Operation analysis system

Abstract

This operation analysis system comprises: a production efficiency information map creation unit (231) that creates a production efficiency information map, which is an information map indicating the correspondence relationship between production efficiency information and operation-related information; a production efficiency feature amount calculation unit (233) that extracts, as elements, individual information related to the production efficiency information of a region of interest from a plurality of pieces of the operation-related information, and calculates, for all combinations of the operation-related information and the production efficiency information, the aggregate value of the production efficiency information for each element as a production efficiency feature amount; and a factor candidate extraction unit (234) that calculates, for all combinations of the operation-related information and the production efficiency information, the degree of deviation, which is an index for evaluating the difference in the production efficiency feature amount between the elements for each type of the operation-related information, and extracts the type of the operation-related information in descending order of the degree of deviation from all the combinations of the operation-related information and the production efficiency information of the region of interest. According to the operation analysis system, it is possible to reduce the burden on a user during introduction and analyze the cause of a decrease in the production efficiency of a facility.

Description

Operation Analysis System

[0001] The present disclosure relates to an operation analysis system that analyzes causes of declines in production efficiency of production equipment.

[0002] In factories, there is a need to improve product productivity by operating equipment such as processing machines. When producing products using equipment, various wastes or losses exist in the equipment's operating status that can reduce the equipment's productivity, i.e., various wastes or losses that can reduce the equipment's production efficiency. Therefore, in order to improve equipment productivity, it is necessary to detect the factors that reduce the equipment's production efficiency, identify the causes of those factors, and then take measures to reduce those factors. However, because various factors affect the equipment's operating status, it is difficult to identify the causes of factors that reduce the equipment's production efficiency.

[0003] Patent Document 1 describes a productivity improvement system that extracts problems in product production and estimates the causes of the problems based on an evaluation value for product production calculated based on performance data on production results in the product production process. The productivity improvement system described in Patent Document 1 stores in advance multiple scenarios including judgment formulas that determine the occurrence of factors that reduce product productivity based on multiple pieces of information such as the day of the week and working hours, and estimates the causes of problems in product production according to the scenarios.

[0004] Furthermore, the productivity improvement system described in Patent Document 1 stores in advance cause / measure data, which is information that indicates the correspondence between the causes of problems that may occur in product production at a facility such as a factory and effective measures for the problems. The productivity improvement system described in Patent Document 1 refers to the cause / measure data, and adopts, from among the measures previously set for each scenario, the measure that corresponds to the scenario identified as having the highest degree of suitability when the cause is estimated, to plan and present the measures to the user.

[0005] Japanese Patent Application Laid-Open No. 2023-119612

[0006] However, in the productivity improvement system described in the above-mentioned Patent Document 1, the user must prepare a plurality of scenarios and cause / measure data in advance and set them in the productivity improvement system, which places a heavy burden on the user.

[0007] Furthermore, factors that reduce productivity, as well as the causes and countermeasures for those factors, differ for each factory or facility. For this reason, the productivity improvement system described in Patent Document 1 requires the user to prepare multiple scenarios and cause / countermeasure data for each factory or facility in advance and set them in the productivity improvement system. However, if the user prepares multiple scenarios and cause / countermeasure data for each factory or facility in advance and sets them in the productivity improvement system, there is a problem in that it takes a lot of time and effort to introduce the productivity improvement system, which places a heavy burden on the user.

[0008] The present disclosure has been made in consideration of the above, and aims to provide an operation analysis system that places little burden on the user when installing and that is capable of analyzing the cause of a decline in production efficiency of equipment.

[0009] In order to solve the above-mentioned problems and achieve the objectives, the operation analysis system according to the present disclosure includes a production efficiency information map creation unit that creates a production efficiency information map, which is an information map in which the production efficiency information is displayed using two or more types of operation-related information as display axes and the correspondence between the production efficiency information and the operation-related information is shown, based on production efficiency information, which is information related to the production of products in the production equipment and serves as an index for evaluating the production efficiency of the products in the production equipment, and operation-related information, which is information related to the production of products in the production equipment and is candidate factors for causing a decrease in the production efficiency of the products in the production equipment, and a focus area acquisition unit that acquires focus area designation information, which is information that designates a focus area selected in the production efficiency information map. The operation analysis system includes a production efficiency feature calculation unit that extracts, as elements, individual pieces of information related to production efficiency information of a region of interest from a plurality of pieces of operation-related information, and calculates an aggregate value of the production efficiency information for each element as a production efficiency feature for all combinations of the operation-related information and the production efficiency information; and a factor candidate extraction unit that calculates a deviation, which is an index for evaluating differences in production efficiency feature values ​​between elements, for each type of operation-related information for all combinations of the operation-related information and the production efficiency information, and extracts types of operation-related information in descending order of deviation from all combinations of the operation-related information and the production efficiency information of the region of interest.

[0010] The present disclosure provides an advantageous effect of providing an operation analysis system that places little burden on the user when it is introduced and that is capable of analyzing the cause of a decline in production efficiency of equipment.

[0011] Diagram showing a configuration example of the operation analysis system according to Embodiment 1. Diagram showing an example of the configuration of the server included in the operation analysis system according to Embodiment 1. Diagram showing an example of the production efficiency information map created in the operation analysis system according to Embodiment 1. Diagram showing an example of the configuration of the terminal device included in the operation analysis system according to Embodiment 1. Flowchart showing an example of the processing of the operation analysis system according to Embodiment 1. First diagram showing an example of the concept of the method by which the factor candidate extraction unit of the operation analysis system according to Embodiment 1 calculates the degree of deviation for each type of operation-related information. Second diagram showing an example of the concept of the method by which the factor candidate extraction unit of the operation analysis system according to Embodiment 1 calculates the degree of deviation for each type of operation-related information. Diagram showing an example of the information on the production efficiency decrease factor candidates displayed on the display unit of the terminal device in the operation analysis system according to Embodiment 1. Flowchart showing an example of the processing of the operation analysis system according to Embodiment 2. Diagram showing an example of the concept of the method by which the factor candidate extraction unit of the operation analysis system calculates the degree of deviation in Embodiment 2. Flowchart showing an example of the processing of the operation analysis system according to Embodiment 3. Diagram showing an example of two focused areas specified in the production efficiency information map shown in FIG. 3. Diagram showing the production efficiency characteristic amount when the operation-related information is an operator for area A shown in FIG. 12. Diagram showing the production efficiency characteristic amount when the operation-related information is an operator for area B shown in FIG. 12. Diagram showing the production efficiency characteristic amount when the operation-related information is a day of the week for area A shown in FIG. 12. Diagram showing the production efficiency characteristic amount when the operation-related information is a day of the week for area B shown in FIG. 12. Flowchart showing an example of the processing of the operation analysis system according to Embodiment 4. Diagram showing an example of the production efficiency information map created by the operation analysis system in Embodiment 4. Diagram showing another example of the production efficiency information map created by the operation analysis system in Embodiment 4. Diagram showing a configuration in which the respective functions of the control units according to Embodiments 1 to 4 are realized by hardware. Diagram showing a configuration in which the respective functions of the control units according to Embodiments 1 to 4 are realized by software.

[0012] Hereinafter, the operation analysis system according to the embodiment will be described in detail based on the drawings.

[0013] First Embodiment. FIG. 1 is a diagram illustrating an example of the configuration of an operation analysis system according to a first embodiment. The operation analysis system 1 according to the first embodiment is a system that provides appropriate support for improving the productivity of products at a production facility 6 by helping a user identify factors that cause a decline in product production efficiency at the production facility 6, thereby reducing the user's workload during product production. The operation analysis system 1 automatically analyzes information related to the operation status of the production facility 6 during product production at the production facility 6 and presents the analysis results to the user as information on factors that cause a decline in the production efficiency of the production facility 6. As a result, the operation analysis system 1 helps the user identify factors that cause a decline in product production efficiency at the production facility 6, thereby reducing the user's workload in analyzing factors that cause a decline in the production efficiency of the production facility 6. Hereinafter, a "decline in product productivity at the production facility 6" may be simply referred to as a "decline in productivity." Hereinafter, a "decline in product production efficiency at the production facility 6" may be simply referred to as a "decline in production efficiency."

[0014] The user of the operation analysis system 1 according to the first embodiment is, for example, a manager who manages the production of products by the production equipment 6, and an analyst who analyzes the operating status of the production equipment 6, but the user is not limited to this.

[0015] As shown in FIG. 1 , the operation analysis system 1 according to the first embodiment includes a server 2 and a terminal device 3 .

[0016] In the operation analysis system 1, the server 2 is connected to the terminal device 3 so that they can communicate with each other via a network such as the Internet or an intranet, which is a global information communication network. In the first embodiment, the server 2 is connected to the terminal device 3 so that they can communicate with each other via the Internet 4. That is, the server 2 and the terminal device 3 are connected to the network and can send and receive information to and from each other. The communication between the server 2 and the terminal device 3 may be wireless communication or wired communication.

[0017] The server 2 is an operation analysis server that automatically analyzes information related to the past operating status of the production facility 6 and presents the analysis results to a user as information on factors causing a decline in the production efficiency of the production facility 6 in order to support work to improve the production efficiency of products at the production facility 6. The server 2 is a server built in a cloud environment 5. The cloud environment 5 includes computer resources provided in a cloud service platform. The cloud service platform is provided by a cloud service provider and includes, for example, PaaS (Platform as a Service). Because the server 2 is built in the cloud environment 5, it is sometimes called a cloud server. Note that an on-premise server may be used as the server 2.

[0018] A terminal device such as a desktop personal computer (PC) or a notebook PC is used as the terminal device 3. Note that a portable terminal device such as a tablet PC or a smartphone may also be used as the terminal device 3. The terminal device 3 is used by a user of the operation analysis system 1.

[0019] The configuration of the operation analysis system 1 will be described in more detail below.

[0020] The server 2 holds production efficiency information and operation-related information regarding past product production processes at the production facility 6 as information related to the operation status of product production at the production facility 6. The server 2 automatically analyzes information related to the past operation status of the production facility 6 using the production efficiency information and the operation-related information, and presents the analysis results to the user as information on factors behind the decline in production efficiency of the production facility 6.

[0021] The production efficiency information is information related to the production of products in the production facility 6, and serves as an index for evaluating the production efficiency of products in the production facility 6. The production efficiency information includes raw data acquired in the production of products in the production facility 6, and information obtained by processing the raw data. Furthermore, the production efficiency information is information that directly expresses waste or loss that is a factor in reducing the production efficiency of products in the production facility 6, and can be said to be information that serves as an index for evaluating the factors that reduce the production efficiency of the production facility 6.

[0022] The production efficiency information includes, for example, information such as "operation rate," "operational availability rate," "failure rate," "alert time rate," "basic unit," and "deviation from set value or standard processing time."

[0023] The "operation rate" is the ratio of the actual operation time of the production equipment 6 to the standard operation time.

[0024] The "availability rate" is the ratio of the time that the production equipment 6 was actually available to the total time that the production equipment 6 was in use.

[0025] The "failure rate" is the rate of defective products produced in the production facility 6.

[0026] The "alert time rate" is the ratio of the time during which an alert is issued during the production of a product in the production facility 6.

[0027] The "basic unit" is the amount of material or the amount of time used or discharged in the production facility 6 to produce a certain product.

[0028] The "deviation from the set value or standard processing time" is the ratio of the deviation from the set value or standard processing time set for the production equipment 6.

[0029] The operation-related information is information related to the production of products in the production facility 6, and is information that is a candidate for a factor in the decline in production efficiency of products in the production facility 6. The operation-related information includes raw data acquired during the production of products in the production facility 6. In other words, the operation-related information is information that does not directly express waste or loss that is a factor in the decline in production efficiency of products in the production facility 6, and is not an index for evaluating the factor in the decline in production efficiency of the production facility 6.

[0030] The operation-related information includes, for example, "worker information," "operation performance data," "processing performance data," "reference time," and "workpiece information."

[0031] "Worker information" is information about the workers who operated the production equipment 6 and the transition of workers.

[0032] The "operation record data" is the operation record data of the production equipment 6, and includes data such as the operation time, processing start time, processing end time, date, and day of the week when the production equipment 6 is in operation.

[0033] The "processing performance data" is processing performance data in the production equipment 6, and includes data such as processing parameters, processing programs, stop logs, and other status data when the production equipment 6 performs processing.

[0034] The "reference time" is the time it typically takes to produce a product in the production facility 6, and is also called the standard time.

[0035] "Information about workpiece" is information about the workpiece used in processing in the production facility 6, and includes data such as standard time, processing cost, material of the workpiece, and thickness of the workpiece.

[0036] FIG. 2 is a diagram illustrating an example of a configuration of a server included in the operation analysis system according to the first embodiment.

[0037] 2, the server 2 includes a server communication unit 21, a server storage unit 22, a server processing unit 23, and a server control unit 24. The above-described components of the server 2 can exchange information with each other.

[0038] The server communication unit 21 is connected to the Internet 4 and communicates with devices external to the server 2 via the Internet 4. The server communication unit 21 communicates with the terminal device 3 via the Internet 4.

[0039] The server storage unit 22 stores various types of information, such as information acquired from outside the server 2 and information created inside the server 2, as information used for analyzing information related to the past operating status of the production equipment 6 and for controlling the server 2. The server 2 stores an operation analysis server program, which is a program used for analyzing information related to the past operating status of the production equipment 6. The server storage unit 22 has an analysis data storage unit 221.

[0040] The analysis data storage unit 221 stores production efficiency information and operation-related information as information related to the past operating status of the production facility 6, which is used to analyze the causes of a decrease in production efficiency of the production facility 6.

[0041] The server processing unit 23 includes a production efficiency information map creation unit 231, a region of interest acquisition unit 232, a production efficiency feature quantity calculation unit 233, and a factor candidate extraction unit 234. The above-described components of the server processing unit 23 can exchange information with each other.

[0042] The production efficiency information map creation unit 231 acquires production efficiency information and operation-related information from the analysis data storage unit 221, and creates production efficiency information map data, which is data for displaying a production efficiency information map on the terminal device 3, based on the acquired production efficiency information and operation-related information. The production efficiency information map creation unit 231 stores the created production efficiency information map data in the analysis data storage unit 221 of the server storage unit 22. In addition, the production efficiency information map creation unit 231 transmits the created production efficiency information map data to the terminal device 3 via the server communication unit 21.

[0043] The production efficiency information map is an information map in which production efficiency information is displayed in association with operation-related information using two or more types of operation-related information as display axes, and the correspondence between the production efficiency information and the operation-related information is shown. In other words, the production efficiency information map is an information map in which the correspondence between production efficiency information and operation-related information is shown using two or more types of operation-related information as display axes. The production efficiency information map is data that displays one or more types of production efficiency information using multiple types of operation-related information, such as time of day and day of the week, as display axes.

[0044] 3 is a diagram showing an example of a production efficiency information map created in the operation analysis system according to the first embodiment. In the production efficiency information map 40 shown in FIG. 3, information on "operation rate," which is production efficiency information, is displayed in association with information on two types of operation-related information, "operation time" and "day of the week," and the correspondence between the operation-related information, "operation time" and "day of the week," and the production efficiency information, "operation rate," is shown. That is, in the production efficiency information map 40 shown in FIG. 3, the correspondence between the operation-related information, "operation time" and "day of the week," and the production efficiency information, "operation rate," is shown using the operation-related information, "operation time" and "day of the week," as display axes.

[0045] 3, the size of the circle indicates the magnitude of the value of the "operating rate," which is production efficiency information. This allows a user checking the production efficiency information map on the terminal device 3 to easily and visually grasp the bias in the "operating rate," which is production efficiency information.

[0046] The region-of-interest acquisition unit 232 acquires, from the terminal device 3 via the server communication unit 21, region-of-interest designation information that is information that designates the region of interest selected in the production efficiency information map.

[0047] The area-of-interest designation information is information that designates an area of ​​interest selected by a user in the production efficiency information map displayed by the production efficiency information map data. The area-of-interest designation information is input to the terminal device 3 by the user who has checked the production efficiency information map on the terminal device 3, and is transmitted from the terminal device 3 to the area-of-interest acquisition unit 232. The area-of-interest acquisition unit 232 acquires the area-of-interest designation information for one or more areas of interest from the terminal device 3. The area-of-interest acquisition unit 232 transmits the acquired area-of-interest designation information to the production efficiency feature quantity calculation unit 233.

[0048] The region of interest is a region in which a range of production efficiency information is specified in the production efficiency information map displayed by the production efficiency information map data. The region of interest is specified by the user, for example, in the production efficiency information map, it is a range of production efficiency information that the user wants to be the target of factor analysis of the decline in production efficiency of products in the production facility 6, and it is a range of production efficiency information in which the user wants to identify the factor of the decline in production efficiency.

[0049] For example, a user looking at the production efficiency information map 40 shown in Figure 3 can select an area corresponding to a time period or day of the week where circles with small production efficiency information values ​​are concentrated in the production efficiency information map 40 as the area of ​​interest 41. For example, if the user believes that the availability rate drops at similar times between 10:00 and 15:00 on each day of the week from Monday to Saturday, the user can select the range from 10:00 to 15:00 on Monday to Saturday as the area of ​​interest 41. The area of ​​interest can be selected by any method, such as by specifying a single circle in Figure 3 or by selecting the 15:00 hour period for a week.

[0050] The production efficiency feature quantity calculation unit 233 calculates the production efficiency feature quantity for the region of interest designation information. That is, the production efficiency feature quantity calculation unit 233 calculates the production efficiency feature quantity for the region of interest designated in the production efficiency information map. The production efficiency feature quantity calculation unit 233 extracts, as elements, individual pieces of information related to the production efficiency information of the region of interest from the plurality of pieces of operation-related information, and calculates, as the production efficiency feature quantity, an aggregate value of the production efficiency information for each element for all combinations of the operation-related information and the production efficiency information.

[0051] The production efficiency feature amount is calculated based on the production efficiency information of the target area, and serves as an index for evaluating the production efficiency of the production facility 6 .

[0052] The production efficiency feature quantity calculation unit 233 acquires area-of-interest designation information from the area-of-interest acquisition unit 232. The production efficiency feature quantity calculation unit 233 extracts one or more elements of operation-related information related to the production efficiency information of the area of ​​interest designated in the area-of-interest designation information. The production efficiency feature quantity calculation unit 233 extracts one or more elements of operation-related information for each piece of operation-related information from the plurality of pieces of operation-related information.

[0053] Specifically, the production efficiency feature quantity calculation unit 233 first acquires operation-related information related to the production efficiency information of the region of interest from the analysis data storage unit 221. The production efficiency feature quantity calculation unit 233 can acquire the operation-related information from the analysis data storage unit 221 based on, for example, predetermined operation-related information acquisition conditions. Note that the method by which the production efficiency feature quantity calculation unit 233 acquires operation-related information related to the production efficiency information of the region of interest specified in the production efficiency information map is not limited to the method using the operation-related information acquisition conditions.

[0054] The operation-related information acquisition conditions are conditions under which the production efficiency feature quantity calculation unit 233 acquires operation-related information related to the production efficiency information of a region of interest specified in the production efficiency information map from the various types of operation-related information stored in the analysis data storage unit 221. The operation-related information acquisition conditions are determined in advance by the user and stored in the production efficiency feature quantity calculation unit 233. For example, the user can set information that associates information on the types of operation-related information that may be factors that cause fluctuations in the production efficiency information with the production efficiency information as the operation-related information acquisition conditions for each piece of production efficiency information.

[0055] Next, the production efficiency feature quantity calculation unit 233 extracts one or more elements of each piece of operation-related information from the acquired plurality of pieces of operation-related information.

[0056] An element of operation-related information is individual information related to the production efficiency information of the target area in each piece of operation-related information, and is a specific item included in each type of operation-related information. An element of operation-related information is a specific subordinate concept of each type of operation-related information. For example, if the type of operation-related information is "worker," specific worker names such as "worker A, worker B, worker C, ..." are exemplified as elements of the operation-related information. If the type of operation-related information is "day of the week," specific days of the week such as "Monday, Tuesday, ..." are exemplified as elements of the operation-related information. If the type of operation-related information is "time of day," specific times such as "8:00, 9:00, 10:00, ..." are exemplified as elements of the operation-related information. Hereinafter, "elements of operation-related information" may be simply referred to as "elements."

[0057] Next, the production efficiency feature calculation unit 233 acquires the production efficiency information of the area of ​​interest from the analysis data storage unit 221, and aggregates the production efficiency information of the area of ​​interest for each element of the operation-related information for all combinations of the extracted elements of the operation-related information and the production efficiency information of the area of ​​interest.

[0058] Aggregating production efficiency information for a region of interest means calculating aggregate values ​​for the target production efficiency information according to a predetermined calculation method. Examples of aggregation methods for production efficiency information for a region of interest include methods for calculating statistical quantities such as the mean, median, standard deviation, variance, maximum value, and minimum value for the target production efficiency information. Furthermore, if the elements of the operation-related information have a hierarchical structure, the production efficiency feature quantity calculation unit 233 may aggregate the production efficiency information for each hierarchical level of the elements of the operation-related information. An example of the hierarchical structure of the elements of the operation-related information is a hierarchical structure of control programs and subprograms of the control programs, which are elements of the operation-related information.

[0059] It should be noted that the aggregation method used when aggregating the production efficiency information of the area of ​​interest is not limited to one; for example, for the worker, which is operation-related information, multiple aggregations may be performed for each element of the production efficiency information, such as the average value, median, and standard deviation.

[0060] Next, the production efficiency feature quantity calculation unit 233 normalizes the aggregated value of the production efficiency information of the region of interest for each element of the operation-related information that has been aggregated for all combinations of the elements of the operation-related information and the production efficiency information of the region of interest. The production efficiency feature quantity calculation unit 233 normalizes the extracted aggregated value by converting the aggregated value so that the range is, for example, from 0 to 1.

[0061] Then, the production efficiency feature quantity calculation unit 233 acquires the normalized aggregated value as the production efficiency feature quantity. Through the above processing, the production efficiency feature quantity calculation unit 233 can calculate the production efficiency feature quantity for each element of the operation-related information for all combinations of the elements of the operation-related information and the production efficiency information of the region of interest.

[0062] The normalization of the aggregated values ​​is performed to facilitate comparison of variations in the aggregated values ​​between different types of production efficiency information. In other words, by using the normalized aggregated values ​​as the production efficiency feature quantities for each element of the operation-related information, it becomes possible to compare variations and deviations in the production efficiency feature quantities when comparing multiple different types of production efficiency information.

[0063] The production efficiency feature calculation unit 233 transmits to the factor candidate extraction unit 234 the area of ​​interest designation information acquired from the area of ​​interest acquisition unit 232, information on the type of operation-related information acquired from the analysis data storage unit 221 based on the area of ​​interest designation information, information on the elements of the operation-related information extracted from the operation-related information acquired from the analysis data storage unit 221, and information on each production efficiency feature for all combinations of the extracted elements of the operation-related information and the production efficiency information of the area of ​​interest.

[0064] The factor candidate extraction unit 234 extracts candidate factors for production efficiency decline from among all combinations of operation-related information and production efficiency information of the region of interest, based on the degree of deviation found from the production efficiency feature amount calculated by the production efficiency feature amount calculation unit 233. The factor candidate extraction unit 234 calculates the degree of deviation for each type of operation-related information for all combinations of operation-related information and production efficiency information, and extracts operation-related information from among all combinations of operation-related information and production efficiency information of the region of interest in descending order of the degree of deviation.

[0065] The candidate factors for the decline in production efficiency are candidate factors for the decline in production efficiency of the production equipment 6 that are analyzed by the operation analysis system 1.

[0066] The deviation is an index for evaluating the difference in production efficiency feature values ​​between a plurality of pieces of operation-related information. In the first embodiment, the deviation is the degree of prominence of the production efficiency feature value of an element having a significantly larger or smaller production efficiency feature value than other elements among a plurality of elements of operation-related information included in each type of operation-related information. In other words, the deviation is a value obtained by evaluating the difference between a plurality of production efficiency feature values ​​based on the magnitude relationship between the plurality of production efficiency feature values.

[0067] "Significantly" means that the deviation meets a predetermined standard. The predetermined standard may be, for example, a standard such as ±3σ or a significant difference that can be measured using general statistics and set in the factor candidate extraction unit 234 in advance, or may be determined based on statistics of production efficiency feature quantities. A method for calculating the deviation will be described later.

[0068] Specifically, the factor candidate extraction unit 234 calculates the degree of deviation for each type of operation-related information for all combinations of operation-related information and production efficiency information of the target area based on the production efficiency feature amount calculated by the production efficiency feature amount calculation unit 233. Then, the factor candidate extraction unit 234 extracts, as candidate factors for production efficiency decline, a predetermined number of types of operation-related information in descending order of deviation from all combinations of operation-related information and production efficiency information of the target area, i.e., from the plurality of pieces of operation-related information for which deviation amounts have been calculated. When the predetermined number is K, the factor candidate extraction unit 234 extracts the top K types of operation-related information with the highest deviation amounts from all types of operation-related information for which deviation amounts have been calculated.

[0069] The factor candidate extraction unit 234 stores information on the candidate factors of production efficiency reduction for each of the top K pieces of operation-related information of the extracted type in the server storage unit 22. In addition, the factor candidate extraction unit 234 transmits the information on the candidate factors of production efficiency reduction to the terminal device 3 via the server communication unit 21.

[0070] Here, the information on the candidate factors of the decline in production efficiency includes "information on the type of operation-related information," "information on the degree of deviation in the operation-related information," and "information on the name of an element, among the multiple elements in the operation-related information, that has a significantly prominent deviation in production efficiency feature value from other elements."

[0071] An example of "information on the type of operation-related information" is information such as "worker." An example of "information on the degree of deviation in the operation-related information" is information such as "the degree of deviation for the worker is 0.9." An example of "information on the names of elements that have a significantly high deviation in production efficiency feature amount from other elements among multiple elements in the operation-related information" is information such as "worker B and worker D."

[0072] The terminal device 3 is a device that presents various types of information of the operation analysis system 1 to the user. The terminal device 3 displays the production efficiency information map created by the production efficiency information map creation unit 231 of the server processing unit 23 of the server 2, and accepts attention area designation information that designates an attention area in the production efficiency information map. The user can use the terminal device 3 to view the production efficiency information map created by the production efficiency information map creation unit 231 of the server processing unit 23 of the server 2. The user can also use the terminal device 3 to view information on candidate factors for production efficiency decline created by the candidate factor extraction unit 234 of the server processing unit 23 of the server 2.

[0073] Fig. 4 is a diagram illustrating an example of the configuration of a terminal device included in the operation analysis system according to the first embodiment. As illustrated in Fig. 4, the terminal device 3 includes an input unit 31, a display unit 32, a terminal communication unit 33, a terminal storage unit 34, and a terminal control unit 35. Information can be exchanged between the components of the terminal device 3.

[0074] The input unit 31 is a functional unit that is operated by a user when using the operation analysis system 1. The user performs various operations using the input unit 31 on the operation screen of the operation analysis system 1 displayed on the display unit 32. The input unit 31 accepts information input by the user and transmits input information corresponding to the information to the terminal control unit 35.

[0075] The display unit 32 displays information about operations performed on the input unit 31 and information about the analysis function of candidate factors for reducing production efficiency performed by the operation analysis system 1. The display unit 32 is a display device such as an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display.

[0076] The terminal communication unit 33 communicates with the server communication unit 21 of the server 2 .

[0077] The terminal memory unit 34 is a memory unit that stores information used in the operation analysis system 1, and stores information used to control the terminal device 3, information input in the input unit 31, and information obtained from the server 2.

[0078] The terminal control unit 35 is a control unit that controls the overall processing of the terminal device 3. The terminal control unit 35 transmits input information received from the input unit 31 to the server processing unit 23 of the server 2. The terminal control unit 35 transmits input information corresponding to the operation content operated by the user on the operation screen of the operation analysis system 1 displayed on the display unit 32 of the terminal device 3 to the server processing unit 23 of the server 2, obtains screen data corresponding to the user's operation content from the server processing unit 23, and displays it on the display unit 32.

[0079] Next, the operation of the operation analysis system 1 according to the first embodiment will be described with reference to a flowchart of FIG. 5. FIG.

[0080] In step S110, a production efficiency information map is created. Specifically, the production efficiency information map creating unit 231 of the server processing unit 23 of the server 2 creates the production efficiency information map.

[0081] The user inputs analysis instruction information that instructs an analysis of the causes of a decline in production efficiency as input to the input unit 31 on the operation screen of the operation analysis system 1 displayed on the display unit 32 of the terminal device 3. The production efficiency information map creation unit 231 creates a production efficiency information map based on the user's analysis instruction information input from the terminal device 3. That is, the production efficiency information map creation unit 231 acquires production efficiency information and operation-related information from the analysis data storage unit 221, and creates production efficiency information map data that is data for displaying the production efficiency information map based on the acquired production efficiency information and operation-related information.

[0082] In the first embodiment, the production efficiency information map creation unit 231 acquires one type of production efficiency information and two types of operation-related information from the analysis data storage unit 221 based on, for example, predetermined map creation conditions, and creates a production efficiency information map based on the acquired information. That is, the production efficiency information map creation unit 231 creates a production efficiency information map for a predetermined combination of production efficiency information and operation-related information. As shown in FIG. 3 , for example, information on "operation rate," which is one type of production efficiency information, is displayed in association with information on two types of operation-related information, "operation time" and "day of the week," and the production efficiency information map creates a production efficiency information map that shows the correspondence between the operation-related information, "operation time" and "day of the week," and the production efficiency information, "operation rate."

[0083] The map creation conditions are information that specifies one type of production efficiency information and two types of operation-related information that are used when the production efficiency information map creation unit 231 creates a production efficiency information map. The map creation conditions include one or more sets of information that combines one type of production efficiency information and two types of operation-related information. The map creation conditions are determined in advance and stored in the production efficiency information map creation unit 231.

[0084] The user can set, as the map creation conditions, information on any combination of production efficiency information and operation-related information that the user wants to analyze for factors of a decline in production efficiency. For example, the user can set, as the map creation conditions, information on a combination of production efficiency information and operation-related information based on tacit knowledge, and can set, as the map creation conditions, information on a combination of production efficiency information and operation-related information that is suitable for analyzing factors of a decline in production efficiency. This allows the production efficiency information map creation unit 231 to create, based on tacit knowledge, a production efficiency information map that is suitable for analyzing factors of a decline in production efficiency.

[0085] The production efficiency information map creating unit 231 creates a production efficiency information map for the set included in the map creation conditions.

[0086] Then, the production efficiency information map creation unit 231 transmits the created production efficiency information map data to the terminal control unit 35 of the terminal device 3 via the server communication unit 21. The terminal control unit 35 receives the production efficiency information map data transmitted from the production efficiency information map creation unit 231 via the terminal communication unit 33. Then, the process proceeds to step S120.

[0087] In step S120, the region-of-interest designation information is acquired. Specifically, the region-of-interest acquisition unit 232 of the server processing unit 23 of the server 2 acquires the region-of-interest designation information.

[0088] When the terminal control unit 35 of the terminal device 3 receives the production efficiency information map data, it uses the production efficiency information map data to display the production efficiency information map on the display unit 32, and presents the production efficiency information map to the user. After checking the production efficiency information map displayed on the display unit 32, the user selects one area of ​​interest on the production efficiency information map, and inputs area of ​​interest designation information for the selected area of ​​interest into the terminal device 3 using the input unit 31 of the terminal device 3. The terminal control unit 35 transmits the input area of ​​interest designation information to the area of ​​interest acquisition unit 232.

[0089] The region of interest acquisition unit 232 acquires the region of interest designation information by receiving the region of interest designation information transmitted from the terminal device 3. The region of interest acquisition unit 232 transmits the acquired region of interest designation information to the production efficiency feature amount calculation unit 233 of the server processing unit 23 of the server 2. The production efficiency feature amount calculation unit 233 receives the region of interest designation information transmitted from the region of interest acquisition unit 232. Then, the process proceeds to step S130.

[0090] In steps S130 to S150, the production efficiency feature amount is calculated based on the region-of-interest designation information. Specifically, the production efficiency feature amount calculation unit 233 of the server processing unit 23 of the server 2 calculates the production efficiency feature amount for the region of interest designated in the production efficiency information map based on the region-of-interest designation information.

[0091] In step S130, elements of the operation-related information are extracted. When the production efficiency feature quantity calculation unit 233 acquires the area-of-interest designation information, it acquires multiple pieces of operation-related information related to the production efficiency information of the area of ​​interest designated in the area-of-interest designation information from the analysis data storage unit 221. The production efficiency feature quantity calculation unit 233 then extracts one or more elements of the operation-related information from each of the acquired pieces of operation-related information. Then, the process proceeds to step S140.

[0092] In step S140, the production efficiency information of the target area is compiled for each element of the operation-related information. The production efficiency feature quantity calculation unit 233 compiles the production efficiency information of the target area for each element of the operation-related information for all combinations of the elements of the operation-related information extracted in step S130 and the production efficiency information of the target area. Then, the process proceeds to step S150.

[0093] In step S150, the aggregated values ​​are normalized. The production efficiency feature quantity calculation unit 233 normalizes the aggregated value of the production efficiency information of the region of interest for each element of the aggregated operation-related information for all combinations of the elements of the operation-related information and the production efficiency information of the region of interest.

[0094] Then, the production efficiency feature quantity calculation unit 233 acquires the normalized aggregated value as the production efficiency feature quantity. Through the above processing, the production efficiency feature quantity calculation unit 233 calculates the production efficiency feature quantity for each element of the operation-related information for all combinations of the elements of the operation-related information and the production efficiency information of the target area. Then, the process proceeds to step S160.

[0095] In step S160, the degree of deviation of the production efficiency feature amount is calculated for each type of operation-related information. The factor candidate extraction unit 234 calculates the degree of deviation for each type of operation-related information based on the production efficiency feature amount calculated by the production efficiency feature amount calculation unit 233 for all combinations of the operation-related information and the production efficiency information of the target area.

[0096] A method for calculating the degree of deviation for each type of operation-related information will be described. The degree of deviation for each type of operation-related information may be any value that can highlight and evaluate differences in production efficiency feature amounts of the same type of operation-related information between elements of the operation-related information. In the first embodiment, for example, the maximum value of differences in production efficiency feature amounts between elements of the same operation-related information is calculated, and the maximum value of differences in production efficiency feature amounts between the elements can be used as the degree of deviation for each type of operation-related information.

[0097] Examples of a calculation method for calculating the degree of deviation for each type of operation-related information from the production efficiency feature for each element of the operation-related information include methods for calculating values ​​such as the difference between production efficiency feature values, the percentage of the difference between production efficiency feature values, the difference from a representative value representing the production efficiency feature values, and the percentage of the difference from a representative value representing the production efficiency feature values, for elements of the type of operation-related information in question. Examples of representative values ​​include the average, median, and various percentiles as simple statistics. Alternatively, a representative value representing the production efficiency feature values ​​may be calculated and further aggregated using statistics to calculate the difference. Alternatively, the production efficiency feature values ​​of multiple elements of operation-related information may be relatively ranked, and the difference in the rankings may be calculated as the degree of deviation.

[0098] Furthermore, the production efficiency feature may be further aggregated for each element, and the above statistics may be calculated for each element, and then a similar comparison may be performed to calculate the deviation. For example, if there are six elements "worker" from worker A to worker F, the production efficiency feature for each worker may be calculated, and then all combinations ( ６ C ２ The difference itself may be used as the deviation, or the differences may be ranked relatively and the difference in rank may be used as the deviation.

[0099] Regardless of which calculation method is used, the value obtained by evaluating the difference between elements of a plurality of production efficiency feature quantities based on the magnitude relationship between the plurality of production efficiency feature quantities is the degree of deviation for each type of operation-related information in embodiment 1.

[0100] There are production efficiency feature quantities that, when larger than the production efficiency feature quantities of other elements in the same operation-related information, will have an impact on a decline in the production efficiency of the production equipment 6, and conversely, there are production efficiency feature quantities that, when smaller than the production efficiency feature quantities of other elements in the same operation-related information, will have an impact on a decline in the production efficiency of the production equipment 6. For example, a production efficiency feature quantity for an availability rate has a smaller impact on a decline in the production efficiency of the production equipment 6. Conversely, a production efficiency feature quantity for a failure rate has a larger impact on a decline in the production efficiency of the production equipment 6. Such a relationship between the magnitude of a production efficiency feature quantity and a decline in the production efficiency of the production equipment 6 is self-evident in many cases.

[0101] Similarly, with regard to the method of aggregating production efficiency feature quantities, the magnitude of the aggregated value is related to the decline in production efficiency of the production equipment 6. For example, the relationship between the average value of the production efficiency feature quantities, the maximum value of the production efficiency feature quantities, and the minimum value of the production efficiency feature quantities and the decline in production efficiency of the production equipment 6 is basically the same as that of the original production efficiency information before aggregation. On the other hand, with regard to the standard deviation of the production efficiency feature quantities, a larger value has a stronger influence on the decline in production efficiency of the production equipment 6 than a smaller value.

[0102] Therefore, in the operation analysis system 1, information regarding the relationship between each value of the production efficiency information and the method of aggregating the production efficiency information and the decline in production efficiency of the production equipment 6 is stored in advance in the production efficiency feature calculation unit 233 as attribute information.

[0103] The attribute information is information relating to the relationship between each value of the production efficiency information and each method of aggregating the production efficiency information and the decline in production efficiency of the production equipment 6. An example of the attribute information is information such as "when the production efficiency feature value of the failure rate is larger than the production efficiency feature values ​​of other elements in the failure rate, it affects the decline in productivity" and "when the production efficiency feature value of the operation rate is smaller than the production efficiency feature values ​​of other elements in the operation rate, it affects the decline in productivity."

[0104] As mentioned above, these attribute information items are basically self-evident and fixed, and do not require trial and error during design or maintenance during operation, as do the scenarios and tables used in the technology of Patent Document 1.

[0105] Furthermore, when calculating the deviation, the direction of the deviation is also taken into consideration. For example, if the deviation is in the direction of a decline in the production efficiency of the production equipment 6, the deviation is calculated as a positive value. On the other hand, if the deviation is in the direction opposite to the direction of a decline in production efficiency, the deviation is calculated as a negative value. The positive or negative value of the deviation value corresponds to whether the evaluation of the deviation is meaningful in assessing the decline in production efficiency of the production equipment 6. A positive deviation value is a deviation that is meaningful in assessing the decline in production efficiency of the production equipment 6. A negative deviation value is a deviation that is meaningless in assessing the decline in production efficiency of the production equipment 6.

[0106] When considering workers as operation-related information, if all workers can exhibit uniformly high work performance, the production efficiency of the production equipment 6 is considered to be high, and the worker deviation will be small. For example, if there is one novice worker among multiple skilled workers, the deviation will be calculated as a positive value. In this case, only the novice worker will exhibit low work performance, so evaluating the deviation in evaluating the production efficiency of the production equipment 6 is meaningful from the perspective of productivity decline.

[0107] Conversely, if there is only one skilled worker among multiple novice workers, the deviation is calculated as a negative value. In this case, since only one skilled worker demonstrates high work performance, the deviation is considered to be meaningless in terms of productivity decline when evaluating the production efficiency of the production facility 6. For this reason, the deviation is calculated as a negative value.

[0108] FIG. 6 is a first diagram illustrating an example of the concept of a method in which the factor candidate extraction unit of the operation analysis system according to the first embodiment calculates the degree of deviation for each type of operation-related information. FIG. 7 is a second diagram illustrating an example of the concept of a method in which the factor candidate extraction unit of the operation analysis system according to the first embodiment calculates the degree of deviation for each type of operation-related information. The horizontal axes of the graphs illustrated in FIGS. 6 and 7 represent worker names, which are elements of the operation-related information. The vertical axes of the graphs illustrated in FIGS. 6 and 7 represent production efficiency feature amounts for each worker name. The production efficiency feature amount is, for example, a normalized average value of the operation rate, which is production efficiency information. In the graphs illustrated in FIGS. 6 and 7, the value of the production efficiency feature amount for worker D on the vertical axis is "1," and the bottom of the vertical axis is normalized to "0." Then, the degree of deviation for each type of operation-related information is calculated based on the graphs illustrated in FIGS. 6 and 7.

[0109] In the graph shown in Fig. 6, there is little deviation when comparing the production efficiency feature values ​​of different workers. That is, when worker B, whose production efficiency feature value is the smallest, is used as the reference, there is little deviation between the production efficiency feature value of worker D, whose production efficiency feature value is the largest, and the production efficiency feature value of worker B. The graph shown in Fig. 6 corresponds to a case where the cause of the decrease in the operating rate, which is production efficiency information, is not the work performance of each worker, but is due to a cause other than the worker.

[0110] In the graph shown in FIG. 7 , when workers C and F, whose production efficiency feature values ​​are the smallest, are used as the reference, the deviation of the production efficiency feature values ​​for specific workers B and D is large. The difference in production efficiency feature value between workers C and F, whose difference in production efficiency feature value between workers is the largest, and worker D is set as the deviation degree when the operation-related information is a worker. That is, the factor candidate extraction unit 234 calculates the difference in production efficiency feature value between workers, which is the difference in production efficiency feature value between elements, calculates the maximum value of the difference in production efficiency feature value between elements, and sets this maximum value of the difference in production efficiency feature value between elements as the deviation degree. The graph shown in FIG. 7 corresponds to a case where specific workers B and D are responsible for the decrease in production efficiency.

[0111] 6 and 7 are shown for explaining the concept of the method for calculating the deviation, and the factor candidate extraction unit 234 may calculate the deviation without creating graphs such as those shown in Figures 6 and 7. Furthermore, the factor candidate extraction unit 234 can transmit graphs comparing production efficiency feature quantities for each element of operation-related information to the terminal device 3 as shown in Figures 6 and 7, and present the graphs to the user together with information on the candidate factors for production efficiency decline.

[0112] The factor candidate extraction unit 234 calculates the difference in production efficiency feature values ​​between workers, which is the difference in production efficiency feature values ​​between elements, for operation-related information other than workers for all combinations of operation-related information and production efficiency information of the region of interest, and calculates the maximum value of the differences in production efficiency feature values ​​between elements, thereby similarly calculating the degree of deviation of the production efficiency feature values ​​for each type of operation-related information. Then, the process proceeds to step S170.

[0113] In step S170, candidate factors for production efficiency reduction are extracted. The candidate factor extraction unit 234 extracts a predetermined number of types of operation-related information as candidate factors for production efficiency reduction from all combinations of operation-related information and production efficiency information of the target area, i.e., from the multiple pieces of operation-related information for which the deviation degrees have been calculated, in descending order of deviation degree. The candidate factor extraction unit 234 stores information on candidate factors for production efficiency reduction for each of the extracted types of operation-related information in the server storage unit 22. The candidate factor extraction unit 234 also transmits information on candidate factors for production efficiency reduction to the terminal device 3 via the server communication unit 21. The terminal device 3 receives the information on candidate factors for production efficiency reduction transmitted from the candidate factor extraction unit 234. Thereafter, the process proceeds to step S180.

[0114] In step S180, information on the candidate factors for reducing production efficiency is displayed. When the terminal control unit 35 of the terminal device 3 receives the information on the candidate factors for reducing production efficiency transmitted from the candidate factor extraction unit 234, the terminal control unit 35 displays the information on the candidate factors for reducing production efficiency on the display unit 32, thereby presenting the candidate factors for reducing production efficiency to the user.

[0115] FIG. 8 is a diagram illustrating an example of information about candidate factors for reducing production efficiency displayed on a display unit of a terminal device in the operation analysis system according to the first embodiment. The information about candidate factors for reducing production efficiency is displayed in descending order of deviation. The information about candidate factors for reducing production efficiency includes "information about the ranking of deviation magnitude," "information about the type of operation-related information," "information about deviation degree," and "information about the name of an element, among the multiple elements in the operation-related information, whose deviation in production efficiency feature value from other elements is significantly prominent." In the example of information about candidate factors for reducing production efficiency shown in FIG. 8 , the information about the candidate factor for reducing production efficiency with the largest deviation degree includes "1" as "information about the ranking of deviation magnitude," "worker" as "information about the type of operation-related information," "0.9" as "information about deviation degree," and "worker B and worker D" as "information about the name of an element, among the multiple elements in the operation-related information, whose deviation in production efficiency feature value from other elements is significantly prominent." In FIG. 8, the name of an element in which the deviation of the production efficiency feature amount from other elements among the multiple elements in the operation-related information is significantly outstanding is abbreviated as the "significantly outstanding element."

[0116] When the user checks the candidate factors of production efficiency reduction displayed on the display unit 32 in step S180, the user may think that the candidate factors of production efficiency reduction do not include factors that contribute to improving the production efficiency of the production facility 6. In this case, the user inputs change instruction information for the candidate factors of production efficiency reduction, which instructs the user to change the candidate factors of production efficiency reduction, to the terminal device 3 using the input unit 31 of the terminal device 3. The terminal control unit 35 transmits the input change instruction information for the candidate factors of production efficiency reduction to the candidate factor extraction unit 234.

[0117] When the candidate factor extraction unit 234 receives change instruction information for the candidate factors of production efficiency reduction, it presents to the user candidate factors of production efficiency reduction that are different from the candidate factors of production efficiency reduction that were previously transmitted to the terminal control unit 35 of the terminal device 3. The candidate factor extraction unit 234 presents to the user candidate factors of production efficiency reduction that have the next largest deviation from the candidate factors of production efficiency reduction that were previously transmitted to the terminal control unit 35 of the terminal device 3.

[0118] According to the operation analysis system 1 of the first embodiment described above, the production efficiency information map creation unit creates a production efficiency information map, which is an information map in which the production efficiency information is displayed using two or more types of operation-related information as display axes and shows the correspondence between the production efficiency information and the operation-related information, based on production efficiency information, which is information related to the production of products in the production facility and serves as an index for evaluating the production efficiency of the products in the production facility, and operation-related information, which is information related to the production of products in the production facility and serves as a candidate for a cause of a decrease in the production efficiency of the products in the production facility; and an attention area designation information unit, which is information for designating an attention area selected in the production efficiency information map. an operation analysis system comprising: an area of ​​interest acquisition unit that acquires information; a production efficiency feature calculation unit that extracts individual pieces of information related to the production efficiency information of the area of ​​interest from a plurality of pieces of operation-related information as elements, and calculates an aggregate value of the production efficiency information for each element as a production efficiency feature for all combinations of the operation-related information and the production efficiency information; and a factor candidate extraction unit that calculates a deviation, which is an index for evaluating the difference in production efficiency feature between elements, for each type of operation-related information for all combinations of the operation-related information and the production efficiency information, and extracts types of operation-related information in descending order of deviation from all combinations of the operation-related information and the production efficiency information of the area of ​​interest.

[0119] As described above, the operation analysis system 1 according to the first embodiment automatically analyzes and estimates factors for a decline in production efficiency of the production equipment 6 based on bias in production efficiency feature quantities for elements of operation-related information related to production efficiency information of a target area. As a result, the operation analysis system 1 can present to the user appropriate candidates for factors for a decline in production efficiency of the production equipment 6 that have been analyzed based on the production efficiency information and operation-related information, without using prior information such as a scenario and cause / measure data as disclosed in Patent Document 1.

[0120] That is, the operation analysis system 1 can automatically analyze the causes of a decline in product production efficiency at the production facility 6 by combining statistical processing that combines production efficiency information such as the availability rate, which is a production efficiency index of the production facility 6, which is equipment for producing products, with operation-related information such as people, things, and information involved in the production of products at the production facility 6, and interactive information input by the user. As a result, the operation analysis system 1 can automatically identify various waste or loss factors that contribute to a decline in product production efficiency at the production facility 6 and present them to the user, without using prior knowledge of the causes of the decline in production efficiency of the production facility 6.

[0121] Furthermore, the operation analysis system 1 estimates factors that cause declines in product productivity at the production facility 6 based on biases in production efficiency feature quantities for each element of operation-related information, and therefore can estimate various factors of waste or loss that cause declines in product production efficiency at the production facility 6 without the user having to prepare in advance information such as scenarios and cause / measure data as shown in Patent Document 1. This allows the operation analysis system 1 to reduce the user's effort when being introduced.

[0122] Furthermore, in the operation of the production facility 6, new factors that reduce production efficiency may arise due to changes in the operation of the production facility 6 or the production facility 6, and changes in the products produced, resulting from improvements to the production facility 6 and the work methods for producing products at the production facility 6. Maintaining advance information such as scenarios and cause / measure data as shown in Patent Document 1 in response to such changes in the environment in the operation of the production facility 6 also leads to increased workload in operating the system.

[0123] On the other hand, since the operation analysis system 1 does not use prior information such as scenarios and cause / countermeasure data as shown in Patent Document 1, there is no increase in operational effort due to changes in the operating environment of the production equipment 6.

[0124] Furthermore, the operation analysis system 1 includes a terminal device 3 as an interactive interface with the operation analysis system 1, and is able to incorporate the user's knowledge and judgment into the estimation of the causes of the decline in product production efficiency at the production facility 6. This allows the operation analysis system 1 to reflect the user's knowledge based on their experience as tacit knowledge in the estimation of the causes of the decline in product production efficiency at the production facility 6, improving the accuracy of the estimation of the causes of the decline in product production efficiency at the production facility 6.

[0125] Therefore, the operation analysis system 1 according to the first embodiment has the effect of providing an operation analysis system that places little burden on the user in the implementation and is capable of analyzing the cause of a decline in production efficiency of the production equipment 6.

[0126] Second Embodiment In the second embodiment, other functions of the operation analysis system 1 according to the first embodiment will be described. In the second embodiment, the operation analysis system 1 performs a multi-axis evaluation in which a process of calculating a production efficiency feature is performed for a combination of two or more aggregation methods to calculate a deviation. In the second embodiment, the production efficiency feature calculation unit 233 calculates, as a production efficiency feature, an aggregated value of production efficiency information for each element of operation-related information for a combination of two or more aggregation methods. Also, in the second embodiment, the factor candidate extraction unit 234 calculates a deviation for each type of operation-related information for each combination of aggregation methods.

[0127] Hereinafter, details of the processing of the operation analysis system 1 according to the second embodiment will be described with reference to a flowchart. Fig. 9 is a flowchart showing an example of the processing of the operation analysis system according to the second embodiment.

[0128] First, steps S110 to S130 are performed, and then the process proceeds to step S210. In the second embodiment, the production efficiency feature is calculated in steps S130, S210, and S220.

[0129] In step S210, the production efficiency information of the target area is tallied for each element of the operation-related information for a combination of two or more aggregation methods. The production efficiency feature quantity calculation unit 233 tallies the production efficiency information of the target area for each element of the operation-related information for all combinations of the elements of the operation-related information extracted in step S130 and the production efficiency information of the target area. Then, the process proceeds to step S220.

[0130] Specifically, when the production efficiency feature quantity calculation unit 233 acquires the area-of-interest designation information from the area-of-interest acquisition unit 232, it extracts one or more elements of operation-related information related to the production efficiency information of the area of ​​interest designated in the area-of-interest designation information. That is, the production efficiency feature quantity calculation unit 233 acquires the operation-related information related to the production efficiency information of the area of ​​interest from the analysis data storage unit 221.

[0131] Next, the production efficiency feature calculation unit 233 acquires the production efficiency information of the area of ​​interest from the analysis data storage unit 221, and aggregates the production efficiency information of the area of ​​interest for each element of the operation-related information for all combinations of the elements of the operation-related information extracted in step S130 and the production efficiency information of the area of ​​interest.

[0132] Here, the production efficiency feature amount calculation unit 233 creates two or more combinations of methods for aggregating production efficiency information of the region of interest. An example of a combination of methods for aggregating production efficiency information of the region of interest is a combination of "variance of production efficiency information" and "average value of production efficiency information." Hereinafter, the "combination of methods for aggregating production efficiency information of the region of interest" may be simply referred to as a "combination of aggregation methods."

[0133] It should be noted that if all combinations of the counting methods were created, the number of combinations of the counting methods would be enormous. For this reason, it is practical to create a maximum of three combinations of the counting methods in the production efficiency feature quantity calculation unit 233. It should be noted that for combinations where it is obvious that there is little meaning in combining them, such as "standard deviation" and "variance," which can be calculated mutually, the creation of combinations may be omitted.

[0134] Next, the production efficiency feature quantity calculation unit 233 creates all combinations of the created "combination of counting methods" and "one type of operation-related information" for all of the operation-related information acquired from the analysis data storage unit 221. An example of a combination of a "combination of counting methods" and "one type of operation-related information" is a combination of "variance of production efficiency information" and "average value of production efficiency information" with "worker."

[0135] Then, the production efficiency feature quantity calculation unit 233 calculates an aggregate value of the production efficiency information of the region of interest for each element of the operation-related information using a combination of two or more aggregation methods for all combinations of the elements of the operation-related information extracted in step S130 and the production efficiency information of the region of interest. That is, the production efficiency feature quantity calculation unit 233 calculates two or more different types of aggregate values ​​as the aggregate value of the production efficiency information of the region of interest for each element of the operation-related information by calculating the aggregate value of the production efficiency information of the region of interest for each element of the operation-related information using each of the two or more aggregation methods.

[0136] In step S220, the aggregated values ​​are normalized. The production efficiency feature quantity calculation unit 233 normalizes the aggregated value of the production efficiency information of the region of interest for each element of the operation-related information that has been aggregated, for all combinations of the elements of the operation-related information and the production efficiency information of the region of interest. Here, the production efficiency feature quantity calculation unit 233 normalizes the two or more different types of aggregated values ​​calculated in step S210 for each combination of the elements of the operation-related information and the production efficiency information of the region of interest.

[0137] Then, the production efficiency feature quantity calculation unit 233 acquires the normalized aggregated value as the production efficiency feature quantity. Through the above processing, the production efficiency feature quantity calculation unit 233 calculates the production efficiency feature quantity for each element of the operation-related information for all combinations of the elements of the operation-related information and the production efficiency information of the region of interest. In other words, the production efficiency feature quantity calculation unit 233 calculates two or more different types of production efficiency feature quantities for each combination of the elements of the operation-related information and the production efficiency information of the region of interest. Then, the process proceeds to step S230.

[0138] In step S230, the deviation of the production efficiency feature amount is calculated for each type of operation-related information. The factor candidate extraction unit 234 calculates the deviation for each type of operation-related information for all combinations of the operation-related information and the production efficiency information of the region of interest based on the production efficiency feature amount calculated by the production efficiency feature amount calculation unit 233. More specifically, the factor candidate extraction unit 234 calculates the deviation for each combination of aggregation methods for all combinations of the operation-related information and the production efficiency information of the region of interest based on the production efficiency feature amount calculated by the production efficiency feature amount calculation unit 233. That is, for combinations of two or more aggregation methods, the production efficiency feature amount calculation unit 233 calculates the deviation by using the aggregated value of the production efficiency information for each element as the production efficiency feature amount. Then, the process proceeds to steps S170 and S180.

[0139] FIG. 10 is a diagram illustrating an example of the concept of a method in which the factor candidate extraction unit of the operation analysis system calculates the deviation degree in the second embodiment. FIG. 10 illustrates a result of aggregating the production efficiency feature quantity of the production efficiency information of the region of interest for each worker, which is an element of the operation-related information, when the combination of the "combination of aggregation methods" and the "one type of operation-related information" is a combination of the "variance of production efficiency information," the "average value of production efficiency information," and the "worker." The vertical axis of the graph illustrated in FIG. 10 represents the "variance of production efficiency information," which is the production efficiency feature quantity of the production efficiency information of the region of interest. The horizontal axis of the graph illustrated in FIG. 10 represents the "average value of production efficiency information," which is the production efficiency feature quantity of the production efficiency information of the region of interest. The black circles illustrated in FIG. 10 represent workers, which are elements of the operation-related information.

[0140] In Fig. 10, the value on the vertical axis at a position moved vertically from the black circle of the worker toward the vertical axis is the value of the "variance of production efficiency information." In Fig. 10, the value on the horizontal axis at a position moved vertically from the black circle of the worker toward the horizontal axis is the value of the "average value of production efficiency information." In Fig. 10, the maximum value of the degree of deviation from the nearest black circle among the distances between the black circles of the workers is the deviation.

[0141] 10 , workers A, C, E, and F are located close to one another. On the other hand, workers B and D are farther away from workers A, C, E, and F, who are located close to one another. Furthermore, worker B is farther away from workers A, C, E, and F, who are located close to one another, than worker D. The factor candidate extraction unit 234 determines the degree of distance between worker B and worker E, which is the maximum value of the degree of distance from the nearest worker among the distances between workers, as the degree of deviation.

[0142] An example of a method for calculating the deviation degree in embodiment 2 will be shown. In embodiment 2, similarly to embodiment 1, the deviation degree may be a value that can highlight and evaluate differences in production efficiency feature quantities of the same type of operation-related information between elements of the operation-related information.

[0143] As shown in FIG. 10 , when elements of operation-related information and production efficiency feature quantities of the elements of operation-related information are mapped onto a plane, the factor candidate extraction unit 234 can calculate, as the deviation, the maximum value of the distance to the nearest point among the distances between points corresponding to the mapped elements of operation-related information. In other words, when elements of operation-related information and production efficiency feature quantities of the elements of operation-related information are mapped onto a plane, the deviation for a certain type of operation-related information is calculated as, for example, the maximum value of the distance to the nearest point among the distances between the elements of operation-related information. In FIG. 10 , the factor candidate extraction unit 234 can calculate, as the deviation, the distance between the black circle of worker B and the black circle of worker E, which is the maximum value of the distance to the nearest point among the distances between black circles that correspond to the elements of operation-related information mapped onto the plane.

[0144] Representative methods used to calculate the distance between points corresponding to elements of operation-related information mapped onto a plane include statistical quantities such as Euclidean distance, Manhattan distance, and Mahalanobis distance.

[0145] In addition, the distance between points corresponding to elements of operation-related information mapped onto a plane may be defined as a convex hull problem on a plane that searches for the outer frame of the point with the furthest distance, and the deviation may be calculated using an algorithm such as Graham scan.

[0146] Note that the factor candidate extraction unit 234 may calculate, as the deviation, the maximum value of the average value of the distances to the k-nearest points in the k-nearest neighbor method, rather than the maximum value of the distances to the nearest points between the black circles that are points corresponding to the elements of the operation-related information mapped onto a plane. The k-nearest points are the top k points in order of closest distance between the black circles that are points corresponding to the elements of the operation-related information mapped onto a plane. In other words, the factor candidate extraction unit 234 may calculate, as the deviation, the maximum value of the average value of the distances to the top k points in order of closest distance between the black circles that are points corresponding to the elements of the operation-related information mapped onto a plane.

[0147] Alternatively, a representative value of the production efficiency feature may be calculated, and the maximum value of the difference from the representative value may be used as the deviation. When calculating the representative value, points on a plane may be categorized using a clustering algorithm such as the k-means method, and then the distance from the center point may be calculated.

[0148] In either case, in the multi-axis evaluation, the deviation in the second embodiment is a value that can evaluate the magnitude of the production efficiency feature amount of each element of the operation-related information as well as the neighboring relationship.

[0149] It should be noted that information equivalent to that shown in Figure 10 can be sent to the terminal device 3 together with information on potential factors that could reduce production efficiency and presented to the user, but it need only be temporarily stored within the server 2 of the operation analysis system 1 and does not necessarily need to be presented to the user.

[0150] As described above, in the second embodiment, the operation analysis system 1, like the first embodiment, automatically analyzes and estimates factors for a decline in production efficiency of the production equipment 6 based on bias in production efficiency feature quantities for elements of operation-related information related to production efficiency information in a target area. As a result, in the second embodiment, like the first embodiment, the operation analysis system 1 can present to the user appropriate candidates for factors for a decline in production efficiency of the production equipment 6 that have been analyzed based on the production efficiency information and operation-related information, without using prior information such as scenarios and cause / measure data as disclosed in Patent Document 1. As a result, the operation analysis system 1 can reduce the effort required for system implementation and system operation.

[0151] Third Embodiment In the third embodiment, other functions of the operation analysis system 1 according to the first embodiment will be described. In the third embodiment, the operation analysis system 1 receives two pieces of area-of-interest designation information and extracts candidate factors for reducing production efficiency. That is, the operation analysis system 1 acquires, from the terminal device 3, two pieces of area-of-interest designation information for two locations designated by the user in the production efficiency information map displayed by the production efficiency information map data. Then, the operation analysis system 1 calculates production efficiency feature quantities for each of the two areas of interest designated by the two pieces of area-of-interest designation information, using the same procedure as in the first embodiment.

[0152] That is, in the third embodiment, the region-of-interest acquisition unit 232 acquires two pieces of region-of-interest designation information. In the third embodiment, the production efficiency feature calculation unit 233 calculates an aggregate value as a production efficiency feature for the two regions of interest designated in the region-of-interest designation information. Then, in the third embodiment, the factor candidate extraction unit 234 calculates the similarity of the production efficiency feature for the two regions of interest designated in the region-of-interest designation information.

[0153] In embodiment 3, the operation analysis system 1 accepts two pieces of target area designation information: a first target area in the production efficiency information map where production efficiency has not declined relatively, and a second target area in the production efficiency information map where production efficiency has declined relatively, and extracts candidate factors for decline in production efficiency.

[0154] In the third embodiment, two regions of interest, a first region of interest and a second region of interest, are specified in order to extract candidate factors of production efficiency reduction for a second region of interest where production efficiency is relatively reduced in the production efficiency information map. That is, in the third embodiment, in order to extract candidate factors of production efficiency reduction for the second region of interest where production efficiency is relatively reduced in the production efficiency information map, the first region of interest, which is an exemplary region in terms of production efficiency with relatively good production efficiency, is also specified as a region of interest for comparison with the second region of interest.

[0155] Therefore, in the third embodiment, the second region of interest in the production efficiency information map where production efficiency is relatively low can be said to be a region of interest from which candidate factors for production efficiency decline are extracted. Also, in the third embodiment, the second region of interest in the production efficiency information map where production efficiency is relatively low is a region of interest in which the user wants to identify the factors for the decline in production efficiency. Also, in the third embodiment, the second region of interest in the production efficiency information map where production efficiency is relatively low can be said to be a region of interest in the production efficiency information map where the value of production efficiency information is relatively low.

[0156] Furthermore, the first region of interest in the production efficiency information map where production efficiency has not declined relatively can be considered a region of interest to be compared with when extracting candidate factors for decline in production efficiency in the second region of interest. Furthermore, the first region of interest in the production efficiency information map where production efficiency has not declined relatively can be considered a region of interest in the production efficiency information map where the value of production efficiency information is relatively high.

[0157] When two areas of interest, a first area of ​​interest and a second area of ​​interest, are specified, i.e., when two pieces of area of ​​interest specification information are received, the operation analysis system 1 extracts candidate factors for reducing production efficiency in the second area of ​​interest by comparing the production efficiency feature of the first area of ​​interest with the production efficiency feature of the second area of ​​interest.

[0158] Specifically, when two areas of interest are specified in the production efficiency information map, namely, a first area of ​​interest where production efficiency is not relatively low and a second area of ​​interest where production efficiency is relatively low, the operation analysis system 1 extracts candidate factors for production efficiency reduction in the second area of ​​interest by comparing the production efficiency feature values ​​of the first area of ​​interest with the production efficiency feature values ​​of the second area of ​​interest, using the production efficiency feature values ​​of the first area of ​​interest as a reference, for each type of operation-related information. That is, when the operation analysis system 1 receives two area-of-interest specification information, namely, a target area of ​​interest from which candidate factors for production efficiency reduction are extracted and a target area of ​​interest as a comparison object, which is an exemplary area, the operation analysis system 1 extracts candidate factors for production efficiency reduction in the second area of ​​interest by comparing the production efficiency feature values ​​of the target area of ​​interest from which candidate factors for production efficiency reduction are extracted with the production efficiency feature values ​​of the comparison object area of ​​interest, using the comparison object area of ​​interest as an exemplary area as a reference, for each type of operation-related information.

[0159] Hereinafter, details of the processing of the operation analysis system 1 according to the third embodiment will be described with reference to a flowchart. Fig. 11 is a flowchart showing an example of the processing of the operation analysis system according to the third embodiment.

[0160] First, step S110 is performed, and then the process proceeds to step S310. In the third embodiment, the production efficiency feature is calculated in steps S320 to S340.

[0161] In step S310, two pieces of area-of-interest designation information are acquired. Specifically, the area-of-interest acquisition unit 232 of the server processing unit 23 of the server 2 acquires the two pieces of area-of-interest designation information from the terminal device 3 via the server communication unit 21. The two pieces of area-of-interest designation information are for two locations designated by the user in the production efficiency information map displayed on the display unit 32 of the terminal device 3 using the production efficiency information map data. The area-of-interest acquisition unit 232 transmits the two pieces of acquired area-of-interest designation information to the production efficiency feature quantity calculation unit 233 of the server processing unit 23 of the server 2. The production efficiency feature quantity calculation unit 233 receives the two pieces of area-of-interest designation information transmitted from the area-of-interest acquisition unit 232. Then, the process proceeds to step S320.

[0162] Fig. 12 is a diagram showing an example of two areas of interest specified in the production efficiency information map shown in Fig. 3. In Fig. 12, area A and area B are specified as areas of interest.

[0163] Here, area A is an example of an area of ​​interest in the production efficiency information map 40 shown in Figure 3 where production efficiency is not relatively reduced, and is the first area of ​​interest described above. Area B is an example of an area of ​​interest in the production efficiency information map 40 shown in Figure 3 where production efficiency is relatively reduced, and is the second area of ​​interest described above. In Figure 12, two areas of interest, area A and area B, are specified in order to extract candidate factors for reducing production efficiency for area B, which is the area of ​​interest where production efficiency is relatively reduced. That is, in Figure 12, area A, which is an exemplary area in terms of production efficiency, is also specified as an area of ​​interest for comparison in order to extract candidate factors for reducing production efficiency for area B.

[0164] In step S320, elements of operation-related information are extracted for each of the two areas of interest specified in the two pieces of area-of-interest designation information. Upon acquiring the two pieces of area-of-interest designation information, the production efficiency feature quantity calculation unit 233 acquires, from the analysis data storage unit 221, a plurality of pieces of operation-related information related to the production efficiency information of the areas of interest specified in each of the two pieces of area-of-interest designation information. The production efficiency feature quantity calculation unit 233 then extracts, for each of the two areas of interest, one or more elements of the operation-related information from each of the acquired pieces of operation-related information. The process then proceeds to step S330.

[0165] In step S330, for each of the two regions of interest specified in the two pieces of region-of-interest designation information, production efficiency information for each element of the operation-related information is tallied. For each of the two regions of interest, the production efficiency feature amount calculation unit 233 tallies the production efficiency information for each element of the operation-related information for all combinations of the elements of the operation-related information extracted in step S320 and the production efficiency information of the regions of interest. Then, the process proceeds to step S340.

[0166] In step S340, the aggregated values ​​are normalized for each of the two regions of interest specified in the two pieces of region-of-interest designation information. For each of the two regions of interest, the production efficiency feature quantity calculation unit 233 normalizes the aggregated value of the production efficiency information of the region of interest for each element of the aggregated operation-related information for all combinations of the elements of the operation-related information and the production efficiency information of the region of interest.

[0167] The production efficiency feature quantity calculation unit 233 then acquires the normalized aggregate value as the production efficiency feature quantity for each of the two regions of interest. Through the above processing, the production efficiency feature quantity calculation unit 233 calculates the production efficiency feature quantity for each element of the operation-related information for each of the two regions of interest specified in the two region-of-interest designation information, for all combinations of elements of the operation-related information and the production efficiency information of the regions of interest. Then, the process proceeds to step S350.

[0168] In step S350, the similarity of the production efficiency feature values ​​between the two regions of interest is calculated for each type of operation-related information. The factor candidate extraction unit 234 calculates the similarity by comparing the production efficiency feature values ​​of the same operation-related information for each element of the operation-related information in the two regions of interest. That is, for all of the operation-related information extracted in step S320, the factor candidate extraction unit 234 calculates the similarity by comparing the production efficiency feature value of the operation-related information for one of the two regions of interest with the production efficiency feature value of the operation-related information for the other of the two regions of interest. Specifically, the factor candidate extraction unit 234 compares the production efficiency feature value of the operation-related information for the comparison region, which is an exemplary region, with the production efficiency feature value of the operation-related information for the region of interest from which the production efficiency reduction factor candidate is extracted, and calculates the similarity for each type of operation-related information. The production efficiency feature values ​​of the operation-related information compared here are production efficiency feature values ​​of the same type of operation-related information. Then, proceed to step S360.

[0169] In step S360, candidate factors for production efficiency reduction are extracted. The candidate factor extraction unit 234 extracts a predetermined number of types of operation-related information as candidate factors for production efficiency reduction from all combinations of operation-related information and production efficiency information of the target area, i.e., from the multiple pieces of operation-related information for which similarities have been calculated, in order of decreasing similarity. The candidate factor extraction unit 234 stores information on candidate factors for production efficiency reduction for each of the extracted types of operation-related information in the server storage unit 22. The candidate factor extraction unit 234 also transmits information on candidate factors for production efficiency reduction to the terminal device 3 via the server communication unit 21. The terminal device 3 receives the information on candidate factors for production efficiency reduction transmitted from the candidate factor extraction unit 234. Thereafter, the process proceeds to step S180.

[0170] An example of a method for calculating similarity in embodiment 3 will be described. In embodiment 3, the production efficiency feature amounts for the same operation-related information in two regions of interest are compared to calculate the similarity. That is, in embodiment 3, the production efficiency feature amounts for the same operation-related information are compared between two regions of interest to calculate the similarity. In embodiment 3, the production efficiency feature amounts for the same operation-related information are compared between two regions of interest to find the similarity for each similarity analysis element between the two regions of interest.

[0171] The similarity analysis element is the target of the similarity analysis, and is a production efficiency feature amount corresponding to an element of the operation-related information.

[0172] As an example of calculating the similarity, the Euclidean distance, the Pearson correlation coefficient, the cosine similarity, etc., as in the second embodiment, are exemplified.

[0173] FIG. 13 is a diagram showing production efficiency feature values ​​for region A shown in FIG. 12 when the operation-related information is a worker. FIG. 14 is a diagram showing production efficiency feature values ​​for region B shown in FIG. 12 when the operation-related information is a worker. The horizontal axis of the graphs shown in FIGS. 13 and 14 represents worker names, which are elements of the operation-related information. The vertical axis of the graphs shown in FIGS. 13 and 14 represents production efficiency feature values ​​for each worker name. The production efficiency feature value is, for example, the average value of the operation rate. The production efficiency feature value is, for example, a normalized average value of the operation rate, which is production efficiency information. In the graphs shown in FIGS. 13 and 14, the value of the production efficiency feature value for worker D on the vertical axis is "1," and the bottom of the vertical axis is normalized to "0." Then, based on the graphs shown in FIGS. 13 and 14, similarity is calculated when the operation-related information is a worker.

[0174] When comparing the production efficiency feature values ​​of area A and area B, the factor candidate extraction unit 234 compares the production efficiency feature value in Fig. 13 with the production efficiency feature value in Fig. 14. The similarity in this case indicates how much the trends of the production efficiency feature value in Fig. 13 and the production efficiency feature value in Fig. 14 differ.

[0175] For example, the factor candidate extraction unit 234 calculates the average value of the production efficiency feature amounts of workers in area A and the average value of the production efficiency feature amounts of workers in area B, and compares the two to calculate the similarity. The factor candidate extraction unit 234 calculates the similarity for all of the operation-related information for all combinations of the extracted elements of operation-related information and the production efficiency information of the area of ​​interest. Then, the factor candidate extraction unit 234 extracts, as candidate factors for decline in production efficiency, a predetermined number of types of operation-related information in ascending order of similarity from all combinations of the operation-related information and the production efficiency information of the area of ​​interest, i.e., from the multiple pieces of operation-related information for which the similarity has been calculated.

[0176] FIG. 15 is a diagram illustrating the production efficiency feature for region A shown in FIG. 12 when the operation-related information is the day of the week. FIG. 16 is a diagram illustrating the production efficiency feature for region B shown in FIG. 12 when the operation-related information is the day of the week. The horizontal axis of the graphs shown in FIGS. 15 and 16 represents the day of the week, which is an element of the operation-related information. The vertical axis of the graphs shown in FIGS. 15 and 16 represents the production efficiency feature for each day of the week. The production efficiency feature is, for example, the average value of the operation rate. The production efficiency feature is, for example, the normalized average value of the operation rate, which is the production efficiency information. In the graphs shown in FIGS. 15 and 16, the value of the production efficiency feature for Thursday on the vertical axis is "1," and the bottom of the vertical axis is normalized to "0." Based on the graphs shown in FIGS. 15 and 16, similarity is calculated when the operation-related information is the day of the week. Note that in FIGS. 15 and 16, "Monday," "Tuesday," "Wednesday," "Thursday," "Friday," and "Saturday" are abbreviated as "Monday," "Tuesday," "Wednesday," "Thursday," "Friday," and "Saturday," respectively.

[0177] 15 and 16 , when the operation-related information is days of the week, the factor candidate extraction unit 234 calculates, for example, the average value of the production efficiency feature quantities from Monday to Saturday in area A and the average value of the production efficiency feature quantities from Monday to Saturday in area B, and compares the two to calculate the similarity. The factor candidate extraction unit 234 calculates the similarity for all of the operation-related information for all combinations of the extracted elements of the operation-related information and the production efficiency information of the region of interest. Then, the factor candidate extraction unit 234 extracts, as candidate factors for decline in production efficiency, a predetermined number of types of operation-related information in ascending order of similarity from all combinations of the operation-related information and the production efficiency information of the region of interest, i.e., from the multiple pieces of operation-related information for which similarities have been calculated.

[0178] For example, when the similarity of the production efficiency feature amounts between area A and area B when the type of operation-related information is “worker,” calculated based on Figures 13 and 14, is compared with the similarity of the production efficiency feature amounts between area A and area B when the type of operation-related information is “day of the week,” calculated based on Figures 15 and 16, the similarity of the production efficiency feature amounts when the type of operation-related information is “worker” is smaller than the similarity of the production efficiency feature amounts when the type of operation-related information is “day of the week.” In this case, the factor candidate extraction unit 234 can determine that “worker” is more likely to be a factor in reducing the production efficiency of area B than “day of the week.”

[0179] From the extraction results of candidate factors for reduced production efficiency in the operation analysis systems 1 in the first and second embodiments described above, it is possible to present to the user candidate factors for reduced production efficiency of the production equipment 6, such as "the productivity of a specific worker is low at a certain time on a certain day of the week." On the other hand, from the extraction results of candidate factors for reduced production efficiency in the operation analysis system 1 in the third embodiment, it is possible to present to the user candidate factors for reduced production efficiency of the production equipment 6, such as "the productivity of all workers is low over a plurality of days of the week and a plurality of times of the day." In other words, by analyzing the extraction results in the operation analysis systems 1 in the first to third embodiments, it is possible to present to the user a wider variety of candidate factors for reduced production efficiency of the production equipment 6.

[0180] Furthermore, in the above-described first to third embodiments, the production efficiency feature is expressed as an analog value. However, there are cases where it is more appropriate for the production efficiency feature to be expressed as a categorical variable rather than as an analog value, and the production efficiency feature can be expressed as a set relationship. In such cases, the Jaccard coefficient can also be applied to calculate the similarity. For example, if the operation-related information is temperature, the production efficiency feature can be expressed as an analog value. On the other hand, examples of production efficiency feature that are better expressed as a categorical variable include categorical variables such as sunny, cloudy, rainy, and snowy.

[0181] When calculating the similarity by comparing production efficiency feature values ​​for the same operation-related information, it is practical to compare two regions of interest. Note that, even when calculating the similarity by comparing production efficiency feature values ​​for the same operation-related information in three or more regions of interest, in addition to applying the similarity calculation algorithm described above, the similarity can be calculated by compressing the dimensions using principal component analysis as preprocessing and then applying the same algorithm.

[0182] As described above, in the third embodiment, when two or more areas of interest are selected as areas to be compared, the operation analysis system 1 can extract the top K elements that have the largest differences between other operation-related information and the areas of interest, by comparing the production efficiency features extracted from each area of ​​interest.

[0183] Furthermore, in the third embodiment, the operation analysis system 1 extracts candidate factors for reducing production efficiency in the second region of interest by comparing the production efficiency feature values ​​of the first region of interest, which is an exemplary region with relatively good production efficiency, with the production efficiency feature values ​​of the second region of interest, which is a comparison region. This improves the accuracy of the extraction of candidate factors for reducing production efficiency in the second region of interest. As a result, in the third embodiment, the operation analysis system 1 can extract candidate factors for reducing production efficiency in the second region of interest with greater accuracy than when only the second region of interest, which is the region of interest from which candidate factors for reducing production efficiency are extracted, is specified as the region of interest and candidate factors for reducing production efficiency are extracted.

[0184] That is, in the third embodiment, when the region of interest acquisition unit 232 acquires two pieces of region of interest designation information, namely, region of interest designation information designating a first region of interest having a relatively high production efficiency information value in the production efficiency information map, and region of interest designation information designating a second region of interest having a relatively low production efficiency information value in the production efficiency information map, the production efficiency feature quantity calculation unit 233 calculates an aggregate value for the two regions of interest designated in the region of interest designation information as the production efficiency feature quantity. Then, the factor candidate extraction unit 234 calculates the similarity of the production efficiency feature quantity for the two regions of interest designated in the region of interest designation information for each type of operation-related information, and extracts the types of operation-related information in order of decreasing similarity from all combinations of the operation-related information and the production efficiency information of the regions of interest.

[0185] In the third embodiment, similarly to the first embodiment, the operation analysis system 1 automatically analyzes and estimates factors for a decline in production efficiency of the production equipment 6 based on bias in production efficiency feature quantities for elements of operation-related information related to production efficiency information in a target area. As a result, similarly to the first embodiment, the operation analysis system 1 in the third embodiment can present to the user appropriate candidates for factors for a decline in production efficiency of the production equipment 6 that have been analyzed based on the production efficiency information and operation-related information, without using prior information such as the scenario and cause / measure data shown in Patent Document 1. As a result, the operation analysis system 1 can reduce the effort required for system implementation and system operation.

[0186] Fourth Embodiment In a fourth embodiment, other functions of the operation analysis system 1 according to the first embodiment will be described. In the fourth embodiment, the operation analysis system 1 automatically searches for and creates combinations of one type of production efficiency information and two types of operation-related information, and creates a production efficiency information map for the created combinations of one type of production efficiency information and two types of operation-related information.

[0187] In the first embodiment, the production efficiency information map creation unit 231 of the server processing unit 23 of the server 2 acquires one type of production efficiency information and two types of operation-related information from the analysis data storage unit 221 in accordance with preset conditions, and creates a production efficiency information map based on the acquired one type of production efficiency information and two types of operation-related information. That is, in the first embodiment, the production efficiency information map creation unit 231 acquires one type of production efficiency information and two types of operation-related information from the analysis data storage unit 221 based on, for example, predetermined map creation conditions, and creates a production efficiency information map based on the acquired one type of production efficiency information and two types of operation-related information.

[0188] In contrast to this, in the fourth embodiment, the production efficiency information map creation unit 231 automatically searches for and creates a combination of one type of production efficiency information and two types of operation-related information without using map creation conditions, and creates a production efficiency information map.

[0189] Hereinafter, details of the processing of the operation analysis system 1 according to the fourth embodiment will be described with reference to a flowchart. Fig. 17 is a flowchart showing an example of the processing of the operation analysis system according to the fourth embodiment.

[0190] In step S410, a production efficiency information map is created by automatically searching the production efficiency information and the operation-related information. Specifically, the production efficiency information map creation unit 231 of the server processing unit 23 of the server 2 creates the production efficiency information map.

[0191] The user inputs analysis instruction information that instructs an analysis of the causes of a decline in production efficiency as input to the input unit 31 on the operation screen of the operation analysis system 1 displayed on the display unit 32 of the terminal device 3. The production efficiency information map creation unit 231 creates a production efficiency information map based on the user's analysis instruction information input from the terminal device 3. That is, the production efficiency information map creation unit 231 acquires production efficiency information and operation-related information from the analysis data storage unit 221, and creates production efficiency information map data that is data for displaying a production efficiency information map on the terminal device 3 based on the acquired production efficiency information and operation-related information.

[0192] In the fourth embodiment, the production efficiency information map creation unit 231 automatically searches for and creates a plurality of combinations of one type of production efficiency information and two types of operation-related information without using map creation conditions, and creates a production efficiency information map. The production efficiency information map creation unit 231 automatically searches for and creates, for example, all combinations as a plurality of combinations of one type of production efficiency information and two types of operation-related information, and creates a production efficiency information map.

[0193] The production efficiency information map creation unit 231 automatically searches for combinations of one type of production efficiency information and two types of operation-related information from the multiple pieces of production efficiency information and operation-related information stored in the analysis data storage unit 221, and creates multiple sets of combinations of one type of production efficiency information and two types of operation-related information.The production efficiency information map creation unit 231 then creates a production efficiency information map for the created multiple sets of combinations.In other words, the production efficiency information map creation unit 231 creates multiple production efficiency information maps based on the created multiple sets of combinations.

[0194] Next, the production efficiency information map creation unit 231 selects one production efficiency information map from the created multiple production efficiency information maps that has a large difference in production efficiency information and a large bias in the distribution of large and small production efficiency information.

[0195] When selection criteria are stored in advance in the production efficiency information map creation unit 231 as criteria for selecting a production efficiency information map having a large difference in production efficiency information and a large bias in the distribution of magnitudes of the production efficiency information, the production efficiency information map creation unit 231 selects one production efficiency information map in accordance with the selection criteria. When selection criteria are not stored in advance in the production efficiency information map creation unit 231 as criteria for selecting a production efficiency information map having a large difference in production efficiency information and a large bias in the distribution of magnitudes of the production efficiency information, the production efficiency information map creation unit 231 selects one production efficiency information map using a numerical value calculated by a predetermined testing method based on statistics of the production efficiency information. Note that the production efficiency information map creation unit 231 can also select one or more production efficiency information maps.

[0196] Then, the production efficiency information map creation unit 231 transmits the selected piece of production efficiency information map data to the terminal control unit 35 of the terminal device 3 via the server communication unit 21. The terminal control unit 35 receives the production efficiency information map data transmitted from the production efficiency information map creation unit 231 via the terminal communication unit 33. Then, the process proceeds to step S120.

[0197] Thereafter, the processes from step S120 to step S180 are carried out based on the selected one piece of production efficiency information map data.

[0198] Note that, after checking the production efficiency information map displayed on the display unit 32, the user selects one area of ​​interest in the production efficiency information map, as in the case of embodiment 1, and inputs area of ​​interest designation information for the selected area of ​​interest to the terminal device 3 using the input unit 31 of the terminal device 3. Here, if the user wants to change the production efficiency information map from which the area of ​​interest is selected to another production efficiency information map, the user inputs production efficiency information map change instruction information that instructs the user to change the production efficiency information map from which the area of ​​interest is selected to the terminal device 3 using the input unit 31 of the terminal device 3. The terminal control unit 35 transmits the input production efficiency information map change instruction information to the production efficiency information map creation unit 231.

[0199] When the production efficiency information map creation unit 231 receives the change instruction information for the production efficiency information map, it presents to the user a production efficiency information map that is different from the production efficiency information map that was previously transmitted to the terminal control unit 35 of the terminal device 3. The production efficiency information map creation unit 231 selects, from the multiple production efficiency information maps that have been created, one production efficiency information map that has the next largest difference in production efficiency information and the largest bias in the distribution of large and small production efficiency information after the production efficiency information map that was previously transmitted to the terminal control unit 35 of the terminal device 3, and presents this to the user as the second production efficiency information map.

[0200] The user can select one area of ​​interest in the second production efficiency information map displayed on the display unit 32. Note that the user can select areas of interest in the third and subsequent production efficiency information maps by using the same process.

[0201] FIG. 18 is a diagram showing an example of a production efficiency information map created by the operation analysis system in embodiment 4. FIG. 19 is a diagram showing another example of a production efficiency information map created by the operation analysis system in embodiment 4. In production efficiency information map 51 shown in FIG. 18 , information on "operation rate," which is production efficiency information, is displayed in association with information on two types of operation-related information, "operation time" and "day of the week," and the correspondence relationship between the operation-related information, "operation time" and "day of the week," and the production efficiency information, "operation rate." That is, in production efficiency information map 51 shown in FIG. 18 , the correspondence relationship between the operation-related information, "operation time" and "day of the week," and the production efficiency information, "operation rate," is shown using the operation-related information, "operation time" and "day of the week," as display axes.

[0202] 19, the production efficiency information map 52 displays information on "operating rate", which is production efficiency information, in association with information on two types of operation-related information, "operating time" and "date", and shows the correspondence between the operation-related information "operating time" and "date" and the production efficiency information "operating rate". That is, the production efficiency information map 52 shown in FIG. 19 uses the operation-related information "operating time" and "date" as display axes and shows the correspondence between the operation-related information "operating time" and "date" and the production efficiency information "operating rate".

[0203] The production efficiency information map 51 shown in Figure 18 is an example in which there is little difference in size between the circles indicating production efficiency information, and there is also little bias in the distribution of the sizes of the circles indicating production efficiency information. A production efficiency information map with characteristics like the production efficiency information map 51 corresponds to a case in which the operating state of the production equipment 6 is stable, and the production efficiency of the production equipment 6 is stable. The production efficiency information map 52 shown in Figure 19 is an example in which there is a large difference in size between the circles indicating production efficiency information, and there is also a large bias in the distribution of the sizes of the circles indicating production efficiency information. A production efficiency information map with characteristics like the production efficiency information map 52 corresponds to a case in which there is variation in the operating state of the production equipment 6, and the production efficiency of the production equipment 6 is unstable.

[0204] In this case, since the production efficiency information map 51 shown in FIG. 18 has a small difference in size between the circles indicating production efficiency information and also has a small bias in the distribution of the sizes of the circles indicating production efficiency information, the production efficiency information map creation unit 231 does not transmit the production efficiency information map 51 shown in FIG. 18 to the terminal control unit 35.

[0205] As described above, in the fourth embodiment, it is not necessary to previously set the production efficiency information and operation-related information that the production efficiency information map creation unit 231 acquires from the analysis data storage unit 221. As a result, the fourth embodiment can further reduce the effort required to introduce the operation analysis system 1 compared to the first to third embodiments described above.

[0206] Next, the hardware configuration of each of the control units 80 according to the first to fourth embodiments will be described. The control units 80 according to the first to fourth embodiments correspond to the server processing unit 23 and the server control unit 24 of the server 2, and the terminal control unit 35 of the terminal device 3, respectively. Each function of the control unit 80 according to the first to fourth embodiments is realized by a processing circuit. The processing circuit may be dedicated hardware, or may be a processing device that executes a program stored in a storage device.

[0207] When the processing circuit is dedicated hardware, the processing circuit may be a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an application specific integrated circuit, a field programmable gate array, or a combination thereof. Figure 20 is a diagram showing a configuration in which the functions of the control unit according to the first to fourth embodiments are realized by hardware. The processing circuit 81 incorporates a logic circuit 81a that realizes the functions of the control unit 80.

[0208] When the processing circuit 81 is a processing device, the functions of the control unit 80 are realized by software, firmware, or a combination of software and firmware.

[0209] FIG. 21 is a diagram illustrating a configuration in which the functions of the control unit according to the first to fourth embodiments are implemented by software. The processing circuit 81 includes a processor 811 that executes a program 81b, a random access memory 812 that the processor 811 uses as a work area, and a storage device 813 that stores the program 81b. The processor 811 deploys the program 81b stored in the storage device 813 on the random access memory 812 and executes it, thereby realizing the functions of the control unit 80. The software or firmware is written in a programming language and stored in the storage device 813. The processor 811 may be, but is not limited to, a central processing unit. The storage device 813 may be a semiconductor memory such as a random access memory (RAM), a read-only memory (ROM), a flash memory, an erasable programmable read-only memory (EPROM), or an electrically erasable programmable read-only memory (EEPROM). The semiconductor memory may be either a non-volatile memory or a volatile memory. In addition to semiconductor memory, a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disc) can be used as the storage device 813. The processor 811 may output data such as calculation results to the storage device 813 for storage, or may store the data in an auxiliary storage device (not shown) via the random access memory 812. By integrating the processor 811, the random access memory 812, and the storage device 813 on a single chip, the functions of the control unit 80 can be realized by a microcomputer.

[0210] The processing circuitry 81 reads and executes the program 81b stored in the storage device 813 to realize the functions of the control unit 80. It can also be said that the program 81b causes the computer to execute the procedures and methods for realizing the functions of the control unit 80.

[0211] In the processing circuit 81 for realizing the functions of the server processing unit 23 in the server 2, the program 81b includes an operation analysis server program.

[0212] The processing circuit 81 may be configured so that some of the functions of the control unit 80 are realized by dedicated hardware, and some of the functions of the control unit 80 are realized by software or firmware.

[0213] In this way, the processing circuitry 81 can realize each of the above-described functions by hardware, software, firmware, or a combination of these.

[0214] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies, or different embodiments may be combined with each other. It is also possible to omit or modify parts of the configurations as long as they do not deviate from the gist of the invention.

[0215] 1 Operation analysis system, 2 Server, 3 Terminal device, 4 Internet, 5 Cloud environment, 6 Production equipment, 21 Server communication unit, 22 Server storage unit, 23 Server processing unit, 24 Server control unit, 31 Input unit, 32 Display unit, 33 Terminal communication unit, 34 Terminal storage unit, 35 Terminal control unit, 40, 51, 52 Production efficiency information map, 41 Area of ​​interest, 80 Control unit, 81 Processing circuit, 81a Logic circuit, 81b Program, 221 Analysis data storage unit, 231 Production efficiency information map creation unit, 232 Area of ​​interest acquisition unit, 233 Production efficiency feature calculation unit, 234 Factor candidate extraction unit, 811 Processor, 812 Random access memory, 813 Storage device.

Claims

1. A production efficiency information map creation unit that creates a production efficiency information map, which is an information map showing a correspondence between the production efficiency information and the operation-related information by displaying two or more types of the operation-related information as display axes, based on production efficiency information, which is information related to the production of products in a production facility and serves as an index for evaluating the production efficiency of the products in the production facility, and operation-related information, which is information related to the production of the products in the production facility and serves as a candidate for a cause of a decrease in the production efficiency of the products in the production facility; an area of ​​interest acquisition unit that acquires area of ​​interest designation information, which is information that designates an area of ​​interest selected in the production efficiency information map; and a production efficiency feature calculation unit that extracts individual pieces of information related to the production efficiency information of the area of ​​interest from a plurality of pieces of operation-related information as elements, and calculates an aggregate value of the production efficiency information for each element as a production efficiency feature for all combinations of the operation-related information and the production efficiency information. a factor candidate extraction unit that calculates a deviation, which is an index for evaluating a difference in the production efficiency feature amount between the elements, for each type of operation-related information for all combinations of the operation-related information and the production efficiency information, and extracts the types of operation-related information in descending order of the deviation from among all combinations of the operation-related information and the production efficiency information of the region of interest.

2. The operation analysis system according to claim 1, wherein the factor candidate extraction unit extracts a predetermined number of types of the operation-related information in descending order of the degree of deviation, and for each of the extracted types of the operation-related information, outputs information on candidate factors of production efficiency decline, including information on the type of the operation-related information, information on the degree of deviation in the operation-related information, and information on the name of an element, among a plurality of elements in the operation-related information, for which the deviation of the production efficiency feature amount between the element and other elements meets a predetermined criterion.

3. The operation analysis system according to claim 1 or 2, wherein the production efficiency feature value calculation unit calculates a normalized aggregate value of the production efficiency information as the production efficiency feature value.

4. An operation analysis system according to any one of claims 1 to 3, characterized in that it comprises a terminal device that displays the production efficiency information map and receives area of ​​interest designation information that designates the area of ​​interest on the production efficiency information map.

5. The operation analysis system according to any one of claims 1 to 4, wherein the production efficiency feature calculation unit calculates the aggregated value of the production efficiency information for each element as the production efficiency feature for a combination of two or more aggregation methods, and the factor candidate extraction unit calculates the degree of deviation for each type of operation-related information for each combination of the aggregation methods.

6. The operation analysis system according to any one of claims 1 to 4, wherein when the focus area acquisition unit acquires two pieces of focus area designation information, the focus area designation information designating a first focus area in the production efficiency information map where the production efficiency information value is relatively high, and the focus area designation information designating a second focus area in the production efficiency information map where the production efficiency information value is relatively low, the production efficiency feature amount calculation unit calculates the aggregate value as a production efficiency feature amount for the two focus areas designated in the focus area designation information, and the factor candidate extraction unit calculates the similarity for the two focus areas designated in the focus area designation information for each type of operation-related information, and extracts the types of operation-related information in order of decreasing similarity from all combinations of the operation-related information and the production efficiency information of the focus areas.

7. An operation analysis system according to any one of claims 1 to 4, wherein the production efficiency information map creation unit creates the production efficiency information map for a predetermined combination of the production efficiency information and the operation-related information.

8. An operation analysis system according to any one of claims 1 to 4, wherein the production efficiency information map creation unit automatically searches for and creates combinations of one type of production efficiency information and two types of operation-related information from a plurality of pieces of production efficiency information and a plurality of pieces of operation-related information, and creates the production efficiency information map for the created combinations of one type of production efficiency information and two types of operation-related information.

9. An operation analysis system according to any one of claims 1 to 8, further comprising an analysis data storage unit that stores the production efficiency information and the operation-related information.

Images