neural network in artificial intelligence. That is, the weighting coefficients for the output of these neural network nodes correspond to the correlation coefficient described above. Moreover, it may not be limited to a neural network, but may be composed of any decision-making factors that constitute artificial intelligence.

[0102] This degree of correlation is what artificial intelligence calls "trained data." After creating this trained data through a dataset of previous reference equipment data for each region and maintenance costs, the trained data described above will be used to search for maintenance costs when actually determining new maintenance costs. These datasets may be created by reading from databases managed by the contractors. The method of searching for solutions is the same as in the first embodiment described above, so the explanation below will be omitted.

[0103] In this second embodiment, the search solution may be one that determines the maintenance period, which is the period required for maintenance, as an alternative to the maintenance cost. In this case as well, when constructing the training data, the actual maintenance period required may be accumulated and read out and included in the dataset.

[0104] In this second embodiment, the search solution may be one that seeks a maintenance method as an alternative to maintenance costs. Similarly, when constructing the training data, the maintenance methods actually used may be stored and then read out and included in the dataset.

[0105] In this second embodiment, the search solution may be to determine the maintenance frequency as an alternative to the maintenance cost. The maintenance frequency referred to here is the frequency corresponding to the number of times the contractor performs maintenance during a predetermined period. In this case as well, when constructing the training data, the actual number of maintenance sessions required may be accumulated, read out, and the maintenance frequency for the predetermined period may be calculated and included in the dataset.

[0106] These search solutions may be classified by region and by type of maintenance.

[0107] In the second embodiment, insurance conditions linked to the calculated maintenance costs may also be calculated. In this case, the insurance is obtained in advance by the business operator acting on behalf of the customer's insured interests as the policyholder, and the maintenance costs are covered by the insurance when maintenance is actually needed. As a result, the customer does not need to pay maintenance fees directly to the business operator.

[0108] Such insurance conditions refer to various specific concepts that define all information and requirements constituting an insurance scheme, such as the insurance period, premium, coverage conditions, exclusion clauses, insurance payout (maintenance cost compensation), payment limits, and other items related to insurance.

[0109] Such insurance conditions are set to be optimal in relation to maintenance cost coverage. Therefore, as a requirement for the continuity of the insurance contract, it is desirable that the premium rate applied to each contract year be appropriately adjusted using a results-trading method in accordance with increases or decreases in the actual payment record of insurance claims for maintenance cost coverage.

[0110] In such cases, insurance conditions may be linked to individual maintenance costs, and the insurance conditions linked to the calculated maintenance costs may be calculated accordingly.

[0111] In addition to the above, maintenance costs and other related information obtained by the aforementioned methods will be accumulated over a predetermined period. From this accumulated information, it will be possible to estimate the average annual maintenance cost, statistically analyze the frequency of malfunctions, and revise the applicable insurance conditions. In any case, the various applicable insurance conditions may be based on any method of public notification. The purpose of using this information is to achieve a balance of revenue and expenditure for the business in question based on the law of large numbers, and to achieve a long-term, leveled overall cost burden structure through stable insurance contracts.

[0112] In such cases, the maintenance costs obtained by the method described above are accumulated for a predetermined period, and the total, average, maximum, and median values ​​of the accumulated maintenance costs during that predetermined period are calculated. Based on these calculated values, the insurance conditions are then determined. As for how to determine these insurance conditions, a conversion formula may be used in which the insurance period, premium, coverage conditions, exclusion clauses, insurance payout, payment limit, etc., change according to the changes in the total, average, maximum, and median values ​​of the accumulated maintenance costs during that predetermined period. Alternatively, templates may be prepared in advance, with the insurance period, premium, coverage conditions, exclusion clauses, insurance payout, payment limit, etc., associated with each of the total, average, maximum, and median values ​​of the maintenance costs during that predetermined period, and the insurance conditions may be determined by referring to these templates.

[0113] The aforementioned specified period for calculating the requested maintenance costs may consist of any period (days, months, or years).

[0114] Even when using the maintenance frequency as the search solution, the number of maintenance sessions obtained using the method described above is accumulated for a predetermined period, and the maintenance frequency is determined from the accumulated number of maintenance sessions. Then, the average, maximum, and median values ​​of this maintenance frequency are calculated. Based on these calculated values, the insurance conditions are then determined. As for how to determine these insurance conditions, a conversion formula may be used in which the insurance period, premium, coverage conditions, exclusion clauses, insurance payout, payment limit, etc., change according to the changes in the accumulated average, maximum, and median values ​​of the maintenance frequency. Alternatively, templates may be prepared in advance, with the insurance period, premium, coverage conditions, exclusion clauses, insurance payout, payment limit, etc., associated with the average, maximum, and median values ​​of the maintenance frequency within the predetermined period, and the insurance conditions may be determined by referring to these templates.

[0115] Furthermore, insurance conditions may be determined based on both the maintenance frequency and maintenance costs described above. In such cases, the maintenance frequency and maintenance costs may be obtained by the methods described above, but are not limited to this; either one may be determined by other methods, or the maintenance frequency and maintenance costs for a specified period may be measured using conventional methods.

[0116] In this invention, such insurance conditions may be automatically determined and the calculation results output. In such a case, for example, a table of basic insurance premiums (insurance claim costs excluding the portion equivalent to the insurance company's costs and profits) corresponding to the total maintenance costs for a predetermined period may be prepared in advance.

[0117] Furthermore, in the second embodiment, if it is desired to search for applicable insurance conditions, as shown in Figure 8, the maintenance work details may be requested from the reference information, and insurance conditions linked to the requested maintenance work details may be calculated. The maintenance work details referred to here are categories of what maintenance work is actually performed, and may include not only broad categories such as replacement, maintenance, repair, and exchange, but may also be limited to specifying which parts are to be repaired or replaced.

[0118] Furthermore, this maintenance work may be developed into, or replaced by, status summary information that actually summarizes the condition of the equipment. The status summary information referred to here is a classification of the actual condition of the equipment, classifying the degree of deterioration, the degree of equipment health, and the degree of maintenance or work required.

[0119] Such maintenance work details and status information may be classified and judged by experts or professionals in that field.

[0120] When determining insurance conditions, it is also possible to link insurance conditions to such maintenance work details and situation summary information, and output the insurance conditions linked to the determined maintenance work details and situation summary information.

[0121] In addition to the above, maintenance work details and status summary information are accumulated for a predetermined period. Then, statistical data such as the total number of times and averages for each type of maintenance work details and status summary information accumulated for the predetermined period can be obtained, and the applicable modified insurance conditions can be planned based on this data. Since maintenance costs are often related to such maintenance work details and status summary information, insurance conditions can also be narrowed down from this maintenance work details and status summary information. In any case, the method for calculating insurance conditions may be based on any well-known method. That is, insurance premiums and insurance conditions may be calculated using any well-known method, taking into account the relationship between the insurance premiums collected from businesses and the maintenance work details and status summary information, and the amount of work and costs based on them. When searching for insurance conditions, the system is not limited to the embodiments described above, and insurance conditions may be trained as an alternative to the maintenance work details as the output of the search solution in Figure 8. In such cases, the above-mentioned reference information and the actual insurance conditions at that time are obtained from the customer or business and these are used as a dataset for training. Applicable modified insurance conditions can also be searched in the same way by this method.

[0122] It should be noted that both the first and second embodiments are not limited to the embodiments described above. For example, as shown in Figure 9, it is also possible to utilize three or more levels of correlation between the key reference information and the service provider (in the case of the second embodiment, maintenance costs, maintenance methods, maintenance periods, maintenance frequency, maintenance work details, status summary information, insurance conditions, etc.). In such cases, the solution search will be performed based on three or more levels of correlation between the newly acquired reference information and the service provider. All of the above-mentioned reference information (reference equipment data, reference service provider status information, reference weather information, reference location information, reference traffic congestion information, reference external environment information, reference usage information, reference failure history information, reference equipment type information, reference customer preference information, reference atmosphere information, etc.) can be applied as the key reference information.

[0123] Similarly, in these cases, when information corresponding to the reference information used as training data is input, the solution search will be performed based on the method described above.

[0124] The search solution obtained through correlation may be further modified or its weighting changed based on other reference information.

[0125] The term "other reference information" as used herein refers to any reference information other than the primary reference information, provided that one of the aforementioned reference information sources is designated as the primary reference information.

[0126] For example, suppose that in the past, a certain reference weather information F has frequently identified company B. When new weather information corresponding to such reference weather information F is acquired, the system is pre-configured to increase the weight of the search solution B for company B, in other words, to make it more likely to lead to company search solution B.

[0127] For example, suppose reference information G is an analysis result that more strongly suggests search solution C as a vendor, and reference information F is an analysis result that more strongly suggests search solution D as a vendor. After setting up the relationships with the reference information in this way, if the information actually obtained is the same as or similar to reference information G, the weighting of vendor C is increased. Conversely, if the information actually obtained is the same as or similar to reference information F, the weighting of vendor D is increased. In other words, the degree of association with vendors itself may be controlled based on these reference information F to H. Alternatively, vendors may be determined solely by the aforementioned degree of association, and then the search solution obtained may be modified based on reference information F to H. In the latter case, how and with what weight the vendors as a search solution are modified based on reference information F to H will be reflected in the system design on a case-by-case basis.

[0128] Furthermore, the reference information is not limited to being composed of only one type; the solution search may be based on two or more types of reference information. Similarly, in such cases, the more the case leads to a company suggested by the reference information, the higher the classification type of the search solution obtained through the correlation degree may be modified.

[0129] Similarly, as shown in Figure 10, when forming the degree of association with a business for a combination of key reference information and other reference information, the key reference information can be any type of reference information (reference equipment data, reference business status information, reference weather information, reference location information, reference traffic congestion information, reference external environment information, reference usage information, reference failure history information, reference equipment type information, reference customer preference information, reference atmosphere information, etc.). The other reference information includes any reference information other than the key reference information.

[0130] In this case, if the primary reference information is reference equipment data, then any other reference information may be included.

[0131] In such cases, the contractor can be estimated by performing a solution search in the same manner. At this time, as shown in Figure 9 above, the contractor may be modified using further reference information (reference information F, G, H, etc.) in addition to the search solution obtained through the correlation degree.

[0132] In this case, the degree of association may be learned by combining not just one but two or more pieces of other reference information.

[0133] Furthermore, as shown in Figure 11, a degree of correlation may be formed between the vendor and only the basic reference information. This basic reference information can be any reference information from the first and second embodiments (reference equipment data, reference vendor status information, reference weather information, reference location information, reference traffic congestion information, reference external environment information, reference usage information, reference failure history information, reference equipment type information, reference customer preference information, reference atmosphere information, etc.). The solution search method in Figure 11 will be omitted below by referring to the explanation in Figure 3.

[0134] In addition, in the present invention, as shown in Figure 8, after searching for maintenance work details or situation summary information, the above-mentioned search solutions (contractor, maintenance cost, maintenance method, maintenance frequency, maintenance period, insurance conditions) may be obtained from the searched maintenance work details or situation summary information.

[0135] In such cases, the input may be maintenance work details or situation summary information, and the output may be each search solution (contractor, maintenance cost, maintenance method, maintenance period, maintenance frequency, insurance conditions), and the input and output may be associated and learned through the correlation degree described above. Then, as shown in Figure 8, after searching for the maintenance work details or situation summary information, by inputting this searched maintenance work details or situation summary information, it becomes possible to search for search solutions (contractor, maintenance cost, maintenance method, maintenance period, maintenance frequency, insurance conditions) in the same way as described above. In such cases, the first correlation degree of three or more levels between the above-mentioned reference information and the categorized maintenance work details or situation summary information is used to identify the maintenance work details or situation summary information based on the reference information corresponding to the acquired information. Next, the second correlation degree of three or more levels between the reference maintenance details or reference situation summary information acquired in the past and the search solutions (contractor, maintenance cost, maintenance method, maintenance period, maintenance frequency, insurance conditions) is used to find search solutions based on the reference maintenance details or reference situation summary information corresponding to the searched maintenance work details or situation summary information.

[0136] Furthermore, the present invention may also be used to train the system by training two or more of the search solutions (contractor, maintenance cost, maintenance method, maintenance period, maintenance frequency, insurance conditions, maintenance work details, and situation summary information) as a single search solution. In other words, the contractor and its maintenance cost may be trained as a single search solution. As a result, the contractor to be selected and the maintenance fee will be output as estimated results.

[0137] This allows for automated arrangements with contractors, where estimated contractors and maintenance fees can be inserted into the format of any of the electronic documents—such as quotations, request forms, completion reports, or invoices—to complete these documents. [Explanation of Symbols]

[0138] 1. Maintenance Contractor Selection System 2 Search device 21 Internal bus 23 Display section 24 Control Unit 25 Control section 26 Communications Department 27 Discrimination part 28 Memory section 61 nodes

Claims

1. An information acquisition step to obtain equipment data from the equipment to be maintained, The system includes a proposal step that proposes insurance conditions based on reference equipment data corresponding to the equipment data obtained in the above information acquisition step, utilizing reference equipment data obtained in the past that has been linked to insurance conditions at a level of three or more. In the above information acquisition step, we acquire information about the status of the contractors. In the above proposal step, the computer is instructed to propose insurance conditions based on the above-mentioned reference equipment data, the reference vendor status information regarding the status of the vendor, and the correlation degree of three or more levels between the vendor to be selected, and further based on the reference vendor status information corresponding to the vendor status information obtained in the above information acquisition step. The above correlation is composed of nodes in a neural network in artificial intelligence. An insurance terms proposal program characterized by the following.

2. An information acquisition step to obtain equipment data from the equipment to be maintained, The system includes a proposal step that proposes insurance conditions based on reference equipment data corresponding to the equipment data obtained in the above information acquisition step, utilizing reference equipment data obtained in the past that has been linked to insurance conditions at a level of three or more. In the above information acquisition step, we acquire information about the status of the contractors. In the above proposal step, priority is given to those with a higher degree of relevance, and the computer is instructed to propose insurance conditions based on the business status information obtained in the above information acquisition step. The above correlation is composed of nodes in a neural network in artificial intelligence. An insurance terms proposal program characterized by the following.

3. In a maintenance contractor selection program for selecting a company to perform maintenance on equipment, An information acquisition step to obtain information on the status of contractors who maintain the equipment, Using reference status information regarding the status of the service provider and a correlation level of three or more levels with the service provider to be selected, the computer is instructed to execute a proposal step that proposes insurance conditions based on the reference status information corresponding to the status information obtained in the above information acquisition step. The above correlation is composed of nodes in a neural network in artificial intelligence. An insurance terms proposal program characterized by the following.

Images